Efficient traffic violation processing method based on cloud computing

Through efficient traffic violation handling methods based on cloud computing, the problem of insufficient data processing capabilities in the existing system is solved, efficient and accurate violation handling is achieved, and the level of traffic management is improved.

CN119091638AActive Publication Date: 2024-12-06SHENZHEN URBAN TRANSPORT PLANNING CENT CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411339892.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-25
Publication Date
2024-12-06
Estimated Expiration
2044-09-25

AI Technical Summary

Technical Problem

The existing traffic violation processing system faces the problems of limited data storage and processing capabilities, slow processing speed and low accuracy, and there are difficulties and risks in obtaining and transmitting illegal data.

Method used

Efficient traffic violation processing method based on cloud computing is adopted. By obtaining violation data and dividing it into fragments, extracting feature values, calculating the mean value and standard deviation, allocating it to different computing nodes for parallel processing, generating violation notices, and training the decision tree model for classification Judgment and generate penalty decisions based on constraints.

Benefits of technology

It effectively improves the efficiency and accuracy of traffic violation handling, reduces processing costs, and improves the level of traffic management and service quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091638A_ABST
    Figure CN119091638A_ABST
Patent Text Reader

Abstract

The invention provides an efficient traffic violation processing method based on cloud computing, and belongs to the technical field of intelligent traffic. Comprising the following steps: S1, acquiring violation data and performing fragment segmentation on the violation number to generate a plurality of fragments containing the violation data; s2, peccancy feature extraction is carried out according to the data fragments; s3, calculating an average value and a standard deviation of specific features in each segment; s4, calculating a specific characteristic difference value of violation according to the average value and the standard deviation of the characteristics in the fragment, and determining a critical value of the specific characteristic difference value; s5, distributing the data fragments to different computing nodes, and processing the data fragments in parallel by each computing node; s6, aggregating each data fragment result to obtain an analysis result; s7, generating a violation notice according to an analysis result; the technical problems that in the prior art, the data storage and processing capacity is limited, the processing speed is low, and the accuracy is not high can be effectively solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a traffic violation processing method, in particular to an efficient traffic violation processing method based on cloud computing, and belongs to the field of intelligent transportation technology. Background Art

[0002] With the popularization of intelligence, off-site law enforcement has become an indispensable and most important part of traffic management. Off-site law enforcement refers to the use of radar, cameras, electronic eyes and other technological means by traffic management departments to record traffic violations of moving vehicles and form image data, which is used as evidence to punish traffic violators in accordance with the law afterwards. At present, traffic violation processing is a cumbersome and complicated process. Traditional violation processing systems usually face problems such as limited data storage and processing capabilities, slow processing speed, and low accuracy. At the same time, there are certain difficulties and risks in the acquisition and transmission of violation data. Therefore, an efficient traffic violation processing system based on cloud computing technology is needed to solve these problems. Summary of the invention

[0003] A brief overview of the present invention is provided below in order to provide a basic understanding of certain aspects of the present invention. It should be understood that this overview is not an exhaustive overview of the present invention. It is not intended to identify key or important parts of the present invention, nor is it intended to limit the scope of the present invention. Its purpose is merely to present certain concepts in a simplified form as a prelude to a more detailed description discussed later.

[0004] In view of this, in order to solve the technical problems existing in the prior art of limited data storage and processing capabilities, slow processing speed and low accuracy, the present invention provides an efficient traffic violation processing method based on cloud computing.

[0005] Solution 1: An efficient traffic violation processing method based on cloud computing, comprising the following steps: S1. Obtain the violation data and segment the violation data to generate multiple segments containing the violation data; S2. Extracting violation features based on data fragments; S3. Calculate the mean and standard deviation of specific features in each segment; S4. Calculate the specific feature difference value of the violation according to the mean value and standard deviation of the specific feature in the fragment, and determine the critical value of the specific feature difference value; S5. distribute the data fragments to different computing nodes, and each computing node processes the data fragments in parallel; S6. Aggregate the results of each data segment to obtain the analysis result; S7. Generate a violation notice based on the analysis results, the method comprising the following steps: S71. Generate a violation data training set based on the analysis results; S72. Training a decision tree model based on the violation data training set; S73. Classify and judge the violation data; S74. Generate a violation penalty decision based on the classification judgment results and constraint conditions.

[0006] Preferably, the specific feature difference value is calculated by: ; Where t represents the specific feature difference value; A represents data segment A, B represents data segment B, represents the average value of A data segment, represents the standard deviation of the A data segment; represents the standard deviation of the B data segment; n represents the number of specific eigenvalues ​​in the A data segment, and m represents the number of specific eigenvalues ​​in the B data segment.

[0007] Preferably, the method for training a decision tree model based on a violation data training set is: including the following steps: S721. Initialize the root node and take the training data set as input; S722. Select the best feature, divide the data set into multiple subsets, and evaluate the quality of the division by calculating the Gini index of each feature; S723. Recursively execute S722 for each subset until the stop condition is met; S724. Build a decision tree and associate each node with corresponding features and segmentation conditions.

[0008] Preferably, the method for classifying and judging the violation data is: comprising the following steps: S731. Input the feature vector x of the next violation data; S732. Starting from the root node, the data is gradually classified into child nodes according to the node characteristics and segmentation conditions until a leaf node is reached. The leaf node is the classification result of the new violation data.

[0009] Preferably, the constraints include: Constraint 1: Violation handling requirements constraints; Constraint 2: Legal constraints.

[0010] Preferably, the objective function of the violation penalty decision is: ; Among them, punishment_amount is the penalty amount, and handling_method is the handling method.

[0011] Preferably, the constraints required for violation handling are: a. Processing timeliness; b. Selection of treatment method; C. Complaint procedures; d. Processing record keeping; e. Notice of penalty decision; The legal constraints are: a. the minimum statutory penalty; b. The statutory penalty amount; c. Legal processing methods; d. Legal right to appeal; e. Legal time limit.

[0012] Solution 2: An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of an efficient traffic violation processing method based on cloud computing as described in Solution 1.

[0013] Solution three: A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the efficient traffic violation processing method based on cloud computing described in Solution one is implemented.

[0014] The beneficial effects of the present invention are as follows: the present invention effectively improves the efficiency and accuracy of traffic violation processing, reduces processing costs, effectively solves the technical problems of limited data storage and processing capabilities, slow processing speed, and low accuracy in the prior art, while improving the level of traffic management and service quality; the present invention also has broad application prospects and has important practical significance in the field of traffic management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 The flowchart of an efficient traffic violation processing method based on cloud computing is shown in FIG. DETAILED DESCRIPTION

[0016] In order to make the technical solutions and advantages of the embodiments of the present invention more clearly understood, the exemplary embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0017] Example 1: Reference Figure 1The present embodiment describes an efficient traffic violation processing method based on cloud computing, comprising the following steps: S1. Obtain the violation data and segment the violation data to generate multiple segments containing the violation data; The method of obtaining violation data can be through surveillance cameras or real-time acquisition through radar collection; Traffic violation data includes vehicle information, time of violation, and location of violation; The vehicle information includes the license plate number and vehicle type; S2. Extracting violation features based on data fragments; Number of violations in the statistics segment; Count the number of different types of violations in the data segment and calculate the frequency of different types of violations; The locations where the violations occurred in the statistical data segment, and the distribution of violations at different locations; S3. Calculate the mean and standard deviation of specific features in each segment; Calculate the data of specific features in each fragment. The specific features in data fragment A are , the specific features in the B data segment are ; A is the average value of the data segment: ; Standard deviation of a data segment: ; The average value of the B data segment: ; Standard deviation of data segment B: ; S4. Calculate the specific feature difference value of the violation based on the mean and standard deviation of the features in the segment; Specific feature difference value: ; Where t represents the specific feature difference value; A represents data segment A, B represents data segment B, represents the average value of A data segment, represents the standard deviation of the A data segment; represents the standard deviation of the B data segment; n represents the number of specific eigenvalues ​​in the A data segment, and m represents the number of specific eigenvalues ​​in the B data segment; S5. distribute the data fragments to different computing nodes, and each computing node processes the data fragments in parallel; Each computing node of the present invention can process one or more data fragments in parallel, and the distributed processing of data fragments can improve computing efficiency; S6. Aggregate the results of each data segment to obtain the analysis result; The analysis results can be visualized using histograms. The matplotlib library is used to draw histograms so that the feature differences between different data segments can be visualized. S7. Generate a violation notice based on the analysis results, analyze the patterns and trends of the violation data, and help improve the traffic management strategy, the method includes the following steps: S71. Generate a violation data training set using the analysis results ,in is a feature vector of violation data, is the corresponding classification label, is the number of training samples; ,in is the number of features; , where 0 means no violation and 1 means violation; S72. Train a decision tree model based on the violation data training set, S721. Initialize the root node and take the training data set as input; S722. Select the best feature, divide the data set into multiple subsets, and evaluate the quality of the division by calculating the Gini index of each feature; The method for selecting the best features is to calculate the information entropy of each feature. Information entropy is an indicator to measure the uncertainty of data, defined as H(D) = - ∑ p(x) log2 p(x), where x is a sample in the data set and p(x) is the probability of the sample appearing. Calculate the information gain Gain(D, A) of each feature, Gain(D, A) = H(D) - H(D|A), where A is the feature to be evaluated, H(D) is the information entropy of the data set, and H(D|A) is the conditional entropy, which represents the uncertainty of the data set considering feature A. The calculation formula for conditional entropy is H(D|A) = ∑p(a) H(D|A=a), where a is the value of feature A, p(a) is the probability that feature A takes value a, and H(D|A=a) is the conditional information entropy of the sample when feature A takes value a. Finally, select the feature with the largest information gain as the best feature; For each possible value a of feature A, the dataset Divide into subsets . Calculate each subset The Gini index of feature A is then calculated.

[0018] The weighted Gini index calculation formula of feature A is: ,in, ,in, is the upper limit of the value, Indicates the proportion of cases where feature A takes the value a.

[0019] The quality of the evaluation division depends on the size of the Gini index. When the value of the Gini index is less than the threshold, the evaluation result is good, otherwise the evaluation result is bad; When the evaluation result is bad, , when the evaluation result is good, ; S723. Recursively execute S722 for each subset until the stop condition is met; Stop condition: The number of samples in the subset is less than the threshold. The range of the threshold depends on the severity of the violation that needs to be punished. For example, when lighter violations need to be punished, the threshold value is low, and when only serious violations need to be punished, the threshold is raised, depending on the severity of the local punishment for violations.

[0020] S724. Construct a decision tree and associate each node with a corresponding feature and segmentation condition; S73. Classify and judge the violation data; S731. Input the feature vector x of the next violation data; S732. Starting from the root node, the data is gradually classified into child nodes according to the node characteristics and segmentation conditions until a leaf node is reached. The leaf node is the classification result of the new violation data.

[0021] S74. Generate a violation penalty decision based on the classification judgment result and constraint conditions; The constraints include: Constraint 1: Violation handling requirements constraints; Constraint 2: Constraints imposed by law; Constraints on violation handling requirements: a. Timeliness of handling: It is required to complete the handling of violations within a certain period of time to ensure timely disposal; b. Action options: Specifies the available action options, such as fines, penalty points, educational courses, etc., which may vary depending on the circumstances of the violation.

[0022] C. Appeal Procedure: It stipulates the appeal process, allowing violators to raise objections or appeals at different stages; d. Record keeping: detailed information of the processing process must be recorded and stored for review and audit; e. Notification of penalty decisions: Violators are required to be notified of penalty decisions in a timely manner to ensure transparency and legality; Legal constraints: a. Minimum statutory penalties: minimum statutory penalties for certain violations to ensure a certain degree of punishment for violations; b. Legal penalty amount: the range of penalty amounts for different types of violations, so that decisions can be made within this range; c. Statutory treatment: It stipulates that certain types of violations must be dealt with in a specific way, such as revoking the driver's license; d. Statutory right of appeal: The right of appeal of violators, including the procedures and conditions for raising objections or appeals; e. Legal timeliness: Timeliness requirements for handling violations to ensure that they are handled within a reasonable time; The objective function of violation penalty decision-making is: ; Among them, punishment_amount is the penalty amount, and handling_method is the handling method.

[0023] The present invention can not only generate a violation notice using the above method, but also automatically generate a violation handling decision suggestion.

[0024] The violation notice generated by the present invention includes information such as the violation time, violation location and violation type.

[0025] Embodiment 2: The computer device of the present invention may be a device including a processor and a memory, such as a single chip microcomputer including a central processing unit, etc. Moreover, the processor is used to implement the steps of the above-mentioned efficient traffic violation processing method based on cloud computing when executing the computer program stored in the memory.

[0026] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0027] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0028] Embodiment 3: Computer readable storage medium embodiment.

[0029] The computer-readable storage medium of the present invention can be any form of storage medium that can be read by the processor of a computer device, including but not limited to non-volatile memory, volatile memory, ferroelectric memory, etc. A computer program is stored on the computer-readable storage medium. When the processor of the computer device reads and executes the computer program stored in the memory, the steps of the above-mentioned efficient traffic violation processing method based on cloud computing can be implemented.

[0030] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0031] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative, not restrictive, with respect to the scope of the present invention, which is defined by the appended claims.

Claims

1. An efficient traffic violation processing method based on cloud computing, characterized in that: The following steps are involved: S1. Obtain the violation data and segment the violation data to generate multiple segments containing the violation data; S2. Extracting violation features based on data fragments; S3. Calculate the mean and standard deviation of specific features in each segment; S4. Calculate the specific feature difference value of the violation according to the mean value and standard deviation of the specific feature in the fragment, and determine the critical value of the specific feature difference value; S5. distribute the data fragments to different computing nodes, and each computing node processes the data fragments in parallel; S6. Aggregate the results of each data segment to obtain the analysis result; S7. Generate a violation notice based on the analysis results, the method comprising the following steps: S71. Generate a violation data training set based on the analysis results; S72. Training a decision tree model based on the violation data training set; S73. Classify and judge the violation data; S74. Generate a violation penalty decision based on the classification judgment results and constraint conditions.

2. According to the cloud computing-based efficient traffic violation processing method of claim 1, it is characterized in that: The calculation method of the difference value of a specific feature is: ; Where t represents the specific feature difference value; A represents data segment A, B represents data segment B, represents the average value of A data segment, represents the standard deviation of the A data segment; represents the standard deviation of the B data segment; n represents the number of specific eigenvalues ​​in the A data segment, and m represents the number of specific eigenvalues ​​in the B data segment.

3. The efficient traffic violation processing method based on cloud computing according to claim 3 is characterized in that: The method of training a decision tree model based on the violation data training set is: The following steps are included: S721. Initialize the root node and take the training data set as input; S722. Select the best feature, divide the data set into multiple subsets, and evaluate the quality of the division by calculating the Gini index of each feature; S723. Recursively execute S722 for each subset until the stop condition is met; S724. Build a decision tree and associate each node with corresponding features and segmentation conditions.

4. The efficient traffic violation processing method based on cloud computing according to claim 4 is characterized in that: The method for classifying and judging the violation data is: The following steps are included S731. Input the feature vector x of the next violation data; S732. Starting from the root node, the data is gradually classified into child nodes according to the node characteristics and segmentation conditions until a leaf node is reached. The leaf node is the classification result of the new violation data.

5. The efficient traffic violation processing method based on cloud computing according to claim 5 is characterized in that: The constraints include: Constraint 1: Violation handling requirements constraints; Constraint 2: Legal constraints.

6. The efficient traffic violation processing method based on cloud computing according to claim 6 is characterized in that: The objective function of violation penalty decision-making is: ; Among them, punishment_amount is the penalty amount, and handling_method is the handling method.

7. The efficient traffic violation processing method based on cloud computing according to claim 7 is characterized in that: The constraints for violation handling requirements are: a. Processing timeliness; b. Selection of treatment method; C. Complaint procedures; d. Processing record keeping; e. Notice of penalty decision; The legal constraints are: a. the minimum statutory penalty; b. The statutory penalty amount; c. Legal processing methods; d. Legal right to appeal; e. Legal time limit.

8. An electronic device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of an efficient traffic violation processing method based on cloud computing as described in any one of claims 1-8 when executing the computer program.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for efficiently handling traffic violations based on cloud computing as described in any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • Method for playback and analysis of violation data in tunnel construction process, computer device and computer readable storage medium

    CN115035726A

  • Traffic violation behavior detection system and method based on computer vision

    CN116778434A

  • Intelligent substation illegal operation early warning system

    CN117372723A

  • Distributable feature analysis and tree model training system

    US11093864B1

  • Data updating method, model training method, apparatus, electronic device and medium

    US20240282103A1