ETC business abnormal behavior identification method and system based on OCR identification and information comparison

Abstract

The invention provides an ETC business abnormal behavior identification method and system based on OCR identification and information comparison, and the method comprises the steps: inputting the registered vehicle information of a vehicle, the registered vehicle information comprising a license plate, a color and a vehicle type; in the transaction process of the vehicle, the transaction is completed through the OBU of the vehicle, corresponding registered vehicle information is obtained, and a vehicle image of the vehicle is collected; acquiring actual vehicle information based on the vehicle image, and comparing the actual vehicle information with registered vehicle information; and judging whether the transaction is an abnormal transaction based on a comparison result. According to the scheme, the vehicle image of the vehicle during the transaction can be captured, the actual vehicle information in the vehicle image is extracted, and then the actual vehicle information is compared with the registered vehicle information, so that more refined processing can be realized through comparison according to actual conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation systems, and in particular, to an ETC service abnormal behavior recognition method and system based on OCR recognition and information comparison. Background Art

[0002] The Electronic Toll Collection (ETC) system, also known as the non-stop toll collection system, is an intelligent transportation toll collection method that uses modern communication technology and automatic identification technology to automatically deduct vehicle tolls. The ETC system realizes the rapid and accurate deduction of vehicle tolls by installing an electronic tag (or in-vehicle device) on the vehicle and exchanging information with the antenna and vehicle type recognition system at the toll station.

[0003] Specifically, when a vehicle equipped with ETC enters the toll station, the electronic tag on the vehicle establishes wireless communication with the toll station antenna. The antenna reads the vehicle information in the electronic tag, such as the license plate number, vehicle type, etc., and sends this information to the background processing system. The background system calculates the toll to be paid according to the vehicle information and the preset toll standard, and automatically deducts it from the payment account bound to the electronic tag. During the whole process, the vehicle does not need to stop and there is no need for manual operation, which greatly improves the traffic efficiency.

[0004] The ETC system is not only applied to highway toll collection, but also extended to areas such as urban bridge crossing, tunnel crossing, and parking lot management. Its characteristics of high efficiency, speed, and environmental protection are of great significance for alleviating traffic congestion and improving the operation efficiency of highway traffic. In addition, using ETC can also enjoy a certain toll discount, reducing the travel cost of vehicle owners. In the context of the intelligent transportation system, the Electronic Toll Collection (ETC) system has been widely used due to its high efficiency and convenience. As an important part of urban intelligent transportation management, the accuracy of the issuance and transaction verification of the ETC system is of great significance for ensuring smooth traffic and financial security.

[0005] However, the existing ETC systems often only perform specific processing based on license plate information, with limited processing accuracy and difficulty in achieving more refined processing. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide an ETC service abnormal behavior recognition method based on OCR recognition and information comparison to eliminate or improve one or more defects existing in the prior art.

[0007] One aspect of the present invention provides an ETC service abnormal behavior recognition method based on OCR recognition and information comparison. The steps of the method include:

[0008] Enter the registered vehicle information of the vehicle, where the registered vehicle information includes license plate, color, and vehicle model;

[0009] During the process of vehicle trading, complete the transaction through the vehicle's OBU, obtain the corresponding registered vehicle information, and collect the vehicle image of the vehicle;

[0010] Based on the vehicle image, obtain the actual vehicle information, and compare the actual vehicle information with the registered vehicle information;

[0011] Based on the comparison result, determine whether it is an abnormal transaction.

[0012] Adopting the above solution, this solution can capture the vehicle image when the vehicle is traded, extract the actual vehicle information in the vehicle image, and then compare the actual vehicle information with the registered vehicle information. Since some users may modify the vehicle model information privately and reinstall the vehicle's OBU, resulting in the charging not matching the actual vehicle model, through the above solution of this solution, it can be compared according to the actual situation to achieve more refined processing.

[0013] In some embodiments of the present invention, in the step of obtaining the actual vehicle information based on the vehicle image, the OCR technology is used to identify the actual vehicle information in the vehicle image, and the actual vehicle information corresponds to the registered vehicle information, including license plate, color, and vehicle model.

[0014] In some embodiments of the present invention, in the step of comparing the actual vehicle information with the registered vehicle information, the corresponding actual vehicle information items are compared item by item with the registered vehicle information items.

[0015] In some embodiments of the present invention, in the step of determining whether it is an abnormal transaction based on the comparison result, obtain the comparison result of each corresponding actual vehicle information item and the registered vehicle information item to determine whether the determination of each item passes. If the determination of all items passes, it is determined as a normal transaction; if the determination of any one item does not pass, it is determined as an abnormal transaction.

[0016] In some embodiments of the present invention, in the step of obtaining the comparison result of each corresponding actual vehicle information item and the registered vehicle information item to determine whether the determination of each item passes:

[0017] Encode each extracted actual vehicle information item, and calculate the similarity between the code corresponding to each actual vehicle information item and the code corresponding to the registered vehicle information item;

[0018] Based on the similarity, determine whether the determination of this item passes.

[0019] In some embodiments of the present invention, in the step of determining whether it is an abnormal transaction based on the comparison result, each of the extracted actual vehicle information items is encoded, the similarity between the code corresponding to each actual vehicle information item and the code corresponding to the registered vehicle information item is calculated, and a weighted calculation is performed based on the similarities of multiple items to determine whether it is an abnormal transaction.

[0020] In some embodiments of the present invention, in the step of using OCR technology to identify the actual vehicle information in the vehicle image, the vehicle image is preprocessed, and the preprocessing process includes:

[0021] Using a filter to reduce the image noise of the vehicle image;

[0022] Converting the vehicle image into a black-and-white image;

[0023] Applying a Canny edge detector to determine the object contour in the image and locate the text area.

[0024] In some embodiments of the present invention, the step of using OCR technology to identify the actual vehicle information in the vehicle image further includes:

[0025] For the preprocessed vehicle image, morphological operations are used to locate the license plate area, and color filtering is used to further define the license plate area;

[0026] And an OCR engine is used to identify the text in the license plate area.

[0027] In some embodiments of the present invention, the steps of the method include:

[0028] Based on the transaction data in the vehicle OBU, the corresponding data points of the calculated transaction data for each transaction are calculated, and the Z-Score statistical method is used to determine whether this transaction is an abnormal transaction.

[0029] The second aspect of the present invention further provides an ETC service abnormal behavior recognition system based on OCR recognition and information comparison. The system includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0030] The third aspect of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps implemented by the foregoing ETC service abnormal behavior recognition method based on OCR recognition and information comparison.

[0031] Additional advantages, objects, and features of the present invention will be partly set forth in the description which follows, and will partly become apparent to those of ordinary skill in the art upon examination of the following, or may be learned by practice of the present invention. The objects and other advantages of the present invention may be realized and attained by the means particularly pointed out in the specification and drawings.

[0032] Those skilled in the art will understand that the objects and advantages that can be achieved by the present invention are not limited to those specifically described above, and the above and other objects that the present invention can achieve will be more clearly understood according to the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, and do not limit the present invention.

[0034] Figure 1 It is a schematic diagram of an embodiment of the ETC service abnormal behavior recognition method based on OCR recognition and information comparison of the present invention;

[0035] Figure 2 It is a schematic diagram of the software processing mode of the ETC service abnormal behavior recognition method based on OCR recognition and information comparison of the present invention;

[0036] Figure 3 It is a schematic diagram of the processing architecture of the ETC service abnormal behavior recognition method based on OCR recognition and information comparison of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] To make the objects, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the embodiments and the drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but do not limit the present invention.

[0038] Here, it should also be noted that in order to avoid obscuring the present invention due to unnecessary details, only the structures and / or processing steps closely related to the solution of the present invention are shown in the drawings, and other details less related to the present invention are omitted.

[0039] In the context of the intelligent transportation system, the Electronic Toll Collection (ETC) system has been widely used due to its high efficiency and convenience. As an important part of urban intelligent transportation management, the accuracy of the ETC system's issuance and transaction verification is of great significance for ensuring traffic flow and financial security. However, the existing systems face the following challenges when processing ETC issuance and transaction verification:

[0040] Evading toll behavior: Some users may privately modify the vehicle type information, resulting in the toll not matching the actual vehicle type, thereby evading tolls and causing losses to the enterprise;

[0041] Business handling error: During the handling process, business personnel may, due to negligence, wrongly handle vehicle type information, resulting in toll losses.

[0042] Complicated manual operations: When users handle ETC activation and other services, they need to go through online or offline channels. There are many manual operation links, and the efficiency is low.

[0043] Inaccurate information verification: Relying on manual review of vehicle information and transaction records is prone to errors and has a high error rate.

[0044] Limited data processing capacity: When the existing system processes a large amount of transaction data, the response time is long, and it cannot meet the demand for the rapidly growing data volume.

[0045] Such as Figure 1 and 3 As shown, the present invention proposes an ETC service abnormal behavior recognition method based on OCR recognition and information comparison. The steps of this method include:

[0046] Step S100, input the registered vehicle information of the vehicle. The registered vehicle information includes license plate, color, and vehicle type.

[0047] In the specific implementation process, in the step of inputting the registered vehicle information of the vehicle, OCR can also be used for collection.

[0048] The registered vehicle information also includes vehicle type and vehicle brand, etc.

[0049] Step S200, during the transaction of the vehicle, complete the transaction through the OBU of the vehicle, obtain the corresponding registered vehicle information, and collect the vehicle image of the vehicle.

[0050] In the specific implementation process, the image of the vehicle is collected by a lane camera.

[0051] In the specific implementation process, OBU (On-Board Unit) - on-vehicle unit, a device installed on the vehicle in the ETC system for communicating with the toll collection system; OCR (Optical Character Recognition) - optical character recognition, referring to the technology of recognizing and extracting text from image files; ETC (Electronic Toll Collection) - electronic toll collection system, an automatic toll collection system for highways and toll stations.

[0052] Step S300, obtain the actual vehicle information based on the vehicle image, and compare the actual vehicle information with the registered vehicle information.

[0053] In the specific implementation process, in the step of obtaining the actual vehicle information based on the vehicle image, the vehicle information of the vehicle is recognized through OCR.

[0054] Step S400, determine whether it is an abnormal transaction based on the comparison result.

[0055] Adopting the above solution, this solution can capture the vehicle image of the vehicle during the transaction, extract the actual vehicle information in the vehicle image, and then compare the actual vehicle information with the registered vehicle information. Since some users may cause the toll to not match the actual vehicle type by privately modifying the vehicle type information and reinstalling the OBU of the vehicle, through the above solution of this solution, it can be compared according to the actual situation to achieve more refined processing.

[0056] In some embodiments of the present invention, in the step of obtaining the actual vehicle information based on the vehicle image, the OCR technology is used to recognize the actual vehicle information in the vehicle image, and the actual vehicle information corresponds to the registered vehicle information, including license plate, color, and vehicle type.

[0057] In some embodiments of the present invention, in the step of comparing the actual vehicle information with the registered vehicle information, the corresponding actual vehicle information items are compared item by item with the registered vehicle information items.

[0058] In some embodiments of the present invention, in the step of determining whether it is an abnormal transaction based on the comparison result, obtain the comparison result of each corresponding actual vehicle information item and the registered vehicle information item to determine whether the determination of each item passes. If the determination of all items passes, it is determined as a normal transaction; if the determination of any one item does not pass, it is determined as an abnormal transaction.

[0059] In some embodiments of the present invention, in the step of obtaining the comparison result of each corresponding actual vehicle information item and the registered vehicle information item to determine whether the determination of each item passes:

[0060] Encode each extracted actual vehicle information item, and calculate the similarity between the code corresponding to each actual vehicle information item and the code corresponding to the registered vehicle information item;

[0061] Determine whether the determination of this item passes based on the similarity.

[0062] In the specific implementation process, in the step of determining whether the determination of this item passes based on the similarity, set a threshold for the comparison result to determine the matching situation of two feature vectors, and the threshold can be flexibly adjusted according to business requirements and historical data.

[0063] In some embodiments of the present invention, in the step of determining whether it is an abnormal transaction based on the comparison result, each of the extracted actual vehicle information items is encoded, the similarity between the code corresponding to each actual vehicle information item and the code corresponding to the registered vehicle information item is calculated, and a weighted calculation is performed based on the similarities of multiple items to determine whether it is an abnormal transaction.

[0064] In the specific implementation process, in the step of calculating the similarity between the code corresponding to each actual vehicle information item and the code corresponding to the registered vehicle information item, methods such as Euclidean distance or cosine similarity are used for calculation.

[0065] In the specific implementation process, the user assigns a weight value to each selected element item, and the weight value reflects the importance of the element in the comparison process. The system provides intuitive sliders or input boxes for the user to set the weights, ensuring that the user can flexibly adjust the influence of each element according to different business scenarios and risk assessments. The element items and weights configured by the user are not static, but can be flexibly adjusted and take effect immediately. This means that the user can quickly adjust the configuration according to real-time feedback and business requirements, and the system will immediately perform comparison and verification according to the new configuration to ensure the accuracy and real-time nature of the transaction information.

[0066] In some embodiments of the present invention, in the step of using OCR technology to identify the actual vehicle information in the vehicle image, the vehicle image is preprocessed, and the preprocessing process includes:

[0067] Using a filter to reduce the image noise of the vehicle image;

[0068] Converting the vehicle image into a black-and-white image to make it easier to identify text areas, etc.;

[0069] Applying the Canny edge detector to determine the object contour in the image and locate the text area; Applying an algorithm (Canny edge detector) to determine the object contour in the image to provide a basis for locating the text area.

[0070] In the specific implementation process, filters (such as Gaussian blur and median filter) are used to reduce the image noise and improve the accuracy of subsequent processing steps.

[0071] In some embodiments of the present invention, the step of using OCR technology to identify the actual vehicle information in the vehicle image further includes:

[0072] For the preprocessed vehicle image, morphological operations are used to locate the license plate area, and color filtering is used to further limit the license plate area. The morphological operations include erosion and dilation, etc.;

[0073] And an OCR engine is used to recognize the text in the license plate area. The OCR engine processes problems such as deformation, illumination change, and partial occlusion through a deep learning model: convolutional neural network (CNN).

[0074] In the specific implementation process, an exact matching algorithm is used for license plate number matching to ensure complete data consistency; a fuzzy matching algorithm is used for vehicle brand and model matching to handle spelling mistakes or format differences; for vehicle color image recognition and database record matching, a machine learning algorithm is selected, and the machine learning comparison model is implemented using the scikit-learn library of Python.

[0075] In some embodiments of the present invention, the steps of the method include:

[0076] Based on the transaction data in the vehicle OBU, calculate the corresponding data points of each transaction for calculating the transaction data, and use the Z-Score statistical method to determine whether this transaction is an abnormal transaction.

[0077] In the specific implementation process, the present solution uses the Z-Score (standard score) statistical method in the statistical analysis algorithm to measure the standard deviation of a single data point relative to the average value of the entire data set. Analyze the relative distance between the data point and the central tendency (i.e., the mean) of the data set;

[0078] 1. Abnormal transaction detection: By calculating the Z-Score of the transaction data, identify transactions that are significantly different from most transaction patterns, and analyze possible errors or other abnormal behaviors.

[0079] 2. User behavior analysis: Analyze the operation records when the user activates the OBU (on-board unit), and combine with the Z-Score model to automatically locate the user and track the information of their first passing transaction, and verify whether the user behavior pattern is within the normal range.

[0080] 3. Risk assessment: During the transaction verification process, use Z-Score to evaluate the transaction risk level. According to the high or low of the Z-Score, determine whether the transaction is within the acceptable risk range.

[0081] In some embodiments of the present invention, extract the feature element information to be compared from the transaction data: extract license plate number, vehicle color, brand logo features from the vehicle image; extract features such as transaction time and amount from the transaction data.

[0082] In the specific implementation process, the present invention realizes the efficient and accurate verification of ETC issuance and transaction information by integrating advanced data processing technologies and automated comparison algorithms. The core of the model lies in the following aspects:

[0083] Automated operation record positioning: By analyzing the operation records of users when activating the OBU (On-Board Unit), automatically locate the users and track their first passing transaction information.

[0084] User-defined configuration: Users can flexibly configure comparison element items and element weights. The present invention can perform flexible comparison calculations according to the configurations of users; at the same time, users are allowed to assign different weights to each comparison element item to reflect its importance in the transaction verification process. This enhances the adaptability of the model and the ability of personalized services.

[0085] Multi-source information comparison: Use OCR technology to extract vehicle information from lane pictures and comprehensively compare it with the vehicle information in the exit transaction information and handling documents.

[0086] Audit platform integration: Establish a display page in the audit platform, provide filtering conditions and query functions, and achieve rapid retrieval and processing of transaction information.

[0087] Intelligent verification and risk assessment: Add a logical verification function, such as the matching analysis of axle inspection information and issued vehicle types, to identify potential error risks.

[0088] User interaction optimization: Provide functions of "one-key audit" and picture viewing and downloading, which are convenient for manual review and subsequent processing.

[0089] In the specific implementation process, when the system of this solution is initialized, necessary ETC service data and transaction basic data are collected, including but not limited to user information, vehicle information, and transaction records;

[0090] Such as Figure 2As shown in the figure, through the efficient offline data synchronization tool DataX, key business data in other business databases is incrementally synchronized to the ods layer of the Hive database in the distributed file system based on HDFS at a fixed time every day. Through the scheduling tool dolphinschuler, the data is ETLed from the ods layer to the dwd layer. In this process, refined data governance is carried out to ensure data consistency and integrity. In the data governance process, technologies such as data cleaning, deduplication, and standardization are used to improve data quality. After the data is synchronized to the Hive database, using the Spark data analysis program, combined with SQL queries and data frameworks, different types of business order information are extracted from the order table in the Hive database by distinguishing order types. These information include the basic information of users, vehicle information, order status, and relevant metadata. In addition, the order data includes the vehicle driving license and vehicle exterior photos when handling. Through the OBU number in the order, the transaction records of this OBU number in the first-issue road network are deeply queried, and the vehicle photos at the time of the transaction are obtained using data stream processing technology. The pictures at the time of handling and the pictures at the time of the transaction provide support for subsequent ocr recognition and data verification after recognition and locating abnormal data. The analysis results are stored in the result table of the ads layer in the data modeling of the Hive, and the picture information is stored in the distributed picture storage system Minio. This process is fully automated and finally realizes visual analysis and intelligent decision support of data.

[0091] Specifically, the system architecture of this solution includes:

[0092] 1. High-performance data acquisition interface: Adopt advanced API gateway technologies such as Kong or Tyk to manage the interface calls with the ETC issuance system and transaction system to ensure real-time data acquisition and transmission security;

[0093] 2. Big data processing framework: Use stream processing frameworks such as Apache Kafka, Apache Storm, or Apache Flink to achieve high-throughput and low-latency data stream processing;

[0094] 3. Distributed file system: Utilize Hadoop HDFS or cloud storage solutions (such as Amazon S3, Google Cloud Storage) to store large-scale data sets;

[0095] 4. ETL tools: Adopt ETL tools such as Apache NiFi, Talend, or Informatica to perform data extraction, transformation, and loading operations;

[0096] 5. Containerization and orchestration: Use Docker containers and Kubernetes orchestration tools to achieve rapid deployment, expansion, and management of data acquisition services;

[0097] 6. Data Quality and Governance: Implement data quality checks, data cleaning, and governance strategies to ensure data accuracy and consistency;

[0098] 7. Data Security Technologies: Apply technologies such as data encryption, access control, and security tokens to protect data during transmission and storage;

[0099] 8. API Management: Use API gateways such as Kong or Tyk to manage API calls during the data collection process and ensure API security and availability;

[0100] 9. Data Monitoring and Logging: Utilize tools such as Prometheus and Grafana to monitor performance metrics and log information during the data collection process;

[0101] 10. Intelligent Data Parsing: Use natural language processing (NLP) and machine learning technologies to intelligently parse unstructured data and extract useful information.

[0102] The system of this solution includes a user module, and the user module includes:

[0103] Result Display: The user interface displays the comparison results, including the comparison situation of each element item and the overall matching score.

[0104] Abnormal Data Review: Users can review abnormal data, confirm whether it is a false alarm, and can adjust the comparison element items and weights.

[0105] The beneficial effects of this solution include:

[0106] 1. Reduce manual operations: By introducing automation technologies, reduce manual intervention and improve the efficiency of ETC issuance and transaction verification;

[0107] 2. Improve the accuracy of information verification: Establish a standardized automated verification process to ensure the accuracy of vehicle information and the consistency of transactions;

[0108] 3. Enhance the detection and prevention of abnormal transactions: Develop effective mechanisms to detect and prevent user fee evasion behavior and incorrect handling by business personnel;

[0109] 4. Improve data processing capabilities: Optimize the data processing process to improve the system's processing speed and real-time performance for a large amount of transaction data;

[0110] 5. Increase the degree of automation: By integrating OCR technology, this invention can automatically identify vehicle information, reduce the need for manual input, and thus reduce the error rate caused by manual operations.

[0111] 6. Comprehensive information comparison: The present invention is not limited to license plate number verification. Instead, it extracts more comprehensive vehicle information from lane pictures through OCR technology, including vehicle brand, color, etc., and conducts comprehensive comparison with transaction information and issued materials, significantly improving the accuracy of verification.

[0112] 7. Detection and prevention of abnormal transactions: Through an intelligent verification and risk assessment mechanism, the present invention can effectively identify and prevent users' fare evasion behaviors and incorrect handling by business personnel, reducing potential losses for enterprises.

[0113] 8. Data processing and feedback efficiency: The present invention optimizes the data processing process, can quickly process and feedback transaction verification results, improves the response speed of the system, and meets the requirements of rapidly growing data volume.

[0114] 9. Flexible comparison item configuration: The present invention allows users to customize the information element items and their weights participating in the comparison according to specific business requirements, providing a high degree of flexibility and adaptability. This user-driven configuration method enables the system to adapt to changing business scenarios and personalized verification needs.

[0115] 10. Advanced comparison algorithm: The present invention adopts an advanced comparison algorithm. This algorithm can not only handle complex data relationships but also dynamically adjust the comparison logic according to the weights defined by users, thereby providing more accurate matching results. The high efficiency of the algorithm ensures that the system can maintain high-performance comparison capabilities even when the data volume increases significantly.

[0116] An embodiment of the present invention also provides an ETC service abnormal behavior recognition system based on OCR recognition and information comparison. The system includes a computer device, the computer device includes a processor and a memory, computer instructions are stored in the memory, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0117] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps implemented by the aforementioned ETC service abnormal behavior recognition method based on OCR recognition and information comparison. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, floppy disk, hard disk, removable storage disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0118] Those of ordinary skill in the art should understand that the various exemplary components, systems, and methods described in connection with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Specifically, whether to implement in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted through a data signal carried in a carrier wave on a transmission medium or a communication link.

[0119] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present invention.

[0120] In the present invention, the features described and / or illustrated for one embodiment can be used in the same or a similar manner in one or more other embodiments, and / or combined with the features of other embodiments or replace the features of other embodiments.

[0121] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, various changes and variations can be made to the embodiments of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison, characterized in that: The steps of the method include: Enter the registered vehicle information of the vehicle, the registered vehicle information including license plate, color and model; During the vehicle transaction, the transaction is completed through the vehicle's OBU, the corresponding registered vehicle information is obtained, and the vehicle image of the vehicle is collected; acquiring actual vehicle information based on the vehicle image, and comparing the actual vehicle information with registered vehicle information; Determine whether it is an abnormal transaction based on the comparison results.

2. The method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison according to claim 1 is characterized in that: In the step of acquiring actual vehicle information based on the vehicle image, OCR technology is used to identify actual vehicle information in the vehicle image, and the actual vehicle information corresponds to the registered vehicle information, including license plate, color and vehicle model.

3. The method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison according to claim 1 is characterized in that: In the step of comparing the actual vehicle information with the registered vehicle information, the corresponding actual vehicle information items are compared with the registered vehicle information items item by item.

4. The method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison according to claim 3 is characterized in that: In the step of determining whether it is an abnormal transaction based on the comparison result, the comparison result between each corresponding actual vehicle information item and the registered vehicle information item is obtained to determine whether the determination of each item is passed. If the determination of all items is passed, it is determined to be a normal transaction; if the determination of any item is not passed, it is determined to be an abnormal transaction.

5. The method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison according to claim 4 is characterized in that: In the step of obtaining the comparison result of each corresponding actual vehicle information item with the registered vehicle information item to determine whether the determination of each item is passed: Encode each of the extracted actual vehicle information items, and calculate the similarity between the code corresponding to each of the actual vehicle information items and the code corresponding to the registered vehicle information item; Whether the item is passed or not is determined based on the similarity.

6. The method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison according to claim 1 is characterized in that: In the step of determining whether it is an abnormal transaction based on the comparison result, each of the extracted actual vehicle information items is encoded, and the similarity between the code corresponding to each actual vehicle information item and the code corresponding to the registered vehicle information item is calculated. A weighted calculation is performed based on the similarity of multiple items to determine whether it is an abnormal transaction.

7. The method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison according to any one of claims 1 to 6, characterized in that: In the step of using OCR technology to recognize the actual vehicle information in the vehicle image, the vehicle image is preprocessed, and the preprocessing process includes: Using filters to reduce image noise in vehicle images; Convert vehicle images to black and white; The Canny edge detector is used to determine the contours of objects in the image and locate the text area.

8. The method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison according to claim 7 is characterized in that: The steps of using OCR technology to identify the actual vehicle information in the vehicle image also include: For the preprocessed vehicle image, morphological operations are used to locate the license plate area, and color filtering is used to further limit the license plate area; And use the OCR engine to recognize the text in the license plate area.

9. The method for identifying abnormal behavior of ETC services based on OCR recognition and information comparison according to claim 1 is characterized in that: The steps of the method include: Based on the transaction data in the vehicle OBU, the corresponding data points of the calculated transaction data of each transaction are calculated, and the Z-Score statistical method is used to determine whether the transaction is an abnormal transaction.

10. An ETC business abnormal behavior identification system based on OCR recognition and information comparison, characterized in that: The system includes a computer device, which includes a processor and a memory. The memory stores computer instructions. The processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method as described in any one of claims 1 to 9.

Images