Rapid detection method and system for green traffic of expressway

Abstract

The invention provides an expressway green traffic rapid detection method and system. A vehicle is reserved through the ETC platform, a basic database is established, driving, parking, cargo and other data are collected through the informatization system and the monitoring platform, the data are input into the artificial intelligence system for analysis, counterfeit suspicions are graded through data processing, rule comparison and combination of various information, results are output to the toll station and the supervision platform, and suspicion vehicles are checked according to the grades. And the key data is transmitted to the cloud platform for storage and credit evaluation is generated to provide a basis for inspection. According to the invention, data can be provided by using a monitoring network, passing efficiency is improved through X-ray scanning, defects of manual inspection are effectively improved, review difficulty is reduced and internal risks are inhibited by means of artificial intelligence and big data analysis, management scientificity is improved based on credit rating, and multi-dimensional data comparison is realized to guarantee policy execution. And the accuracy and efficiency of green channel vehicle inspection are obviously improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent transportation technology, and specifically relates to a method and system for rapid detection of green passes on highways, aiming to solve many problems in the process of vehicle inspection for green passes (green passes) on highways, improve inspection efficiency and accuracy, and ensure the effective implementation of green pass policies. Background Art

[0002] Green Pass is the green passage of highways. By setting up special passages at highway toll stations, vehicles that legally transport fresh agricultural products are given preferential policies of "no vehicle detention, no unloading, no fines" and toll reductions. In 2019, the Ministry of Transport, together with the National Development and Reform Commission and the Ministry of Finance, issued a policy notice clarifying that vehicles transporting fresh agricultural products can install ETC devices to pass through ETC, establish a national unified reservation service system and a fresh agricultural product credit system. Gradually establish automatic detection as the main method and manual inspection as the auxiliary method, use scientific and technological means to shorten the inspection time of vehicles transporting fresh agricultural products as much as possible, and improve the traffic efficiency of legal transportation vehicles.

[0003] Some toll stations and road sections have installed professional equipment to conduct X-ray imaging inspections on Green Pass vehicles, but due to the huge investment and safety risks, it is difficult to popularize it on a full scale. Currently, Green Pass vehicles are mainly inspected based on manual verification at the exit station. Due to manual inspection, it is difficult to check all the goods on the vehicle, and random inspections are often used. Therefore, some illegal personnel pile up goods that meet the Green Pass requirements on the outside of the goods to achieve the purpose of passing through. In this case, mixed transportation has become a relatively common and concealed Green Pass toll evasion scenario.

[0004] With the continuous advancement of technology and the popularization of informatization, through the national informatization system combined with the arrangement of relevant detection equipment at highway toll stations, the driving trajectory, stop location and time, vehicle license plate, vehicle weight change and other information of green pass vehicles can be collected; artificial intelligence is used to process and analyze the collected green pass vehicle trajectory information, vehicle license plate, vehicle weight, cargo loading volume change and other data and decompose them into key words and phrases. Using the designed data analysis system, it can be determined whether the green pass vehicle is suspected of being counterfeit.

[0005] Patent document CN201910683483.2 discloses a green pass vehicle inspection method based on big data analysis and judgment, which combines green pass inspection data with toll vehicle traffic data to form a green pass information big data database. On this basis, it analyzes and judges based on attributes such as license plate number, tonnage, amount, entry and exit station, vehicle model, and cargo type to provide data support for green pass vehicle inspection, guide the front-end inspection of green pass from manual judgment and experience judgment to data judgment, thereby improving inspection efficiency, forming a summary analysis of green pass vehicles, reducing statistical workload, improving green pass vehicle inspection efficiency, and reducing the difficulty of audit and re-inspection. It has a strong crackdown effect on vehicles that do not meet the green pass requirements. At the same time, it analyzes and judges the distribution of goods, vehicles, intervals, and time and space, providing strong decision-making support and guidance for toll road management departments and transportation departments, and improving the green pass vehicle inspection speed and toll station traffic capacity.

[0006] Patent document CN201810084236.6 discloses a highway green channel vehicle information management system, including a data acquisition subsystem for collecting vehicle body image information, license plate image information, and cargo image information, and sending the body image information, license plate image information, and cargo image information through the data transmission subsystem to the data storage subsystem; the data transmission subsystem is used to transmit the information sent by the data acquisition subsystem to the data storage subsystem and transmit the data sent by the data storage subsystem to the remote access subsystem; the data storage subsystem is used to store the vehicle body image information, license plate image information, cargo image information, axle number information, lane information, release mode information, exemption amount information, operator information, and analyze; the remote access subsystem is used to provide an interface for the client to access the data in the data storage subsystem. The present invention realizes the automated management of the entire green channel, with high audit efficiency and simple procedures.

[0007] However, the above method has problems such as difficulty in manual inspection, low inspection efficiency, and inconsistent inspection standards. At the same time, it is impossible to realize cross-provincial and cross-regional green pass vehicle monitoring and review. Summary of the invention

[0008] In order to solve the above problems, the present invention provides a method for rapid detection of green passage on a highway, comprising the following steps:

[0009] S1, connect to the ETC platform, and the green pass vehicles make reservations for the route plan through the ETC platform in advance, obtain the license plate, weight and other information of the green pass vehicles through the ETC platform, and establish a basic database for the basic information of the green pass vehicles;

[0010] S2, records the driving trajectory of green pass vehicles along the route, the stop time, the weight change of the vehicle when passing through the toll station, the cargo loading situation, the location time of the stop area and the surrounding construction situation;

[0011] S3, input the collected data into the designed artificial intelligence analysis system, decompose the data, extract keywords and key data, and compare and analyze the key information with the set rules to classify the counterfeit suspicion of green pass vehicles, and output the results to the terminal toll station and supervision platform;

[0012] S4: For suspicious vehicles, according to the set suspicion level, medium-suspicion vehicles will be manually re-inspected at the terminal toll station, and for highly suspicious vehicles, the relevant regulatory authorities will be contacted to guide the vehicles to the inspection point at the terminal toll station for focused inspection;

[0013] S5, uploads the basic data such as the license plate and model of the green pass vehicles and the key data such as the inspection report of the inspection instrument to the cloud management platform for storage, forms the green pass vehicle history record and generates the green pass vehicle credit evaluation. The cloud platform data can provide a basis for rapid inspection and key inspection.

[0014] Furthermore, in step S3, the counterfeit suspicion of Green Pass vehicles is specifically graded as follows: first, the collected data is classified and collected, and then the basic information such as the vehicle license plate and model is compared with the ETC reservation information of the Green Pass vehicle in the basic database to confirm whether it is a reserved Green Pass vehicle. After confirming that it is a reserved Green Pass vehicle, the corresponding POI data is collected and word segmentation is performed, and the transportation industry and transportation goods types that comply with the latest Green Pass preferential policies are defined. The monitoring information network along the way is used to continuously monitor and record the driving trajectory of the Green Pass vehicle, the location information around the stop area, the POI data, and the stop time t. The artificial intelligence analysis and calculation system for setting analysis and training is used to classify and grade the above-collected stop location POI data and stop time t, and then analyze them in combination with the Green Pass abnormal behavior analysis system. The results are divided into high suspicion, medium suspicion and low suspicion, and the results are output to the terminal toll station and the supervision platform.

[0015] Furthermore, the collecting of corresponding POI data includes collecting POI data of the province where the use area is located, surrounding provinces and cities, or the whole country.

[0016] Furthermore, by utilizing the monitoring information network along the way, in addition to continuously monitoring and recording the driving trajectory of the green pass vehicle, the location information around the stop area, and the POI data, and the stop time t, the vehicle information data collected at the toll stations on and off the highway is collected to determine whether the preset conditions for the same highway are met; the first stop point data of the vehicle stopping time exceeding the preset time threshold t within the preset time T before getting on the highway is obtained, and the first POI data around the radius of the set area of ​​the first stop point is obtained, and the first POI data is segmented to obtain X POIs; the second stop point data of the vehicle stopping time exceeding the preset time threshold t within the preset time T after getting off the highway is obtained, and the second POI data within the radius of the set area of ​​the second stop point data is obtained, and the obtained second POI data is segmented to obtain Y POI data.

[0017] Furthermore, after step S3 and before step S4, it also includes firstly performing a preliminary classification analysis on the collected data, and using the detection instrument installed at the highway toll station to compare whether the loading types of the reserved green pass vehicles are consistent; then, the data obtained by the detection instrument is input into the identification and analysis system to construct a vehicle data model, and the deviation value analysis is performed with the normal range model set by the system to determine whether there is any abnormality in the cargo loaded on the vehicle and determine the distribution of abnormal areas of the vehicle; finally, the analysis results are transmitted to the toll station staff, and the staff takes corresponding measures according to the actual situation. For abnormal vehicles, manual handheld detectors are used to carry out key inspections on the detected abnormal areas.

[0018] Furthermore, the recognition and analysis system is obtained through neural network model training and analysis, and the neural network is one or more of a convolutional neural network, a feedforward neural network, a recurrent neural network, a long short-term memory network, and a generative adversarial network.

[0019] Furthermore, the abnormal and suspicious vehicle data generated by the analysis and judgment will be combined with the vehicle's credit status and compared with the data in the Green Pass database, and then quickly fed back to each Green Pass inspection site, thereby providing a strong basis for rapid inspection and key inspection work.

[0020] The present invention further provides a highway green pass rapid detection system, which is characterized by comprising a monitoring system, a data acquisition system, a data analysis and processing system, a toll station X-ray rapid detection system and a cloud data service platform;

[0021] Monitoring system: used to connect to road monitoring, track and monitor green pass vehicles, record their basic information, driving trajectory, stop time, surrounding conditions and other information, and transmit the data to the data acquisition system.

[0022] Data collection system: The collected data is classified into keywords and transmitted to the data analysis and processing system.

[0023] Data analysis and processing system: The data from the acquisition system is input into a data model, the artificial intelligence neural network is trained according to relevant rules, a set data judgment system rule is formed, the input data is processed and analyzed according to the settings, and the results are classified and output by grade.

[0024] Toll station X-ray rapid inspection system: It consists of an X-ray scanner, a rapid imaging device, a scanning image analysis device, a display control device, etc. It can quickly scan and identify the distribution of cargo loading in the vehicle, and transmit the data to the analysis system for analysis and judgment to determine whether there are any abnormal conditions in the vehicle.

[0025] Cloud data service platform: stores historical data of green pass vehicles, vehicle credit evaluation analysis results, and the number of times a vehicle has pretended to be a green pass vehicle. Government departments in charge can view relevant vehicle data information after access. Data from several surrounding provinces and cities or the whole country can be connected, making it easy to retrieve information on cross-provincial transport vehicles.

[0026] Furthermore, the highway green pass rapid detection system also includes a manual handheld detector. For abnormal vehicles, a manual handheld detector is used to conduct key inspections in the abnormal detection area.

[0027] Furthermore, the manual handheld detector is composed of a handheld detector main body and a mobile phone installed above the main body. The main body is gun-shaped and is the main supporting structure of the entire device. The mobile phone is used to display detection data, operation interface or perform image transmission and other functions.

[0028] The beneficial effects of the present invention are as follows:

[0029] (1) The monitoring information network can be used to monitor and retrieve information such as the driving records and parking times of green pass vehicles, providing data support for data analysis. At the same time, POI data from various places can be obtained by accessing major map open platforms, urban big data platforms, and field surveys. Combined with the driving records of green pass vehicles recorded by the monitoring system, POI (location name, category, longitude and latitude, and address) information of the vehicle driving and parking areas can be collected to provide data support for the subsequent big data analysis system.

[0030] (2) Greatly improve the efficiency of rapid passage. The detection is an X-ray scan of the cargo on the vehicle, which can be quickly checked without stopping or opening the compartment. The vehicle inspection time is greatly reduced, the accuracy is high, the passage efficiency is improved, and congestion is effectively alleviated.

[0031] (3) Effectively improve problems such as missed inspections, difficulty in inspections, low inspection efficiency, and inconsistent inspection standards that occur during manual inspections.

[0032] (4) Through artificial intelligence and big data analysis, abnormal conditions of green pass vehicles are analyzed and judged, and abnormal conditions of vehicles are classified and abnormal areas are demarcated, which reduces the difficulty of manual review and improves the efficiency of review.

[0033] (5) To suppress internal management risks, each Green Pass vehicle passing through the road is recorded and uploaded to the cloud service platform for easy access at any time, thus preventing internal management risks such as corruption and lack of law enforcement evidence.

[0034] (6) Credit rating of the historical driving records of green pass vehicles can be conducted through the cloud service platform, which can reduce the probability of vehicle re-inspection and serve as an encouragement to law-abiding personnel. Credit rating has a certain scoring proportion in the abnormal analysis model of the data analysis system, which can broaden the comprehensiveness of the analysis system.

[0035] (7) The analysis of abnormal Green Pass vehicles is based on multi-dimensional inspection data comparison and analysis, which has the advantage of being more comprehensive. The comprehensive comparison of basic vehicle information, driving data and credit data improves the accuracy of the verification results and can more accurately identify vehicle disguises or information fraud. It enhances the scientific nature of management, determines the verification results based on multi-faceted data, makes Green Pass management more fair and reasonable, and effectively guarantees the standardized implementation of policies. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work. In the drawings:

[0037] Figure 1 Flow chart of the rapid detection method for green passage on highways.

[0038] Figure 2 This is the layout diagram of the toll station X-ray detection system.

[0039] Figure 3 This is a structural diagram of a manual handheld detector.

[0040] In the figure: 1. Mobile phone installation position; 2. Mobile phone; 3. Display screen; 4. Handle; 5. Battery compartment; 6. Power switch; 7. Function button; 8. Hose; 9. Detection probe; 11. Main shell of handheld detector. DETAILED DESCRIPTION

[0041] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0042] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections.

[0043] In order to simplify the drawings, only the parts related to the present invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0044] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0045] In the embodiments shown in the drawings, the indications of directions (such as up, down, left, right, front and back) used to explain the structure and movement of the various components of the present invention are not absolute but relative. These descriptions are appropriate when these components are in the positions shown in the drawings. If the descriptions of the positions of these components change, the indications of these directions also change accordingly.

[0046] In addition, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation of the present invention will be described below with reference to the accompanying drawings.

[0048] Figure 1 It is a flowchart of the rapid detection method of green pass on highways, which specifically includes connecting to the ETC platform, green pass vehicles pre-booking driving route plans through the ETC platform, preliminarily obtaining the license plate, weight and other information of green pass vehicles through the ETC platform, and establishing a basic database for the basic information of green pass vehicles;

[0049] Utilize the national information system and monitoring network platform to record the driving trajectory of green pass vehicles along the route, stop time, vehicle weight changes when passing through toll stations, cargo loading conditions, stop area location time and surrounding construction conditions;

[0050] Input the data collected in the previous step into the designed artificial intelligence analysis system, decompose the data, extract keywords and key data, and compare and analyze the key information with the set rules to classify the counterfeit suspicion of green pass vehicles, and output the results to the subsequent toll stations and supervision platforms;

[0051] The specific example of analyzing fake Green Pass is to classify and group the collected data. First, compare the vehicle license plate, model and other basic information with the Green Pass vehicle ETC reservation information in the original database to confirm that it is a Green Pass vehicle, and then proceed to the next step of analysis and processing;

[0052] Collect POI data from the province where the area is located, surrounding provinces and cities, or the whole country, and perform word segmentation on the collected POI data to define the transportation industries and transportation goods types that meet the latest green pass preferential policies;

[0053] With the help of advanced monitoring information network along the way, we can realize all-round and uninterrupted monitoring and data collection of green-pass vehicles. In terms of vehicle trajectory tracking, high-precision positioning technology is used to accurately record the detailed driving path of green-pass vehicles during the entire transportation process to ensure the accuracy and consistency of trajectory information. At the same time, for the location information around the vehicle parking area, advanced collection equipment is used to widely collect POI data, covering various key information points related to the surrounding environment, such as nearby farmers' markets, agricultural product processing points, logistics storage facilities, etc., to provide rich materials for subsequent data analysis.

[0054] In terms of time, the vehicle's stop time t is closely monitored, and the start and end time of each stop is accurately recorded. In addition, the focus is on the toll station link, and the vehicle information data collected by the toll station when the green pass vehicles enter and exit the highway is comprehensively collected. These data include basic vehicle information, cargo conditions, travel time and other aspects. Through strict comparison with the preset conditions of the same highway, it is determined whether the vehicle meets the relevant regulations to ensure the accuracy and fairness of the implementation of the green pass policy.

[0055] Further dig into the vehicle's driving history data to obtain detailed information within the preset time T before getting on the highway. During this time period, filter out the first stop point data where the vehicle's stop time exceeds the preset time threshold t, and then focus on the radius of the set area of ​​the first stop point to obtain a wide range of rich first POI data. In order to process this data more efficiently, use professional text processing technology to perform word segmentation on the first POI data, and finally obtain X POIs with clear semantics and classification. These POIs can clearly reflect key information such as the possible source of goods or distribution center of goods before transportation.

[0056] Similarly, within the preset time T after the vehicle gets off the highway, the second stop point data whose stop time exceeds the preset time threshold t is screened out again, and the second POI data within the radius of the set area of ​​the second stop point data is obtained. Using the same word segmentation processing technology, the acquired second POI data is deeply processed to obtain Y POI data. These data are helpful for analyzing important information such as the possible destination of the vehicle after the transportation or the delivery location of the goods, thereby providing comprehensive, in-depth and targeted data support for the supervision of green-pass vehicles, and effectively ensuring the standardized and orderly conduct of green-pass transportation.

[0057] By comparing the vehicle information data collected at the toll stations and the preset highway conditions, it is possible to accurately determine whether the vehicle truly meets the requirements of the Green Pass policy. This effectively prevents vehicles that do not meet the conditions from illegally enjoying Green Pass benefits, ensures that Green Pass resources are used reasonably, and maintains the seriousness and fairness of the policy.

[0058] Analyzing the stop points and surrounding POI data before and after vehicles enter and exit the highway can provide an in-depth understanding of the source and destination of vehicle transportation. It helps to confirm whether the transported goods are indeed from legal agricultural product production or distribution areas, and whether they are delivered to the specified destination, ensuring that the goods transported by the Green Pass meet the category and source requirements stipulated by the policy. It can determine whether the vegetable transport vehicles depart from regular vegetable planting bases and whether they are transported to legal agricultural product wholesale markets.

[0059] Continuous monitoring and recording of driving trajectories and stop times enables regulatory authorities to understand the dynamics of green-pass vehicles in real time. Combined with the analysis of stop points and POI data, regulatory personnel can quickly discover abnormal transportation behaviors, such as long stops in non-agricultural product-related areas, and conduct timely investigations and handling, thereby improving regulatory efficiency and reducing the waste of manpower and time costs.

[0060] Comprehensive analysis of the driving trajectories and parking data of a large number of vehicles can summarize the common transportation routes and parking patterns of green-pass vehicles. Based on this information, the traffic management department can optimize the traffic flow planning of highways, reasonably allocate resources such as green-pass channels, improve the overall operation efficiency of highways, and also provide a more convenient transportation environment for green-pass vehicles.

[0061] By setting up an artificial intelligence analysis and calculation system for analysis and training, the above-collected stop location POI data and stop time t are classified and graded, and then analyzed in combination with the Green Pass abnormal behavior analysis system. The results are output according to the classified suspicion levels (high suspicion, medium suspicion, low suspicion), and different response measures are taken.

[0062] The example of rapid detection of green pass is: the collected data is preliminarily classified and analyzed, and the detection instrument set up at the high-speed toll station is used to compare whether the type of cargo loaded by the scheduled green pass vehicle is consistent, and the detection data of the detection instrument is input into the recognition analysis system after the artificial intelligence neural network learning training analysis, and the vehicle data model is established. The deviation value of the normal range model set by the system is analyzed to determine whether there is an abnormality in the cargo loaded on the vehicle and the distribution of abnormal areas. The analysis results are output to the toll station staff, and the staff adopts different response measures according to the situation. For abnormal vehicles, a manual handheld detector is used to focus on the abnormal detection area. The neural network is one or more of a convolutional neural network, a feedforward neural network, a recurrent neural network, a long short-term memory network, and a generative adversarial network.

[0063] For vehicles that are suspected in the above steps, according to the set suspicion level, for medium-suspicion vehicles, manual re-inspection will be carried out at the terminal toll station. For highly suspicious vehicles, the relevant regulatory authorities will be contacted to guide the vehicles to the inspection point at the terminal toll station for focused inspection.

[0064] Upload key data such as the license plate and model of green pass vehicles and the inspection report of the inspection instrument to the cloud management platform for storage. Temporary data such as vehicle trajectory and stop time will be deleted regularly after the vehicle completes the high-speed journey. Green pass vehicles without suspicion, suspected vehicles that have been re-inspected and confirmed as counterfeit green pass vehicles will be classified and graded to form a green pass vehicle history record and generate a green pass vehicle credit evaluation. The historical traffic record is good and accounts for a certain proportion of the points assigned by the vehicle abnormality judgment system. By comparing the abnormal and suspected vehicle data generated by the analysis and judgment with the data in the green pass database in combination with the credit status of the vehicle, and quickly feeding back to each green pass inspection site, it can provide a basis for rapid inspection and key inspection.

[0065] Another embodiment discloses a rapid detection system for green passage on expressways, which includes a monitoring system, a data acquisition system, a data analysis and processing system, a toll station X-ray rapid detection system, and a cloud data service platform.

[0066] Monitoring system: used to connect to road monitoring, track and monitor green pass vehicles, record their basic information, driving trajectory, stop time, surrounding conditions and other information, and transmit the data to the data acquisition system.

[0067] Data collection system: The collected data is classified into keywords and transmitted to the data analysis and processing system.

[0068] Data analysis and processing system: The data from the acquisition system is input into a data model, the artificial intelligence neural network is trained according to relevant rules, a set data judgment system rule is formed, the input data is processed and analyzed according to the settings, and the results are classified and output by grade.

[0069] Toll station x-ray rapid inspection system: Figure 2 It is the structural diagram of the toll station's X-ray rapid inspection system, which consists of an X-ray scanner, a rapid imaging device, a scanning image analysis device, a display control device, etc. It can quickly scan and identify the distribution of vehicle cargo loading, and transmit the data to the analysis system for analysis and judgment to determine whether there are any abnormalities in the vehicle.

[0070] Cloud data service platform: stores historical data of green pass vehicles, vehicle credit evaluation analysis results, and the number of times a vehicle has pretended to be a green pass vehicle. Government departments in charge can view relevant vehicle data information after access. Data from several surrounding provinces and cities or the whole country can be connected, making it easy to retrieve information on cross-provincial transport vehicles.

[0071] The highway green pass rapid detection system also includes manual handheld detectors. Figure 3 It is a structural diagram of a manual handheld detector, including a handheld detector main body shell 11, which is the basic structure of the entire handheld detector, plays a role in supporting and protecting the internal components, and its shape and design are convenient for operators to hold and operate. The mobile phone installation position 1 is used to fix the mobile phone 2 so that the mobile phone is connected to the main body of the detector. It may be possible to realize data transmission, power supply or use the screen of the mobile phone as the display interface of the detector through this position. The display screen 3 is used to display various information during the detection process, such as detection values, working status, operation prompts, etc., so that users can understand the operation status and detection results of the equipment in real time. The handle 4 is ergonomically designed, which is convenient for operators to hold, reduce fatigue during long-term use, and improve the comfort and stability of operation. The battery compartment 5 is used to install batteries to provide power support for the entire handheld detector, ensure that the device can work normally without an external power supply, and is convenient for use in different places and environments. Power switch 6: a switch used to turn on or off the detector. Function keys 7 include various function keys for realizing different operating functions; the interface may be used to connect external devices, charge or transmit data, etc., to further expand the functions and application scenarios of the detector. The retractable hose 8 can be extended or retracted in length according to the detection requirements, so that the detection probe can penetrate into different depths or difficult to directly reach locations for detection, increasing the scope of use and convenience of the detector. The detection probe 9 is directly in contact with or close to the object to be detected, and is used to collect detection data, such as temperature, humidity, material properties, etc. It is a key component for realizing the detection function, and its performance and accuracy directly affect the accuracy of the detection results. These corresponding components together constitute a more comprehensive manual handheld detector, and each part works together to achieve efficient and accurate detection tasks. The specific functions and usage methods may vary according to the actual design and application scenarios.

[0072] The embodiments described above are part of the embodiments of the present invention, rather than all of the embodiments. The detailed description of the embodiments of the present invention is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Claims

1. A method for rapid detection of green traffic on expressways, characterized in that: The steps include: S1, connect to the ETC platform, and the green pass vehicles make reservations for the route plan through the ETC platform in advance, obtain the license plate, weight and other information of the green pass vehicles through the ETC platform, and establish a basic database for the basic information of the green pass vehicles; S2, records the driving trajectory of green pass vehicles along the route, the stop time, the vehicle weight change when passing through the toll station, the cargo loading situation, the stop area location time and the surrounding construction situation; S3, input the collected data into the designed artificial intelligence analysis system, decompose the data, extract keywords and key data, and compare and analyze the key information with the set rules to classify the counterfeit suspicion of green pass vehicles, and output the results to the terminal toll station and supervision platform; S4: For suspicious vehicles, according to the set suspicion level, medium-suspicion vehicles will be manually re-inspected at the terminal toll station, and for highly suspicious vehicles, the relevant regulatory authorities will be contacted to guide the vehicles to the inspection point at the terminal toll station for focused inspection; S5, uploads the basic data such as the license plate and model of the green pass vehicles and the key data such as the inspection report of the inspection instrument to the cloud management platform for storage, forms the green pass vehicle history record and generates the green pass vehicle credit evaluation. The cloud platform data can provide a basis for rapid inspection and key inspection.

2. The method for rapid detection of green traffic on expressways according to claim 1, characterized in that: In step S3, the counterfeit suspicion of Green Pass vehicles is specifically graded as follows: first, the collected data is classified and collected, and then the basic information such as the vehicle license plate and model is compared with the ETC reservation information of the Green Pass vehicle in the basic database to confirm whether it is a reserved Green Pass vehicle. After confirming that it is a reserved Green Pass vehicle, the corresponding POI data is collected and word segmentation is performed, and the transportation industry and transportation goods types that comply with the latest Green Pass preferential policies are defined. The monitoring information network along the way is used to continuously monitor and record the driving trajectory of the Green Pass vehicle, the location information around the stop area, the POI data, and the stop time t. Through the artificial intelligence analysis and calculation system that is set for analysis and training, the above-collected stop location POI data and stop time t are classified and graded, and then analyzed in combination with the Green Pass abnormal behavior analysis system, and the results are divided into high suspicion, medium suspicion and low suspicion, and the results are output to the terminal toll station and the supervision platform.

3. The method for rapid detection of green traffic on expressways according to claim 2 is characterized in that: The collecting of corresponding POI data includes collecting POI data of the province where the use area is located, surrounding provinces and cities, or the whole country.

4. The method for rapid detection of green traffic on expressways according to claim 2, characterized in that: The monitoring information network along the way is used to continuously monitor and record the driving trajectory of green pass vehicles, the location information around the stop area, the POI data, and the stop time t. In addition, the vehicle information data collected at the toll stations on and off the highway is also collected to determine whether the preset conditions for the same highway are met; the first stop point data of the vehicle stopping time exceeding the preset time threshold t within the preset time T before getting on the highway is obtained, and the first POI data around the radius of the set area of ​​the first stop point is obtained, and the first POI data is segmented to obtain X POIs; the second stop point data of the vehicle stopping time exceeding the preset time threshold t within the preset time T after getting off the highway is obtained, and the second POI data within the radius of the set area of ​​the second stop point data is obtained, and the obtained second POI data is segmented to obtain Y POI data.

5. The method for rapid detection of green traffic on expressways according to claim 1, characterized in that: After step S3 and before step S4, the method also includes firstly performing a preliminary classification analysis on the collected data, and using the detection instrument installed at the highway toll station to compare whether the cargo types of the reserved green pass vehicles are consistent; then, the data obtained by the detection instrument is input into the identification and analysis system to construct a vehicle data model, and a deviation value analysis is performed with the normal range model set by the system to determine whether there is any abnormality in the cargo loaded on the vehicle and determine the distribution of abnormal areas of the vehicle; finally, the analysis results are transmitted to the toll station staff, and the staff takes corresponding measures according to the actual situation. For abnormal vehicles, manual handheld detectors are used to carry out key inspections on the detected abnormal areas.

6. The method for rapid detection of green passage on expressways according to claim 5 is characterized in that: The recognition and analysis system is obtained through neural network model training and analysis, and the neural network is one or more of a convolutional neural network, a feedforward neural network, a recurrent neural network, a long short-term memory network, and a generative adversarial network.

7. According to the method for rapid detection of highway green pass according to claim 1, step S5 also includes combining the abnormal and suspicious vehicle data generated by the analysis and judgment with the credit status of the vehicle, and comparing it with the data in the green pass database, and then quickly feeding back to each green pass inspection site, thereby providing a strong basis for rapid inspection and key inspection work.

8. A fast detection system for green traffic on expressways, characterized in that: Including monitoring system, data acquisition system, data analysis and processing system, toll station X-ray rapid inspection system and cloud data service platform; Monitoring system: used to connect to road monitoring, track and monitor green pass vehicles, record their basic information, driving trajectory, stop time, surrounding conditions and other information, and transmit the data to the data acquisition system. Data collection system: The collected data is classified into keywords and transmitted to the data analysis and processing system. Data analysis and processing system: The data from the acquisition system is input into a data model, the artificial intelligence neural network is trained according to relevant rules, a set data judgment system rule is formed, the input data is processed and analyzed according to the settings, and the results are classified and output by grade. Toll station X-ray rapid inspection system: It consists of an X-ray scanner, a rapid imaging device, a scanning image analysis device, a display control device, etc. It can quickly scan and identify the distribution of cargo loading in the vehicle, and transmit the data to the analysis system for analysis and judgment to determine whether there are any abnormal conditions in the vehicle. Cloud data service platform: stores historical data of green pass vehicles, vehicle credit evaluation analysis results, and the number of times a vehicle has pretended to be a green pass vehicle. Government departments in charge can view relevant vehicle data information after access. Data from several surrounding provinces and cities or the whole country can be connected, making it easy to retrieve information on cross-provincial transport vehicles.

9. The highway green pass rapid detection system according to claim 8 is characterized in that: The highway green pass rapid detection system also includes a manual handheld detector. For abnormal vehicles, a manual handheld detector is used to conduct key inspections in the abnormal detection area.

10. The highway green pass rapid detection system according to claim 8, characterized in that: The manual handheld detector consists of a handheld detector main body and a mobile phone installed above the main body. The main body is gun-shaped and is the main supporting structure of the entire device. The mobile phone is used to display detection data, operation interface or perform image transmission and other functions.

Images