Urban traffic intelligent planning auxiliary system and method based on big data analysis

Abstract

The invention discloses an urban traffic intelligent planning auxiliary system and method based on big data analysis, and relates to the technical field of traffic planning. Historical travel habit data of residents in a city and historical traffic flow data of urban traffic are collected, and feature extraction is performed on the historical travel habit data and the historical traffic flow data; the method comprises the following steps: constructing a historical feature set, training a travel demand prediction model for predicting passenger flow among different urban areas based on the historical feature set, identifying high travel demand stations in each time period according to a prediction result of the travel demand prediction model, and determining the travel demand of each time period by using a shortest path algorithm according to position distribution of the high travel demand stations in each time period. Planning a new travel route; and the service quality and efficiency of urban public transportation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic planning, and in particular to an urban traffic intelligent planning assistance system and method based on big data analysis. Background Art

[0002] Existing public transportation route planning often relies on historical data and empirical judgments, lacking accurate grasp of current travel demand and real-time response. This traditional planning method has obvious shortcomings: first, it often ignores the dynamic characteristics of traffic changes between different regions, resulting in insufficient services in some high-demand areas; second, there is a lack of flexible adjustment mechanisms for peak hours and special events, making it difficult for route planning to adapt to changing needs in actual operation. In addition, the existing planning lacks a scientific prediction model and cannot effectively identify and utilize historical travel data, resulting in inefficient and wasteful resource allocation.

[0003] The patent with the publication number CN114330106A discloses a method for urban public transportation planning, including: measuring the carbon emissions of the city, calculating the optimization range that various modes of transportation should obtain; collecting taxi and private car travel data in the city to be optimized; processing the collected travel data; performing map matching on the original GPS track points in the itinerary; clustering the starting and ending points in the map matching data to obtain candidate public transportation stations; using the BiLSTM neural network model based on the attention mechanism to calculate the probability of the current public transportation station to the next different public transportation station from the candidate public transportation stations obtained above; comparing the new public transportation routes obtained with the existing public transportation system routes to see whether the expected goals are achieved. However, this method fails to take into account the subjective needs of residents such as station traffic;

[0004] To this end, the present invention proposes an urban traffic intelligent planning assistance system and method based on big data analysis. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes an urban traffic intelligent planning auxiliary system and method based on big data analysis, which improves the service quality and efficiency of urban public transportation.

[0006] To achieve the above objectives, an urban traffic intelligent planning auxiliary method based on big data analysis is proposed, which includes the following steps:

[0007] Step 1: Collect historical travel habit data of city residents and historical traffic flow data of urban traffic;

[0008] Step 2: Extract features from historical travel habit data and historical traffic flow data to construct a historical feature set;

[0009] Step 3: Based on the historical feature set, train a travel demand prediction model to predict passenger flow between different urban areas;

[0010] Step 4: According to the prediction results of the travel demand prediction model, identify the high travel demand stations in each time period;

[0011] Step 5: Plan new travel routes using the shortest path algorithm based on the location distribution of high travel demand sites in each time period.

[0012] The historical travel habit data is collected in the following manner:

[0013] Collect the number and location of each public site;

[0014] Statistics are collected on the riding habits of residents at each public stop in each time period; the time period is a preset statistical duration;

[0015] The residents’ riding habits at each public station in each time period constitute the historical travel habit data.

[0016] The historical traffic flow data is collected in the following manner:

[0017] For each public site, all adjacent sites are traversed and found; the traversal method of the adjacent sites is:

[0018] Mark public sites as i;

[0019] Label the remaining public sites as j;

[0020] If there is at least one route between public site j and public site i, and there is no other public site in the route, then public site j is called an adjacent site of public site i;

[0021] The combination of each common site and any of its adjacent sites is regarded as a set of site combinations;

[0022] For any combination of sites, one of the public sites is used as the starting site, and the other public site is used as the destination site. All feasible paths from the starting site to the destination site are traversed and queried as road segments.

[0023] For any combination of stations, the traffic flow parameters of all its road segments in each past time period are counted;

[0024] The traffic flow parameters of all road segments constitute the historical traffic flow data.

[0025] The method of extracting features from historical travel habit data and historical traffic flow data and constructing a historical feature set is as follows:

[0026] Create a data framework with multiple feature fields to integrate historical travel habits data and historical traffic flow data into a unified data set;

[0027] Extract the first key feature from the historical travel habit data;

[0028] The first key features form a first feature set;

[0029] Extracting the second key feature from historical traffic flow data;

[0030] The second key features constitute a second feature set;

[0031] The number of each public site and its corresponding first feature set and second feature set are integrated into a unified historical feature set.

[0032] The method of training the travel demand prediction model for predicting passenger flow between different urban areas based on the historical feature set is as follows:

[0033] The travel demand prediction model takes features in the historical feature set as input and outputs predicted passenger flow from one area to another area within a specific time period;

[0034] Preprocess the historical feature set;

[0035] The preprocessed historical feature set is divided into a training set, a validation set, and a test set according to a preset ratio;

[0036] Use the training set data to train the travel demand forecasting model and set hyperparameters;

[0037] The mean square error function is used as the loss function to evaluate the performance of the travel demand forecasting model;

[0038] Use Adam as the optimization algorithm to update the parameters of the travel demand forecasting model;

[0039] Use the validation set to evaluate the performance of the travel demand forecasting model and adjust the hyperparameters based on the evaluation results;

[0040] The performance of the final travel demand forecasting model is evaluated on the test set, the error between the predicted result and the actual value is calculated, and the mean square error is used for evaluation.

[0041] The step of identifying the high travel demand sites in each time period according to the prediction results of the travel demand prediction model comprises the following steps:

[0042] Step 11: By inputting the historical feature set of each public station into the travel demand prediction model, the predicted value of the passenger flow transported by each public station to each adjacent station in each future time period is obtained;

[0043] Step 12: Count the total number of predicted values ​​of passenger flow at each public station in each future time period as the total demand number;

[0044] Step 13: Preset traffic threshold; for each time period:

[0045] If the total demand number of a public station is greater than the flow threshold, the public station will be regarded as a high travel demand station in that time period.

[0046] The method of planning a new travel route using the shortest path algorithm based on the location distribution of high travel demand sites in each time period is as follows:

[0047] For each time period:

[0048] Create a transportation network graph, where each node represents a public station and each edge represents a traversable path between two public stations;

[0049] Assign an edge weight to each edge, where the edge weight is the length of each edge;

[0050] Filter out all high travel demand stations in the transportation network diagram;

[0051] Select a high travel demand station as the starting point and use the Dijkstra algorithm to obtain the shortest path between other high travel demand stations;

[0052] Plan new travel routes based on the shortest paths between all high travel demand stations and other high travel demand stations.

[0053] The method of planning a new travel route is:

[0054] Assign path weights to each shortest path;

[0055] The evaluation method of the path weight is calculated based on passenger demand, path length and traffic flow;

[0056] Sorting the path weights of all shortest paths, selecting the shortest paths with high weights for aggregation, and using them as the basis for preliminary bus routes; the high weight means that the path weight is greater than a preset path weight threshold;

[0057] All public sites included in the shortest path after aggregation are regarded as core sites;

[0058] Use a greedy algorithm to connect all common sites included in the aggregated shortest path, giving priority to connecting the site with the highest path weight.

[0059] The steps of the greedy algorithm are:

[0060] Starting from the departure site, each time select the path with the highest path weight connected to the current site.

[0061] Iterate until all core stations are covered and a connected public transportation line is generated, that is, a new travel route is planned.

[0062] An urban traffic intelligent planning auxiliary system based on big data analysis is proposed, which includes a historical data collection module, a feature set construction module, a prediction model training module and a route planning module; wherein each module is electrically connected;

[0063] A historical data collection module collects historical travel habit data of city residents and historical traffic flow data of city traffic, and sends the historical travel habit data and historical traffic flow data to a feature set construction module;

[0064] The feature set construction module extracts features from historical travel habit data and historical traffic flow data, constructs a historical feature set, and sends the historical feature set to the prediction model training module;

[0065] A prediction model training module, which trains a travel demand prediction model for predicting passenger flow between different urban areas based on a historical feature set, and sends the travel demand prediction model to a route planning module;

[0066] The route planning module identifies the high travel demand sites in each time period based on the prediction results of the travel demand prediction model, and plans new travel routes using the shortest path algorithm based on the location distribution of the high travel demand sites in each time period.

[0067] An electronic device is proposed, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0068] The processor executes the above-mentioned urban traffic intelligent planning assistance method based on big data analysis by calling the computer program stored in the memory.

[0069] A computer-readable storage medium is provided, on which a rewritable computer program is stored;

[0070] When the computer program runs on a computer device, the computer device executes the above-mentioned urban traffic intelligent planning assistance method based on big data analysis.

[0071] Compared with the prior art, the present invention has the following beneficial effects:

[0072] The present invention collects historical travel habit data of urban residents and historical traffic flow data of urban traffic, extracts features from the historical travel habit data and historical traffic flow data, constructs a historical feature set, and trains a travel demand prediction model for predicting passenger flow between different urban areas based on the historical feature set. According to the prediction results of the travel demand prediction model, the high travel demand sites in each time period are identified, and according to the location distribution of the high travel demand sites in each time period, the shortest path algorithm is used to plan new travel routes; by analyzing the high travel demand sites in each time period, new routes are scientifically designed to ensure that the areas in the city that need the most service are covered. At the same time, the scheme uses the shortest path algorithm to optimize the route design, so that traffic resources can be allocated more efficiently, reducing the travel time and cost of passengers, thereby improving the service quality and efficiency of public transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a flow chart of the urban traffic intelligent planning assistance method based on big data analysis in Example 1 of the present invention;

[0074] Figure 2 This is a module connection diagram of the urban traffic intelligent planning assistance system based on big data analysis in Example 2 of the present invention. DETAILED DESCRIPTION

[0075] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] Example 1

[0077] like Figure 1 As shown, the urban traffic intelligent planning auxiliary method based on big data analysis includes the following steps:

[0078] Step 1: Collect historical travel habit data of city residents and historical traffic flow data of urban traffic;

[0079] Step 2: Extract features from historical travel habit data and historical traffic flow data to construct a historical feature set;

[0080] Step 3: Based on the historical feature set, train a travel demand prediction model to predict passenger flow between different urban areas;

[0081] Step 4: According to the prediction results of the travel demand prediction model, identify the high travel demand stations in each time period;

[0082] Step 5: Plan new travel routes using the shortest path algorithm based on the location distribution of high travel demand sites in each time period.

[0083] Specifically, the historical travel habit data is collected in the following manner:

[0084] Collect the number and location of each public station; specifically, the public station is a station for public transportation, including but not limited to urban bus stations, rural-urban bus stations, inter-city bus stations, etc.;

[0085] Statistics are collected on the riding habits of residents at each public station in each time period; the time period is a preset statistical duration, such as every 6 hours, every 12 hours, every working day, every weekend, etc.;

[0086] The residents’ riding habits at each public station in each time period constitute the historical travel habit data;

[0087] Specifically, the residents' riding habits include but are not limited to the number of people getting on and off the bus at the station and the average waiting time in each past time period. It is understandable that the more people getting on and off the bus in a certain time period, or the longer the average waiting time, the greater the passenger flow demand of the station, and more public transportation routes may need to be planned;

[0088] The number of people getting on and off the bus and the average waiting time can be calculated by installing monitoring facilities at public stops and using artificial intelligence technology in the background of the monitoring facilities to count the number of people getting on and off the bus and the waiting time of each waiting resident at the public stop.

[0089] Furthermore, the historical traffic flow data is collected in the following manner:

[0090] For each public site, all adjacent sites are traversed and found; the traversal method of the adjacent sites is:

[0091] Mark public sites as i;

[0092] Label the remaining public sites as j;

[0093] If there is at least one route between public site j and public site i, and there is no other public site in the route, then public site j is called an adjacent site of public site i;

[0094] The combination of each common site and any of its adjacent sites is regarded as a set of site combinations;

[0095] For any combination of sites, one of the public sites is used as the starting site, and the other public site is used as the destination site. All feasible paths from the starting site to the destination site are traversed and queried as road segments.

[0096] For any combination of stations, the traffic flow parameters of all its road segments in each past time period are counted;

[0097] The traffic flow parameters of all road segments constitute the historical traffic flow data.

[0098] Specifically, the traffic flow parameters include but are not limited to:

[0099] The sum of the traffic volume of all road sections, the traffic density within a unit section, the average vehicle speed, and the ratio of vehicles on the same road;

[0100] Among them, the same-vehicle ratio refers to the ratio of the number of vehicles that pass both the departure station and the destination station to the total flow; it can be understood that the same-vehicle ratio measures the travel demand from the departure station to the destination station; and the traffic flow, traffic density and average speed measure the congestion level of the road section in each time period, and the more congested it is, the greater the travel demand.

[0101] Furthermore, the method of extracting features from the historical travel habit data and the historical traffic flow data and constructing a historical feature set is as follows:

[0102] Create a data framework with multiple feature fields to integrate historical travel habits data and historical traffic flow data into a unified data set;

[0103] The feature fields in the multiple feature fields include but are not limited to station number, time period, number of people getting on and off the bus, average waiting time, adjacent station number, traffic volume, traffic density, average vehicle speed, ratio of vehicles in the same vehicle, etc.;

[0104] Extract the first key feature from the historical travel habit data;

[0105] Preferably, the method of extracting the first key feature includes but is not limited to:

[0106] 1. Statistical characteristics:

[0107] Total number of boardings and alightings: Calculate the total number of boardings and alightings at each station in different time periods.

[0108] Average waiting time: Calculate the average waiting time of residents in each time period.

[0109] 2. Peak characteristics:

[0110] Peak Pickup and Dropoff Numbers: Identify the number of pick-ups and drop-offs at each station during peak hours.

[0111] Peak Waiting Time: Calculates the average waiting time during peak hours.

[0112] 3. Proportional characteristics:

[0113] Boarding and alighting ratio: Calculate the ratio of the number of boarding and alighting passengers in a certain time period to the total traffic volume in that time period to determine the relative demand for the station;

[0114] The first key features form a first feature set;

[0115] Extracting the second key feature from historical traffic flow data;

[0116] The method of extracting the second key feature includes but is not limited to:

[0117] Traffic flow characteristics:

[0118] Total traffic volume: Calculate the sum of the traffic volume of each road in different time periods.

[0119] Average speed: Statistics on the average speed of each road.

[0120] Traffic density: Calculates the number of vehicles in a unit road section to reflect the degree of congestion.

[0121] Shared vehicle ratio: Calculate the shared vehicle ratio, that is, the ratio of the number of vehicles passing through the departure and destination stations to the total flow, as a characteristic to measure travel demand.

[0122] Peak flow characteristics:

[0123] Peak traffic volume: Traffic volume data during peak hours.

[0124] Peak traffic density: traffic density within a unit road section during peak hours.

[0125] The second key features constitute a second feature set;

[0126] Integrate the number of each public site and its corresponding first feature set and second feature set into a unified historical feature set;

[0127] An example of a unified historical feature set is shown in Table 1:

[0128] Table 1 Example table of historical feature sets

[0129]

[0130]

[0131] Furthermore, the method of training the travel demand prediction model for predicting passenger flow between different urban areas based on the historical feature set is:

[0132] The travel demand prediction model takes features in the historical feature set as input and outputs predicted passenger flow from one area to another area within a specific time period;

[0133] Preprocess the historical feature set;

[0134] Specifically, the pretreatment includes but is not limited to:

[0135] Remove missing values ​​and outliers to ensure data quality;

[0136] Feature encoding: Numerical encoding (such as one-hot encoding) of categorical variables (such as site number and time period);

[0137] Standardization: Standardize the numerical features to make their mean 0 and standard deviation 1 to improve the training effect of the model;

[0138] The preprocessed historical feature set is divided into a training set, a validation set, and a test set according to a preset ratio;

[0139] Use the training set data to train the travel demand forecasting model and set hyperparameters;

[0140] The mean square error function is used as the loss function to evaluate the performance of the travel demand forecasting model;

[0141] Use Adam as the optimization algorithm to update the parameters of the travel demand forecasting model;

[0142] Use the validation set to evaluate the performance of the travel demand forecasting model, adjust the hyperparameters based on the evaluation results, and optimize the travel demand forecasting model structure;

[0143] K-fold cross validation is used to improve the generalization ability of the travel demand forecasting model;

[0144] The performance of the final travel demand forecasting model is evaluated on the test set, the error between the predicted result and the actual value is calculated, and the mean square error is used for evaluation.

[0145] Furthermore, the step of identifying the high travel demand sites in each time period according to the prediction results of the travel demand prediction model includes the following steps:

[0146] Step 11: By inputting the historical feature set of each public station into the travel demand prediction model, the predicted value of the passenger flow transported by each public station to each adjacent station in each future time period is obtained;

[0147] Step 12: Count the total number of predicted values ​​of passenger flow at each public station in each future time period as the total demand number;

[0148] Step 13: Preset traffic threshold; for each time period:

[0149] If the total demand number of a public station is greater than the flow threshold, the public station will be regarded as a high travel demand station in that time period.

[0150] Furthermore, the method of planning a new travel route using the shortest path algorithm according to the location distribution of high travel demand sites in each time period is as follows:

[0151] For each time period:

[0152] Create a transportation network graph, where each node represents a public station and each edge represents a traversable path between two public stations;

[0153] Assign an edge weight to each edge, where the edge weight is the length of each edge;

[0154] Preferably, the edge weight may be the travel distance, or the average travel time of the path in the time period, or the average traffic flow of the path in the time period, or the weighted sum of the travel distance, travel time average and traffic flow average;

[0155] Filter out all high travel demand stations in the transportation network diagram;

[0156] Select a high travel demand station as the starting point and use the Dijkstra algorithm to obtain the shortest path between other high travel demand stations;

[0157] Plan new travel routes based on the shortest paths between all high travel demand stations and other high travel demand stations.

[0158] Specifically, the method of planning a new travel route is:

[0159] Assign path weights to each shortest path;

[0160] Preferably, the evaluation method of the path weight is calculated based on passenger demand, path length and traffic flow;

[0161] Specifically, the path weight can be: W = α × D + β × T + γ × F, where W is the path weight, α, β, γ are preset weight coefficients, and D, T and F represent the travel distance, travel time and traffic flow of the path respectively; it can be understood that passenger demand: the greater the passenger flow on the path, the higher the weight. Path length: shorter paths are given priority, and the shorter the path, the higher the weight; traffic conditions: the less traffic flow on the path, the higher the weight.

[0162] Sorting the path weights of all shortest paths, selecting the shortest paths with high weights for aggregation, and using them as the basis for preliminary bus routes; the high weight means that the path weight is greater than a preset path weight threshold;

[0163] All public stations included in the aggregated shortest path are regarded as core stations to ensure that the key areas served by the bus routes are covered;

[0164] A greedy algorithm is used to connect all public sites included in the aggregated shortest path, with the site with the highest path weight being connected first to ensure the effectiveness of the line.

[0165] The steps of the greedy algorithm are:

[0166] Starting from the departure site, each time select the path with the highest path weight connected to the current site.

[0167] Iterate until all core stations are covered and a connected public transportation line is generated, that is, a new travel route is planned.

[0168] Preferably, the new travel route may be further optimized:

[0169] Specific optimization measures include:

[0170] Redundant site removal:

[0171] In the generated preliminary route, there may be some redundant stations, which have less passenger flow and do not affect the route connectivity. Use the dynamic programming algorithm to remove these redundant stations:

[0172] Define a cost function to evaluate the cost of the route, taking into account factors such as distance, time, and traffic;

[0173] Use dynamic programming to traverse all station combinations and remove those stations that contribute less to line costs to ensure a balance between passenger demand and line efficiency;

[0174] Loop line optimization:

[0175] In some cases, bus routes can be designed as loops to improve passenger transfer efficiency. Use the Euler circuit or Hamiltonian circuit method in graph theory to check whether a loop can be constructed that covers all core stations.

[0176] If the routes can form a circular path, the shortest path of the circular route is calculated;

[0177] Departure frequency calculation:

[0178] Based on the passenger flow during high-demand periods, the departure frequency of each station is calculated. Using linear programming methods, the departure schedule of each line is optimized so that high-demand stations have a higher departure frequency during peak hours.

[0179] Example 2

[0180] like Figure 2As shown, the urban traffic intelligent planning auxiliary system based on big data analysis includes a historical data collection module, a feature set construction module, a prediction model training module and a route planning module; wherein each module is electrically connected;

[0181] A historical data collection module collects historical travel habit data of city residents and historical traffic flow data of city traffic, and sends the historical travel habit data and historical traffic flow data to a feature set construction module;

[0182] The feature set construction module extracts features from historical travel habit data and historical traffic flow data, constructs a historical feature set, and sends the historical feature set to the prediction model training module;

[0183] A prediction model training module, which trains a travel demand prediction model for predicting passenger flow between different urban areas based on a historical feature set, and sends the travel demand prediction model to a route planning module;

[0184] The route planning module identifies the high travel demand sites in each time period based on the prediction results of the travel demand prediction model, and plans new travel routes using the shortest path algorithm based on the location distribution of the high travel demand sites in each time period.

[0185] Example 3

[0186] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by the one or more processors, the urban traffic intelligent planning assistance method based on big data analysis as described above may be executed.

[0187] The method or device according to the implementation mode of the present application can also be implemented with the help of the architecture of the electronic device of the present application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, an input / output component, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, can store the urban traffic intelligent planning auxiliary method based on big data analysis provided by the present application.

[0188] Furthermore, the electronic device may also include a user interface. Of course, the architecture disclosed in this application is only exemplary, and when implementing different devices, one or more components in the electronic device disclosed in this application may be omitted according to actual needs.

[0189] Example 4

[0190] The present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by a processor, the urban traffic intelligent planning auxiliary method based on big data analysis disclosed in the present application can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0191] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, and when the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0192] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0193] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0194] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0195] The above preset parameters or preset thresholds are all set by technicians in this field according to actual conditions or obtained through large-scale data simulation.

[0196] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An urban traffic intelligent planning auxiliary method based on big data analysis, characterized in that: The following steps are involved: Step 1: Collect historical travel habit data of city residents and historical traffic flow data of urban traffic; Step 2: Extract features from historical travel habit data and historical traffic flow data to construct a historical feature set; Step 3: Based on the historical feature set, train a travel demand prediction model to predict passenger flow between different urban areas; Step 4: According to the prediction results of the travel demand prediction model, identify the high travel demand stations in each time period; Step 5: Plan new travel routes using the shortest path algorithm based on the location distribution of high travel demand sites in each time period.

2. The urban traffic intelligent planning auxiliary method based on big data analysis according to claim 1 is characterized in that: The historical travel habit data is collected in the following manner: Collect the number and location of each public site; Statistics are collected on the riding habits of residents at each public stop in each time period; the time period is a preset statistical duration; The residents’ riding habits at each public station in each time period constitute the historical travel habit data.

3. The urban traffic intelligent planning auxiliary method based on big data analysis according to claim 2 is characterized in that: The historical traffic flow data is collected in the following manner: For each public site, all adjacent sites are traversed and found; the traversal method of the adjacent sites is: Mark public sites as i; Label the remaining public sites as j; If there is at least one route between public site j and public site i, and there is no other public site in the route, then public site j is called an adjacent site of public site i; The combination of each common site and any of its adjacent sites is regarded as a set of site combinations; For any combination of sites, one of the public sites is used as the starting site, and the other public site is used as the destination site. All feasible paths from the starting site to the destination site are traversed and queried as road segments. For any combination of stations, the traffic flow parameters of all its road segments in each past time period are counted; The traffic flow parameters of all road segments constitute the historical traffic flow data.

4. The urban traffic intelligent planning auxiliary method based on big data analysis according to claim 3 is characterized in that: The method of extracting features from historical travel habit data and historical traffic flow data and constructing a historical feature set is as follows: Create a data framework with multiple feature fields to integrate historical travel habits data and historical traffic flow data into a unified data set; Extract the first key feature from the historical travel habit data; The first key features form a first feature set; Extracting the second key feature from historical traffic flow data; The second key features constitute a second feature set; The number of each public site and its corresponding first feature set and second feature set are integrated into a unified historical feature set.

5. The urban traffic intelligent planning auxiliary method based on big data analysis according to claim 4 is characterized in that: The method of training the travel demand prediction model for predicting passenger flow between different urban areas based on the historical feature set is as follows: The travel demand prediction model takes features in the historical feature set as input and outputs predicted passenger flow from one area to another area within a specific time period; Preprocess the historical feature set; The preprocessed historical feature set is divided into a training set, a validation set, and a test set according to a preset ratio; Use the training set data to train the travel demand forecasting model and set hyperparameters; The mean square error function is used as the loss function to evaluate the performance of the travel demand forecasting model; Use Adam as the optimization algorithm to update the parameters of the travel demand forecasting model; Use the validation set to evaluate the performance of the travel demand forecasting model and adjust the hyperparameters based on the evaluation results; The performance of the final travel demand forecasting model is evaluated on the test set, the error between the predicted result and the actual value is calculated, and the mean square error is used for evaluation.

6. The urban traffic intelligent planning auxiliary method based on big data analysis according to claim 5 is characterized in that: The step of identifying the high travel demand sites in each time period according to the prediction results of the travel demand prediction model comprises the following steps: Step 11: By inputting the historical feature set of each public station into the travel demand prediction model, the predicted value of the passenger flow transported by each public station to each adjacent station in each future time period is obtained; Step 12: Count the total number of predicted values ​​of passenger flow at each public station in each future time period as the total demand number; Step 13: Preset traffic threshold; for each time period: If the total demand number of a public station is greater than the flow threshold, the public station will be regarded as a high travel demand station in that time period.

7. The urban traffic intelligent planning auxiliary method based on big data analysis according to claim 6 is characterized in that: The method of planning a new travel route using the shortest path algorithm based on the location distribution of high travel demand sites in each time period is as follows: For each time period: Create a transportation network graph, where each node represents a public station and each edge represents a traversable path between two public stations; Assign an edge weight to each edge, where the edge weight is the length of each edge; Filter out all high travel demand stations in the transportation network diagram; Select a high travel demand station as the starting point and use the Dijkstra algorithm to obtain the shortest path between other high travel demand stations; Plan new travel routes based on the shortest paths between all high travel demand stations and other high travel demand stations.

8. The urban traffic intelligent planning auxiliary method based on big data analysis according to claim 7 is characterized in that: The method of planning a new travel route is: Assign path weights to each shortest path; The evaluation method of the path weight is calculated based on passenger demand, path length and traffic flow; Sorting the path weights of all shortest paths, selecting the shortest paths with high weights for aggregation, and using them as the basis for preliminary bus routes; the high weight means that the path weight is greater than a preset path weight threshold; All public sites included in the aggregated shortest path are regarded as core sites; Use a greedy algorithm to connect all common sites included in the aggregated shortest path, giving priority to connecting the site with the highest path weight.

9. The urban traffic intelligent planning auxiliary method based on big data analysis according to claim 8 is characterized in that: The steps of the greedy algorithm are: Starting from the departure site, each time select the path with the highest path weight connected to the current site; Iterate until all core stations are covered and a connected public transportation line is generated, that is, a new travel route is planned.

10. An urban traffic intelligent planning assistance system based on big data analysis, which is used to implement the urban traffic intelligent planning assistance method based on big data analysis as described in any one of claims 1 to 9, characterized in that: It includes a historical data collection module, a feature set construction module, a prediction model training module and a route planning module; wherein each module is electrically connected; A historical data collection module collects historical travel habit data of city residents and historical traffic flow data of city traffic, and sends the historical travel habit data and historical traffic flow data to a feature set construction module; The feature set construction module extracts features from historical travel habit data and historical traffic flow data, constructs a historical feature set, and sends the historical feature set to the prediction model training module; A prediction model training module, which trains a travel demand prediction model for predicting passenger flow between different urban areas based on a historical feature set, and sends the travel demand prediction model to a route planning module; The route planning module identifies the high travel demand sites in each time period based on the prediction results of the travel demand prediction model, and plans new travel routes using the shortest path algorithm based on the location distribution of the high travel demand sites in each time period.

Images