CN-116311565-B - Container trailer fee evasion recognition method, system, device and storage medium

CN116311565BCN 116311565 BCN116311565 BCN 116311565BCN-116311565-B

Abstract

The application discloses a method, a system, a device and a storage medium for identifying the fee evasion of a container trailer, and relates to the technical field of expressway electronic toll collection. The method for identifying the fare escaping of the container trailer comprises the following steps of obtaining the current use shaft number of the current pass of the container trailer, obtaining pass data of continuous multiple passes of the container trailer before the current pass when the current use shaft number is smaller than the common shaft number of the container trailer, constructing a Markov chain according to the pass data, determining a probability transition matrix of the Markov chain, wherein elements in the probability transition matrix are used for representing the state transition probability of the shaft number i to the shaft number j, and determining whether the fare escaping behavior exists in the next pass according to the probability transition matrix and a probability threshold. The application can improve the accuracy of identifying the fare evasion behavior of the container trailer.

Inventors

SUN BINJIE
XI LONG
LUO HAOXIAN

Assignees

广州天长信息技术有限公司

Dates

Publication Date: 20260508
Application Date: 20230309

Claims (8)

1. The method for identifying the fare evasion of the container trailer is characterized by comprising the following steps: Acquiring the current number of axles used in the current pass of the container trailer; When the current used axle number is smaller than the common axle number of the container trailer, acquiring the continuous multi-pass passing data of the container trailer before the current pass; constructing a Markov chain according to a plurality of traffic data, and determining a probability transition matrix of the Markov chain, wherein elements in the probability transition matrix are used for representing the state transition probability of transition from the axis number i to the axis number j; determining the actual use axis number probability of the next pass according to the current use axis number and the probability transition matrix, wherein the actual use axis number probability of the next pass is determined by inquiring the probability transition matrix according to the current use axis number to obtain state transition probability, and taking the state transition probability obtained by inquiring as the actual use axis number probability of the next pass; The method comprises the steps of determining whether the next pass has the fee escaping action according to the actual use shaft number probability and a probability threshold value, wherein the method specifically comprises the steps of determining that the next pass does not have the fee escaping action when the actual use shaft number probability is larger than the probability threshold value, and determining that the next pass has the fee escaping action when the actual use shaft number probability is smaller than or equal to the probability threshold value.
2. The method for identifying the fare evasion of a container trailer according to claim 1, characterized in that the number of common axles of the container trailer is obtained by: acquiring the historical use axle number of the historical traffic of the container trailer; Calculating the ratio of the number of each history use axis number in the plurality of history use axis numbers to the number of all obtained history use axis numbers; And determining the common shaft number according to the shaft number proportion.
3. A container trailer fare evasion recognition method as claimed in claim 1, characterized in that the constructing a markov chain from a plurality of the traffic data and determining a probability transition matrix of the markov chain comprises the steps of: arranging the shaft numbers in the traffic data according to the traffic entry time in the traffic data from small to large to obtain a Markov chain; Counting the state transition probability of the current node in the Markov chain as the axis number i and the next node as the axis number j; And constructing a probability transition matrix by taking the axis number of the current node as a column and the axis number of the next node as a row and taking the state transition probability as a corresponding element value.
4. A container trailer fare evasion recognition method as claimed in claim 3, characterized in that the determination of the actual number of axes probability of the next pass from the current number of axes used and the probability transition matrix comprises the steps of: Acquiring the actual number of used axles of the next pass; Inquiring the columns of the probability transition matrix according to the current use axis number, and inquiring the rows of the probability transition matrix according to the actual use axis number to obtain state transition probability; and taking the state transition probability obtained by the inquiry as the actual use axis number probability of the next pass.
5. A method of identifying a fare evasion of a container trailer according to claim 1, characterized in that the probability threshold is obtained by: Obtaining the proportion of the number of the common shaft numbers to the number of all the historical use shaft numbers of the historical traffic, and obtaining the proportion of the common shaft numbers; and taking the complement of the common axis number proportion to obtain a probability threshold value.
6. A container trailer fare evasion recognition system, comprising: the first module is used for acquiring the current use axle number of the container trailer in the current pass; the second module is used for acquiring the traffic data of the container trailer for a plurality of passes continuously before the current pass when the current used shaft number is smaller than the common shaft number of the container trailer; A third module, configured to construct a markov chain according to a plurality of the traffic data, and determine a probability transition matrix of the markov chain, where an element in the probability transition matrix is used to characterize a state transition probability of transition from an axis number i to an axis number j; A fourth module for performing the steps of: determining the actual use axis number probability of the next pass according to the current use axis number and the probability transition matrix, wherein the actual use axis number probability of the next pass is determined by inquiring the probability transition matrix according to the current use axis number to obtain state transition probability, and taking the state transition probability obtained by inquiring as the actual use axis number probability of the next pass; The method comprises the steps of determining whether the next pass has the fee escaping action according to the actual use shaft number probability and a probability threshold value, wherein the method specifically comprises the steps of determining that the next pass does not have the fee escaping action when the actual use shaft number probability is larger than the probability threshold value, and determining that the next pass has the fee escaping action when the actual use shaft number probability is smaller than or equal to the probability threshold value.
7. A container trailer fare evasion recognition device, comprising: at least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor is caused to implement a container trailer fare identification method as claimed in any one of claims 1 to 5.
8. A computer readable storage medium in which a processor executable program is stored, characterized in that the processor executable program is for implementing a container trailer fare evasion recognition method as claimed in any one of claims 1 to 5 when being executed by the processor.

Description

Container trailer fee evasion recognition method, system, device and storage medium Technical Field The invention relates to the technical field of expressway electronic toll collection, in particular to a method, a system and a device for identifying the fee evasion of a container trailer and a storage medium. Background With the implementation of the national expressway 'one net', each province cancels the expressway provincial boundaries toll station. To improve the traffic experience, the ETC traffic for no-stop tolls is forced. However, as ETC is becoming popular, some container trailer drivers use the tractor head of the container trailer to register when registering an OBU, connect the trailer when driving on the actual road, and the actual traffic is greater than the number of axles used during registration. The method has the advantages that the axle leakage is easy to cause when the vehicle enters the high-speed, the toll is less due to the fact that the axle leakage is caused by the sight or equipment of a toll booth, meanwhile, the container trailer is flexible, the actual running axle number is changed due to the fact that the trailer is replaced, if the axle number of the vehicle is changed due to the fact that the trailer is changed by a driver, in the method for judging the container trailer according to statistical statistics frequency, the model is easily caused by the fact that the traffic is smaller than the common axle number, the toll escaping behavior of the container trailer is mistakenly considered to occur, and the toll escaping behavior accuracy is low. Disclosure of Invention The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a method, a system, a device and a storage medium for identifying the fee evasion of the container trailer, which can improve the accuracy of identifying the fee evasion behavior of the container trailer. In one aspect, the embodiment of the invention provides a method for identifying the fee evasion of a container trailer, which comprises the following steps: Acquiring the current number of axles used in the current pass of the container trailer; When the current used axle number is smaller than the common axle number of the container trailer, acquiring the continuous multi-pass passing data of the container trailer before the current pass; constructing a Markov chain according to a plurality of traffic data, and determining a probability transition matrix of the Markov chain, wherein elements in the probability transition matrix are used for representing the state transition probability of transition from the axis number i to the axis number j; and determining whether the next pass has the fee evasion behavior according to the probability transition matrix and the probability threshold value. According to some embodiments of the invention, the number of common axles of the container trailer is obtained by: acquiring the historical use axle number of the historical traffic of the container trailer; Calculating the ratio of the number of each history use axis number in the plurality of history use axis numbers to the number of all obtained history use axis numbers; And determining the common shaft number according to the shaft number proportion. According to some embodiments of the invention, the constructing a markov chain from a plurality of the traffic data and determining a probability transition matrix of the markov chain includes the steps of: arranging the shaft numbers in the traffic data according to the traffic entry time in the traffic data from small to large to obtain a Markov chain; Counting the state transition probability of the current node in the Markov chain as the axis number i and the next node as the axis number j; And constructing a probability transition matrix by taking the axis number of the current node as a column and the axis number of the next node as a row and taking the state transition probability as a corresponding element value. According to some embodiments of the invention, the determining whether the next pass has an escape behavior according to the probability transition matrix and the probability threshold comprises the steps of: determining the actual use axis number probability of the next pass according to the current use axis number and the probability transition matrix; and determining whether the next pass has the fee evasion behavior according to the actual use axis number probability and the probability threshold value. According to some embodiments of the invention, the determining the actual used shaft number probability of the next pass according to the current used shaft number and the probability transition matrix comprises the following steps: Acquiring the actual number of used axles of the next pass; Inquiring the columns of the probability transition matrix according to the current use axis number, and inquiring the ro