CN116071931A - Expressway traffic vehicle information prediction method and system - Google Patents
Expressway traffic vehicle information prediction method and system Download PDFInfo
- Publication number
- CN116071931A CN116071931A CN202310207791.4A CN202310207791A CN116071931A CN 116071931 A CN116071931 A CN 116071931A CN 202310207791 A CN202310207791 A CN 202310207791A CN 116071931 A CN116071931 A CN 116071931A
- Authority
- CN
- China
- Prior art keywords
- information
- data
- vehicle
- measured value
- license plate
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001914 filtration Methods 0.000 claims abstract description 35
- 238000012937 correction Methods 0.000 claims abstract description 27
- 238000005259 measurement Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000010365 information processing Effects 0.000 claims abstract description 5
- 238000005303 weighing Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 2
- 238000005192 partition Methods 0.000 claims description 2
- 239000003086 colorant Substances 0.000 description 4
- 206010000117 Abnormal behaviour Diseases 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to a method and a system for predicting expressway traffic vehicle information, wherein the method comprises the following steps: step S1, collecting original vehicle passing original data information, performing first processing operation to obtain first data, and formatting and storing the first data; step S2, performing a first filtering operation on the first data obtained after the original information processing to obtain second data; step S3, calculating a physical information credibility weight measurement value for the second data obtained after the first filtering operation; s4, carrying out third correction on the measured value of the old calendar history file information and updating evolution; step S5, merging and storing the physical information credibility weight measured value obtained in the step S3 and the measured value subjected to the third correction in the step S4; and S6, generating real physical information of vehicle prediction from the measured value generated in the step S5 according to the vehicle information to be queried. The present invention is able to provide predictive information of a vehicle that helps identify troublesome counterfeit-related high-speed anomalies.
Description
Technical Field
The invention relates to the field of traffic equipment, in particular to a method and a system for predicting expressway vehicle information.
Background
Because of the popularization of ETC charging systems, many highway toll booths gradually replace manual toll collection windows with unattended non-stop traffic lanes. And the vehicle physical information is limited by a short time and can not be completely and accurately inferred, and the determination method based on manual work, sensors and machine vision cannot ensure that the vehicle physical information (including vehicle types, vehicle axle numbers, special vehicle types and the like) is given efficiently and accurately.
In practice, both detection and pursuit, including high-speed fare evasions, require accurate vehicle-based information, and false vehicle information may lead to missed detection of abnormal behavior. In the case of partial abnormal behaviors (such as changing license plate related situations of fake license plate vehicles, temporary license plate replacement and the like, vehicle axle related situations of throwing, middle license plate replacement and the like, and special vehicle type related situations of embezzling green vehicles and the like), the existing method does not have a reference standard with certain authenticity because of depending on traffic data, and vehicle information cannot be accurately known, and correct deep data analysis cannot be correctly performed.
Disclosure of Invention
The invention provides a method and a system for predicting vehicle information on a highway, which are characterized in that historical information is stored through a plurality of weighting methods to establish an archive, vehicle physical information which is distinguished by license plates is stored in an increment mode, and an interface is provided for providing a vehicle information prediction conclusion for other service systems.
The technical scheme of the invention is as follows: a method for predicting highway traffic vehicle information comprises the following steps:
step S1, collecting original vehicle passing original data information, performing first processing operation to obtain first data, and formatting and storing the first data;
step S2, performing a first filtering operation on the first data obtained after the original information processing to obtain second data;
step S3, calculating a physical information credibility weight measurement value for the second data obtained after the first filtering operation;
s4, carrying out third correction on the measured value of the old calendar history file information and updating evolution;
step S5, merging and storing the physical information credibility weight measured value obtained in the step S3 and the measured value subjected to the third correction in the step S4;
and S6, generating real physical information of vehicle prediction in the generated measured values according to the vehicle information to be queried.
According to another aspect of the present invention, there is also provided a multi-weight adaptive expressway traffic vehicle information prediction system, including:
the data collection module is used for collecting original vehicle passing original data information to perform first processing operation to obtain first data, and formatting and storing the first data;
the first processing module is used for performing first filtering operation on the first data obtained after the original information is processed to obtain second data;
the physical information credibility measuring value calculating module calculates a physical information credibility weight measuring value for the second data obtained after the first filtering operation;
the old history file information measured value updating evolution module is used for carrying out third correction on the old history file information measured value and updating evolution;
the measured value combining module combines and stores the physical information credibility weight measured value obtained in the step S3 and the measured value subjected to the third correction in the step S4;
and the prediction module is used for generating real physical information of vehicle prediction in the generated measured values according to the vehicle information to be queried.
Advantageous effects
The method and the system for predicting the expressway passing vehicle information are provided, and a vehicle physical data prediction table is generated according to all past passing records, so that all past passing records can be effectively utilized, and long-term changes (such as license plate transfer) of vehicles can be contained. According to the prediction table, it is possible to provide prediction information of the vehicle, which helps to identify troublesome forgery-related high-speed abnormal behavior.
Drawings
FIG. 1 is a flow chart of a method for predicting highway traffic vehicle information according to the present invention;
FIG. 2 is a schematic diagram of a method for calculating an information reliability weight measurement value of original information of a single vehicle after filtering according to the method of the present invention (taking a 2-axis passenger 1 type vehicle, and a vehicle weighing 2 tons as an example);
FIG. 3 is a schematic diagram of a method for calculating information reliability weight measurement values of original information of a plurality of vehicles with the same license plate (taking the same vehicle as in FIG. 2 as an example);
FIG. 4 is a schematic diagram of a method for measuring vehicle information in a history file table (for example, the same vehicle as that of FIG. 2).
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without the inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
According to an embodiment of the invention, the method provides a method for predicting expressway traffic vehicle information, which comprises the following steps:
step S1, collecting original vehicle passing original data information, performing first processing operation to obtain first data, and formatting and storing the first data;
step S2, performing a first filtering operation on the first data obtained after the original information processing to obtain second data;
step S3, calculating a physical information credibility weight measurement value for the second data obtained after the first filtering operation;
s4, carrying out third correction on the measured value of the old calendar history file information and updating evolution;
step S5, merging and storing the physical information credibility weight measured value obtained in the step S3 and the measured value subjected to the third correction in the step S4;
step S6, generating real physical information of vehicle prediction from the measured value generated in the step S5 according to the query;
the steps are described in detail below.
Step S1, collecting vehicle passing original data information, performing first processing operation to obtain first data, and formatting and storing the first data;
in the traffic field, vehicles are generally monitored and identified by an identification device when passing through a high-speed entrance, so that operations such as charging and the like are facilitated. However, due to various violations of fake license plates, refitting and the like in society, the identification of the vehicle is not necessarily consistent with the true identity of the vehicle. In the invention, in order to judge the true identity information of the current vehicle more accurately, the physical information prediction of the vehicle data can be fully obtained from the historical data, and the vehicle information prediction is assisted; meanwhile, due to objective misentry and misidentification of historical data and reliable change of vehicle physical information which can occur in a few times, deviation and adverse effect on prediction of the historical data can be caused. In addition, since a large amount of historical data is generated every day, a good method for storing is required to reduce the complexity to an acceptable range and save the disk space.
The method is characterized in that the original data information required to be collected and used at present is traffic data of all vehicles in one recording period of a certain road section, the starting day of the one recording period is the corresponding day one month before the current day is collected, and the ending day is the current day is collected. For example, when the current day is 2022, 5, 1, then the recording period is 2022, 4, 1, to 2022, 5, 1.
The data fields that the method currently needs to collect and use include: the method comprises the following steps of passing medium types, inlet card reading license plates, inlet card reading license plate colors, inlet image recognition license plates, inlet image recognition license plate colors, outlet card reading license plates, outlet card reading license plate colors, outlet image recognition license plates, outlet image recognition license plate colors, inlet vehicle types, outlet vehicle types, inlet vehicle axle numbers, outlet vehicle axle numbers, inlet special vehicle types, outlet special vehicle types, inlet weighing, outlet weighing and outlet time; in addition, other fields are discarded.
The data information sources may be different, for example, some are collected at a high-speed gateway, some are collected from a network, some are obtained from an offline database, some are obtained from an online database, the data information at different sources may be different in format, and the invention needs to perform form specification on the data of different sources after collecting the data information of the fields.
According to one embodiment of the invention, the collected raw data information includes: first source data information, second source data information, third source data information and fourth source data information;
according to one embodiment, the first source is highway exit card reading information; the second source data information is inlet card reading information; the third source data information is expressway exit image identification information; the fourth source data information is expressway entrance image identification information;
for the data information from different sources, performing a first processing operation refers to performing a first screening step, including:
step S1101: if the third source data information and the fourth source data information identify license plate information with completely consistent license plates, the license plate information is directly reserved as a real license plate;
for example, license plate information with completely consistent license plate identification of the exit and entrance images is directly reserved as a real license plate;
step S1102: if the third source data information and the fourth source data information identify that license plates are not completely consistent, extracting two license plate character strings which are not completely consistent, and calculating a first distance;
optionally, the first distance is, for example, a character string levenstein distance, i.e., two character strings a, bThe minimum number of editing operations for data conversion between them, denoted lev a，b (|a|, |b|), wherein: the 'a' and the 'b' respectively represent the lengths of the character strings a and b, and the a and the b respectively refer to an entering image recognition license plate or a card reading license plate according to different conditions, for example: the entrance image identifies the license plate and reads the card license plate, the exit image identifies the license plate and reads the card license plate,
wherein, the liquid crystal display device comprises a liquid crystal display device,
is when a is i ≠b i The value is 1, otherwise the value is an indication function of 0. Thus lev a，b (i, j) is the distance between the first i characters of a and the first j characters of b, i, j representing the character number in a or b;
step S1103: if the first distance is smaller than or equal to a first threshold value, further calculating a second distance, wherein the second distance is the second distance between the third or fourth source data information and the first or second source data information;
step S1104: if the second distance is smaller than the second threshold value, the first or second source data information is reserved as a real license plate; according to one embodiment, the first threshold is, for example, 2, the second threshold is, for example, 1, for the license plate information of the exit and entrance image recognition license plates, where the license plate information is not consistent with the image recognition license plate of the exit and entrance image recognition license plate, but the check character string levenstein distance is less than or equal to 2, and if the image recognition license plate of the exit and entrance image recognition license plate is less than or equal to 1 with the read truck license plate levenstein distance, the read truck license plate is reserved as a real license plate;
optionally, step S1105: regarding the rest data in the source data information as license plate data;
further, the invention further comprises a second screening step for vehicles with the same license plate data, comprising:
step S1201, through the exiting and entering vehicle type data, the vehicle type data shown in the passing with the maximum record number is regarded as the real vehicle type data.
In step S1202, the axle number data shown at the time of passing having the largest record number is regarded as the real axle number data for the axle number data of the vehicles passing through the exit and entrance.
Step S1203, through the special vehicle type data of the vehicles at the exit and the entrance, regarding the special vehicle type data shown in the passing with the maximum record number as real special vehicle type data.
In step S1204, the weighing data of the vehicles passing through the exit and entrance are regarded as the actual exit weighing data with the weighing data shown in the passing with the maximum record number.
In step S1205, for the data not being given, the-1 flag data is missing.
The maximum record number is the maximum record number of the displayed vehicle type, the vehicle axle number, the special vehicle type, the weighing and other data information in all records of the vehicle with the same license plate data passing through the road section within a certain month.
As described above, the data is subjected to the normalization processing, so that the error data in different data sources can be eliminated, and the data information of each different source is unified to the data most likely to be close to the accurate value.
After the steps, the processed first data are obtained and stored according to a preset format.
Step S2, performing a first filtering operation on the first data obtained after the original information processing to obtain second data;
specifically, in this step S2, condition constraint filtering is performed on the data stored after format normalization in step S1.
Conditional constraint filtering includes:
step S2101, first condition constraint filtering;
specifically, the first condition filtering means that, by using license plate validity constraint, for example, license plate information must conform to legal standards that allow traffic in the people's republic of China, a regular expression may be used to constrain the license plate information, for example: is prepared by using ≡A ([ Jingjin Shanghu Yu Ji Yu Liao Hexiang Henan Wanlu New Suzhejiang Gan jaw Gui Ganjin Mong shan JiMin Guiyue Qinghai Chuan Ning Qiong ] Collar A-Z ] {1} [ A-Z ] {1} ([ 0-9] {5} [ DF ])| (DF [0-9] {4 }) | ([ Jinjinhu Yujiyu) the Guanliao Hexiang Wan Luzhou New SuZhejiang Gan Gui Ganjin Mong Shaan JiMin Gui Yue Qinghai-Tibet Chuan Ning Qiong makes the collar A-Z ] {1} [ A-Z ] {1} [ A-HJ-NP-Z0-9] {4} [ A-HJ-NP-Z0-9 Xingqiang Kong {1 }) be used as a regular expression constraint.
Step S2102, second condition constraint filtering;
the second condition constraint filtering is to utilize legal description of the vehicle type to carry out constraint, for example, the vehicle type must conform to axle description corresponding to the vehicle type, the type 1 and type 2 vehicles cannot have more than 2 axle numbers, and the axle numbers are taken as actual vehicle types under the condition that the axle numbers exceed the corresponding axle numbers of the vehicle type.
Step S2103, third condition constraint filtering
The third constraint filtering means constraint filtering by license plate color legality description, for example, the license plate color of the vehicle must conform to the corresponding vehicle model description, and only type 1 vehicles can use blue license plates.
The filtered second data are obtained through the data filtering operation;
step S3, calculating a physical information credibility weight measurement value for the second data obtained after the first filtering operation;
specifically, a record is generated for the data obtained after the first filtering operation processing in the step S2, and a physical information credibility weight measurement value is calculated, wherein the physical information credibility weight measurement value represents the credibility weight value of the physical information in the prediction operation; the generated records are respectively a basic information record and a score information record. The basic information comprises an information license plate, a license plate color, a recording time and a passing medium type, wherein the score record comprises a plurality of parts, and optionally, the record can be expressed in a form of a table or a matrix or can be expressed as a one-bit array;
in one embodiment, expressed in tabular form, the specific generation process is as follows:
step S311: acquiring an acquired vehicle data information item;
the data information items include, for example: a 2-axis passenger 1-type vehicle weighing 2 tons and passing through the entrance of the toll station A on the 13 th year 2022; the vehicle body is blue, and the type of traffic medium installed on the vehicle is CPC card;
step S312: reading first information and second information based on the acquired vehicle data information items; the first information includes: vehicle type, axle number, vehicle weight, and special vehicle type category; the method specifically comprises the following steps:
step S3121, vehicle type score: the vehicle type scores are a list of scores of each vehicle type, the vehicle types are divided into trucks 1-5, buses 1-4 and special operation vehicles, the basic scores of the corresponding vehicle types shown when the vehicles pass are marked as 1, and the basic scores of the other vehicle types are marked as 0;
step S3122, shaft number score: the number of axles is 1-12, and the vehicle types larger than 12 are respectively a list of scores, the basic score of the corresponding number of axles is 1 when the vehicle passes, and the basic scores of the other numbers of axles are 0;
step S3123, vehicle weight score: the vehicle weight is 3 tons or less, 3-6 tons, 6-12 tons, 12-24 tons and more than 24 tons are respectively a series of scores, the basic score of the corresponding vehicle weight is 1 when the vehicle passes through, and the basic scores of the other vehicle weights are 0;
step S3124, scoring of the special vehicle type: the special vehicle type refers to a special vehicle (such as police car, ambulance, supervision car, fire truck, sprinkler car, etc.) for executing special tasks, has special marks or has special vehicle types, the special vehicle types score a row of scores for each special vehicle type, and the non-special vehicle types score a row of scores for each special vehicle type. The basic score of the corresponding special vehicle model is marked as 1 when the vehicle passes through, and the basic scores of the other special vehicle models are marked as 0;
for example, a 2-axis passenger type 1 vehicle weighing 2 tons has the following basic scores:
TABLE 1 vehicle information record base score indication (2-axis passenger 1 type vehicle, weight 2 ton)
Step 3126 is performed to obtain second information of the vehicle, where the second information is a traffic medium type;
the traffic medium types are divided into CPC cards and ETC cards, wherein in data record items of vehicles, a field symbol character string 'CPC' is arranged corresponding to the CPC, and a field symbol 'ETC' is arranged corresponding to the ETC cards;
step S313, based on the second information, performing a first correction operation on the measured value corresponding to the first information; see fig. 3.
The first correction operation refers to: considering that the CPC cartoon traffic has a more accurate physical information recording system, each score value of the vehicle passing through the CPC cartoon traffic medium type needs to be multiplied by an accurate coefficient k (k is more than 1) on the original basic score, so that correction operation is carried out on the measured value corresponding to the first information, and according to the prior data analysis, the invention preferably has k=2, and can take any value between 1.1 and 5. Referring to fig. 3, for a traffic medium of "CPC", each score is multiplied by an exact coefficient k=2, and for a traffic medium of "ETC", each score is multiplied by an exact coefficient k=1;
step S314, performing a second correction operation on the measured value subjected to the first correction;
the second correction operation comprises the following specific processes:
for each measurement, the daily decay coefficient needs to be multiplied by the whole, so that the second correction is performed on the measurement:
d day ＝day now /(day firstday -day lastday )，
wherein, for the recording period in step S1, the number of cycles of the initial day is collected to be 1, and then 1 is added to the number of cycles of each day;
dday now representing the number of cycles of the current day, day firstday Represents the number of cycles of the collection start day, day lastday The number of cycles of the collection expiration date is indicated.
See FIG. 3For different license plates, different data are recorded, for example, for license plate number 1, 3 records are stored in one recording period, the serial numbers are respectively 1, 2 and 3, the license plate color is not blue, the recording time of the 1 st record is X years, X months and X days, the passing medium type is CPC, the vehicle type is passenger 1, the vehicle axle number is 2, the vehicle weight is 2 tons, and the special vehicle type is a non-special vehicle. Wherein, for record 1, the recording time of record 1 is X years, X months and X days, the score corresponding to the measured value is 1, X_d in FIG. 3 day I.e. the corresponding solar attenuation coefficient d day Multiplying each score by a daily attenuation coefficient and a passing medium weight value; similarly, the recording time for the 2 nd recording was Y years, Y months, Y days, the traffic medium type was CPC, and the recording time for the 3 rd recording was Z years, Z months, Z days, the traffic medium type was ETC.
Step S315, for a plurality of records of the vehicle shown by the same license plate, after each record is processed in the steps S311-S314, accumulating the scores of different records by taking the license plate as a unit;
wherein the weight of the physical information after correction is obtained, for example, as shown in FIG. 3, for 3 records of license plate number 1, the accumulated measured value X C ＝2X_d day +2Y_d day +Z_d day ；
S4, carrying out third correction on the measured value of the old calendar history file information and updating evolution;
the method adopts an incremental constant volume storage scheme, and the physical space occupied by the information of any license plate is fixed, namely, each license plate can only correspond to the uniquely determined vehicle information; thus, the history archive score needs to be updated by time each time it is updated.
Step S4101, judging whether the current history file list is empty, if so, initializing alignment; otherwise, step S4102 is executed; the score information record of the vehicle information shown in the history archive table consists of four parts, namely a vehicle type score, an axle number score, a vehicle weight score and a special vehicle type score, the specific classification is consistent with the original data shown in the step S3, the basic score of each type corresponding to the vehicle information recorded in the history archive table is marked as 1, and the other classification scores are marked as 0.
For example, the history file table records that a vehicle corresponding to a license plate number is a 2-axis passenger 1 type vehicle, the weight of the vehicle is 2 tons, and the basic scores of the respective basic scores are shown in the following table 2:
table 2 historic archives table vehicle information base score indication (2-axis passenger 1 type vehicle, weight 2 ton)
Step 4102, obtaining a measured value in the history file table, judging whether the vehicle information exists in the history file table, and if so, performing a third correction operation on the measured value;
the third correction is performed according to the month information, specifically, in this embodiment, the last update time recorded in the history file table is obtained, and the month attenuation coefficient d is obtained according to the current time and the last update time of the history record:
wherein ΔMonth is the number of months (if less than one month, calculated as one month) from the expiration date of the current recording period to the last update time recorded in the history archive table, for example, X final ＝dXc＝d*0.5 △month 。
For each score of the historical archival vehicle information, the overall multiplication by the month decay factor is required to reduce the confidence of the earlier time score.
In step 4103, if there is no vehicle information shown in the history file table, each score of the obtained record is assigned to 0.
Step S5, merging the measured value obtained in the step S3 with the measured value subjected to the third correction in the step S4 and storing the merged measured value;
the values of S3 and S4 are added and the new score obtained is stored in a data warehouse and a history archive table, which score table is used for the subsequent predicted conclusion, and the table requires an additional update time column for the continuation of S4.
Step S6, generating real physical information of vehicle prediction from the measured value generated in the step S5 according to the query;
for the scoring table of S5, each category of S3 partition takes one of the highest scores as a prediction conclusion.
The method can predict and calculate all the vehicle information in the recording period to obtain a prediction conclusion.
While the foregoing has been described in relation to illustrative embodiments thereof, so as to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, but is to be construed as limited to the spirit and scope of the invention as defined and defined by the appended claims, as long as various changes are apparent to those skilled in the art, all within the scope of which the invention is defined by the appended claims.
Claims (10)
1. The method for predicting the information of the expressway passing vehicles is characterized by comprising the following steps of:
step S1, collecting original vehicle passing original data information, performing first processing operation to obtain first data, and formatting and storing the first data;
step S2, performing a first filtering operation on the first data obtained after the original information processing to obtain second data;
step S3, calculating a physical information credibility weight measurement value for the second data obtained after the first filtering operation;
s4, carrying out third correction on the measured value of the old calendar history file information and updating evolution;
step S5, merging and storing the physical information credibility weight measured value obtained in the step S3 and the measured value subjected to the third correction in the step S4;
and S6, generating real physical information of vehicle prediction in the generated measured values according to the vehicle information to be queried.
2. The method for predicting highway traffic vehicle information as recited in claim 1, comprising the steps of:
the collected raw data information includes: first source data information, second source data information, third source data information and fourth source data information.
3. The method for predicting information about vehicles passing through highway according to claim 1, wherein in the step 1, the first processing operation is a first screening step, which includes:
step S1101: if the third source data information and the fourth source data information identify license plate information with completely consistent license plates, the license plate information is directly reserved as a real license plate;
step S1102: if the third source data information and the fourth source data information identify that license plates are not completely consistent, extracting two license plate character strings which are not completely consistent, and calculating a first distance;
step S1103: if the first distance is smaller than or equal to a first threshold value, further calculating a second distance, wherein the second distance is the second distance between the third or fourth source data information and the first or second source data information;
step S1104: if the second distance is smaller than the second threshold value, the first or second source data information is reserved as a real license plate;
comprises the following steps of: and regarding the rest data in the source data information as license plate data.
4. A method for predicting highway traffic vehicle information as recited in claim 3, further comprising a second screening step for vehicles with the same license plate data, comprising:
step S1201, through the exiting and entering vehicle type data, the vehicle type data shown in the passing with the maximum record number is regarded as real vehicle type data;
step S1202, regarding the axle number data of the vehicles passing through the exit and the entrance, regarding the axle number data shown in the passing with the maximum record number as the real axle number data;
step S1203, through the special type data of the vehicles at the exit and the entrance, regarding the special type data shown by the passing with the maximum record number as real special type data;
step S1204, taking the weighing data shown in the passing with the maximum record number as the real exit weighing data according to the weighing data of the vehicles at the exit and the entrance;
in step S1205, for the data not being given, the-1 flag data is missing.
5. A method for predicting information about vehicles passing on highway according to claim 3, wherein said step 2 specifically comprises:
step S2101, performing first condition constraint filtering; the first condition filtering means that license plate legality constraint is utilized;
step S2102, second condition constraint filtering, wherein the second condition constraint filtering is constraint by utilizing the legal description of the vehicle type;
step S2103, third condition constraint filtering, namely, constraint filtering by license plate color legality description;
step S2104, performing the above data filtering operation to obtain filtered second data.
6. The method for predicting information about vehicles passing through highway according to claim 3, wherein the step S3 is to calculate the weight measurement value of the physical information reliability for the second data obtained after the first filtering operation, and specifically comprises:
generating a record for the data obtained after the first filtering operation processing in the step S2, and calculating a physical information credibility weight measurement value, wherein the physical information credibility weight measurement value represents the credibility weight value of the physical information in the prediction operation; the generated records are respectively a basic information record and a score information record.
7. A method for predicting highway traffic vehicle information as recited in claim 3, wherein said step S3 further comprises:
step S311: acquiring an acquired vehicle data information item;
step S312: reading first information and second information based on the acquired vehicle data information items; the first information includes: vehicle type, axle number, vehicle weight, and special vehicle type category;
step S313, based on the second information, performing a first correction operation on the measured value corresponding to the first information;
step S314, performing a second correction operation on the measured value after the first correction.
8. A method for predicting highway traffic vehicle information as recited in claim 3, wherein said step S5 comprises:
and adding the values of S3 and S4, storing the obtained new score into a data warehouse and a history file table, wherein the score table is used for the subsequent prediction conclusion, and an updating time column is additionally arranged in the table.
9. A method for predicting highway traffic vehicle information as recited in claim 3, wherein said step S6 comprises:
for the scoring table of S5, each category of S3 partition takes one of the highest scores as a prediction conclusion.
10. A highway traffic vehicle information prediction system, comprising:
the data collection module is used for collecting original vehicle passing original data information to perform first processing operation to obtain first data, and formatting and storing the first data;
the first processing module is used for performing first filtering operation on the first data obtained after the original information is processed to obtain second data;
the physical information credibility measuring value calculating module calculates a physical information credibility weight measuring value for the second data obtained after the first filtering operation;
the old history file information measured value updating evolution module is used for carrying out third correction on the old history file information measured value and updating evolution;
the measured value combining module combines and stores the physical information credibility weight measured value obtained in the step S3 and the measured value subjected to the third correction in the step S4;
and the prediction module is used for generating real physical information of vehicle prediction in the generated measured values according to the vehicle information to be queried.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2022117081265 | 2022-12-29 | ||
| CN202211708126 | 2022-12-29 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116071931A true CN116071931A (en) | 2023-05-05 |
| CN116071931B CN116071931B (en) | 2024-01-09 |
Family
ID=86180288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310207791.4A Active CN116071931B (en) | 2022-12-29 | 2023-02-27 | Expressway traffic vehicle information prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116071931B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016107302A1 (en) * | 2014-12-30 | 2016-07-07 | 北京握奇智能科技有限公司 | Method and system for inspecting moving vehicles |
| CN106297304A (en) * | 2016-09-08 | 2017-01-04 | 同济大学 | A kind of based on MapReduce towards the fake-licensed car recognition methods of extensive bayonet socket data |
| CN107204114A (en) * | 2016-03-18 | 2017-09-26 | 中兴通讯股份有限公司 | A kind of recognition methods of vehicle abnormality behavior and device |
| CN108021361A (en) * | 2017-12-01 | 2018-05-11 | 北京博宇通达科技有限公司 | A kind of the highway fee evasion of falling card vehicle screening method and device |
| CN111738098A (en) * | 2020-05-29 | 2020-10-02 | 浪潮(北京)电子信息产业有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN111767776A (en) * | 2019-12-28 | 2020-10-13 | 西安宇视信息科技有限公司 | Abnormal license plate selection method and device |
| CN114565982A (en) * | 2022-02-28 | 2022-05-31 | 福建省高速公路信息科技有限公司 | ETC-based vehicle state monitoring method |
| JP2022105433A (en) * | 2021-01-04 | 2022-07-14 | 株式会社東芝 | Vehicle type determination system, central processing unit, and vehicle type determination method |
| CN114780591A (en) * | 2022-04-15 | 2022-07-22 | 广州天长信息技术有限公司 | Calculation method and system for detecting travel license plate recognition error |
| KR20220138308A (en) * | 2021-04-05 | 2022-10-12 | 주식회사 디메타 (D-meta,corp.) | Method and device for determining whether a license plate is forged |
-
2023
- 2023-02-27 CN CN202310207791.4A patent/CN116071931B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016107302A1 (en) * | 2014-12-30 | 2016-07-07 | 北京握奇智能科技有限公司 | Method and system for inspecting moving vehicles |
| CN107204114A (en) * | 2016-03-18 | 2017-09-26 | 中兴通讯股份有限公司 | A kind of recognition methods of vehicle abnormality behavior and device |
| CN106297304A (en) * | 2016-09-08 | 2017-01-04 | 同济大学 | A kind of based on MapReduce towards the fake-licensed car recognition methods of extensive bayonet socket data |
| CN108021361A (en) * | 2017-12-01 | 2018-05-11 | 北京博宇通达科技有限公司 | A kind of the highway fee evasion of falling card vehicle screening method and device |
| CN111767776A (en) * | 2019-12-28 | 2020-10-13 | 西安宇视信息科技有限公司 | Abnormal license plate selection method and device |
| CN111738098A (en) * | 2020-05-29 | 2020-10-02 | 浪潮(北京)电子信息产业有限公司 | Vehicle identification method, device, equipment and storage medium |
| JP2022105433A (en) * | 2021-01-04 | 2022-07-14 | 株式会社東芝 | Vehicle type determination system, central processing unit, and vehicle type determination method |
| KR20220138308A (en) * | 2021-04-05 | 2022-10-12 | 주식회사 디메타 (D-meta,corp.) | Method and device for determining whether a license plate is forged |
| CN114565982A (en) * | 2022-02-28 | 2022-05-31 | 福建省高速公路信息科技有限公司 | ETC-based vehicle state monitoring method |
| CN114780591A (en) * | 2022-04-15 | 2022-07-22 | 广州天长信息技术有限公司 | Calculation method and system for detecting travel license plate recognition error |
Non-Patent Citations (1)
| Title |
|---|
| 张迅?;白文娟;高寒;赵松;丁辉;: "高速公路偷逃费稽查筛选方法研究", 公路交通科技(应用技术版), no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116071931B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751828B (en) | Road congestion measuring method and device, computer equipment and storage medium | |
| CN104408547A (en) | Data-mining-based detection method for medical insurance fraud behavior | |
| CN115880894A (en) | Traffic state determination method, device and equipment | |
| CN116071931B (en) | Expressway traffic vehicle information prediction method and system | |
| CN113793693A (en) | Infectious disease prevalence trend prediction method and device | |
| US20140074672A1 (en) | Fraud tracking network | |
| CN113139743A (en) | Sewage discharge index analysis method and device, electronic equipment and storage medium | |
| CN112365352A (en) | Anti-cash-out method and device based on graph neural network | |
| CN109960707B (en) | College recruitment data acquisition method and system based on artificial intelligence | |
| CN116681207A (en) | Lane special condition business auditing method, equipment and medium | |
| CN111860412A (en) | License plate information repairing method and system based on historical data | |
| CN114757447B (en) | Multi-model mixed passenger transport hub station passenger flow prediction method and system | |
| CN116541786A (en) | Network appointment vehicle identification method, device and system based on driving behaviors | |
| CN112990881B (en) | Related party attendance checking system and method | |
| JP3243129B2 (en) | Fund management support equipment for automatic transaction equipment | |
| CN115496440A (en) | Method and device for determining second-hand car inventory | |
| CN115718872A (en) | Abnormal electricity utilization analysis method for transformer district users based on historical data | |
| CN115587128A (en) | Real population point management system for cell | |
| CN116452387A (en) | Method and system for analyzing group event | |
| CN114780591A (en) | Calculation method and system for detecting travel license plate recognition error | |
| CN113870020A (en) | Overdue risk control method and device | |
| CN111709720A (en) | Vehicle annual inspection automatic identification method and system based on big data | |
| CN113129018B (en) | Financing platform account classification method and system | |
| CN116977062B (en) | Risk label management system and method for financial business | |
| CN115019551B (en) | Correction method of redundant bits of field library, training method and device of redundant bit prediction model |
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 |