WO2011079707A1 - Traffic road condition information filling method and system - Google Patents

Traffic road condition information filling method and system Download PDF

Info

Publication number
WO2011079707A1
WO2011079707A1 PCT/CN2010/079732 CN2010079732W WO2011079707A1 WO 2011079707 A1 WO2011079707 A1 WO 2011079707A1 CN 2010079732 W CN2010079732 W CN 2010079732W WO 2011079707 A1 WO2011079707 A1 WO 2011079707A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
data
trend
traffic
road condition
Prior art date
Application number
PCT/CN2010/079732
Other languages
French (fr)
Chinese (zh)
Inventor
贾学力
李建军
梅生
申小次
Original Assignee
北京世纪高通科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority to CN 200910244141 priority Critical patent/CN101763730B/en
Priority to CN200910244141.7 priority
Application filed by 北京世纪高通科技有限公司 filed Critical 北京世纪高通科技有限公司
Publication of WO2011079707A1 publication Critical patent/WO2011079707A1/en

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions

Abstract

A traffic road condition information filling method and system are provided. The method includes: completing vacant data in traffic road condition data according to the historical road condition data (S101); carrying out clustering treatment on all the road condition data of a same road in a same time period for obtaining the road condition change trend, and establishing a road traffic road condition trend mode library according to the road condition change trend (S102); matching the road condition trend of the road in the time period containing the time point t with the road condition change trend of the road in the traffic road condition trend mode library, and calculating the traveling speed on the road at the time point t for filling the road condition (S103).

Description

 Traffic road condition information filling method and system

 The present invention relates to the field of traffic information processing, and in particular, to a method and system for filling traffic condition information. Background technique

 The Advanced Traffic Information System (ATIS) is based on a well-established information network and is equipped with sensors and transmission equipment on the road, on the bus, on the transfer station, on the parking lot, and in the weather center. All kinds of real-time traffic information are comprehensively processed to provide comprehensive, accurate and real-time road traffic information to the society in real time.

 Traffic travellers can use this information to determine the mode of travel and route selection, and the driver can dynamically select the route of travel through the automatic positioning and navigation system. The advanced traffic information service system not only provides timely and accurate traffic information for traffic management personnel, but also enables the traffic management control system to effectively adapt to various traffic conditions, provide decision support for the planning and transformation of traffic network capacity, and help road users effectively. Avoid traffic congestion, relieve congestion anxiety, thereby reducing frequent traffic accidents and improving the effective capacity of road network systems.

 The floating car technology is one of the advanced technical means for obtaining real-time road conditions in the international advanced intelligent transportation system in recent years. It can obtain the average speed of the vehicle on the road segment and the travel time between the two points in the road segment in real time. However, due to the limited number of floating cars and the irregularity of driving, many roads are not covered by floating cars during the same processing cycle, especially when there are fewer floating cars in the early morning. Therefore, if the road traffic congestion that the floating car does not cover is not calculated, there will be a lot of road vacancies when the information is released, which reduces the integrity and availability of the information. Therefore, how to fill the vacant road congestion information in a processing cycle is an urgent problem in traffic information processing.

The vacancy road congestion information filling is to use the local correlation of road traffic congestion status in time to fill the vacancy data. The prior art provides a method for filling traffic condition information, which is empty The missing road congestion information is used in the historical data of the floating road road congestion information, and the same road is filled with the average value of all the traveling speeds at the same time.

 The inventor found that the prior art road condition information filling method has at least the following problems in implementing the technical solution of the present invention: Although the daily speed change trend is substantially similar, the daily road traffic congestion has a certain delay in the morning and evening peaks, if the usage history The mean method will result in large errors and the filled data is not accurate enough. Summary of the invention

 The technical problem to be solved by the present invention is to provide a method and system for filling traffic condition information, which can improve the accuracy of road condition information filling.

 In order to solve the above technical problem, the method and system for filling traffic condition information of the present invention use the following technical solutions:

 A method for filling traffic condition information, comprising:

 According to the historical road condition data, the data lacking in the traffic condition data is completed;

 According to the trend of road conditions obtained by clustering all the road condition data of the same road in the same time period, a trend mode library of road traffic conditions is established;

 The road condition trend of the road during the time period t is matched with the road condition change trend of the road in the road traffic road trend mode library, and the time point t is used as the driving speed for filling the road condition.

 According to the historical road condition data, the data for completing the lack of traffic condition data includes: reading historical road condition data of at least three months;

 Filling the road condition data at a time point before the time when the road condition data is vacant to the time point when the road condition data is vacant;

 Mark the time period in which the time point is located;

 Save the traffic data after completion.

The road condition data at a time point before the time point when the road condition data is vacant is filled to the time point when the road condition data is vacant: The time period is divided according to the time point of the road condition.

 The road condition change trend obtained by clustering all the road condition data of the same road in the same time period, and establishing a road traffic road trend trend pattern library includes:

 Read the traffic condition data after completion;

 Clustering the traffic road data of the same road, different dates, and the same time period, and obtaining cluster data of different dates and the same time period under the same classification;

 Performing an average calculation on the clustering data;

 Curve fitting the results of the mean calculation;

 According to the curve fitting results of different classifications under different time periods of each road, a road traffic trend trend pattern library is established.

 The road condition trend of the road in the time period of the time point t is matched with the road condition change trend of the road in the road traffic road trend mode library, and the time point t is calculated as the speed of the road to fill the road condition:

 Read real-time traffic condition data;

 All road trend polynomial curves of the roads with vacant road conditions at time point t are read; the vacancy road conditions on the road are estimated by pattern matching.

 After speculating the vacant road conditions on the road through pattern matching, it includes:

 Output complete real-time traffic conditions data.

 A traffic condition information filling system, comprising:

 The historical data pre-processing unit is configured to complete the data lacking in the traffic condition data according to the historical road condition data;

A road condition trend analysis unit is configured to establish a road traffic road trend mode library according to a road condition change trend obtained by clustering all road condition data of the same road in the same time period; a road condition filling processing unit, configured to use the time point The road condition trend of the road during the time period is matched with the road condition change trend of the road in the road traffic road trend pattern library, and the road speed at the time point t is calculated as the driving speed for filling the road condition. The historical data preprocessing unit includes:

 a first reading module, configured to read historical road condition data of at least three months;

 a filling module, configured to fill road condition data at a time point before the time point when the road condition data is vacant to a time point at which the road condition data is vacant;

 a marking module, used to mark a time period in which the time point is located;

 The save module is used to save the traffic condition data after completion.

 The road condition trend analysis unit includes:

 a second reading module, configured to read the completed traffic condition data;

 The clustering processing module is configured to perform clustering processing on traffic road data of the same road, different dates and the same time period, and obtain cluster data of different dates and the same time period under the same classification; the average calculation module is used for the The clustering data is used for mean calculation;

 a curve fitting module for performing curve fitting on the result of the mean calculation;

 The pattern library building module is configured to establish a road traffic trend trend pattern library according to the curve fitting results of different classifications under different time periods of each road.

 The road condition filling processing unit includes:

 a third reading module, configured to read real-time traffic condition data;

a fourth reading module, configured to read all road trend polynomial curves of the roads that are vacant at the time point t ;

 A speculation module for estimating the vacant road conditions on the road by pattern matching.

The method and system for filling traffic condition information provided by the embodiment of the present invention firstly supplements the vacancy information of the floating vehicle historical data, and then performs cluster analysis on all the road condition data of the same road in the same certain period of time, respectively, and establishes each road. The different speed trends in the time period constitute the trend mode library of road traffic conditions. The road traffic information trend in the road traffic trend mode library is matched with the road traffic trend in the current time period, and the driving speed of the road at the current time is estimated as the filling road condition, so that the estimated traffic information of the vacancy is more accurate and improved. The accuracy of road condition information filling. DRAWINGS

 In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only the present invention. For some embodiments, other drawings may be obtained from those of ordinary skill in the art without departing from the drawings.

 1 is a flowchart of a method for filling traffic condition information according to an embodiment of the present invention;

 2 is a schematic structural diagram of a traffic condition information filling system according to an embodiment of the present invention;

 3 is a flowchart of a method for filling traffic condition information according to Embodiment 2 of the present invention;

 FIG. 4 is a schematic structural diagram of a traffic road condition information filling system according to Embodiment 2 of the present invention. Detailed ways

 The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without making creative labor are within the scope of the present invention.

 Embodiments of the present invention provide a method and system for filling traffic condition information, which can improve the accuracy of filling road condition information.

 Embodiment 1 An embodiment of the present invention provides a method for filling traffic condition information. As shown in FIG. 1, the method includes:

 Step S101: Complement data that is lacking in traffic condition data according to historical road condition data; Step S102: Establish a trend of road traffic conditions according to a trend of road conditions obtained by clustering all road condition data of the same road in the same time period Pattern library

Step S103: Matching the road condition trend of the road in the time period of the time point t with the road condition change trend of the road in the road traffic road trend mode library, and calculating the traveling speed of the road at the time point t as the filling road condition. The embodiment of the present invention further provides a traffic road condition information filling system. As shown in FIG. 2, the system includes: a historical data pre-processing unit 1, a road condition trend analysis unit 2, and a road condition filling processing unit 3.

 The historical data preprocessing unit 1 is configured to complement the data of the traffic condition data that is lacking according to the historical road condition data. The unit takes the accumulated historical road condition information as input, firstly completes the information of the historical floating vehicle road condition data, and then divides the statistical time period according to the time point of the road condition.

 Among them, the choice of roads includes the main roads of the city, such as the collection of all road units in the main line of Beijing, such as: Zhichun Road, College Road, etc. The value of the time point includes the demarcation from 00:00-23:59 every 5 minutes. Time periods, such as: 08:00, 08:05, 08: 10, 08:15, etc., there are 288 time points in a day.

 In order to better reflect the trend of the speed of the vehicle on a certain road with time, all the time points in the day are divided into 70 time periods, and each 8 time points (ie 40 minutes) is a time period, and the time point is The interleaving exists in two consecutive time periods, for example: time point 0-7 is time period 0, time point 4-11 is time period 1, time point 8-15 is time period 2, ... time point 280- 287 is time period 70.

 The road condition trend analysis unit 2 is configured to establish a road traffic trend trend mode library according to a road condition change trend obtained by clustering all the road condition data of the same road in the same time period. The unit clusters all the road condition data of the road in the same period of time, calculates the road condition change trend on the road during this period of time, and finally establishes the road traffic information trend according to different speed change trends in all time periods of all roads. Pattern library.

The road condition filling processing unit 3 is configured to match the road condition trend of the road in the time period of the time point t with the road condition change trend of the road in the road traffic road trend mode library, and calculate the time point t as the road to fill the road condition. speed. The unit reads the real-time floating car traffic information, scans the road vacancy road condition data, matches the road traffic information trend in the road traffic information trend mode library with the road condition trend of the current time period, and estimates the current speed of the road at the current time. As a way to fill the road. In the embodiment of the present invention, first, the historical road condition data of the floating vehicle is supplemented with the vacancy information, and then all the road condition data of the same road are clustered and analyzed in the same period of time, and similar road condition information units are combined to distinguish Dissimilar road condition information units, and then the speed change trend of these road condition unit responses is fitted to a polynomial curve, and different speed change trends in all time periods of all roads constitute a road traffic road trend pattern library. The road traffic trend in the road traffic trend mode library is matched with the road traffic trend in the current time period, and the driving speed of the road at the current time is estimated as the filling road condition, so that the filling road condition is more accurate.

 The filling method uses the pipeline method, and the statistical analysis of all roads is completed ahead of time, and the filling of the road conditions of the empty roads with real-time road information is carried out one by one.

 The method and system for filling traffic condition information provided by the embodiment of the present invention firstly supplements the vacancy information of the floating vehicle historical data, and then performs cluster analysis on all the road condition data of the same road in the same certain period of time, respectively, and establishes each road. The different speed trends in the time period constitute the trend mode library of road traffic conditions. The road traffic information trend in the road traffic trend mode library is matched with the road traffic trend in the current time period, and the current speed of the road is estimated as the filling road condition, so that the estimated traffic information of the vacancy is more accurate.

 Embodiment 2

 On the basis of the first embodiment, the embodiment of the present invention provides a method for filling traffic condition information. As shown in FIG. 3, the method includes:

 S201. Read historical road condition data of at least three months;

 The historical data preprocessing module is based on the accumulated historical road data of more than 3 months, and carries out the filling calculation of the vacant road conditions at the time points on each road, that is, reading the historical road conditions of the floating car city of n (n≥3) months. data.

 Further, the statistical time period is divided according to the time point of the road condition.

Among them, the choice of roads includes the main roads of the city, such as the collection of all road units in the main line of Beijing, such as: Zhichun Road, Xueyuan Road, etc. The value of the time point includes the demarcation from 00:00-23:59 every 5 minutes. Time period, such as: 08:00, 08:05, 08: 10, 08: 15, etc., a total of 288 a day Time point.

 In order to better reflect the trend of the speed of the vehicle on a certain road with time, all the time points in the day are divided into 70 time periods, and each 8 time points (ie 40 minutes) is a time period, and the time point is The interleaving exists in two consecutive time periods, for example: time point 0-7 is time period 0, time point 4-11 is time period 1, time point 8-15 is time period 2, ... time point 280- 287 is time period 70.

 S202: Scanning the road condition data of each road from time point 0 in time, and finding a time point when the road condition is empty;

 S203. Fill the road condition data at a previous time point of the time point when the road condition data is vacant to a time point when the road condition data is empty;

 At the time point t when the road condition data is empty, the road condition data at a time point before the time point is filled at this time point, and the completion of the road condition data at all time points throughout the day is completed in turn.

 5204. Mark a time period in which the time point is located;

 Marking the time period in which the time point is located. Generally, one time point belongs to two consecutive time segments. According to the time series, one time point will be located in the latter part of one time period and the previous time in another time period, for example, time point 6 (00) : 30 ) Located in the back of time period 0 (00: 00 to 00: 40) and at the same time as time period 1 (00: 20 to 00: 55).

 5205. Save the traffic condition data after completion;

 5206. Read the traffic condition data after completion;

 5207. Perform clustering processing on traffic road data of the same road, different dates, and the same time period, and obtain cluster data of different dates and the same time period under the same classification;

Each time period contains 8 time points, and a road corresponds to a speed value at each time point of the day, so the road has 8 speed values in each time period of the day, and these 8 The velocity value is treated as a vector (array) of length 8, so a road will have m vectors (array) for each time period on m dates. The vector (array) of length 8 corresponding to the road speed at each time point in the time period reflects the trend of the speed of the road during this period. For the above m data, the present invention distinguishes dissimilar vectors (array) and merges similar vectors (array) by cluster analysis in data mining, and the obtained result data (or mode) reflects the road. All speed trends during this time period.

 The present invention uses the maximum and minimum clustering algorithm for cluster analysis, and selects a new initial class center in the vector set with the maximum Euclidean distance between the speed change trend curves, and performs model classification by the minimum clustering principle.

 5208. Perform an average calculation on the clustering data.

 The mean value of the road conditions for different date and time periods under the same classification is calculated. After clustering, calculate the mean value of the road speed at the same time point in different arrays in each class. Finally, multiple arrays in each class are combined into one array, which reflects the trend of the road speed in a certain period of time. The trend of road speed is called a mode.

 5209. Perform curve fitting on the result of the mean calculation;

Since there are 8 time points in a time period and the time range is small, the trend of the speed of the road in a time range can be reflected by the polynomial curve. The present invention performs a m-degree polynomial curve fitting according to a least squares criterion by a velocity variation trend corresponding to a series of consecutive time points corresponding to a road, and m+1 parameters of the m-th order polynomial function are used as a final curve. The result of the combination. The curve equation can be set as follows: = "„^+ — ^― 1 + + , where a m e R,m>=0; xe Z,x>=0;y>=0 ^ x represents the time point of the day , y represents the speed value corresponding to the time point 。.

 These curves provide an optional match pattern for the final fill gap data, and all alternative match patterns for all roads at each time period provide an optional all-mode for all road link gap data.

 5210. Establish a trend mode library of road traffic conditions according to the curve fitting results of different classifications under different time segments of each road.

The curve fitting results of different classifications under different time periods of each road are saved as a historical trend model of road traffic conditions. The road traffic trend mode library describes the m-degree polynomial curve of all speed trends of all roads in the road network in each time period in the historical data of the floating car. This model library is based on roads, that is, a pattern library for each road, which contains polynomial curves of all reaction road speed change patterns at various time periods.

 5211, reading real-time traffic condition data;

 Read the traffic condition data of the real-time floating car.

 5212. Scan the roads of vacant road conditions and process the roads of vacant roads one by one;

 5213. Read all the road trend polynomial curves of the roads with the vacant road conditions at the time point t; find the two time periods where the time point t is located, select the time period where the time point t is located in the latter stage, and the road condition at the time point t In the data, the polynomial curves of all the road travel speed change patterns of the road during this time period are taken out.

 5214. Predicting a vacant road condition on the road by pattern matching;

 According to the change trend of the speeds vt-1, vt-2, vt-3, vt-4 corresponding to the four time points before the current time point t in the real-time road condition data of the floating vehicle, the curve in S213 is matched ( Suppose the number of curves is k). Since the curves in the trend pattern library are all m-degree polynomial curves, the curve equation is:

y = a m x m +a m _ 1 m " 1 +... + a l x + a 0 where eR' ^O^EZ^^Oj^O , χ denotes the time of day, y denotes the time point The speed value corresponding to X. Then the curve equation can be set as:

t = a m x i m + m _ x i m ~ l +- + α ιΆ + a o

 Where = 1,2..., calculate + — + |

Figure imgf000011_0001
Which represents the velocity value corresponding to the time point X in the real-time data, that is, Tl

Σ I α η,: χ Η + α η-1,: χ η +... + a U X + a 0,i― V X I

^ _ 4 The smallest curve is the curve that matches the success. The velocity value Vi = α ^ + a - u _1 + - + ^u t + a o, at the time point t can be calculated from the equation of the curve. That is, the road speed at the time point t is calculated as the traveling speed for filling the road condition.

 S215, output complete real-time traffic condition data.

 After completing the filling of all vacant road conditions, the real-time road condition data of the complete road network is output.

 On the basis of the first embodiment, the embodiment of the present invention further provides a traffic road condition information filling system. As shown in FIG. 4, the system includes: a historical data preprocessing unit 1, a road condition analysis unit 2, and a road condition filling processing. Unit 3.

 Further, the historical data pre-processing unit 1 includes: a first reading module 11, a padding module 12, a marking module 13, and a saving module 14.

 The first reading module 11 is configured to read the historical road condition data of at least three months; the filling module 12 is configured to fill the road condition data at a time point before the time point when the road condition data is vacant to the time when the road condition data is vacant The marking module 13 is used to mark the time period in which the time point is located; the saving module 14 is configured to save the completed traffic condition data.

 Further, the road condition trend analysis unit 2 includes: a second reading module 21, a clustering processing module 22, an average calculation module 23, a curve fitting module 24, and a pattern library establishing module 25.

 The second reading module 21 is configured to read the completed traffic condition data; the cluster processing module 22 is configured to perform clustering processing on the same road, different dates, and the same time period, to obtain the same classification. Different date, cluster data of the same time period; mean calculation module 23 for performing mean calculation on the cluster data; curve fitting module 24 for curve fitting the result of the mean calculation; Module 25 is configured to establish a road traffic trend trend mode library according to a curve fitting result of different classifications under different time segments of each road.

Further, the road condition filling processing unit 3 includes: a third reading module 31, a fourth reading module 32, and a speculative module 33. a third reading module 31, configured to read real-time traffic condition data; a fourth reading module 32, configured to read all road condition trend polynomial curves of the road that is vacant at the T time point; Predict the vacant road conditions on the road by pattern matching.

 The method and system for filling traffic condition information provided by the embodiment of the present invention firstly supplements the vacancy information of the floating vehicle historical data, and then performs cluster analysis on all the road condition data of the same road in the same certain period of time, and merges similar road condition information. The unit distinguishes the dissimilar road condition information units, and then fits the speed change trend of the reaction of the road condition units to the polynomial curve, and the different speed change trends in each time period of all the roads constitute the road traffic road trend pattern library. Use the road traffic information trend in the road traffic trend mode library to match the road traffic trend in the current time period, and estimate the current speed of the road as the filling road condition. The embodiment of the present invention takes all the speed change trends of the road in the historical data of the floating vehicle as an optional mode, and overcomes the historical mean method by treating the speed change in a certain period of time as a whole. The defects, when actually filling the vacant traffic information, make the estimated traffic information of the vacancies more accurate by matching the optional modes.

 Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software or a combination of both, in order to clearly illustrate hardware and software. Interchangeability, the composition and steps of the various examples have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known. The above is only the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of changes or substitutions within the technical scope of the present invention. It should be covered by the scope of the present invention. Therefore, the scope of the invention should be determined by the scope of the claims.

Claims

Claim
 A method for filling traffic condition information, characterized in that it comprises:
 According to the historical road condition data, the data lacking in the traffic condition data is completed;
 According to the trend of road conditions obtained by clustering all the road condition data of the same road in the same time period, a trend mode library of road traffic road conditions is established;
 The road condition trend of the road in the time period of the time point t is matched with the road condition change trend of the road in the road traffic road trend mode library, and the time point t is used as the driving speed for filling the road condition.
 2. The method according to claim 1, wherein the data for completing the lack of traffic condition data according to the historical road condition data comprises:
 Read historical road data for at least three months;
 Filling the road condition data at a time point before the time when the road condition data is vacant to the time point when the road condition data is vacant;
 Mark the time period in which the time point is located;
 Save the traffic data after completion.
 The method according to claim 2, wherein the road condition data at a time point before the time point when the road condition data is vacant is filled to a time point when the road condition data is vacant:
 The time period is divided according to the time point of the road condition.
 The method according to claim 3, wherein the trend of the road condition obtained by clustering all the road condition data of the same road in the same time period, and establishing the trend mode of the road traffic condition trend comprises:
 Read the traffic condition data after completion;
 The traffic road data of the same road, different dates and the same time period are clustered to obtain cluster data of different dates and the same time period under the same classification;
Performing an average calculation on the clustering data; Curve fitting the results of the mean calculation;
 According to the curve fitting results of different classifications under different time periods of each road, a trend mode library of road traffic conditions is established.
 The method according to claim 4, wherein the road condition trend of the road in the time period of the time point t is matched with the road condition change trend of the road in the road traffic road trend mode library, and the time point is calculated. The speed of the road as a road filling condition includes:
 Read real-time traffic condition data;
 All road trend polynomial curves of the roads with vacant road conditions at time point t are read; the vacancy road conditions on the road are estimated by pattern matching.
 6. The method according to claim 5, wherein after estimating the vacant road condition on the road by pattern matching, the method comprises:
 Output complete real-time traffic conditions data.
 7. A traffic condition information filling system, characterized in that:
 The historical data preprocessing unit is configured to complete the data of the lack of traffic condition data according to the historical road condition data;
 The road condition trend analysis unit is configured to establish a road traffic trend trend mode library according to a road condition change trend obtained by clustering all the road condition data of the same road in the same time period;
 The road condition filling processing unit is configured to match the road condition trend of the road in the time period of the time point t with the road condition change trend of the road in the road traffic road trend mode library, and calculate the traveling speed of the road as the filling road condition at the time point t .
 8. The system according to claim 7, wherein the historical data preprocessing unit comprises:
 a first reading module, configured to read historical road condition data of at least three months;
The filling module is used to fill in the road condition data at a time point before the time point when the road condition data is vacant
Figure imgf000016_0001
a marking module, used to mark a time period in which the time point is located; The save module is used to save the traffic condition data after completion.
 9. The system according to claim 6, wherein the road condition trend analysis unit comprises:
 a second reading module, configured to read the completed traffic condition data;
 The clustering processing module is configured to perform clustering processing on traffic road data of the same road, different dates, and the same time period, to obtain cluster data of different dates and the same time period under the same classification;
 a mean value calculation module, configured to perform mean calculation on the clustering data;
 a curve fitting module for performing curve fitting on the result of the mean calculation;
 The pattern library building module is configured to establish a road traffic trend trend pattern library according to the curve fitting results of different classifications under different time segments of each road.
 10. The system according to claim 6, wherein the road condition filling processing unit comprises:
 a third reading module, configured to read real-time traffic condition data;
 a fourth reading module, configured to read all road condition trend polynomial curves of the roads with vacant road conditions at time point t;
 A speculation module for estimating the vacant road conditions on the road by pattern matching.
PCT/CN2010/079732 2009-12-30 2010-12-13 Traffic road condition information filling method and system WO2011079707A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN 200910244141 CN101763730B (en) 2009-12-30 2009-12-30 Traffic road condition information filling method and system
CN200910244141.7 2009-12-30

Publications (1)

Publication Number Publication Date
WO2011079707A1 true WO2011079707A1 (en) 2011-07-07

Family

ID=42494881

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2010/079732 WO2011079707A1 (en) 2009-12-30 2010-12-13 Traffic road condition information filling method and system

Country Status (2)

Country Link
CN (1) CN101763730B (en)
WO (1) WO2011079707A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103854480A (en) * 2012-12-05 2014-06-11 深圳先进技术研究院 Traffic monitoring data matrix completion algorithm
CN105869404A (en) * 2016-05-25 2016-08-17 成都联众智科技有限公司 Traffic jam pre-warning system
CN109118771A (en) * 2018-09-19 2019-01-01 青岛海信网络科技股份有限公司 A kind of method and device that the urban transportation often property sent out congestion feature determines

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101763730B (en) * 2009-12-30 2012-09-26 北京世纪高通科技有限公司 Traffic road condition information filling method and system
JP5380509B2 (en) * 2011-09-28 2014-01-08 日立オートモティブシステムズ株式会社 Route guidance system
CN102364546B (en) * 2011-10-19 2014-02-26 北京世纪高通科技有限公司 Method and device for processing traffic information data fault
CN102509445B (en) * 2011-10-19 2013-12-04 北京世纪高通科技有限公司 Screening method and device for road condition prediction factor
CN102622880A (en) * 2012-01-09 2012-08-01 北京捷易联科技有限公司 Traffic information data recovery method and device
CN105468594A (en) * 2014-08-11 2016-04-06 中兴通讯股份有限公司 Method and system for optimizing data collection and server
CN104464280B (en) * 2014-09-05 2017-05-03 广州市香港科大霍英东研究院 Vehicle advance expenditure prediction method and system
CN104183135B (en) * 2014-09-05 2016-09-14 广州市香港科大霍英东研究院 The method of estimation of vehicle traveling expense and system
CN104318764A (en) * 2014-10-22 2015-01-28 湖北汽车工业学院 Information feedback method for intelligent traffic system with incomplete information
CN104484999B (en) * 2014-12-31 2017-08-22 百度在线网络技术(北京)有限公司 The method and device of dynamic information is determined based on user trajectory
CN104932863B (en) * 2015-06-26 2018-02-16 厦门大学 A kind of higher-dimension exponential signal Supplementing Data method
CN106355881A (en) * 2016-10-12 2017-01-25 同济大学 Space-autocorrelation-based traffic accident blackspot identification method and device
CN106504534B (en) * 2016-11-28 2019-06-14 北京世纪高通科技有限公司 A kind of method, apparatus and user equipment for predicting road conditions
CN107045788A (en) * 2017-06-28 2017-08-15 北京数行健科技有限公司 Traffic Forecasting Methodology and device
CN107680377B (en) * 2017-11-06 2019-09-27 浙江工商大学 Traffic flow data based on trend fitting intersects complementing method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1637384A (en) * 2003-12-26 2005-07-13 爱信艾达株式会社 Method of interpolating traffic information data, apparatus for interpolating, and traffic information data structure
CN1645402A (en) * 2005-01-19 2005-07-27 北京交通大学 Road traffic flow data quality controlling method and apparatus
CN101325004A (en) * 2008-08-01 2008-12-17 北京航空航天大学 Method for compensating real time traffic information data
JP2009087097A (en) * 2007-09-28 2009-04-23 Panasonic Corp Device for generating traffic information and system for providing traffic information
CN101763730A (en) * 2009-12-30 2010-06-30 北京世纪高通科技有限公司 Traffic road condition information filling method and system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1637384A (en) * 2003-12-26 2005-07-13 爱信艾达株式会社 Method of interpolating traffic information data, apparatus for interpolating, and traffic information data structure
CN1645402A (en) * 2005-01-19 2005-07-27 北京交通大学 Road traffic flow data quality controlling method and apparatus
JP2009087097A (en) * 2007-09-28 2009-04-23 Panasonic Corp Device for generating traffic information and system for providing traffic information
CN101325004A (en) * 2008-08-01 2008-12-17 北京航空航天大学 Method for compensating real time traffic information data
CN101763730A (en) * 2009-12-30 2010-06-30 北京世纪高通科技有限公司 Traffic road condition information filling method and system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103854480A (en) * 2012-12-05 2014-06-11 深圳先进技术研究院 Traffic monitoring data matrix completion algorithm
CN103854480B (en) * 2012-12-05 2016-01-27 深圳先进技术研究院 Traffic monitoring data matrix complementing method
CN105869404A (en) * 2016-05-25 2016-08-17 成都联众智科技有限公司 Traffic jam pre-warning system
CN109118771A (en) * 2018-09-19 2019-01-01 青岛海信网络科技股份有限公司 A kind of method and device that the urban transportation often property sent out congestion feature determines

Also Published As

Publication number Publication date
CN101763730B (en) 2012-09-26
CN101763730A (en) 2010-06-30

Similar Documents

Publication Publication Date Title
Mazloumi et al. Using GPS data to gain insight into public transport travel time variability
Liu et al. Bus stop-skipping scheme with random travel time
El‐Geneidy et al. Analyzing transit service reliability using detailed data from automatic vehicular locator systems
JP3501773B2 (en) Traffic situation determination method based on reported vehicle data for a traffic network including traffic-controlled network nodes
US20100063715A1 (en) Method and structure for vehicular traffic prediction with link interactions and missing real-time data
Chen et al. A study of hybrid neural network approaches and the effects of missing data on traffic forecasting
US6385531B2 (en) Distributed system and method for detecting traffic patterns
DE102012201472A1 (en) Method for providing parking information on free parking spaces
JP4175312B2 (en) Traffic information prediction device
Veloso et al. Urban mobility study using taxi traces
Khouadjia et al. A comparative study between dynamic adapted PSO and VNS for the vehicle routing problem with dynamic requests
US20050091176A1 (en) Forecasting apparatus
Vanajakshi et al. Travel time prediction under heterogeneous traffic conditions using global positioning system data from buses
Krumm Real time destination prediction based on efficient routes
Landex et al. Methods to estimate railway capacity and passenger delays
Cortés et al. Commercial bus speed diagnosis based on GPS-monitored data
CN100463009C (en) Traffic information fusion processing method and system
Cheung et al. Dynamic routing model and solution methods for fleet management with mobile technologies
WO2004021305A3 (en) Apparatus and method for providing traffic information
CN101388143A (en) Bus arriving time prediction method and system based on floating data of the bus
Meier-Hirmer et al. Maintenance optimization for a system with a gamma deterioration process and intervention delay: application to track maintenance
CN103295074A (en) Method and system of electric vehicle (ev) charging infrastructure with charging stations optimumally sited
Yu et al. Real-time partway deadheading strategy based on transit service reliability assessment
CN101383090A (en) Floating vehicle information processing method under parallel road network structure
CN101751777A (en) Dynamic urban road network traffic zone partitioning method based on space cluster analysis

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 10840496

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase in:

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 10840496

Country of ref document: EP

Kind code of ref document: A1