CN112562311B - Method and device for obtaining working condition weight factor based on GIS big data - Google Patents
Method and device for obtaining working condition weight factor based on GIS big data Download PDFInfo
- Publication number
- CN112562311B CN112562311B CN202011127726.3A CN202011127726A CN112562311B CN 112562311 B CN112562311 B CN 112562311B CN 202011127726 A CN202011127726 A CN 202011127726A CN 112562311 B CN112562311 B CN 112562311B
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- road
- gis
- speed
- flow model
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012706 support-vector machine Methods 0.000 claims abstract description 36
- 230000001502 supplementing effect Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 7
- 239000013589 supplement Substances 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 230000010365 information processing Effects 0.000 claims description 5
- 238000011835 investigation Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 239000002245 particle Substances 0.000 claims description 4
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000011160 research Methods 0.000 abstract description 6
- 238000012356 Product development Methods 0.000 abstract description 5
- 238000013461 design Methods 0.000 abstract description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000013401 experimental design Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Remote Sensing (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
Abstract
The invention relates to a method and a device for acquiring a working condition weight factor based on GIS big data. The acquisition method comprises the following steps: s1, supplementing and correcting GIS data; s2, processing and matching road information, and constructing a typical city whole road network GIS database; s3, establishing a traffic flow model selection model based on a support vector machine; s4, calibrating and calculating a traffic flow model to obtain the traffic flow of the whole road network; and S5, calculating a speed interval weight factor. The method can accurately and objectively calculate the weight factors of each speed interval, and provides technical support for government, research institutions and enterprises to extract policy making, test design and product development in related fields under road conditions.
Description
Technical Field
The invention relates to the field of transportation, in particular to a method and a device for acquiring a working condition weight factor based on GIS big data.
Background
The detection condition of the automobile product is an important common basic technology in the automobile industry, and is the basis of an energy consumption/emission test method and a limit value standard of the automobile. In the working condition construction process, how to objectively and scientifically determine the weight factors of the vehicle running in each speed interval is an urgent problem to be solved. The traditional method for determining the weight factor is used for calculating based on actual motorcade collected data, but the calculation result is greatly influenced by the subjectivity of motorcade construction, so that the accuracy of the obtained weight factor is low, and the weight factor of each speed interval cannot be objectively determined.
In view of the above, the present invention is particularly proposed.
Disclosure of Invention
In a first aspect, the invention aims to provide a GIS big data-based working condition weight factor acquisition method, which can accurately and objectively calculate the weight factor of each speed interval and provide technical support for government, research institutions and enterprises to extract policy making, test design and product development in related fields under road conditions.
In a second aspect, the invention aims to provide a device for acquiring a working condition weight factor based on GIS big data.
In a third aspect, the present invention is directed to an electronic device.
In a fourth aspect, the present invention is directed to a medium.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the invention provides a method for obtaining a working condition weight factor based on GIS big data, which comprises the following steps:
s1, supplementing and correcting GIS data;
s2, processing and matching road information, and constructing a typical city whole road network GIS database;
s3, establishing a traffic flow model selection model based on a support vector machine or a traffic flow model selection model based on a particle swarm optimization extreme learning machine;
s4, calibrating and calculating a traffic flow model to obtain the traffic flow of the whole road network;
and S5, calculating a speed interval weight factor.
As a further preferable embodiment, step S1 includes: calculating the loss rate of GIS data of each road, and supplementing and correcting the road data with the loss rate of GIS data within a certain range;
preferably, if the missing rate is greater than or equal to 0.3, the GIS data of the road is directly deleted;
if the deletion rate is greater than or equal to 0.1 and less than 0.3, supplementing by adopting the average speed value of the same time on adjacent dates;
if the loss rate is less than 0.1, supplementing the vehicle information by adopting a linear difference value of the average speeds of adjacent moments in the same day;
preferably, the adjacent dates are from five days before the day to five days after the day;
preferably, the adjacent time is from the first 15 minutes to the last 15 minutes of the current time.
As a further preferable embodiment, step S2 includes: weighting the number of lanes of each road according to the road information to obtain the average number of lanes of the road; matching road GIS data with road information to construct a typical urban whole road network GIS database;
preferably, the average lane number of the road is calculated by the following formula:
wherein n is the average lane number; n isiThe number of the i-th section of road lane on the road is counted; liThe length of the ith road lane on the road is shown.
As a further preferred technical solution, the traffic flow model selection model is established based on a support vector machine;
preferably, step S3 includes:
s3a, providing traffic flow data of a plurality of roads at different moments;
s3b, selecting multiple traffic flow models, respectively calculating the traffic flow of corresponding roads according to the average speed of the roads in the GIS database, then determining the traffic flow models of the corresponding roads, and finally forming a traffic flow model sample library in which each road corresponds to the traffic flow model one by one;
and S3c, selecting a kernel function and parameters by adopting a support vector machine, and constructing a traffic flow model selection model based on the support vector machine.
As a further preferable technical solution, in step S3a, the traffic flow data of a plurality of roads at different times are obtained through analysis processing of the typical road traffic camera video data;
preferably, in step S3b, the traffic flow models are 3;
preferably, in step S3b, a least square method is used to determine a traffic flow model corresponding to the road;
in step S3c, the traffic flow model sample library is divided into a training set and a test set, and then a traffic flow model selection model based on a support vector machine is constructed.
As a further preferable embodiment, step S4 includes:
s4a, inputting the road information into a traffic flow model selection model, calculating a traffic flow model suitable for the road, and then calibrating the traffic flow model, wherein the calibration comprises free flow speed calibration and optimal density coefficient calibration;
s4b, comparing the calculated flow of the traffic flow model with the actual investigation flow, and calculating the relative error average value and the absolute error average value of the traffic flow in each hour;
s4c, taking the GIS database as input, and calculating the traffic flow of the whole road network through a traffic flow model;
preferably, the road information includes road length, road weighted lane number, road speed limit value and road grade;
preferably, the relative error average is calculated by using the following formula:
wherein ε is the average value of the relative errors, QiIs the actual traffic flow at the i-th moment, qiCalculating the traffic flow for the model at the ith moment;
preferably, the absolute error average is calculated by using the following formula:
wherein Q is the average of absolute errors, QiIs the actual traffic flow at the i-th moment, qiAnd calculating the traffic flow for the model at the ith moment.
As a further preferable embodiment, step S5 includes: according to the traffic flow of the road of the whole road network, vehicle running time distribution of different speed sections of the whole road network is obtained, low-speed sections, medium-speed sections and high-speed sections are divided according to speed section thresholds respectively, the accumulated vehicle running time of the low-speed sections, the medium-speed sections and the high-speed sections is calculated respectively, and finally weight factors of the speed sections are obtained.
In a second aspect, the present invention provides a device for obtaining a working condition weight factor based on GIS big data, including:
the GIS data supplement and correction module is used for supplementing and correcting the GIS data;
the road information processing and matching module is used for processing and matching road information and constructing a typical urban whole road network GIS database;
the traffic flow model selection construction module based on the support vector machine is used for constructing a traffic flow model selection model based on the support vector machine;
the traffic flow model calibration and calculation module is used for calibrating and calculating the traffic flow model;
and the speed interval weight factor calculation module is used for calculating the speed interval weight factor.
In a third aspect, the present invention provides an electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the storage stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for obtaining the working condition weight factor based on the GIS big data.
In a fourth aspect, the present invention provides a medium, where computer instructions are stored, where the computer instructions are configured to cause the computer to execute the above method for obtaining a weighting factor of a working condition based on GIS big data.
Compared with the prior art, the invention has the beneficial effects that:
the GIS (Geographic Information System or Geo-Information System) traffic big data capable of relatively objectively reflecting the real driving situation of the vehicles in China is innovatively introduced into the GIS big data based working condition weight factor obtaining method provided by the invention, the travel time ratio of the vehicles in the whole road network of the typical city in the country in different speed intervals is obtained by establishing a traffic flow model selection model, and then the weight factor of each speed interval is determined, so that a basis is provided for the construction of the driving working condition.
The method constructs a traffic flow model selection model based on a support vector machine, and determines a traffic flow model suitable for each road by taking road information as input. And inputting GIS data of each road into a corresponding traffic flow model, and calculating to obtain road flow of a typical urban whole road network and vehicle running hours, thereby realizing the acquisition of weight factors of each speed interval under working conditions. Compared with the traditional method for acquiring the working condition weight factor by actually acquiring data through the vehicle, the method avoids the subjective influence of fleet construction on the determination of the weight factor to a certain extent, so that the weight factor is more accurate and objective, and can provide technical support for government, research institutions and enterprises to extract policy making, experimental design and product development in related fields in road working conditions.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flowchart of a method for obtaining a condition weight factor based on GIS big data according to embodiment 1;
FIG. 2 is a schematic flow chart of the processing and matching of road information in embodiment 1;
FIG. 3 is a graph of measured data fit to simulated data in example 1;
FIG. 4 is a flow chart of a traffic flow model selection model establishment in embodiment 1;
FIG. 5 is a timing chart of a traffic flow in embodiment 1;
fig. 6 shows the ratio of each speed section in embodiment 1.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
With the development of science and technology and the continuous popularization of 4G networks and smart phones, average vehicle speed information of a typical city whole road network at different moments and different geographic positions can be acquired through analysis and processing of vehicle navigation data (GIS big data) of a driver, a new method and a new thought are provided for acquiring weight factors of vehicle running conditions, and under the thought, the inventor creatively provides a method for acquiring the working condition weight factors based on the GIS big data.
The method for acquiring the working condition weight factor based on the GIS big data comprises the following steps:
s1, supplementing and correcting GIS data;
s2, processing and matching road information, and constructing a typical city whole road network GIS database;
s3, establishing a traffic flow model selection model based on a support vector machine or a traffic flow model selection model based on a particle swarm optimization extreme learning machine;
s4, calibrating and calculating a traffic flow model to obtain the traffic flow of the whole road network;
and S5, calculating a speed interval weight factor.
The GIS (Geographic Information System or Geo-Information System) traffic big data capable of relatively objectively reflecting the real driving situation of the vehicles in China is innovatively introduced into the GIS big data based working condition weight factor obtaining method, the traveling time proportion of the vehicles in the whole road network of the typical city in China under different speed intervals is obtained by establishing a traffic flow model selection model, and then the weight factor of each speed interval is determined, so that a basis is provided for the construction of the driving working condition.
The method constructs a traffic flow model selection model based on a support vector machine or a particle swarm optimization extreme learning machine, and determines a traffic flow model suitable for each road by taking road information as input. And inputting GIS data of each road into a corresponding traffic flow model, and calculating to obtain road flow of a typical urban whole road network and vehicle running hours, thereby realizing the acquisition of weight factors of each speed interval under working conditions. Compared with the traditional method for acquiring the working condition weight factor by actually acquiring data through the vehicle, the method avoids the subjective influence of fleet construction on the determination of the weight factor to a certain extent, so that the weight factor is more accurate and objective, and can provide technical support for government, research institutions and enterprises to extract policy making, experimental design and product development in related fields in road working conditions.
In a preferred embodiment, step S1 includes: and calculating the loss rate of the GIS data of each road, and supplementing and correcting the road data with the loss rate of the GIS data within a certain range. Road data with GIS data loss rate within a certain range are supplemented and corrected, so that the completeness and accuracy of the data are improved.
The "missing rate" refers to a ratio of a data accumulation missing duration to an acquisition period.
Preferably, if the missing rate is greater than or equal to 0.3, the GIS data of the road is directly deleted;
if the missing rate is more than 0.1 or equal to and less than 0.3, supplementing by adopting the average speed value of the same time on adjacent dates;
and if the loss rate is less than 0.1, supplementing the vehicle information by adopting a linear difference value of the average speeds of adjacent moments in the same day.
Preferably, the adjacent dates are from five days before the day to five days after the day. For example, if the current day is 15 days of a certain month, the adjacent dates are 10 days, 11 days, 12 days, 13 days, 14 days, 16 days, 17 days, 18 days, 19 days and 20 days of the current month.
Preferably, the adjacent time is from the first 15 minutes to the last 15 minutes of the current time. For example, if the current time is 15: 25, the neighboring times are 15: 10, 15: 15, 15: 20, 15: 30, 15: 35, and 15: 40. It should be understood that the above-listed adjacent time is the time when the data is acquired every 5 minutes, and thus the time from the first 15 minutes to the last 15 minutes is the time when the data is acquired every 5 minutes, which is consistent with the lowest refresh frequency of the current GIS road data, and obviously, the time interval therebetween can also be adjusted according to the refresh frequency of the GIS road data.
In a preferred embodiment, step S2 includes: weighting the number of lanes of each road according to the road information to obtain the average number of lanes of the road; and matching the road GIS data with the road information to construct a typical urban whole road network GIS database. In general, the number of lanes on a road varies from road segment to road segment, and therefore, the number of lanes needs to be weighted first to obtain the average number of lanes on the road.
Preferably, the average lane number of the road is calculated by the following formula:
wherein n is the average lane number; n isiThe number of the i-th section of road lane on the road is counted; liThe length of the ith road lane on the road is shown.
In a preferred embodiment, the traffic flow model selection model is built based on a support vector machine.
Preferably, step S3 includes:
s3a, providing traffic flow data of a plurality of roads at different moments;
s3b, selecting multiple traffic flow models, respectively calculating the traffic flow of corresponding roads according to the average speed of the roads in the GIS database, then determining the traffic flow models of the corresponding roads, and finally forming a traffic flow model sample library in which each road corresponds to the traffic flow model one by one;
and S3c, selecting a kernel function and parameters by adopting a support vector machine, and constructing a traffic flow model selection model based on the support vector machine.
In the preferred embodiment, traffic flow data is provided first, then a traffic flow model sample library in which each road corresponds to a traffic flow model one to one is formed, and then a traffic flow model selection model based on a support vector machine is constructed according to the sample library.
The "plurality" means two or more, for example, 2, 3, 4, 5, etc. The "plural" means two or more, for example, 2, 3, 4, etc.
In a preferred embodiment, in step S3a, traffic flow data of a plurality of roads at different times are obtained through analysis processing of typical road traffic camera video data.
In a preferred embodiment, in step S3b, there are 3 traffic flow models.
Preferably, in step S3b, a least square method is used to determine a traffic flow model corresponding to the road. The traffic flow model which is most suitable for the traffic flow estimation of the road can be determined by adopting a least square method.
In a preferred embodiment, in step S3c, the traffic flow model sample library is divided into a training set and a testing set, and then a traffic flow model selection model based on a support vector machine is constructed. The training set can be used for training the support vector machine, and then the test set is adopted for carrying out verification test on the constructed support vector machine model so as to ensure the accuracy of the model.
In a preferred embodiment, step S4 includes:
s4a, inputting the road information into a traffic flow model selection model, calculating a traffic flow model suitable for the road, and then calibrating the traffic flow model, wherein the calibration comprises free flow speed calibration and optimal density coefficient calibration;
s4b, comparing the calculated flow of the traffic flow model with the actual investigation flow, and calculating the relative error average value and the absolute error average value of the traffic flow in each hour;
and S4c, calculating the traffic flow of the whole road network by using the GIS database as input through a traffic flow model.
In the preferred embodiment, the accuracy and the representativeness of the traffic flow model selection model can be accurately evaluated through the calibration and the calculation in the steps S4a and S4b, and then the traffic flow of the whole road network can be calculated.
Optionally, after obtaining the traffic flow of the whole road network, the vehicle running time (or hours) of the whole road network can be obtained; after the vehicle running time of the whole road network is obtained, the vehicle running time of each level of road can be further obtained.
The vehicle travel time can be calculated using the following formula: VHTi＝qi×Ti；
Wherein, VHTiRepresenting the time of travel of the vehicle, q, for a section i at a certain timeiExpress a certainAverage traffic flow, T, of a section i at a timeiWhich represents the average travel time of the vehicle on a certain road section i.
Preferably, the road information includes a road length, a road weighted lane number, a road speed limit value, and a road grade.
Preferably, the relative error average is calculated by using the following formula:
wherein ε is the average value of the relative errors, QiIs the actual traffic flow at the i-th moment, qiAnd calculating the traffic flow for the model at the ith moment.
Preferably, the absolute error average is calculated by using the following formula:
wherein Q is the average of absolute errors, QiIs the actual traffic flow at the i-th moment, qiAnd calculating the traffic flow for the model at the ith moment.
In a preferred embodiment, step S5 includes: according to the traffic flow of the road of the whole road network, vehicle running time distribution of different speed sections of the whole road network is obtained, low-speed sections, medium-speed sections and high-speed sections are divided according to speed section thresholds respectively, the accumulated vehicle running time of the low-speed sections, the medium-speed sections and the high-speed sections is calculated respectively, and finally weight factors of the speed sections are obtained.
According to another aspect of the present invention, a device for obtaining a condition weight factor based on GIS big data is provided, which includes:
the GIS data supplement and correction module is used for supplementing and correcting the GIS data;
the road information processing and matching module is used for processing and matching road information and constructing a typical urban whole road network GIS database;
the traffic flow model selection construction module based on the support vector machine is used for constructing a traffic flow model selection model based on the support vector machine;
the traffic flow model calibration and calculation module is used for calibrating and calculating the traffic flow model;
and the speed interval weight factor calculation module is used for calculating the speed interval weight factor.
According to the working condition weight factor acquiring device based on the GIS big data, by adopting the GIS data supplement and correction module, the road information processing and matching module, the traffic flow model selection and construction module based on the support vector machine, the traffic flow model calibration and calculation module and the speed interval weight factor calculation module, the weight factors of different speed intervals can be objectively and accurately acquired, and technical support is provided for policy making, test design and product development of governments, research institutions and enterprises in relevant fields of road working condition extraction.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.
The processor in the electronic device is capable of performing the above method and thus has at least the same advantages as the above method.
According to another aspect of the present invention, there is provided a medium having stored thereon computer instructions for causing the computer to perform the above-described method. The computer instructions in the medium enable a computer to perform the above method and thus have at least the same advantages as the above method.
The present invention will be described in further detail with reference to examples.
Example 1
As shown in fig. 1, this embodiment provides a method for obtaining a working condition weight factor based on GIS big data, which includes the following steps:
s1, GIS data supplement and correction: calculating the loss rate of GIS data of each road, and supplementing and correcting the road data with the loss rate of GIS data within a certain range;
if the missing rate is greater than or equal to 0.3, directly deleting the GIS data of the road;
if the deletion rate is greater than or equal to 0.1 and less than 0.3, supplementing by adopting the average speed value at the same moment on adjacent dates (+ -5 days);
and if the loss rate is less than 0.1, supplementing the vehicle information by adopting a linear difference value of the average speeds of adjacent moments in the same day.
S2, road information processing and matching (as shown in fig. 2): weighting the number of lanes of each road according to the road information to obtain the average number of lanes of the road; matching road GIS data with road information to construct a typical urban whole road network GIS database;
the average lane number of the road is calculated by adopting the following formula:
wherein n is the average lane number; n isiThe number of the i-th section of road lane on the road is counted; liThe length of the ith road lane on the road is shown.
S3, establishing a traffic flow model selection model based on the support vector machine:
s3a, analyzing and processing the video data of the road traffic camera, smoothing and graying the image through Gaussian filtering, and finally calculating the traffic flow of the road at different moments by using label tracking;
s3b, selecting 3 traffic flow models, respectively calculating the traffic flow of the corresponding road according to the road average speed in the GIS database, determining the traffic flow model of the corresponding road by adopting a least square method, and finally forming a traffic flow model sample library (shown in figure 3) in which each road and the traffic flow model are in one-to-one correspondence;
and S3c, dividing a traffic flow model sample library into a training set and a testing set by adopting a support vector machine, selecting a kernel function and parameters, and constructing a traffic flow model selection model based on the support vector machine (as shown in FIG. 4, the step of establishing an SVM model in the graph is to establish the traffic flow model selection model based on the support vector machine).
S4, calibrating and calculating a traffic flow model to obtain the traffic flow of the whole road network;
s4a, inputting the road length, the road weighting lane number, the road speed limit value and the road grade into a traffic flow model selection model, calculating a traffic flow model suitable for the road, and then calibrating the traffic flow model, wherein the calibration comprises free flow speed calibration and optimal density coefficient calibration.
The free flow speed generally refers to the theoretical driving speed of a driver without being influenced by traffic conditions, and is related to the speed limit value of the road, and the free flow speed is 80-95% of the speed limit value of the corresponding road in general, and is different from roads in different levels, as shown in table 1.
TABLE 1 proportional relation between free flow speed and speed limit of each grade road
After the speed of the free flow is determined, speed data needing to be calculated are input, in a model calibration stage, assuming that the speed data are 1-120km/h (1 km/h is used as an interval unit) in sequence, a density coefficient is arbitrarily defined, traffic flow data at each speed can be calculated, and the maximum flow is the traffic capacity. And continuously adjusting the coefficient by an iterative method to enable the traffic capacity to approach the recommended value infinitely, wherein the coefficient at the moment is the optimal density coefficient, and the recommended value of the traffic capacity is shown in the following table 2.
TABLE 2 recommended traffic capacity (pcu/h)
| Road grade | Super-large city | Super-huge city | Big city | Middle and small cities |
| 1 | 1800 | 1710 | 1710 | 1710 |
| 2 | 1572 | 1493 | 1493 | 1493 |
| 3 | 700 | 665 | 630 | 630 |
| 4 | 552 | 524 | 497 | 469 |
S4b, comparing the calculated flow of the traffic flow model with the actual investigation flow, and calculating the relative error average value and the absolute error average value of the traffic flow in each hour;
the relative error average value is calculated by adopting the following formula:
wherein ε is the average value of the relative errors, QiIs the actual traffic flow at the i-th moment, qiAnd calculating the traffic flow for the model at the ith moment.
The absolute error average value is calculated by adopting the following formula:
wherein Q is the average of absolute errors, QiIs the actual traffic flow at the i-th moment, qiAnd calculating the traffic flow for the model at the ith moment. The calculation accuracy of the model is generally required to be up to +/-10% with relative error.
S4c, taking the GIS database as input, and calculating the traffic flow of the whole road network through a traffic flow model;
after the calibration of the traffic flow model is completed, the traffic flow of each road can be calculated through the GIS data of each road. To further determine the speed interval weighting factor, a parameter of the number of Vehicle Hours (VHT) needs to be introduced. The number of hours of the vehicle is the product of the average traffic volume on the road section and the average travel time of the vehicle, and the double influences of the length of the road and the congestion degree of the road are included; the traffic jam state can be reflected, and the traffic demand state of traffic travelers can be reflected. In a certain period, the calculation formula of the vehicle hours on a certain road section is as follows:
VHTi＝qi×Ti(ii) a Wherein, VHTiRepresenting the time of travel of the vehicle, q, for a section i at a certain timeiIndicating a trip at a certain timeAverage traffic flow, T, for segment iiWhich represents the average travel time of the vehicle on a certain road section i.
By performing cumulative calculation according to the vehicle hours at each average speed of each road, the vehicle hour ratio distribution in different speed sections can be obtained, as shown in fig. 5 and 6.
S5, calculating a speed interval weight factor:
and integrating GIS data of the typical urban whole road network to finally obtain vehicle running hour number distribution of different speed intervals of the typical urban whole road network, dividing low-speed intervals, medium-speed intervals and high-speed intervals according to speed interval thresholds, calculating accumulated vehicle running hours of the low-speed intervals, the medium-speed intervals and the high-speed intervals, and finally obtaining weight factors of the speed intervals, wherein the results are shown in a table 3.
TABLE 3 typical city speed interval ratio
In conclusion, the GIS big data based working condition weight factor obtaining method provided by the invention can conveniently and quickly obtain the weight factors of different speed intervals of vehicle operation of a typical city, and provides data support for further energy conservation, emission reduction and intelligent traffic research.
It should be understood that various forms of the flows shown above, reordering, adding or deleting steps, may be used. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (12)
1. A working condition weight factor obtaining method based on GIS big data is characterized by comprising the following steps:
s1, supplementing and correcting GIS data;
step S1 includes: calculating the loss rate of GIS data of each road, and supplementing and correcting the road data with the loss rate of GIS data within a certain range;
s2, processing and matching road information, and constructing a typical city whole road network GIS database;
step S2 includes: weighting the number of lanes of each road according to the road information to obtain the average number of lanes of the road; matching road GIS data with road information to construct a typical urban whole road network GIS database;
s3, establishing a traffic flow model selection model based on a support vector machine or a traffic flow model selection model based on a particle swarm optimization extreme learning machine;
step S3 includes:
s3a, providing traffic flow data of a plurality of roads at different moments; in step S3a, the video data of the typical road traffic camera is analyzed and processed to obtain the traffic flow data of a plurality of roads at different times;
s3b, selecting multiple traffic flow models, respectively calculating the traffic flow of corresponding roads according to the average speed of the roads in the GIS database, then determining the traffic flow models of the corresponding roads, and finally forming a traffic flow model sample library in which each road corresponds to the traffic flow model one by one; wherein, the traffic flow models are 3; determining a traffic flow model corresponding to a road by adopting a least square method;
s3c, selecting a kernel function and parameters by adopting a support vector machine, and constructing a traffic flow model selection model based on the support vector machine; in the step S3c, dividing a traffic flow model sample library into a training set and a testing set, and then constructing a traffic flow model selection model based on a support vector machine;
s4, calibrating and calculating a traffic flow model to obtain the traffic flow of the whole road network;
step S4 includes:
s4a, inputting the road information into a traffic flow model selection model, calculating a traffic flow model suitable for the road, and then calibrating the traffic flow model, wherein the calibration comprises free flow speed calibration and optimal density coefficient calibration;
s4b, comparing the calculated flow of the traffic flow model with the actual investigation flow, and calculating the relative error average value and the absolute error average value of the traffic flow in each hour;
s4c, taking the GIS database as input, and calculating the traffic flow of the whole road network through a traffic flow model;
s5, calculating a speed interval weight factor;
step S5 includes: according to the traffic flow of the road of the whole road network, vehicle running time distribution of different speed sections of the whole road network is obtained, low-speed sections, medium-speed sections and high-speed sections are divided according to speed section thresholds respectively, the accumulated vehicle running time of the low-speed sections, the medium-speed sections and the high-speed sections is calculated respectively, and finally weight factors of the speed sections are obtained.
2. The method for acquiring the working condition weight factor based on the GIS big data according to claim 1, wherein if the loss rate is greater than or equal to 0.3, the GIS data of the road is directly deleted;
if the deletion rate is greater than or equal to 0.1 and less than 0.3, supplementing by adopting the average speed value of the same time on adjacent dates;
and if the loss rate is less than 0.1, supplementing the vehicle information by adopting a linear difference value of the average speeds of adjacent moments in the same day.
3. The method for acquiring the working condition weight factor based on the GIS big data according to claim 2, wherein the adjacent dates are five days before the current day to five days after the current day.
4. The method for obtaining the working condition weight factor based on the GIS big data according to claim 2, wherein the adjacent time is from the first 15 minutes to the last 15 minutes of the current time.
5. The method for obtaining the working condition weight factor based on the GIS big data according to claim 1, wherein the average number of lanes of the road is calculated by the following formula:
wherein n is the average lane number; n isiThe number of the i-th section of road lane on the road is counted; liThe length of the ith road lane on the road is shown.
6. The GIS big data-based working condition weight factor obtaining method according to claim 1, wherein the traffic flow model selection model is established based on a support vector machine.
7. The method for acquiring the working condition weight factor based on the GIS big data according to claim 1, wherein the road information comprises road length, road weighted lane number, road speed limit value and road grade.
8. The method for obtaining the working condition weight factor based on the GIS big data according to claim 1, wherein the relative error average value is calculated by adopting the following formula:
wherein ε is the average value of the relative errors, QiIs the actual traffic flow at the i-th moment, qiAnd calculating the traffic flow for the model at the ith moment.
9. The method for obtaining the working condition weight factor based on the GIS big data according to claim 1, wherein the absolute error average value is calculated by adopting the following formula:
wherein Q is the average of absolute errors, QiIs the actual traffic flow at the i-th moment, qiAnd calculating the traffic flow for the model at the ith moment.
10. The utility model provides a condition weight factor acquisition device based on GIS big data which characterized in that includes:
the GIS data supplement and correction module is used for supplementing and correcting the GIS data;
the road information processing and matching module is used for processing and matching road information and constructing a typical urban whole road network GIS database;
the traffic flow model selection construction module based on the support vector machine is used for constructing a traffic flow model selection model based on the support vector machine;
the traffic flow model calibration and calculation module is used for calibrating and calculating the traffic flow model;
the speed interval weight factor calculation module is used for calculating a speed interval weight factor;
the GIS data supplement and correction module is also used for: calculating the loss rate of GIS data of each road, and supplementing and correcting the road data with the loss rate of GIS data within a certain range;
the GIS data supplement and correction module is also used for: weighting the number of lanes of each road according to the road information to obtain the average number of lanes of the road; matching road GIS data with road information to construct a typical urban whole road network GIS database;
the support vector machine-based traffic flow model selection construction module is further used for: providing traffic flow data of a plurality of roads at different moments; the method comprises the steps that through analysis and processing of video data of a typical road traffic camera, traffic flow data of a plurality of roads at different moments are obtained; selecting multiple traffic flow models, respectively calculating the traffic flow of corresponding roads according to the average speed of the roads in the GIS database, then determining the traffic flow models of the corresponding roads, and finally forming a traffic flow model sample library in which each road corresponds to the traffic flow model one by one; wherein, the traffic flow models are 3; determining a traffic flow model corresponding to a road by adopting a least square method; selecting a kernel function and parameters by adopting a support vector machine, and constructing a traffic flow model selection model based on the support vector machine; dividing a traffic flow model sample library into a training set and a testing set, and then constructing a traffic flow model selection model based on a support vector machine;
the traffic flow model calibration and calculation module is also used for: inputting road information into a traffic flow model selection model, calculating a traffic flow model suitable for a road, and calibrating the traffic flow model, including free flow speed calibration and optimal density coefficient calibration; comparing the calculated flow of the traffic flow model with the actual investigation flow, and calculating the relative error average value and the absolute error average value of the traffic flow in each hour; taking the GIS database as input, and calculating the traffic flow of the whole road network through a traffic flow model;
the speed interval weighting factor calculation module is further configured to: according to the traffic flow of the road of the whole road network, vehicle running time distribution of different speed sections of the whole road network is obtained, low-speed sections, medium-speed sections and high-speed sections are divided according to speed section thresholds respectively, the accumulated vehicle running time of the low-speed sections, the medium-speed sections and the high-speed sections is calculated respectively, and finally weight factors of the speed sections are obtained.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for obtaining the weighting factor of the working condition based on the GIS big data according to any one of claims 1 to 9.
12. A medium having stored thereon computer instructions for causing a computer to execute the method for obtaining an operating condition weight factor based on GIS big data according to any one of claims 1 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011127726.3A CN112562311B (en) | 2020-10-21 | 2020-10-21 | Method and device for obtaining working condition weight factor based on GIS big data |
| LU500569A LU500569B1 (en) | 2020-10-21 | 2021-08-24 | Method and device for acquiring driving test cycle weight factors based on gis large data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011127726.3A CN112562311B (en) | 2020-10-21 | 2020-10-21 | Method and device for obtaining working condition weight factor based on GIS big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112562311A CN112562311A (en) | 2021-03-26 |
| CN112562311B true CN112562311B (en) | 2022-04-26 |
Family
ID=75041439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011127726.3A Active CN112562311B (en) | 2020-10-21 | 2020-10-21 | Method and device for obtaining working condition weight factor based on GIS big data |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112562311B (en) |
| LU (1) | LU500569B1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115497306A (en) * | 2022-11-22 | 2022-12-20 | 中汽研汽车检验中心（天津）有限公司 | Speed interval weight calculation method based on GIS data |
| CN117094565B (en) * | 2023-10-19 | 2024-01-12 | 赛飞特工程技术集团有限公司 | Main responsibility implementation grading evaluation system for national group enterprises |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106997662A (en) * | 2017-04-26 | 2017-08-01 | 长安大学 | A kind of city bus operating mode construction method |
| CN107067722A (en) * | 2017-04-24 | 2017-08-18 | 中国汽车技术研究中心 | A kind of new vehicle driving-cycle construction method |
| CN109932191A (en) * | 2019-03-15 | 2019-06-25 | 中国汽车技术研究中心有限公司 | A kind of real road driving cycle library and construction method |
-
2020
- 2020-10-21 CN CN202011127726.3A patent/CN112562311B/en active Active
-
2021
- 2021-08-24 LU LU500569A patent/LU500569B1/en active IP Right Grant
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107067722A (en) * | 2017-04-24 | 2017-08-18 | 中国汽车技术研究中心 | A kind of new vehicle driving-cycle construction method |
| CN106997662A (en) * | 2017-04-26 | 2017-08-01 | 长安大学 | A kind of city bus operating mode construction method |
| CN109932191A (en) * | 2019-03-15 | 2019-06-25 | 中国汽车技术研究中心有限公司 | A kind of real road driving cycle library and construction method |
Non-Patent Citations (2)
| Title |
|---|
| 《基于GIS的北京市道路交通流特性研究》;尹月华等;《公路工程》;20200830;第45卷(第4期);第2页第2段-第6页第6段 * |
| 《基于ｖａｎＡｅｒｄｅ模型的快速路交通流特征参数辨识》;陈大山;《武汉理工大学学报》;20131230;第37卷(第6期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112562311A (en) | 2021-03-26 |
| LU500569B1 (en) | 2022-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110264709B (en) | Method for predicting traffic flow of road based on graph convolution network | |
| CN104330089B (en) | A kind of method that map match is carried out using history gps data | |
| CN112562311B (en) | Method and device for obtaining working condition weight factor based on GIS big data | |
| CN110310474A (en) | A kind of vehicle flowrate prediction technique and device based on space-time residual error network | |
| WO2010107394A1 (en) | Determining a traffic route using predicted traffic congestion | |
| CN112613225B (en) | Intersection traffic state prediction method based on neural network cell transmission model | |
| CN107578620B (en) | Method, system and device for calculating road traffic capacity based on lane level system | |
| CN111428558A (en) | Vehicle detection method based on improved YO L Ov3 method | |
| CN101123038A (en) | A dynamic information collection method for associated road segments of intersection | |
| CN106023592A (en) | Traffic jam detection method based on GPS data | |
| CN112633602B (en) | Traffic congestion index prediction method and device based on GIS map information | |
| CN114976306A (en) | Intelligent echelon utilization method of power lithium battery based on vehicle-connected cloud | |
| CN107331164B (en) | A kind of prediction technique of freeway toll station entrance vehicle number | |
| CN115171377B (en) | Traffic flow parameter detection and analysis method and device based on deep learning | |
| CN105355047A (en) | Data fusion processing method for dynamic time granularity of multiple traffic detection sources | |
| CN112489026A (en) | Asphalt pavement disease detection method based on multi-branch parallel convolution neural network | |
| CN107066501B (en) | motor vehicle exhaust remote measuring equipment distribution method based on road similarity | |
| CN115457764A (en) | Road section traffic density estimation method, device and medium based on vehicle track data | |
| CN111680888B (en) | Method for determining road network capacity based on RFID data | |
| CN114613144B (en) | Method for describing motion evolution law of hybrid vehicle group based on Embedding-CNN | |
| CN108957594B (en) | Method and system for forecasting and correcting total cloud amount of satellite orbit | |
| CN113362488B (en) | OBD monitoring data processing system | |
| CN115271565A (en) | DEA-based method, device and equipment for evaluating highway pavement maintenance measures | |
| CN111275961A (en) | Urban traffic running state feature calculation method based on floating car data | |
| CN111785012A (en) | Energy consumption road spectrum analysis method for vehicle cloud cooperative computing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |