CN111582563B - Short-term prediction method, system, device and storage medium for individual travel time - Google Patents
Short-term prediction method, system, device and storage medium for individual travel time Download PDFInfo
- Publication number
- CN111582563B CN111582563B CN202010332406.5A CN202010332406A CN111582563B CN 111582563 B CN111582563 B CN 111582563B CN 202010332406 A CN202010332406 A CN 202010332406A CN 111582563 B CN111582563 B CN 111582563B
- Authority
- CN
- China
- Prior art keywords
- driver
- under
- road section
- time window
- traffic
- 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 41
- 230000006399 behavior Effects 0.000 claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 33
- 238000001514 detection method Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000003064 k means clustering Methods 0.000 claims description 6
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000000638 solvent extraction 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a short-term prediction method, a short-term prediction system, a short-term prediction device and a short-term prediction storage medium for individual travel time, wherein the method comprises the following steps: constructing an individual travel data set; calculating traffic states of all road sections under all time windows; acquiring driving behaviors of each driver in each traffic state, and determining driving preference of each driver in each traffic state; predicting the traffic state of each road section under each time window according to the traffic state of each road section under each time window; determining a road section travel time predicted value of a driver based on the predicted traffic state of the next time window and combining the driving preference of the driver in each traffic state; and carrying out error analysis on the road section travel time predicted value, and determining the driving behavior probability of the driver. The invention considers the difference of the driver preference of different traffic states, improves the prediction accuracy of the driver preference, and can be widely applied to the technical field of traffic data processing.
Description
Technical Field
The invention relates to the technical field of traffic data processing, in particular to a method, a system, a device and a storage medium for short-term prediction of individual travel time.
Background
Individual link travel times are important indicators reflecting differences in driver preferences, driving behavior. Different from indexes such as average travel time of road sections and average running speed of road networks used by the current main stream evaluation road sections or road networks, the travel time of individual road sections is focused on embodying individual differences, vehicles are managed more finely, and driving preferences of different drivers in different traffic states of different road sections can be obtained by learning driver preferences through a large amount of data. Through the calculated driving preference, a better travel path can be recommended for drivers with different driving preferences, and the running efficiency of the urban road network is improved.
Urban travel time estimation has important significance in various levels of traffic operation and traffic management. Because of the differences of driving preference and driving behavior among drivers, the travel time of different drivers passing through the same road section under similar traffic conditions is obviously different, and meanwhile, because of the differences of different traveler information acquisition modes, such as different navigation-dependent groups and non-navigation-dependent groups, the traveler has different perceptions of road states. The AVI data has the characteristic of full data, detectors are reasonably distributed in the city, almost all vehicles passing through the city can be detected, road section travel time with identity information can be obtained by matching information such as license plates and the like through the detectors, and meanwhile, origin-destination information of the current trip of the identity can also be obtained. Compared with the conventional questionnaire method which is only commonly used in large-scale traffic investigation, the AVI data has the advantages of small workload, reliable data and the like. The conventional data such as floating car data, coil data and sample size are small, and calculation of driver preference in a large range is difficult to support. The matrix decomposition of AVI data by a learner is expected to describe driving preferences in terms of hidden factors, which is less interpretable for driver preferences. There are also scholars desiring to establish driving preferences of different drivers on different road segments, but neglecting that drivers may have different driving preferences in different traffic conditions.
At present, no method for predicting the travel time of an individual road section from the angle that the preferences of drivers are different in different traffic states exists.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a method, a system, a device, and a storage medium for short-term prediction of individual travel time, which can consider the difference of driver preferences in different traffic states and improve the accuracy of prediction.
A first aspect of the present invention provides a method for short-term prediction of individual travel time, comprising:
acquiring the travel time of each driver under a road section corresponding to each time window, and constructing an individual travel data set;
calculating traffic states of all road sections under all time windows based on the average travel time under each time window and the corresponding travel traffic quantity;
acquiring driving behaviors of each driver in each traffic state, and determining driving preference of each driver in each traffic state;
predicting the traffic state of each road section under each time window according to the traffic state of each road section under each time window;
determining a road section travel time predicted value of a driver based on the predicted traffic state of the next time window and combining the driving preference of the driver in each traffic state;
and carrying out error analysis on the road section travel time predicted value, and determining the driving behavior probability of the driver.
The step of obtaining the travel time of each driver under the corresponding road section of each time window and constructing an individual travel data set comprises the following steps:
determining a triplet of original AVI data, wherein the content of the triplet comprises a vehicle identity identifier, a detector identifier and a detection time;
according to the triplets, obtaining detection sequences obtained by the vehicle passing through each detector under each time window;
carrying out validity screening on the data in the detection sequence;
and constructing a travel matrix and a speed matrix of individual travel data according to the screened data.
In some embodiments, the calculating the traffic state of each road section under each time window based on the average travel time under each time window and the corresponding travel traffic volume includes:
acquiring traffic volumes of all road sections under all time windows;
calculating the average speed of each road section under each time window;
according to the traffic volume and the average speed, determining the initial traffic state of each road section under each time window;
acquiring a clustering center under each road section by a K-Means clustering method according to the initial traffic state;
sequencing the clustering centers under each road section according to the average speed to construct a state sequence set of each road section;
and calculating the traffic state of each road section under each time window according to the state sequence set.
In some embodiments, the obtaining driving behavior of each driver in the respective traffic state, determining driving preference of each driver in the respective traffic state, includes:
calculating initial driving preference of a driver in each road section under each time window, and recording state marks of each road section under each time window;
grouping and aggregating the initial driving preferences under different state marks to obtain a driving preference set under different state marks;
according to the driving preference set, driving preferences of the driver in different states corresponding to the road sections are calculated;
and constructing a driver preference matrix according to the driving preference.
In some embodiments, the predicting the traffic state of the next time window according to the traffic state of each road segment under each time window includes:
calculating autocorrelation coefficients of all road sections on a road network, and obtaining traffic state prediction models of all road sections;
and predicting the traffic state of the next time window according to the traffic state prediction model.
In some embodiments, the determining the road-section travel time predicted value of the driver based on the predicted traffic state of the next time window in combination with the driving preference of the driver in each traffic state includes:
searching a driver preference matrix matched with the traffic state according to the predicted traffic state of the next time window;
and calculating the journey time of the driver according to the driver preference matrix.
In some embodiments, the performing error analysis on the road segment travel time predicted value to determine the driving behavior probability of the driver includes:
calculating a deviation value of the road section travel time predicted value;
judging whether the deviation value is in a preset threshold range, if so, determining the road section travel time predicted value as an accurate value, and further determining the driving behavior of a driver; otherwise, updating the driver preference matrix of the driver;
the step of updating the driver preference matrix of the driver includes:
calculating the preference of the current driver;
adding the calculated preference of the current driver to a driving preference set;
calculating driving preferences of the driver corresponding to different states on each road section according to the driving preference set;
and updating a driver preference matrix according to the driving preference.
According to a second aspect of the present invention there is also provided an individual travel time short-term prediction system comprising:
the initial data acquisition module is used for acquiring the travel time of each driver under the corresponding road section of each time window and constructing an individual travel data set;
the traffic state calculation module is used for calculating the traffic state of each road section under each time window based on the average travel time under each time window and the corresponding travel traffic volume;
the driving preference calculation module is used for acquiring driving behaviors of each driver in each traffic state and determining driving preference of each driver in each traffic state;
the traffic state prediction module is used for predicting the traffic state of the next time window according to the traffic state of each road section under each time window;
the travel time prediction module is used for determining a road section travel time predicted value of the driver based on the predicted traffic state of the next time window and combining the driving preference of the driver in each traffic state;
and the correction module is used for carrying out error analysis on the road section travel time predicted value and determining the driving behavior probability of the driver.
According to a third aspect of the present invention there is also provided an apparatus comprising a processor and a memory;
the memory is used for storing programs;
the processor is configured to perform the method according to the first aspect according to the program.
According to a fourth aspect of the present invention there is also provided a storage medium storing a program for execution by a processor to perform the method according to the first aspect of the present invention.
The embodiment of the invention firstly extracts the travel time of each driver under the corresponding road section under each time window and constructs an individual travel data set; then calculating the traffic state of each road section under each time window based on the average travel time under the time window and the corresponding travel traffic; for different drivers, counting driving behaviors of the drivers in different states, and calculating different driving preferences of the drivers in different states; predicting the traffic state under the current window based on the traffic state under the current window; based on the calculated traffic state, predicting the current travel time of the driver road section in combination with the driving preference of the driver; and carrying out error analysis on the predicted travel time, correcting traffic state prediction, and simultaneously correcting driving behavior probability of a driver. The personalized journey time short-term prediction provided by the invention considers the difference of the driver preference of different traffic states, improves the prediction accuracy of the driver preference, and can provide a better individual traffic estimation and more effective road right distribution scheme for cities.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating the overall steps of an embodiment of the present invention;
FIG. 2 is a flow chart of steps of a K-Means clustering process according to an embodiment of the present invention.
Detailed Description
The invention is further explained and illustrated below with reference to the drawing and the specific embodiments of the present specification. The step numbers in the embodiments of the present invention are set for convenience of illustration, and the order of steps is not limited in any way, and the execution order of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.
Referring to fig. 1, an embodiment of the present invention provides a method for short-term prediction of individual travel time, including the steps of:
s1, extracting travel time of each driver under a corresponding road section under each time window, and constructing an individual travel data set;
step S1 of the present embodiment includes S11-S14:
s11, determining a triplet of original AVI data, wherein the content of the triplet comprises a vehicle identity mark, a detector mark and detection time;
s12, acquiring a detection sequence obtained by the vehicle passing through each detector under each time window according to the triplets;
s13, screening the data in the detection sequence for effectiveness;
s14, constructing a travel matrix and a speed matrix of individual travel data according to the screened data.
Specifically, in the step S1, the present embodiment extracts the travel time of each driver under the corresponding road section under each time window, and constructs the individual travel data set; the specific implementation process is that the original AVI data is defined as a triplet < veh, infr, t >, wherein veh is a vehicle identity, infr is a detector identity, and t is a detection time.
Whereas for vehicle i, the AVI data at each detection time t can be given by the retrieval function as:
f infr (i，t)＝infr
the vehicle passes through a series of detectors under a time window T, and AVI data are ordered according to the detection time T and form a detection sequence
In the path sequence, whether the corresponding data is effective data can be judged according to the maximum travel time criterion, and the condition that the adjacent detection f exists in the detection sequence of the vehicle i is assumed infr (i，t a )、f infr (i，t b ) Wherein t is a ＜t b Sequentially pass through the detector infr a And infr b The corresponding road segment is j, if the following two conditions are satisfied:
①t a ∈T
②
wherein, len j For the length of the road section j, v j Is the lowest travel speed of road segment j.
Then the corresponding travel time of the road section j is travelled by the vehicle i in the time window T
The method comprises the following steps:
if the vehicle i does not travel on the road section j traveling under the time window T, the corresponding travel time is obtained
/>
Travel time of vehicle i under travel section j under time window T
Can be given by the equation (1):
for n drivers and m road segments in a region, all data can form a travel matrix W under a time window T (T) ：
For travel matrix W (T) Conversion into velocity matrix V (T) ：
Wherein:
W (T) column partitioning can be performed to obtain equivalent expression forms:
A＝(a 1 ,a 2 ,…,a m )
s2, calculating traffic states of all road sections under all time windows based on the average travel time under the time windows and corresponding traveling traffic volumes;
step S2 of the present embodiment includes S21 to S26:
s21, acquiring traffic volumes of all road sections under all time windows;
s22, calculating the average speed of each road section under each time window;
s23, determining initial traffic states of all road sections under all time windows according to the traffic volume and the average speed;
s24, acquiring a clustering center under each road section through a K-Means clustering method according to the initial traffic state;
s25, sorting the clustering centers under each road section according to the average speed, and constructing a state sequence set of each road section;
s26, calculating the traffic state of each road section under each time window according to the state sequence set.
Specifically, in this embodiment, according to the average travel time and the corresponding traffic volume of travel, the traffic state of each road section under each time window is calculated, and the implementation process is as follows:
1) Counting traffic volume of road section j under time window T
The calculation formula is as formula (2):
wherein, the liquid crystal display device comprises a liquid crystal display device,
2) Calculating the average speed of road section j under time window T
The calculation formula is as formula (3):
3) Using average velocity
And traffic amount->
Initial traffic state s (j, T) under time window T as adjective segment j:
4) Long time window set lt= { T 1 ,T 2 ,…,T N N > N }, where N > N ε Constructing a segment j initial state data set s j ＝{s(j,T 1 ),…,s(j,T k ),…,s(j,T N )|T k Epsilon LT }; k-Means clustering can be utilized to gather k classes, and different k class clustering centers under the road section j can be obtained.
The clustering process of the present embodiment includes the steps of clustering the j-state data sets s of road segments before clustering as shown in FIG. 2 j Normalizing each index of each group of data to obtain normalized data set s' j ＝{s′(j,T 1 ),…,s′(j,T k ),…,s′(j,T N )|T k E LT, normalized equation such as equation set (4):
and after normalization, obtaining a cluster number K and a corresponding initialization center point.
The points on the dataset are then categorized into classes that are closest to Euclidean distance.
Wherein the individual samples s' (j, T) in the normalized dataset are calculated i ) And cluster center vector μ (i) The Euclidean distance dist(s) is used when the distance of i is more than or equal to 1 and less than or equal to k i ,s j ) Calculation is as formula (5):
and finally, after calculating the average value of each class, outputting the center of k class clusters as in formula (6).
5) According to speed
For class kThe cluster center sorts and constructs a road section j state sequence set S j
6) Calculating traffic state of road section j under time window T
The traffic state under road section j under time window T may be expressed as:
alignment according to formula (4) after normalization>
Calculating the distances between the current state and the centers of various clusters according to the formula (5), and calculating the state cluster mark +.>
Calculation is as formula (7):
then the traffic conditions are under the time window T
Wherein the method comprises the steps of
S3, for different drivers, counting driving behaviors of the drivers in different states, and calculating different driving preferences of the drivers in different states;
in some embodiments, step S3 includes S31-S34:
s31, calculating initial driving preference of a driver in each road section under each time window, and recording state marks of each road section under each time window;
s32, grouping and aggregating the initial driving preferences under different state marks to obtain a driving preference set under different state marks;
s33, calculating driving preferences of the driver corresponding to different states on each road section according to the driving preference set;
s34, constructing a driver preference matrix according to the driving preference.
Specifically, in step S3 described in the present embodiment, for different drivers, different driving preferences of the driver in different states are calculated, and the implementation process is as follows:
1) Calculating driving preference of driver i on road section j under time window T
The driving preference is given by the following equation (8) definition: />
Wherein, the liquid crystal display device comprises a liquid crystal display device,
for the time window T the driver i travels at road section j.
2) At the same time, the state of the road section j under the time window T is recorded
3) Long time window set lt= { T 1 ,T 2 ,…,T N N > N }, where N > N ε For being in different states, the mark lambda is marked j Grouping aggregation to obtain different state marks lambda j Lower part(s)
Set->
Calculating the state lambda of the driver on road section j j Lower driving preference
The calculation is shown in formula (9):
wherein N is a set
Number of inner elements.
3) Each driver individual status flag lambda j Lower part(s)
Can be described in a matrix manner as a driver preference matrix C (i) ：
S4, predicting the traffic state of the next time window based on the traffic state of the current time window and the historical time window;
in some embodiments, step S4 includes S41-S42:
s41, calculating autocorrelation coefficients of all road sections on a road network, and obtaining traffic state prediction models of all the road sections;
s42, predicting the traffic state of the next time window according to the traffic state prediction model.
Specifically, in step S4 described in the present embodiment, the traffic state under the next time window is predicted based on the traffic state under the current window, and the implementation procedure is as follows:
(1) the traffic state under the T+1th time window is predicted by using the traffic state under the p time windows by using an AR autoregressive method. The AR autoregressive method is as follows:
1) For a single road segment j, the autocorrelation coefficients ACF are calculated using the acquired time series,
if:
ACF(p+1)＜ε p
wherein ε p Representing a preset infinitesimal amount.
Then the AR model is called p-order truncated, and the AR model order can be confirmed to be p-order. Confirming that the section autoregressive model is selected as AR (p)
2) And respectively calculating all road sections on the road network to obtain a traffic state prediction model of all road sections of the whole road network.
(2) Calculating a predicted state
Distance from history cluster center->
Determining a state mark of the current moment T according to the distance from the nearest moment:
s5, determining a road section travel time predicted value of the driver based on the predicted traffic state of the next time window and combining the driving preference of the driver in each traffic state;
in some embodiments, step S5 includes S51-S52:
s51, searching a driver preference matrix matched with the traffic state according to the predicted traffic state of the next time window;
s52, calculating the journey time of the driver according to the driver preference matrix.
Specifically, step s5 in this embodiment predicts the current travel time of the driver road section based on the calculated traffic state in combination with the preference of the driver, and the implementation process is as follows:
1) State after matching predictions
There is a status flag lambda j Finding the driver veh preference matrix C that matches this state (veh) C matched in (c) j,k An item.
2) Calculating predicted driver veh travel time:
s6, carrying out error analysis on the road section travel time predicted value, and determining the driving behavior probability of the driver.
In some embodiments, step S6 includes S61-S62:
s61, calculating a deviation value of the road section travel time predicted value;
s62, judging whether the deviation value is in a preset threshold range, if so, determining the road section travel time predicted value as an accurate value, and further determining the driving behavior of a driver; otherwise, updating the driver preference matrix of the driver;
wherein the step of updating the driver preference matrix of the driver includes:
calculating the preference of the current driver;
adding the calculated preference of the current driver to a driving preference set;
calculating driving preferences of the driver corresponding to different states on each road section according to the driving preference set;
and updating a driver preference matrix according to the driving preference.
In this embodiment, the step S6 performs error analysis on the predicted travel time to correct the driving behavior probability of the driver, and the implementation process is as follows:
1) Calculating deviation value
2) Judging whether bias is within reasonable range N If yes, receiving a hypothesis; otherwise the driver preference matrix C will be updated (i) 。
The specific updating steps are as follows:
(1) calculating the current driver preference according to equation (8)
(2) Will be
Added to the status flag lambda j Lower set->
(3) Recalculating according to equation (9)
(4) Finally update C (i) 。
The embodiment of the invention also provides a system for short-term prediction of the individual travel time, which comprises the following steps:
the initial data acquisition module is used for acquiring the travel time of each driver under the corresponding road section of each time window and constructing an individual travel data set;
the traffic state calculation module is used for calculating the traffic state of each road section under each time window based on the average travel time under each time window and the corresponding travel traffic volume;
the driving preference calculation module is used for acquiring driving behaviors of each driver in each traffic state and determining driving preference of each driver in each traffic state;
the traffic state prediction module is used for predicting the traffic state of the next time window according to the traffic state of each road section under each time window;
the travel time prediction module is used for determining a road section travel time predicted value of the driver based on the predicted traffic state of the next time window and combining the driving preference of the driver in each traffic state;
and the correction module is used for carrying out error analysis on the road section travel time predicted value and determining the driving behavior probability of the driver.
The embodiment of the invention also provides a device, which comprises a processor and a memory;
the memory is used for storing programs;
the processor is configured to execute the method according to the present invention according to the program.
The embodiment of the invention also provides a storage medium, wherein the storage medium stores a program, and the program is executed by a processor to complete the method.
In summary, the personalized journey time short-term prediction provided by the invention considers the difference of the driver preference of different traffic states, improves the prediction accuracy of the driver preference, and can provide better individual traffic estimation and more effective road right allocation scheme for cities.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the invention is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the described functions and/or features may be integrated in a single physical device and/or software module or one or more functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the invention, which is to be defined in the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the embodiments described above, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present invention, and these equivalent modifications and substitutions are intended to be included in the scope of the present invention as defined in the appended claims.
Claims (8)
1. A method for short-term prediction of individual travel time, comprising:
acquiring the travel time of each driver under a road section corresponding to each time window, and constructing an individual travel data set;
calculating traffic states of all road sections under all time windows based on the average travel time under each time window and the corresponding travel traffic quantity;
acquiring driving behaviors of each driver in each traffic state, and determining driving preference of each driver in each traffic state;
predicting the traffic state of each road section under each time window according to the traffic state of each road section under each time window;
determining a road section travel time predicted value of a driver based on the predicted traffic state of the next time window and combining the driving preference of the driver in each traffic state;
carrying out error analysis on the road section travel time predicted value to determine the driving behavior probability of a driver;
the calculating the traffic state of each road section under each time window based on the average travel time under each time window and the corresponding travel traffic volume comprises the following steps:
acquiring traffic volumes of all road sections under all time windows;
calculating the average speed of each road section under each time window;
according to the traffic volume and the average speed, determining the initial traffic state of each road section under each time window;
acquiring a clustering center under each road section by a K-Means clustering method according to the initial traffic state;
sequencing the clustering centers under each road section according to the average speed to construct a state sequence set of each road section;
calculating traffic states of all road sections under all time windows according to the state sequence set;
the step of obtaining the driving behavior of each driver in the traffic states and determining the driving preference of each driver in the traffic states comprises the following steps:
calculating initial driving preference of a driver in each road section under each time window, and recording state marks of each road section under each time window;
grouping and aggregating the initial driving preferences under different state marks to obtain a driving preference set under different state marks;
according to the driving preference set, driving preferences of the driver in different states corresponding to the road sections are calculated;
and constructing a driver preference matrix according to the driving preference.
2. The method for short-term prediction of individual travel time according to claim 1, wherein the step of obtaining the travel time of each driver under each section corresponding to each time window, and constructing the individual travel data set, comprises:
determining a triplet of original AVI data, wherein the content of the triplet comprises a vehicle identity identifier, a detector identifier and a detection time;
according to the triplets, obtaining detection sequences obtained by the vehicle passing through each detector under each time window;
carrying out validity screening on the data in the detection sequence;
and constructing a travel matrix and a speed matrix of individual travel data according to the screened data.
3. The method for short-term prediction of individual travel time according to claim 1, wherein predicting the traffic state of the next time window according to the traffic state of each road segment under each time window comprises:
calculating autocorrelation coefficients of all road sections on a road network, and obtaining traffic state prediction models of all road sections;
and predicting the traffic state of the next time window according to the traffic state prediction model.
4. The method for short-term prediction of individual travel time according to claim 1, wherein determining the predicted value of the travel time of the road section of the driver based on the predicted traffic state of the next time window in combination with the driving preference of the driver in each traffic state comprises:
searching a driver preference matrix matched with the traffic state according to the predicted traffic state of the next time window;
and calculating the journey time of the driver according to the driver preference matrix.
5. The method for short-term prediction of individual travel time according to claim 1, wherein said performing error analysis on the predicted value of the travel time of the road segment to determine the driving behavior probability of the driver comprises:
calculating a deviation value of the road section travel time predicted value;
judging whether the deviation value is in a preset threshold range, if so, determining the road section travel time predicted value as an accurate value, and further determining the driving behavior of a driver; otherwise, updating the driver preference matrix of the driver;
the step of updating the driver preference matrix of the driver includes:
calculating the preference of the current driver;
adding the calculated preference of the current driver to a driving preference set;
calculating driving preferences of the driver corresponding to different states on each road section according to the driving preference set;
and updating a driver preference matrix according to the driving preference.
6. A system for short-term prediction of travel time of an individual, comprising:
the initial data acquisition module is used for acquiring the travel time of each driver under the corresponding road section of each time window and constructing an individual travel data set;
the traffic state calculation module is used for calculating the traffic state of each road section under each time window based on the average travel time under each time window and the corresponding travel traffic volume;
the driving preference calculation module is used for acquiring driving behaviors of each driver in each traffic state and determining driving preference of each driver in each traffic state;
the traffic state prediction module is used for predicting the traffic state of the next time window according to the traffic state of each road section under each time window;
the travel time prediction module is used for determining a road section travel time predicted value of the driver based on the predicted traffic state of the next time window and combining the driving preference of the driver in each traffic state;
the correction module is used for carrying out error analysis on the road section travel time predicted value and determining the driving behavior probability of the driver;
the traffic state calculation module is specifically configured to:
acquiring traffic volumes of all road sections under all time windows;
calculating the average speed of each road section under each time window;
according to the traffic volume and the average speed, determining the initial traffic state of each road section under each time window;
acquiring a clustering center under each road section by a K-Means clustering method according to the initial traffic state;
sequencing the clustering centers under each road section according to the average speed to construct a state sequence set of each road section;
calculating traffic states of all road sections under all time windows according to the state sequence set;
the driving preference calculation module is specifically configured to:
calculating initial driving preference of a driver in each road section under each time window, and recording state marks of each road section under each time window;
grouping and aggregating the initial driving preferences under different state marks to obtain a driving preference set under different state marks;
according to the driving preference set, driving preferences of the driver in different states corresponding to the road sections are calculated;
and constructing a driver preference matrix according to the driving preference.
7. An apparatus comprising a processor and a memory;
the memory is used for storing programs;
the processor is configured to perform the method according to any one of claims 1-5 according to the program.
8. A storage medium storing a program for execution by a processor to perform the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010332406.5A CN111582563B (en) | 2020-04-24 | 2020-04-24 | Short-term prediction method, system, device and storage medium for individual travel time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010332406.5A CN111582563B (en) | 2020-04-24 | 2020-04-24 | Short-term prediction method, system, device and storage medium for individual travel time |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111582563A CN111582563A (en) | 2020-08-25 |
| CN111582563B true CN111582563B (en) | 2023-04-25 |
Family
ID=72124490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010332406.5A Active CN111582563B (en) | 2020-04-24 | 2020-04-24 | Short-term prediction method, system, device and storage medium for individual travel time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582563B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114257681A (en) * | 2020-09-25 | 2022-03-29 | 深圳市万普拉斯科技有限公司 | Method for controlling terminal to start driving mode, terminal and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484911A (en) * | 2014-10-29 | 2015-04-01 | 云南大学 | QoE-based customized automatic driving parameter optimal setting method |
| CN108896064A (en) * | 2018-07-05 | 2018-11-27 | 晁保锁 | The arrival time Prediction System applied to GPS navigation system based on information sharing |
| CN109635852A (en) * | 2018-11-26 | 2019-04-16 | 汉纳森（厦门）数据股份有限公司 | A kind of building of user's portrait and clustering method based on multidimensional property |
| CN109829601A (en) * | 2018-12-07 | 2019-05-31 | 深圳大学 | A kind of driver drives the prediction technique and system of vehicle risk behavior |
-
2020
- 2020-04-24 CN CN202010332406.5A patent/CN111582563B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484911A (en) * | 2014-10-29 | 2015-04-01 | 云南大学 | QoE-based customized automatic driving parameter optimal setting method |
| CN108896064A (en) * | 2018-07-05 | 2018-11-27 | 晁保锁 | The arrival time Prediction System applied to GPS navigation system based on information sharing |
| CN109635852A (en) * | 2018-11-26 | 2019-04-16 | 汉纳森（厦门）数据股份有限公司 | A kind of building of user's portrait and clustering method based on multidimensional property |
| CN109829601A (en) * | 2018-12-07 | 2019-05-31 | 深圳大学 | A kind of driver drives the prediction technique and system of vehicle risk behavior |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111582563A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rahmati et al. | Influence of autonomous vehicles on car-following behavior of human drivers | |
| Dong et al. | Characterizing driving styles with deep learning | |
| Toledo et al. | Modeling integrated lane-changing behavior | |
| US8554473B2 (en) | Energy efficient routing using an impedance factor | |
| US9846049B2 (en) | Route prediction | |
| Mousa et al. | A comparative analysis of tree-based ensemble methods for detecting imminent lane change maneuvers in connected vehicle environments | |
| Choi et al. | Network-wide vehicle trajectory prediction in urban traffic networks using deep learning | |
| CN109977322B (en) | Travel mode recommendation method and device, computer equipment and readable storage medium | |
| US20210020036A1 (en) | Predicting short-term traffic flow congestion on urban motorway networks | |
| Tamim Kashifi et al. | Efficient histogram-based gradient boosting approach for accident severity prediction with multisource data | |
| Li et al. | Reconstructing vehicle trajectories to support travel time estimation | |
| Nohekhan et al. | A deep learning model for off-ramp hourly traffic volume estimation | |
| CN113706220A (en) | User portrait determination, user demand prediction method, and data processing system | |
| Errampalli et al. | Development of the microscopic traffic simulation model with the fuzzy logic technique | |
| Moriya et al. | Traffic risk mining from heterogeneous road statistics | |
| Taylor et al. | Data mining for vehicle telemetry | |
| CN111582563B (en) | Short-term prediction method, system, device and storage medium for individual travel time | |
| CN112884235A (en) | Travel recommendation method, and training method and device of travel recommendation model | |
| Nafis et al. | Wrong-way driving crash injury analysis on arterial road networks using non-parametric data mining techniques | |
| Zhao et al. | Travel time prediction of expressway based on multi-dimensional data and the particle swarm optimization–autoregressive moving average with exogenous input model | |
| Cai et al. | Machine learning methods to analyze and predict crash injury severity based on contributing factors for southeast Michigan | |
| Chen et al. | Estimating traffic volume for local streets with imbalanced data | |
| Xu et al. | Applying finite mixture models to New York City travel times | |
| Geistefeldt et al. | Comparison of stochastic estimates of capacity and critical density for US and German freeways | |
| CN114398462B (en) | Destination recommendation method and system based on multi-source heterogeneous information network |
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 |