CN116738098A - Urban freight visualization method and system based on WebGIS - Google Patents
Urban freight visualization method and system based on WebGIS Download PDFInfo
- Publication number
- CN116738098A CN116738098A CN202310703075.5A CN202310703075A CN116738098A CN 116738098 A CN116738098 A CN 116738098A CN 202310703075 A CN202310703075 A CN 202310703075A CN 116738098 A CN116738098 A CN 116738098A
- Authority
- CN
- China
- Prior art keywords
- freight
- vehicle
- model
- data
- urban
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007794 visualization technique Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000012800 visualization Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000002372 labelling Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 238000013461 design Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000002790 cross-validation Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000011780 sodium chloride Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a city freight visualization method and system based on WebGIS, wherein the method comprises the following steps: acquiring urban freight vehicle data in a vehicle-mounted satellite positioning system; training a congestion index prediction model, and predicting congestion indexes of different traffic roads in a freight visualization model; labeling the grading result at the corresponding intersection roadside; and backtracking the running track of the vehicle in the freight visualization model. According to the application, the vehicle running data is acquired through the truck-mounted satellite positioning system, and the data is stored in the time sequence database. The deep learning LSTM model is used for constructing a network training based on a time sequence congestion prediction model, and a congestion index threshold value is set for a user to refer to. Besides the congestion index, the method can obtain the target vehicle route and the congestion index of each road section of the route in the time range according to the license plate number and the vehicle running time interval, and provides decision support for route optimization. Meanwhile, a vehicle track backtrack is constructed, and the specific transportation track of the vehicle can be displayed and inquired in real time.
Description
Technical Field
The application relates to the technical field of traffic flow, in particular to a city freight visualization method and system based on WebGIS.
Background
At present, urban traffic and transportation scenes mainly focus on the flow of passenger transportation, and neglect the flow of freight transportation. Although logistic communication is an important means for characterizing the intra-city logistic communication, studies based on logistic communication are generally subject to data constraints. The business or site distribution data used by most research facilities does not truly reflect logistics. Although these studies have not directly correlated the internal logistics space structure of a city, the data and analysis methods provided by the studies can help understand the logistics elements and logistics space system of a city. In particular, the parking behavior and the route of the truck are analyzed according to GPS data, and the method becomes an important means for researching and describing urban logistics and landscapes. However, more specific logistics traffic planning research needs to be able to further refine the analysis in the time dimension, study the logistics network and logistics transportation trajectories under different time slices; and more, the requirement of GPS data with a longer period is needed, so that more stable urban internal logistics relations are analyzed, and compared with urban logistics relations in different periods, the characteristic direction and the power mechanism of the spatial evolution of the urban internal logistics are induced. The method has great analysis significance for project evaluation of urban logistics transportation systems. However, the related art lacks basic graphic presentation based on GIS (Geographic Information System ) spatial concepts, such as: the truck transportation state and flow at any time and position on the map cannot be displayed in a logistics track mode on the map. Therefore, how to propose a method for visualizing a traffic flow showing a physical traffic on a map in a data chart and a track path manner at a corresponding position of the map is a problem to be solved.
Disclosure of Invention
The application aims to provide a city freight visualization method based on WebGIS, which is characterized in that vehicle running data is obtained through a truck-mounted satellite positioning system, the data comprises geographic position information, vehicle speed, azimuth angle and the like, and the data is stored in a time sequence database. The deep learning LSTM model is used for constructing a network training based on a time sequence congestion prediction model, and a congestion index threshold value is set for a user to refer to. Besides the congestion index, the method can obtain the target vehicle route and the congestion index of each road section of the route in the time range according to the license plate number and the vehicle running time interval, and provides decision support for route optimization. Meanwhile, a vehicle track backtrack is constructed, the specific transportation track of the vehicle can be displayed and inquired in real time, and the real driving route characteristics of the truck are known.
The embodiment of the application provides a city freight visualization method based on WebGIS, which comprises the following steps:
acquiring urban freight vehicle data in a vehicle-mounted satellite positioning system;
based on a WebGIS engine, constructing a freight visualization model according to the urban freight vehicle data;
training a congestion index prediction model based on the urban freight vehicle data, and predicting congestion indexes of different traffic roads in the freight visualization model;
classifying according to the congestion index based on a plurality of preset index classification thresholds, and marking classification results beside the corresponding traffic roads; the grading result comprises: smooth, slow, crowded and blocked;
and receiving the vehicle attribute input by the user, tracing back the vehicle running track in the freight visualization model based on the vehicle attribute, and displaying the tracing back result.
Preferably, the city freight vehicle data includes: the location, speed and direction of a large number of freight vehicles in a city.
Preferably, after collecting the data of the urban freight vehicle, the method further comprises:
transmitting the acquired urban freight vehicle data to a database server for storage; the database in the database server is a time sequence database.
Preferably, the training a congestion index prediction model based on the urban freight vehicle data includes:
data preprocessing: preprocessing the urban freight vehicle data, introduced weather conditions, road construction, control and other conditions as variables as a data set; the pretreatment process comprises the steps of data cleaning and normalization;
model design and training: model training the preprocessed data set by using an LSTM network model, and evaluating the performance of the trained model by using a cross-validation technique;
model evaluation: evaluating the accuracy and efficiency of the trained model using the test dataset;
model optimization: and (5) optimizing the trained model by using an L2 regularization and dropout method.
Preferably, the vehicle attribute includes: license plate number, time frame.
Preferably, the tracking back of the vehicle running track is performed on the freight visualization model, which comprises:
and screening out a corresponding target vehicle according to the vehicle attribute in the freight visualization model, and backtracking the vehicle running track of the target vehicle.
The embodiment of the application provides a city freight visualization system based on WebGIS, which is characterized by comprising the following steps:
the urban freight vehicle data acquisition module is used for acquiring urban freight vehicle data in the vehicle-mounted satellite positioning system;
the freight visualization model building module is used for building a freight visualization model according to the urban freight vehicle data based on a WebGIS engine;
the congestion index prediction module is used for training a congestion index prediction model based on the urban freight vehicle data and predicting the congestion indexes of different traffic roads in the freight visualization model;
the congestion grading module is used for grading according to the congestion indexes based on a plurality of preset index grading thresholds, and labeling grading results beside the corresponding traffic roads; the grading result comprises: smooth, slow, crowded and blocked;
and the vehicle running track backtracking module is used for receiving the vehicle attribute input by the user, carrying out vehicle running track backtracking on the freight visualization model based on the vehicle attribute, and displaying the backtracking result.
Preferably, the city freight vehicle data includes: the location, speed and direction of a large number of freight vehicles in a city.
Preferably, after the urban freight data acquisition module acquires the urban freight data, the following operations are further performed:
transmitting the acquired urban freight vehicle data to a database server for storage; the database in the database server is a time sequence database.
Preferably, the congestion index prediction module trains a congestion index prediction model based on the urban freight vehicle data, including:
data preprocessing: preprocessing the urban freight vehicle data, introduced weather conditions, road construction, control and other conditions as variables as a data set; the pretreatment process comprises the steps of data cleaning and normalization;
model design and training: model training the preprocessed data set by using an LSTM network model, and evaluating the performance of the trained model by using a cross-validation technique;
model evaluation: evaluating the accuracy and efficiency of the trained model using the test dataset;
model optimization: and (5) optimizing the trained model by using an L2 regularization and dropout method.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the application is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, serve to explain the application. In the drawings:
FIG. 1 is a schematic diagram of a city freight visualization method based on WebGIS according to an embodiment of the present application;
fig. 2 is a schematic diagram of a practical application flow of a city freight visualization method based on WebGIS in an embodiment of the present application;
FIG. 3 is a schematic diagram of an actual application interface of a city freight visualization method based on WebGIS in an embodiment of the application;
FIG. 4 is a schematic diagram of another practical application interface of the city freight visualization method based on WebGIS according to the embodiment of the present application;
FIG. 5 is a schematic diagram of yet another practical application interface of the city freight visualization method based on WebGIS according to the embodiment of the present application;
FIG. 6 is a schematic diagram of another practical application interface of a city freight visualization method based on WebGIS according to an embodiment of the present application;
fig. 7 is a schematic diagram of a city freight visualization system based on WebGIS according to an embodiment of the present application.
Detailed Description
The preferred embodiments of the present application will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present application only, and are not intended to limit the present application.
The embodiment of the application provides a city freight visualization method based on WebGIS, as shown in figure 1, comprising the following steps:
step S1: acquiring urban freight vehicle data in a vehicle-mounted satellite positioning system;
step S2: based on a WebGIS engine, constructing a freight visualization model according to the urban freight vehicle data;
step S3: training a congestion index prediction model based on the urban freight vehicle data, and predicting congestion indexes of different traffic roads in the freight visualization model;
step S4: classifying according to the congestion index based on a plurality of preset index classification thresholds, and marking classification results beside the corresponding traffic roads; the grading result comprises: smooth, slow, crowded and blocked;
step S5: and receiving the vehicle attribute input by the user, tracing back the vehicle running track in the freight visualization model based on the vehicle attribute, and displaying the tracing back result.
The city freight vehicle data includes: the location, speed and direction of a large number of freight vehicles in a city.
After collecting the data of the urban freight vehicle, the method further comprises the following steps:
transmitting the acquired urban freight vehicle data to a database server for storage; the database in the database server is a time sequence database.
The training of the congestion index prediction model based on the urban freight vehicle data comprises the following steps:
data preprocessing: preprocessing the urban freight vehicle data, introduced weather conditions, road construction, control and other conditions as variables as a data set; the pretreatment process comprises the steps of data cleaning and normalization;
model design and training: model training the preprocessed data set by using an LSTM network model, and evaluating the performance of the trained model by using a cross-validation technique;
model evaluation: evaluating the accuracy and efficiency of the trained model using the test dataset;
model optimization: and (5) optimizing the trained model by using an L2 regularization and dropout method.
The vehicle attributes include: license plate number, time frame.
And backtracking the running track of the vehicle on the freight visualization model, comprising:
and screening out a corresponding target vehicle according to the vehicle attribute in the freight visualization model, and backtracking the vehicle running track of the target vehicle.
The working principle and the beneficial effects of the technical scheme are as follows:
as shown in fig. 2 to 3, the present application, when applied, comprises the following steps:
1. acquisition and storage of data for collecting vehicle satellite positioning system
GPS data acquisition: the scheme adopts high-precision vehicle-mounted GPS equipment to collect information such as the position, the speed, the direction and the like of the vehicle in real time.
And (3) data transmission: the application adopts a rapid and reliable data transmission technology to transmit the collected satellite positioning system data to a database server in real time.
And (3) data storage: the application adopts the high-efficiency stable time sequence database, and compared with the traditional relational database, the database can better meet the characteristics of quick generation frequency, serious time acquisition dependence, multiple point positions, large information quantity and the like of satellite positioning system data.
2. Training congestion index prediction model
Data preprocessing: the position, speed and direction are preprocessed by taking the conditions of weather conditions, road construction, control and the like as variables as a data set so as to adapt to the input format of the LSTM model. The preprocessing process may include steps such as data cleaning, normalization, and the like. The method comprises the steps of obtaining real-time data of weather conditions, road construction and control at the time, and taking the real-time data as a reference value and an environmental background parameter of a model. And constructing a characteristic matrix of the data according to the selected important characteristics, such as the traffic flow, the speed and the like. The raw data is converted into a time series format suitable for the LSTM model. The model is trained by using the training set, and is verified and optimized by using the verification set. And judging whether the vehicle is on the section of the road through the LSTM model. LSTM (long and short term memory network) is a recurrent neural network that is widely used because it works better than conventional recurrent and convolutional neural networks in dealing with time series problems. In the LSTM model, data is input into the model in time sequence, can memorize the prior information and decide which information needs to be discarded and which needs to be reserved, and has good long-term dependence on time sequence. In the LSTM model design, the number of network layers, the number of adjusting units, the learning rate, the loss function and the like are set so as to pointedly optimize the LSTM network.
Model design: the LSTM network model is used for training the data to predict traffic jam. The LSTM model has memory, and can predict future states by using historical data, so that the LSTM model is suitable for predicting continuous data.
Training: model training is performed using the processed data sets and cross-validation techniques are used to evaluate the performance of the model.
Model evaluation: and the accuracy and the efficiency of the model are evaluated by using the test data set, so that the model is ensured to have higher accuracy. The test data includes: road network route, vehicle GPS, real-time speed, real-time weather, actual road conditions. And obtaining the current real-time weather by importing route data, a vehicle GPS (global positioning system) and real-time speed, and outputting flow and vehicle road matching results by carrying out statistics calculation on background big data models. In the model test and verification stage, after the pre-processed test data is subjected to the constructed LSTM model, the LSTM model is compared with the actual road condition through output results, and the performance of the LSTM model is evaluated to determine whether the model has prediction accuracy and robustness, and the rationality of the model is actually applied. And comparing the road section with the real road section to verify whether the measurement matched vehicle is on the road, and then measuring and calculating whether the road belongs to congestion at the moment.
Model optimization: l2 regularization, dropout and other methods are used to improve the generalization capability of the model.
Application: after model training is completed, the model is deployed into a prediction server through a system deployment pipeline, and congestion index prediction service is provided.
3. Exponential ranking threshold setting
Road conditions are divided into four conditions of smoothness, slowness, congestion and blockage. And displaying the congestion condition in a plaintext according to the congestion index prediction structure, so that the user can understand the congestion condition conveniently. Statistical methods: K-Means clustering: K-Means clustering is a distance-based clustering method that can divide data into several clusters, each of which is a set of data that is similar to the data. The existing data are utilized to divide the data into K groups, the machine selects K objects as initial clustering centers, then calculates the distance between each object and each seed clustering center, and distributes each object to the closest clustering center. The cluster centers and the objects assigned to them represent a cluster. For each sample assigned, the cluster center of the cluster is recalculated based on the existing objects in the cluster. This process will repeat until a certain termination condition is met. The termination condition may be that no (or a minimum number of) objects are reassigned to different clusters, no (or a minimum number of) cluster centers are changed again, and the sum of squares of errors is locally minimum. Thereby calculating the number of road vehicles and using the calculated number of road vehicles for vehicle road congestion index calculation. Road conditions are divided into four conditions of smoothness, slowness, congestion and blockage, and each condition is a cluster. And (5) defining a congestion index threshold after obtaining the center, the range, the distribution and the like of each cluster. The road vehicles are divided as follows: the vehicle is unblocked when the vehicle is less than 300 vehicles; vehicle > =300 and vehicle <500 is slow; congestion is when vehicle > =500 and vehicle < 700; congestion when vehicle > =700; the average speed is divided as follows: congestion when the vehicle speed is evaluated to be less than 10 km/h; evaluating that the vehicle speed > = 10km/h and the speed <20km/h is crowded; when speed > = 20km/h and speed <30km/h is slow; when the vehicle speed > =30 km/h is evaluated as clear. In order to better judge the congestion situation, the road length is divided into the following sections according to the ratio of the road length to the vehicle: congestion when the ratio is < 500; congestion is found when the ratio > = 500 and the value < 1000; when the ratio > =1000 and the value <2000 is slow, the value > =2000 is clear.
4. Congestion index prediction and classification
After the three functions are performed, the service system extracts the latest data in real time to predict the congestion index.
The business system extracts the latest data for verification and then sends the data to the message queue, the congestion index prediction module extracts the data in the message queue, the model is called for prediction, and the prediction result is subjected to congestion classification according to the threshold value and is stored in the database.
5. Vehicle travel track backtracking
And submitting license plate numbers and time ranges in the pc-end web page by the user, screening related data by the service system, and displaying a result set to the front-end page. The front-end page renders the path and the congestion situation on the path, and a user can check the congestion situation on each route, road section and point in the path.
6. Real-time display of congestion conditions
Through the processes of data acquisition, data processing, model training, result prediction and the like in the steps, a predicted result is realized through a software system of a B/S architecture adopted by a display system, and the system is developed by adopting JAVA language, so that the system has high stability and high availability, and meets the requirements of access and operation under a high concurrency scene.
In the display system of the method, the real-time congestion condition of each road section and point location, the information such as the average speed, the highest speed, the traffic flow and the like of each road section in the early peak, the late peak and the whole time period, and the congestion ranking, the change condition of the day, the week and the month of the vehicle can be seen.
The data uploaded by the original GPS data acquisition is second-level data, the data density is high, and great calculation pressure is brought to the construction of the geographic information system environment and the path restoration. In order to adapt to the complexity of data and overcome the calculation pressure, a high-efficiency stable time sequence database is adopted, and the characteristics of high generation frequency, time acquisition, multiple points, large information quantity and the like of satellite positioning system data can be better met in the traditional relational database. The study is based on a time sequence database to upload, store and sort truck data and traffic road data.
In order to solve the real-time road condition problem of the truck, the position, the speed and the direction are firstly preprocessed by taking the conditions such as weather conditions, road construction, control and the like as variables as a data set, and the preprocessing process can comprise the steps of data cleaning, normalization and the like. The LSTM network model is used for training data to predict traffic jam, L2 regularization, dropout and other methods are used for improving the generalization capability of the model, and the cross-validation technology is used for evaluating the performance of the model. Through the processes of data acquisition, data processing, model training, result prediction and the like in the steps, a predicted result is realized through a software system of a B/S architecture adopted by a display system, and the system is developed by adopting JAVA language, so that the system has high stability and high availability, and meets the requirements of access and operation under a high concurrency scene.
As shown in fig. 4, to better utilize the visual analysis of the data, the research also self-develops the freight cockpit system on the Web platform, and designs a main interface and four statistical modules. The main interface is a dynamic track display diagram of a truck, and comprises road conditions and congestion degrees of roads; dynamic changes are made in days. The four interface windows are used for statistical display, and the small interfaces comprise average speed, highest speed and traffic flow of a main road in a day unit and an early-late peak time period; real-time dynamic change ranking display of main congestion road sections every day; the number of trucks in the saline field is changed every day (unit hour), every week and every month; and displaying the dynamic track of the vehicle with the highest average speed every day.
As shown in fig. 5 to 6, in order to implement backtracking of the vehicle driving track, the pc end web page is researched to carry a corresponding functional module, and the service system screens related data through license plate numbers and time ranges to display a result set on the front end page. The front-end page renders the path and the congestion situation on the path, and a user can check the congestion situation on each route, road section and point in the path. In the display system, the real-time congestion condition of each road section and point location, the information such as the average speed, the highest speed and the traffic flow of each road section in the early peak, the late peak and the whole time period, and the congestion ranking, the change condition of the day, the week and the month of the vehicle can be seen.
Visual monitoring is provided for urban logistics traffic: by predicting the congestion condition, the road management department, the freight vehicle operation unit and the driver can take measures in advance to reduce the occurrence of congestion; improving traffic efficiency: by predicting the congestion condition in advance, the road management department can more effectively arrange traffic flow and improve road traffic efficiency; road safety is improved: the congested roads are often hidden danger of traffic safety, and the road management department can discover and solve the hidden danger more quickly through predicting the congestion condition; the road management efficiency is improved: by predicting the congestion condition, the road management department can more effectively arrange resources and improve the road management efficiency.
Knowing the city freight passage and traffic flow: through visualization of massive truck GPS data, freight traffic and main freight channels of cities can be counted and known from each period, and more scientific and effective decision assistance is provided for city planning and transportation. And more visual data assistance is provided for further solving the urban freight problem.
The embodiment of the application provides a city freight visualization system based on WebGIS, as shown in FIG. 7, comprising:
the urban freight vehicle data acquisition module 1 is used for acquiring urban freight vehicle data in the vehicle-mounted satellite positioning system;
the freight visualization model building module 2 is used for building a freight visualization model according to the urban freight vehicle data based on a WebGIS engine;
the congestion index prediction module 3 is used for training a congestion index prediction model based on the urban freight vehicle data and predicting the congestion indexes of different traffic roads in the freight visualization model;
the congestion classification module 4 is used for classifying according to the congestion indexes based on a plurality of preset index classification thresholds, and labeling classification results beside the corresponding traffic roads; the grading result comprises: smooth, slow, crowded and blocked;
and the vehicle running track backtracking module 5 is used for receiving the vehicle attribute input by the user, backtracking the vehicle running track in the freight visualization model based on the vehicle attribute, and displaying the backtracking result.
The city freight vehicle data includes: the location, speed and direction of a large number of freight vehicles in a city.
After the urban freight vehicle data acquisition module 1 acquires the urban freight vehicle data, the following operations are further performed:
transmitting the acquired urban freight vehicle data to a database server for storage; the database in the database server is a time sequence database.
The congestion index prediction module 3 trains a congestion index prediction model based on the urban freight vehicle data, including:
data preprocessing: preprocessing the urban freight vehicle data, introduced weather conditions, road construction, control and other conditions as variables as a data set; the pretreatment process comprises the steps of data cleaning and normalization;
model design and training: model training the preprocessed data set by using an LSTM network model, and evaluating the performance of the trained model by using a cross-validation technique;
model evaluation: evaluating the accuracy and efficiency of the trained model using the test dataset;
model optimization: and (5) optimizing the trained model by using an L2 regularization and dropout method.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The city freight visualization method based on the WebGIS is characterized by comprising the following steps of:
acquiring urban freight vehicle data in a vehicle-mounted satellite positioning system;
based on a WebGIS engine, constructing a freight visualization model according to the urban freight vehicle data;
training a congestion index prediction model based on the urban freight vehicle data, and predicting congestion indexes of different traffic roads in the freight visualization model;
classifying according to the congestion index based on a plurality of preset index classification thresholds, and marking classification results beside the corresponding traffic roads; the grading result comprises: smooth, slow, crowded and blocked;
and receiving the vehicle attribute input by the user, tracing back the vehicle running track in the freight visualization model based on the vehicle attribute, and displaying the tracing back result.
2. The web gis-based urban freight visualization method of claim 1, wherein the urban freight vehicle data comprises: the location, speed and direction of a large number of freight vehicles in a city.
3. The method for visualizing a city freight based on WebGIS of claim 1, further comprising, after collecting said city freight data:
transmitting the acquired urban freight vehicle data to a database server for storage; the database in the database server is a time sequence database.
4. The web gis-based urban freight visualization method of claim 1, wherein the training a congestion index prediction model based on the urban freight vehicle data comprises:
data preprocessing: preprocessing the urban freight vehicle data, introduced weather conditions, road construction, control and other conditions as variables as a data set; the pretreatment process comprises the steps of data cleaning and normalization;
model design and training: model training the preprocessed data set by using an LSTM network model, and evaluating the performance of the trained model by using a cross-validation technique;
model evaluation: evaluating the accuracy and efficiency of the trained model using the test dataset;
model optimization: and (5) optimizing the trained model by using an L2 regularization and dropout method.
5. The web gis-based urban freight visualization method of claim 1, wherein the vehicle attributes include: license plate number, time frame.
6. The method for visualizing urban freight based on WebGIS according to claim 1, wherein the tracking of the vehicle travel track in the freight visualization model comprises:
and screening out a corresponding target vehicle according to the vehicle attribute in the freight visualization model, and backtracking the vehicle running track of the target vehicle.
7. A WebGIS-based urban freight visualization system, comprising:
the urban freight vehicle data acquisition module is used for acquiring urban freight vehicle data in the vehicle-mounted satellite positioning system;
the freight visualization model building module is used for building a freight visualization model according to the urban freight vehicle data based on a WebGIS engine;
the congestion index prediction module is used for training a congestion index prediction model based on the urban freight vehicle data and predicting the congestion indexes of different traffic roads in the freight visualization model;
the congestion grading module is used for grading according to the congestion indexes based on a plurality of preset index grading thresholds, and labeling grading results beside the corresponding traffic roads; the grading result comprises: smooth, slow, crowded and blocked;
and the vehicle running track backtracking module is used for receiving the vehicle attribute input by the user, carrying out vehicle running track backtracking on the freight visualization model based on the vehicle attribute, and displaying the backtracking result.
8. The web gis-based urban freight visualization system of claim 7, wherein the urban freight vehicle data comprises: the location, speed and direction of a large number of freight vehicles in a city.
9. The web gis-based urban freight visualization system of claim 7, wherein the urban freight data acquisition module further performs the following operations after acquiring the urban freight data:
transmitting the acquired urban freight vehicle data to a database server for storage; the database in the database server is a time sequence database.
10. The WebGIS-based urban freight visualization system of claim 7, wherein the congestion index prediction module trains a congestion index prediction model based on the urban freight vehicle data, comprising:
data preprocessing: preprocessing the urban freight vehicle data, introduced weather conditions, road construction, control and other conditions as variables as a data set; the pretreatment process comprises the steps of data cleaning and normalization;
model design and training: model training the preprocessed data set by using an LSTM network model, and evaluating the performance of the trained model by using a cross-validation technique;
model evaluation: evaluating the accuracy and efficiency of the trained model using the test dataset;
model optimization: and (5) optimizing the trained model by using an L2 regularization and dropout method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310703075.5A CN116738098A (en) | 2023-06-14 | 2023-06-14 | Urban freight visualization method and system based on WebGIS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310703075.5A CN116738098A (en) | 2023-06-14 | 2023-06-14 | Urban freight visualization method and system based on WebGIS |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116738098A true CN116738098A (en) | 2023-09-12 |
Family
ID=87902351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310703075.5A Pending CN116738098A (en) | 2023-06-14 | 2023-06-14 | Urban freight visualization method and system based on WebGIS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116738098A (en) |
-
2023
- 2023-06-14 CN CN202310703075.5A patent/CN116738098A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110264709B (en) | Method for predicting traffic flow of road based on graph convolution network | |
| CN109544932B (en) | Urban road network flow estimation method based on fusion of taxi GPS data and gate data | |
| CN110298500B (en) | Urban traffic track data set generation method based on taxi data and urban road network | |
| KR102124955B1 (en) | Method and server for identifying the cause of traffic congestion using visual analytics | |
| CN102521965B (en) | Effect evaluation method of traffic demand management measures based on identification data of license plates | |
| CN110570651A (en) | Road network traffic situation prediction method and system based on deep learning | |
| CN109754594A (en) | A kind of road condition information acquisition method and its equipment, storage medium, terminal | |
| CN108242149A (en) | A kind of big data analysis method based on traffic data | |
| CN111275965B (en) | Real-time traffic simulation analysis system and method based on internet big data | |
| CN104778834A (en) | Urban road traffic jam judging method based on vehicle GPS data | |
| CN103956050A (en) | Road network running evaluation method based on vehicle travel data | |
| Ram et al. | SMARTBUS: A web application for smart urban mobility and transportation | |
| CN110400462B (en) | Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory | |
| CN110555544A (en) | traffic demand estimation method based on GPS navigation data | |
| CN113868492A (en) | Visual OD (origin-destination) analysis method based on electric police and checkpoint data and application | |
| CN110021161B (en) | Traffic flow direction prediction method and system | |
| CN110837973A (en) | Human trip selection information mining method based on traffic trip data | |
| Wang et al. | ARIMA model and few-shot learning for vehicle speed time series analysis and prediction | |
| William et al. | Edge based Web Computing for Traffic Control Management for Distributed Environment Conditions | |
| CN108447257B (en) | Web-based traffic data analysis method and system | |
| CN116738098A (en) | Urban freight visualization method and system based on WebGIS | |
| KR20150072470A (en) | System for analyzing dependence of spatiotemporal domain of traffic flow on the city and highway | |
| CN114139984A (en) | Urban traffic accident risk prediction method based on flow and accident collaborative perception | |
| CN113393011A (en) | Method, apparatus, computer device and medium for predicting speed limit information | |
| Xiong | Data Acquisition and Mining Algorithm of Car Networking under Big Data Background. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |