CN112906984B - Road traffic state prediction method and device, storage medium and electronic equipment - Google Patents
Road traffic state prediction method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112906984B CN112906984B CN202110311681.3A CN202110311681A CN112906984B CN 112906984 B CN112906984 B CN 112906984B CN 202110311681 A CN202110311681 A CN 202110311681A CN 112906984 B CN112906984 B CN 112906984B
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- travel data
- road
- sampled
- 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 32
- 230000006870 function Effects 0.000 claims description 58
- 238000005070 sampling Methods 0.000 claims description 23
- 230000000737 periodic effect Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000003203 everyday effect Effects 0.000 claims description 6
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 5
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 description 6
- 239000004973 liquid crystal related substance Substances 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/141—Discrete Fourier transforms
- G06F17/142—Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm
-
- G06Q50/40—
-
- 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
Abstract
The invention relates to a road traffic state prediction method, a device, a storage medium and electronic equipment, which are used for solving the problem of low road traffic state prediction accuracy. Comprising the following steps: extracting characteristic values of the acquired sampled vehicle travel data to obtain travel characteristic data, wherein the travel characteristic data comprises traffic flow characteristic data and vehicle speed characteristic data; based on the traffic flow characteristic data and the vehicle speed characteristic data, expanding the Fourier function to obtain corresponding predicted vehicle travel data under each expansion level; calculating an average absolute percentage error according to the sample number of the sampled vehicle trip data, the sampled vehicle trip data and the predicted vehicle trip data; determining a target expansion level of the Fourier function according to the average absolute percentage error; and expanding the Fourier function according to the target expansion level to obtain the road traffic state prediction result. In this way, the accuracy of road traffic state prediction can be improved.
Description
Technical Field
The invention relates to the technical field of road traffic, in particular to a road traffic state prediction method, a road traffic state prediction device, a storage medium and electronic equipment.
Background
The continuous expansion of urban scale, the gradual increase of the maintenance rate of private cars of people are an important incentive for the increasingly serious road traffic jam, which not only reduces the experience of people on life and reduces the efficiency of people on work and study, but also brings economic loss to people and life loss due to the easy initiation of road traffic safety accidents. Usually, road widening or new road planning and building are performed according to regional economic development and living conditions so as to reduce road traffic pressure, however, the road widening and new road building costs are higher, and only road traffic resources are wasted if effective management cannot be achieved.
In the related art, based on a road network structure, through analysis of historical traffic data, possible road traffic congestion is predicted, so that the road traffic state can be predicted, effective measures can be taken in advance to avoid the road traffic congestion, the road traffic congestion degree is reduced to a certain extent, and the road congestion duration is shortened.
Disclosure of Invention
The invention aims to provide a road traffic state prediction method, a device, a storage medium and electronic equipment, so as to solve the problem of low road traffic state prediction accuracy.
In order to achieve the above object, a first aspect of the present invention provides a road traffic state prediction method, the method comprising:
extracting characteristic values of the acquired sampled vehicle travel data to obtain travel characteristic data, wherein the travel characteristic data comprises traffic flow characteristic data and vehicle speed characteristic data;
based on the traffic flow characteristic data and the vehicle speed characteristic data, expanding the Fourier function to obtain corresponding predicted vehicle travel data under each expansion level;
calculating an average absolute percentage error according to the sample number of the sampled vehicle trip data, the sampled vehicle trip data and the predicted vehicle trip data;
determining a target expansion level of the Fourier function according to the average absolute percentage error;
and expanding the Fourier function according to the target expansion level to obtain the road traffic state prediction result.
Optionally, the extracting the characteristic value of the acquired sampled vehicle trip data includes:
dividing the acquired sampling vehicle travel data according to the same time period in the same time period every day to obtain sampling vehicle travel data of a section corresponding to each time period in each day;
dividing the section of sampling vehicle travel of the same time period in each day into the same data set;
extracting periodic characteristic values of the sampled vehicle travel data of each section in the data set corresponding to each time section;
based on the traffic flow characteristic data and the vehicle speed characteristic data, the Fourier function is unfolded to obtain corresponding predicted vehicle travel data under each unfolding level, and the method comprises the following steps:
and based on the traffic flow characteristic data and the vehicle speed characteristic data of the section sampling vehicle trip data, expanding the Fourier function to obtain corresponding section prediction vehicle trip data under each expansion level.
Optionally, the extracting the characteristic value of the acquired sampled vehicle trip data includes:
dividing road sections of the acquired travel data of the sampled vehicles according to road types, and determining the road types of all the road sections;
based on the road type, carrying out structural processing on the sampled vehicle travel data of each road section;
extracting a periodic term characteristic value of the sampled vehicle travel data after the structuring treatment;
based on the traffic flow characteristic data and the vehicle speed characteristic data, the Fourier function is unfolded to obtain corresponding predicted vehicle travel data under each unfolding level, and the method comprises the following steps:
and expanding the Fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data of each road section after the structuring processing to obtain the predicted vehicle travel data of the corresponding road section under each expansion level.
Optionally, the extracting the characteristic value of the acquired sampled vehicle trip data includes:
extracting the characteristic value of the target travel data from the acquired sampled vehicle travel data to obtain the characteristic value of the target travel data and the characteristic value of the non-target travel data, wherein the target travel data comprises holiday travel data and/or rainy and snowy day travel data;
based on the traffic flow characteristic data and the vehicle speed characteristic data, the Fourier function is unfolded to obtain corresponding predicted vehicle travel data under each unfolding level, and the method comprises the following steps:
based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the target trip data characteristic values, expanding the Fourier function to obtain corresponding target predicted vehicle trip data under each expansion level; and/or the number of the groups of groups,
and expanding the Fourier function based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the non-target travel data characteristic values to obtain corresponding non-target predicted vehicle travel data under each expansion level.
Optionally, the mean absolute percentage error MAPE is determined by the following formula:
where N represents the number of samples of the sampled vehicle travel data,representing the sampled vehicle travel data,representing the predicted vehicle travel data.
A second aspect of the present invention provides a road traffic state prediction apparatus, the apparatus comprising:
the extraction module is used for extracting characteristic values of the acquired sampling vehicle travel data to obtain travel characteristic data, wherein the travel characteristic data comprises vehicle flow characteristic data and vehicle speed characteristic data;
the unfolding module is used for unfolding the Fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data to obtain corresponding predicted vehicle travel data under each unfolding level;
the calculation module is used for calculating an average absolute percentage error according to the sample number of the sampled vehicle travel data, the sampled vehicle travel data and the predicted vehicle travel data;
the determining module is used for determining a target expansion level of the Fourier function according to the average absolute percentage error;
and the execution module is used for expanding the Fourier function according to the target expansion level to obtain the road traffic state prediction result.
Optionally, the extracting module is configured to:
dividing the acquired sampling vehicle travel data according to the same time period in the same time period every day to obtain sampling vehicle travel data of a section corresponding to each time period in each day;
dividing the section of sampling vehicle travel of the same time period in each day into the same data set;
extracting periodic characteristic values of the sampled vehicle travel data of each section in the data set corresponding to each time section;
the expansion module is used for expanding the Fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data of the section sampling vehicle trip data to obtain corresponding section prediction vehicle trip data under each expansion level.
Optionally, the extracting module is configured to:
dividing road sections of the acquired travel data of the sampled vehicles according to road types, and determining the road types of all the road sections;
based on the road type, carrying out structural processing on the sampled vehicle travel data of each road section;
extracting a periodic term characteristic value of the sampled vehicle travel data after the structuring treatment;
the expansion module is used for expanding the Fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data of each road section after the structuring processing to obtain the road section prediction vehicle trip data corresponding to each expansion level.
Optionally, the extracting module is configured to:
extracting the characteristic value of the target travel data from the acquired sampled vehicle travel data to obtain the characteristic value of the target travel data and the characteristic value of the non-target travel data, wherein the target travel data comprises holiday travel data and/or rainy and snowy day travel data;
the unfolding module is used for:
based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the target trip data characteristic values, expanding the Fourier function to obtain corresponding target predicted vehicle trip data under each expansion level; and/or the number of the groups of groups,
and expanding the Fourier function based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the non-target travel data characteristic values to obtain corresponding non-target predicted vehicle travel data under each expansion level.
Optionally, the mean absolute percentage error MAPE is determined by the following formula:
where N represents the number of samples of the sampled vehicle travel data,representing the sampled vehicle travel data,representing the predicted vehicle travel data.
A third aspect of the invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
A fourth aspect of the present invention provides an electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of any of the methods described above.
Through the technical scheme, at least the following technical effects can be achieved:
extracting characteristic values of the acquired sampled vehicle travel data to obtain travel characteristic data, wherein the travel characteristic data comprises traffic flow characteristic data and vehicle speed characteristic data; based on the traffic flow characteristic data and the vehicle speed characteristic data, expanding the Fourier function to obtain corresponding predicted vehicle travel data under each expansion level; calculating an average absolute percentage error according to the sample number of the sampled vehicle trip data, the sampled vehicle trip data and the predicted vehicle trip data; determining a target expansion level of the Fourier function according to the average absolute percentage error; and expanding the Fourier function according to the target expansion level to obtain the road traffic state prediction result. Therefore, the target expansion level of the Fourier function is determined based on the average absolute percentage error, and then the Fourier function is expanded according to the target expansion level to predict the road traffic state, so that the accuracy of the road traffic state prediction can be improved, the basis is provided for road construction planning, the road traffic state is improved, and the degree of road traffic jam is reduced.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate the invention and together with the description serve to explain, without limitation, the invention. In the drawings:
fig. 1 is a flowchart illustrating a road traffic state prediction method according to an exemplary embodiment.
Fig. 2 is a flowchart illustrating another road traffic state prediction method according to an exemplary embodiment.
Fig. 3 is a flowchart illustrating another road traffic state prediction method according to an exemplary embodiment.
Fig. 4 is a block diagram illustrating a road traffic state prediction apparatus according to an exemplary embodiment.
Detailed Description
The following describes specific embodiments of the present invention in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
Fig. 1 is a flowchart illustrating a road traffic state prediction method according to an exemplary embodiment. As shown in fig. 1, the method includes the following steps.
In step S11, extracting a feature value of the acquired travel data of the sampled vehicle to obtain travel feature data, where the travel feature data includes traffic flow feature data and vehicle speed feature data;
in step S12, based on the traffic flow characteristic data and the vehicle speed characteristic data, the fourier function is expanded to obtain corresponding predicted vehicle travel data at each expansion level;
in step S13, calculating an average absolute percentage error according to the number of samples of the sampled vehicle trip data, the sampled vehicle trip data and the predicted vehicle trip data;
in step S14, determining a target expansion level of the fourier function according to the mean absolute percentage error;
in step S15, the fourier function is expanded according to the target expansion level, so as to obtain the road traffic state prediction result.
Optionally, the error data existing in the sampled vehicle trip data are sorted or removed, for example, the sampled vehicle trip data are drawn into a time-varying graph, the abnormal data in which the vehicle flow data are obviously lower than the vehicle flow threshold range in the time-varying graph are removed, and the average value of the sampled vehicle trip data at the previous time and the sampled vehicle trip data at the later time is adopted to supplement the critical sampled vehicle trip data.
The traffic flow characteristic data can be represented by a periodic term, a random term, and a residual term, as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,for the original flow of the traffic flow data at time t, < >>For periodic items of the traffic characteristic data, +.>For random items of traffic characteristic data, +.>And the residual error item of the traffic flow characteristic data.
Similarly, the vehicle speed characteristic data can also be represented by a period term, a random term and a residual term, as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,for the original flow of vehicle speed data at time t, < >>For periodic items of vehicle speed characteristic data, +.>Is a random item of speed characteristic data, +.>And the residual error item of the vehicle speed characteristic data.
Further, selecting traffic flow data in n working days of the same road section, wherein the average value of the n working days in each period is a specific numerical value of a period item of the road section in the current period, and the specific numerical value is represented by the following formula:
wherein, the liquid crystal display device comprises a liquid crystal display device,representing half a period of the sampled vehicle trip data. I.e. < ->Representing a period of the sampled vehicle trip data. For example, if the period of sampling the vehicle travel data is one week, then +.>For 3.5 days.
The traffic flow characteristic data is determined based on road gate numbers, acquired license plate numbers, time nodes and date of license plate acquisition and passing time length of each vehicle, and the traffic flow characteristic data is determined based on road buckle road section IDs, road network numbers, road section names, road section grades, road section speeds, detection time and date.
The invention can predict short-time road traffic states, for example, road traffic states of 7:30-9:30 in the morning for 2 hours, and further extract characteristic values in the sampled vehicle travel data of 7:30-9:30 in the morning each day. The road traffic state of the period of time may also be predicted, for example, the characteristic value in the sampled vehicle travel data at the same time point of each week is extracted in units of weeks.
Alternatively, feature value extraction on the acquired sampled vehicle travel data may be performed by a fourier model, a wavelet model, a gray theory prediction model, or the like.
In one mode, a prediction model is constructed to predict through python code programming according to characteristic values obtained through fitting, one part of data is used as a training set to carry out training fitting, the other part of the data is used as a test set to compare prediction results after model construction, and accuracy of the prediction results is determined.
According to the technical scheme, the target expansion level of the Fourier function is determined based on the average absolute percentage error, and then the Fourier function is expanded according to the target expansion level to predict the road traffic state, so that the accuracy of the road traffic state prediction can be improved, a basis is provided for road construction planning, the road traffic state is improved, and the degree of road traffic jam is reduced. And a data base is provided for intelligent traffic information system construction and traffic flow visualization.
Optionally, referring to the flowchart of another road traffic state prediction method exemplarily shown in fig. 2, in step S11, the extracting a feature value of the acquired sampled vehicle travel data includes:
in step S111, the acquired sampled vehicle travel data is divided according to the same time period in the same time period every day, so as to obtain the sampled vehicle travel data corresponding to each time period in each day;
in step S112, the segment-sampled vehicle trips of the same period of time in each day are divided into the same dataset;
in step S113, periodic feature value extraction is performed for each period of sampled vehicle travel data in the data set corresponding to each period of time;
in step S12, based on the traffic flow feature data and the vehicle speed feature data, developing the fourier function to obtain corresponding predicted vehicle trip data at each development level, including:
in step S121, based on the traffic flow characteristic data and the vehicle speed characteristic data of the segment-sampled vehicle travel data, the fourier function is expanded to obtain segment-predicted vehicle travel data corresponding to each expansion level.
Optionally, referring to the flowchart of another road traffic state prediction method exemplarily shown in fig. 3, in step S11, the extracting a feature value of the acquired sampled vehicle travel data includes:
in step S1101, road segments of the acquired travel data of the sampled vehicle are divided according to road types, and the road types of each road segment are determined;
in step S1102, based on the road type, the sampled vehicle travel data of each of the road segments is structured;
in step S1103, extracting a period term feature value from the sampled vehicle travel data after the structuring process;
in step S12, based on the traffic flow feature data and the vehicle speed feature data, developing the fourier function to obtain corresponding predicted vehicle trip data at each development level, including:
in step S1201, based on the traffic flow characteristic data and the vehicle speed characteristic data of each road section after the structuring process, the fourier function is expanded to obtain the predicted vehicle travel data of the corresponding road section at each expansion level.
In particular, road types may include expressways, non-expressway to expressway up-ramps, expressway to non-expressway down-ramps, and non-expressways. The period in the period term feature value may be in units of weeks, thenThe period value representing sampling the vehicle travel data is 3.5 days.
The time in the raw speed data is stored in coordinated universal time (utc) and is converted to a standardized format by programming decoding through the pandas library in python before data extraction.
Optionally, in step S11, the extracting the feature value of the acquired sampled vehicle trip data includes:
extracting the characteristic value of the target travel data from the acquired sampled vehicle travel data to obtain the characteristic value of the target travel data and the characteristic value of the non-target travel data, wherein the target travel data comprises holiday travel data and/or rainy and snowy day travel data;
in step S12, based on the traffic flow feature data and the vehicle speed feature data, developing the fourier function to obtain corresponding predicted vehicle trip data at each development level, including:
based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the target trip data characteristic values, expanding the Fourier function to obtain corresponding target predicted vehicle trip data under each expansion level; and/or the number of the groups of groups,
and expanding the Fourier function based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the non-target travel data characteristic values to obtain corresponding non-target predicted vehicle travel data under each expansion level.
For example, the target trip data may be special workday trip data and non-special workday trip data, for example, the special workday may be monday and friday, and the time period of the special workday may be divided to obtain Zhou Yizao peak time period trip data and friday and evening peak time period trip data, so as to average the values of the multiple target trip data in the same road section, extract the values of the corresponding period terms, for example, obtain the average value of the values of the multiple target trip data in the same road section through an SQL database.
Through comparison of map values, result prediction is carried out on travel data by excluding holiday travel data and rainy and snowy day travel data, and errors are reduced by about 2% to 5%, so that accuracy of road traffic state prediction is further improved.
Optionally, the mean absolute percentage error MAPE is determined by the following formula:
where N represents the number of samples of the sampled vehicle travel data,representing the sampled vehicle travel data,representing the predicted vehicle travel data.
Based on the same inventive concept, the embodiment of the present invention further provides a road traffic state prediction apparatus 400, referring to a block diagram of a road traffic state prediction apparatus exemplarily shown in fig. 4, the apparatus 400 includes: extraction module 410, expansion module 520, calculation module 430, determination module 440, and execution module 450.
The extracting module 410 is configured to extract a feature value of the acquired travel data of the sampled vehicle, so as to obtain travel feature data, where the travel feature data includes traffic flow feature data and vehicle speed feature data;
the expansion module 420 is configured to expand the fourier function based on the traffic flow feature data and the vehicle speed feature data to obtain predicted vehicle trip data corresponding to each expansion level;
a calculating module 430, configured to calculate an average absolute percentage error according to the number of samples of the sampled vehicle trip data, and the predicted vehicle trip data;
a determining module 440, configured to determine a target expansion level of the fourier function according to the average absolute percentage error;
and the execution module 450 is configured to develop the fourier function according to the target development level, so as to obtain the road traffic state prediction result.
The device determines the target expansion level of the Fourier function based on the average absolute percentage error, and then expands the Fourier function according to the target expansion level to predict the road traffic state, so that the accuracy of the road traffic state prediction can be improved, the basis is provided for road construction planning, the road traffic state is improved, and the degree of road traffic jam is reduced. And a data base is provided for intelligent traffic information system construction and traffic flow visualization.
Optionally, the extracting module 410 is configured to:
dividing the acquired sampling vehicle travel data according to the same time period in the same time period every day to obtain sampling vehicle travel data of a section corresponding to each time period in each day;
dividing the section of sampling vehicle travel of the same time period in each day into the same data set;
extracting periodic characteristic values of the sampled vehicle travel data of each section in the data set corresponding to each time section;
the expansion module 420 is configured to expand the fourier function based on the traffic characteristic data and the vehicle speed characteristic data of the segment-sampled vehicle trip data to obtain segment-predicted vehicle trip data corresponding to each expansion level.
Optionally, the extracting module 410 is configured to:
dividing road sections of the acquired travel data of the sampled vehicles according to road types, and determining the road types of all the road sections;
based on the road type, carrying out structural processing on the sampled vehicle travel data of each road section;
extracting a periodic term characteristic value of the sampled vehicle travel data after the structuring treatment;
the expansion module 420 is configured to expand the fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data of each road segment after the structuring processing to obtain predicted vehicle trip data of the corresponding road segment under each expansion level.
Optionally, the extracting module 410 is configured to:
extracting the characteristic value of the target travel data from the acquired sampled vehicle travel data to obtain the characteristic value of the target travel data and the characteristic value of the non-target travel data, wherein the target travel data comprises holiday travel data and/or rainy and snowy day travel data;
the expanding module 420 is configured to:
based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the target trip data characteristic values, expanding the Fourier function to obtain corresponding target predicted vehicle trip data under each expansion level; and/or the number of the groups of groups,
and expanding the Fourier function based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the non-target travel data characteristic values to obtain corresponding non-target predicted vehicle travel data under each expansion level.
Optionally, the mean absolute percentage error MAPE is determined by the following formula:
where N represents the number of samples of the sampled vehicle travel data,representing the sampled vehicle travel data,representing the predicted vehicle travel data.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the specific details of the above embodiments, and various simple modifications can be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and all the simple modifications belong to the protection scope of the present invention.
In addition, the specific features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various possible combinations are not described further.
Moreover, any combination of the various embodiments of the present invention can be made, as long as it does not depart from the gist of the present invention, which is also regarded as the content of the present invention.
Claims (10)
1. A method of predicting road traffic conditions, the method comprising:
extracting characteristic values of the acquired sampled vehicle travel data to obtain travel characteristic data, wherein the travel characteristic data comprises traffic flow characteristic data and vehicle speed characteristic data;
based on the traffic flow characteristic data and the vehicle speed characteristic data, expanding a Fourier function to obtain corresponding predicted vehicle travel data under each expansion level;
calculating an average absolute percentage error according to the sample number of the sampled vehicle trip data, the sampled vehicle trip data and the predicted vehicle trip data;
determining a target expansion level of the Fourier function according to the average absolute percentage error;
and expanding the Fourier function according to the target expansion level to obtain the road traffic state prediction result.
2. The method of claim 1, wherein the extracting the feature value of the acquired sampled vehicle travel data comprises:
dividing the acquired sampling vehicle travel data according to the same time period in the same time period every day to obtain sampling vehicle travel data of a section corresponding to each time period in each day;
dividing the section of sampling vehicle travel of the same time period in each day into the same data set;
extracting periodic characteristic values of the sampled vehicle travel data of each section in the data set corresponding to each time section;
based on the traffic flow characteristic data and the vehicle speed characteristic data, the Fourier function is unfolded to obtain corresponding predicted vehicle travel data under each unfolding level, and the method comprises the following steps:
and based on the traffic flow characteristic data and the vehicle speed characteristic data of the section sampling vehicle trip data, expanding the Fourier function to obtain corresponding section prediction vehicle trip data under each expansion level.
3. The method of claim 1, wherein the extracting the feature value of the acquired sampled vehicle travel data comprises:
dividing road sections of the acquired travel data of the sampled vehicles according to road types, and determining the road types of all the road sections;
based on the road type, carrying out structural processing on the sampled vehicle travel data of each road section;
extracting a periodic term characteristic value of the sampled vehicle travel data after the structuring treatment;
based on the traffic flow characteristic data and the vehicle speed characteristic data, the Fourier function is unfolded to obtain corresponding predicted vehicle travel data under each unfolding level, and the method comprises the following steps:
and expanding the Fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data of each road section after the structuring processing to obtain the predicted vehicle travel data of the corresponding road section under each expansion level.
4. The method of claim 1, wherein the extracting the feature value of the acquired sampled vehicle travel data comprises:
extracting the characteristic value of the target travel data from the acquired sampled vehicle travel data to obtain the characteristic value of the target travel data and the characteristic value of the non-target travel data, wherein the target travel data comprises holiday travel data and/or rainy and snowy day travel data;
based on the traffic flow characteristic data and the vehicle speed characteristic data, the Fourier function is unfolded to obtain corresponding predicted vehicle travel data under each unfolding level, and the method comprises the following steps:
based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the target trip data characteristic values, expanding the Fourier function to obtain corresponding target predicted vehicle trip data under each expansion level; and/or the number of the groups of groups,
and expanding the Fourier function based on the traffic flow characteristic data and the real-time vehicle speed characteristic data in the non-target travel data characteristic values to obtain corresponding non-target predicted vehicle travel data under each expansion level.
5. The method according to any one of claims 1-4, wherein the mean absolute percentage error MAPE is determined by the following formula:
6. A road traffic condition prediction apparatus, characterized in that the apparatus comprises:
the extraction module is used for extracting characteristic values of the acquired sampling vehicle travel data to obtain travel characteristic data, wherein the travel characteristic data comprises vehicle flow characteristic data and vehicle speed characteristic data;
the unfolding module is used for unfolding the Fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data to obtain corresponding predicted vehicle travel data under each unfolding level;
the calculation module is used for calculating an average absolute percentage error according to the sample number of the sampled vehicle travel data, the sampled vehicle travel data and the predicted vehicle travel data;
the determining module is used for determining a target expansion level of the Fourier function according to the average absolute percentage error;
and the execution module is used for expanding the Fourier function according to the target expansion level to obtain the road traffic state prediction result.
7. The apparatus of claim 6, wherein the extraction module is configured to:
dividing the acquired sampling vehicle travel data according to the same time period in the same time period every day to obtain sampling vehicle travel data of a section corresponding to each time period in each day;
dividing the section of sampling vehicle travel of the same time period in each day into the same data set;
extracting periodic characteristic values of the sampled vehicle travel data of each section in the data set corresponding to each time section;
the expansion module is used for expanding the Fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data of the section sampling vehicle trip data to obtain corresponding section prediction vehicle trip data under each expansion level.
8. The apparatus of claim 6, wherein the extraction module is configured to:
dividing road sections of the acquired travel data of the sampled vehicles according to road types, and determining the road types of all the road sections;
based on the road type, carrying out structural processing on the sampled vehicle travel data of each road section;
extracting a periodic term characteristic value of the sampled vehicle travel data after the structuring treatment;
the expansion module is used for expanding the Fourier function based on the traffic flow characteristic data and the vehicle speed characteristic data of each road section after the structuring processing to obtain the road section prediction vehicle trip data corresponding to each expansion level.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1-5.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110311681.3A CN112906984B (en) | 2021-03-24 | 2021-03-24 | Road traffic state prediction method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110311681.3A CN112906984B (en) | 2021-03-24 | 2021-03-24 | Road traffic state prediction method and device, storage medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112906984A CN112906984A (en) | 2021-06-04 |
CN112906984B true CN112906984B (en) | 2023-06-30 |
Family
ID=76106381
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110311681.3A Active CN112906984B (en) | 2021-03-24 | 2021-03-24 | Road traffic state prediction method and device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112906984B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004264884A (en) * | 2003-01-23 | 2004-09-24 | Matsushita Electric Ind Co Ltd | Method, system and device for providing traffic information |
JP2005250695A (en) * | 2004-03-02 | 2005-09-15 | Sumitomo Electric Ind Ltd | Traveling time prediction method, apparatus and program |
CN104008646A (en) * | 2014-06-12 | 2014-08-27 | 招商局重庆交通科研设计院有限公司 | Urban road traffic identification method and system based on elastic coefficients |
US9142125B1 (en) * | 2014-05-21 | 2015-09-22 | Sap Se | Traffic prediction using precipitation |
JP2016075998A (en) * | 2014-10-02 | 2016-05-12 | 住友電工システムソリューション株式会社 | Road traffic situation prediction device, road traffic situation prediction system, road traffic situation prediction method, and computer program |
CN107170234A (en) * | 2017-06-09 | 2017-09-15 | 东方网力科技股份有限公司 | A kind of method predicted based on SVM algorithm traffic in short-term |
CN107481523A (en) * | 2017-09-27 | 2017-12-15 | 中南大学 | A kind of traffic flow speed Forecasting Methodology and system |
CN108932855A (en) * | 2017-05-22 | 2018-12-04 | 阿里巴巴集团控股有限公司 | Road traffic control system, method and electronic equipment |
CN109035767A (en) * | 2018-07-13 | 2018-12-18 | 北京工业大学 | A kind of tide lane optimization method considering Traffic Control and Guidance collaboration |
CN111462479A (en) * | 2020-02-26 | 2020-07-28 | 南京新一代人工智能研究院有限公司 | Traffic flow prediction method based on Fourier-recurrent neural network |
KR20210000198A (en) * | 2019-06-24 | 2021-01-04 | (주)아레스 | Method for predicting and simulating congestion of road flow |
CN112183868A (en) * | 2020-09-30 | 2021-01-05 | 青岛海信网络科技股份有限公司 | Construction method of traffic flow prediction model and electronic equipment |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9435652B2 (en) * | 2013-12-19 | 2016-09-06 | Novatel Wireless, Inc. | Dynamic routing intelligent vehicle enhancement system |
-
2021
- 2021-03-24 CN CN202110311681.3A patent/CN112906984B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004264884A (en) * | 2003-01-23 | 2004-09-24 | Matsushita Electric Ind Co Ltd | Method, system and device for providing traffic information |
JP2005250695A (en) * | 2004-03-02 | 2005-09-15 | Sumitomo Electric Ind Ltd | Traveling time prediction method, apparatus and program |
US9142125B1 (en) * | 2014-05-21 | 2015-09-22 | Sap Se | Traffic prediction using precipitation |
CN104008646A (en) * | 2014-06-12 | 2014-08-27 | 招商局重庆交通科研设计院有限公司 | Urban road traffic identification method and system based on elastic coefficients |
JP2016075998A (en) * | 2014-10-02 | 2016-05-12 | 住友電工システムソリューション株式会社 | Road traffic situation prediction device, road traffic situation prediction system, road traffic situation prediction method, and computer program |
CN108932855A (en) * | 2017-05-22 | 2018-12-04 | 阿里巴巴集团控股有限公司 | Road traffic control system, method and electronic equipment |
CN107170234A (en) * | 2017-06-09 | 2017-09-15 | 东方网力科技股份有限公司 | A kind of method predicted based on SVM algorithm traffic in short-term |
CN107481523A (en) * | 2017-09-27 | 2017-12-15 | 中南大学 | A kind of traffic flow speed Forecasting Methodology and system |
CN109035767A (en) * | 2018-07-13 | 2018-12-18 | 北京工业大学 | A kind of tide lane optimization method considering Traffic Control and Guidance collaboration |
KR20210000198A (en) * | 2019-06-24 | 2021-01-04 | (주)아레스 | Method for predicting and simulating congestion of road flow |
CN111462479A (en) * | 2020-02-26 | 2020-07-28 | 南京新一代人工智能研究院有限公司 | Traffic flow prediction method based on Fourier-recurrent neural network |
CN112183868A (en) * | 2020-09-30 | 2021-01-05 | 青岛海信网络科技股份有限公司 | Construction method of traffic flow prediction model and electronic equipment |
Non-Patent Citations (3)
Title |
---|
基于傅里叶级数残差修正TDGM(1,1)的车流量预测模型;刘素娟;包天悦;原大明;;价值工程(13);248-250 * |
基于小波神经网络短时交通流量预测;任晓霞;宋海明;;数码设计(06);43-45+49 * |
基于混沌理论和MEA-BPNN模型的快速路短时交通流预测;王硕;谷远利;李萌;陆文琦;张源;;山东科学(02);100-109 * |
Also Published As
Publication number | Publication date |
---|---|
CN112906984A (en) | 2021-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yuan et al. | Driving with knowledge from the physical world | |
US11335191B2 (en) | Intelligent telematics system for defining road networks | |
CN110738856B (en) | Mobile clustering-based urban traffic jam fine identification method | |
Mo et al. | Speed profile estimation using license plate recognition data | |
US11341846B2 (en) | Traffic analytics system for defining road networks | |
US11335189B2 (en) | Method for defining road networks | |
CN110969190B (en) | Illegal operation vehicle detection method, medium, equipment and device | |
Norros et al. | The Palm distribution of traffic conditions and its application to accident risk assessment | |
CN107195177A (en) | Based on Forecasting Methodology of the distributed memory Computational frame to city traffic road condition | |
CN104298832A (en) | Road network traffic flow analytical method based on RFID technology | |
Kumar et al. | Pattern identification based bus arrival time prediction | |
Ma et al. | Estimation of the automatic vehicle identification based spatial travel time information collected in Stockholm | |
US10163339B2 (en) | Monitoring traffic congestion | |
CN112906984B (en) | Road traffic state prediction method and device, storage medium and electronic equipment | |
CN113822487A (en) | Risk early warning method and device for operating vehicle, storage medium and computer equipment | |
Gore et al. | A hazard-based model to derive travel time under congested conditions | |
CN113850297A (en) | Road data monitoring method and device, electronic equipment and storage medium | |
CN112489432A (en) | Method and device for calculating number of vehicles on highway and storage medium | |
CN113393011A (en) | Method, apparatus, computer device and medium for predicting speed limit information | |
Hussain et al. | Visualizing Impact of Weather on Traffic Congestion Prediction: A Quantitative Study | |
EP3922947A2 (en) | Traffic analytics system for defining road networks | |
EP3913551A1 (en) | Method for defining road networks | |
CN110619745B (en) | Data processing method and device for preventing traffic jam | |
EP3919860A1 (en) | Intelligent telematics system for defining road networks | |
CN113282835B (en) | Parking place recommendation method and device and electronic equipment |
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 |