Big Data Comprehensive Analysis and Judgment System for Traffic Business Management

Through distributed data collection, dynamic rule loading and real-time risk identification technology, the problem of insufficient accuracy and timeliness of risk identification in the existing traffic management system is solved, and efficient risk analysis and timely warning in traffic business processes are achieved.

CN119989003BActive Publication Date: 2025-08-01HANGZHOU TRUSTWAY TECH
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510466129.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-04-15
Publication Date
2025-08-01
Estimated Expiration
2045-04-15

AI Technical Summary

Technical Problem

When facing massive traffic data and a rapidly changing traffic environment, the existing traffic management system is difficult to effectively identify potential risks, resulting in insufficient accuracy and timeliness of risk identification methods, and the inability to achieve real-time monitoring and timely early warning.

Method used

Distributed data acquisition technology is used to access multi-source big data streams in real time, generate standardized data streams and clean them; use dynamic rule loading technology to convert risk rules into executable models, and adjust the execution order and priority of rules through rule optimization algorithms; use rule matching technology to conduct real-time risk identification to generate risk identification result sets; use early warning trigger technology to generate and push risk warning signals.

Benefits of technology

It improves the accuracy and timeliness of risk identification in traffic business management, can quickly respond to potential risks, optimize traffic signal control and early warning information release, and ensure road safety and traffic efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119989003B_ABST
    Figure CN119989003B_ABST
Patent Text Reader

Abstract

The present invention discloses a comprehensive analysis and judgment system for big data in traffic service management. The system includes: an access module, which is used to access multi-source big data streams in real time according to traffic service requirements and generate a cleaned real-time data stream; a loading module, which is used to load risk rules into a rule engine, convert the risk rules into an executable rule model, and perform dynamic adjustment to generate an initialized rule engine; a matching module, which is used to perform real-time risk identification based on the real-time data stream and the rule engine, perform rule matching, and generate a risk identification result set based on the matching result; and an early warning module, which is used to trigger an early warning according to the risk identification result set and push the corresponding early warning information to users in real time, so as to realize the comprehensive analysis and judgment of big data in traffic service management. By using the embodiment of the present invention, the potential risks in the traffic service process can be effectively analyzed and judged, and the accuracy and timeliness of risk identification can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic management, and particularly relates to a comprehensive analysis and research and judgment system for big data of traffic business management. Background Art

[0002] With the rapid development of social economy and the acceleration of urbanization process, the demand for transportation is increasing day by day, and the complexity and diversity of traffic business management are also intensifying. The traditional traffic management mode usually relies on manual monitoring and regular data analysis, and cannot effectively cope with the increasing traffic data volume and the real-time changing traffic conditions. In the face of a large amount of traffic data, how to quickly and accurately identify risks and make responses has become an important challenge in traffic business management.

[0003] At present, big data technology has been introduced into the field of traffic management in order to improve the intelligent level of traffic management through the efficient processing and analysis of traffic data. Although there are already multiple traffic data analysis systems and management platforms widely used, they still have certain deficiencies in risk identification and early warning. For example, the existing risk identification methods often rely on static rule libraries and outdated risk assessment models, resulting in difficulty in effectively identifying potential risks in a rapidly changing traffic environment. In addition, the lack of the ability to dynamically load and optimize rules makes the existing systems slow to respond to complex and sudden traffic events, and it is difficult to achieve real-time monitoring and timely early warning. Summary of the Invention

[0004] The purpose of the present invention is to provide a comprehensive analysis and research and judgment system for big data of traffic business management to solve the deficiencies in the prior art, and be able to effectively analyze and research and judge potential risks in the traffic business process, and improve the accuracy and timeliness of risk identification.

[0005] An embodiment of the present application provides a comprehensive analysis and research and judgment system for big data of traffic business management, and the system includes:

[0006] An access module, which is used to, according to traffic business requirements, use distributed data acquisition technology to real-time access multi-source big data streams of traffic business management, generate standardized data streams, and generate cleaned real-time data streams based on the standardized data streams;

[0007] A loading module, which is used to, according to a risk rule library, use dynamic rule loading technology to load predefined risk rules into a rule engine, convert the risk rules into executable rule models, and based on the rule models, use a rule optimization algorithm to dynamically adjust the execution order and priority of the risk rules to generate an initialized rule engine;

[0008] A matching module, which is used to perform real-time risk identification based on the cleaned real-time data stream and the initialized rule engine by using rule matching technology, perform rule matching on each record in the data stream, calculate the risk score of each record based on the matching result, and generate a risk identification result set;

[0009] An early warning module, which is used to generate a risk early warning signal based on the risk identification result set by using early warning triggering technology, trigger an early warning for records whose risk scores exceed the preset threshold, and push the corresponding early warning information to users in real time to achieve comprehensive analysis and judgment of big data in traffic business management.

[0010] Another embodiment of the present application provides a method for comprehensive analysis and judgment of big data in traffic business management, and the method includes:

[0011] According to traffic business requirements, use distributed data acquisition technology to access multi-source big data streams of traffic business management in real time, generate a standardized data stream, and generate a cleaned real-time data stream based on the standardized data stream;

[0012] According to the risk rule library, use dynamic rule loading technology to load predefined risk rules into the rule engine, convert the risk rules into executable rule models, and based on the rule models, use rule optimization algorithms to dynamically adjust the execution order and priority of the risk rules to generate an initialized rule engine;

[0013] According to the cleaned real-time data stream and the initialized rule engine, use rule matching technology to perform real-time risk identification, perform rule matching on each record in the data stream, calculate the risk score of each record based on the matching result, and generate a risk identification result set;

[0014] According to the risk identification result set, use early warning triggering technology to generate a risk early warning signal, trigger an early warning for records whose risk scores exceed the preset threshold, and push the corresponding early warning information to users in real time to achieve comprehensive analysis and judgment of big data in traffic business management.

[0015] Optionally, the step of according to traffic business requirements, using distributed data acquisition technology to access multi-source big data streams of traffic business management in real time, generating a standardized data stream, and generating a cleaned real-time data stream based on the standardized data stream includes:

[0016] According to traffic business requirements, configure multi-source data access interfaces, perform parameter configuration and connection testing on the multi-source data access interfaces to generate an initialized data access status, where the multi-source data at least includes database log data, API interface data, message queue data, and sensor data;

[0017] According to the data access status after initialization, use stream computing technology to capture multi-source data streams in real time. Among them, through a distributed message queue and a data sharding mechanism, the multi-source data streams are sharded by time window or data volume to generate sharded data blocks, and each data block is marked with a data sharding identifier to generate a sharded identifier data set;

[0018] According to the sharded identifier data set, unify the formats of multi-source data. Among them, through data mapping technology and format conversion algorithms, the original data from different data sources is converted into a unified standardized format to generate a standardized data stream;

[0019] Based on the standardized data stream, use data cleaning algorithms to remove noise data and redundant information. Among them, through outlier detection technology and regular expression matching, identify and filter invalid data, duplicate data, and data with format errors to generate a cleaned real-time data stream.

[0020] Optionally, according to the risk rule library, use dynamic rule loading technology to load predefined risk rules into the rule engine, convert the risk rules into an executable rule model, and based on the rule model, use rule optimization algorithms to dynamically adjust the execution order and priority of the risk rules to generate an initialized rule engine, including:

[0021] According to the risk rule library, use rule parsing technology to parse the predefined risk rules. Among them, through syntax analysis technology and rule description languages, convert the rule text in the risk rule library into structured rule objects to generate a set of rule objects;

[0022] Based on the set of rule objects, use rule compilation technology to convert the rules into an executable rule model. Among them, through intermediate code generation technology and an optimization compiler, compile the rule objects into execution code to generate an executable rule model;

[0023] According to the executable rule model, use a rule caching mechanism to load the rules into the rule engine. Among them, through the LRU caching algorithm and distributed caching technology, cache the frequently used rules into the rule engine memory to generate a rule loading state with optimized caching;

[0024] Based on the rule loading state with optimized caching, use rule optimization algorithms to dynamically adjust the rule execution order. Among them, according to the historical execution frequency and business importance of the rules, calculate the priority weight of each rule to generate an adjusted rule execution order with priorities;

[0025] Configure the rule engine according to the execution order of the rules adjusted by priority. Among them, through the state management technology and the concurrency control mechanism, ensure that the rule engine supports dynamic rule updates and real-time adjustments while efficiently executing the rules, and generate an initialized rule engine;

[0026] Based on the initialized rule engine, verify the running state of the rule engine. Among them, through rule coverage analysis and execution log monitoring, ensure that all rules are correctly loaded and executed, and according to the verification results, use the feedback mechanism to dynamically correct the rule loading and running process, and generate the final initialized rule engine state.

[0027] Optionally, according to the cleaned real-time data stream and the initialized rule engine, use rule matching technology to perform real-time risk identification, perform rule matching on each record in the data stream, and based on the matching results, calculate the risk score of each record, and generate a risk identification result set, including:

[0028] According to the cleaned real-time data stream, perform secondary sharding on the data stream according to time window or data volume. Among them, through the hash sharding algorithm and the time window division mechanism, divide the data stream into multiple data shards, and allocate each data shard to different computing nodes to generate a sharding task set;

[0029] Based on the sharding task set and the initialized rule engine, use the multi-pattern matching algorithm to perform rule matching on each data shard. Among them, through the Aho-Corasick algorithm and parallel computing technology, perform rule matching tasks on multiple computing nodes simultaneously to generate a preliminary matching result set;

[0030] According to the preliminary matching result set, summarize the matching results of each computing node. Among them, through the reduction algorithm and the distributed aggregation technology, merge the scattered matching results into a global matching result set, and based on the global matching result set, calculate the risk score of each record. Among them, through the weighted summation algorithm and the risk level mapping, generate a risk score data set;

[0031] Based on the risk score data set, generate a risk identification result set. Among them, through the threshold judgment mechanism and the risk classification technology, mark the records with risk scores exceeding the preset threshold as high-risk, and generate the final risk identification result set.

[0032] Optionally, according to the risk identification result set, use the warning trigger technology to generate a risk warning signal, trigger a warning for the records with risk scores exceeding the preset threshold, and push the corresponding warning information to the user in real time to realize the comprehensive analysis and judgment of the big data of traffic business management, including:

[0033] According to the risk identification result set, filter the risk scores of each record. Among them, through a preset threshold and conditional judgment logic, filter out the records whose risk scores exceed the preset threshold, and generate a high-risk record set;

[0034] Based on the high-risk record set, create warning signals. Among them, through event-driven technology, convert each high-risk record into a warning event, generate corresponding warning signals, and use an event queue to sort the warning signals by priority to generate an ordered warning signal queue;

[0035] According to the ordered warning signal queue, convert the warning signals into standardized warning messages. Among them, through a template engine and dynamic data filling technology, fill the key information in the warning signals into the warning template to generate formatted warning messages;

[0036] Based on the formatted warning messages, through multi-channel distribution technology and priority scheduling algorithms, determine the notification channels and push strategies according to user preferences and the urgency of the warnings, and generate real-time push tasks to push the warning messages to relevant users.

[0037] Another embodiment of the present application provides a storage medium in which a computer program is stored. Among them, the computer program is set to execute the method described in any one of the above when running.

[0038] Another embodiment of the present application provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is set to run the computer program to execute the method described in any one of the above.

[0039] Compared with the prior art, a traffic business management big data comprehensive analysis and research and judgment system provided by the present invention includes an access module for real-time accessing multi-source big data streams according to traffic business requirements and generating a cleaned real-time data stream; a loading module for loading risk rules into a rule engine, converting the risk rules into an executable rule model, and dynamically adjusting to generate an initialized rule engine; a matching module for performing real-time risk identification according to the real-time data stream and the rule engine, performing rule matching, and generating a risk identification result set based on the matching result; and a warning module for triggering a warning according to the risk identification result set and pushing the corresponding warning information to users in real time, realizing the comprehensive analysis and research and judgment of traffic business management big data, so as to effectively analyze and research and judge potential risks in the traffic business process and improve the accuracy and timeliness of risk identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic structural diagram of a traffic business management big data comprehensive analysis and research and judgment system provided by an embodiment of the present invention;

[0041] Figure 2 The hardware structure block diagram of a computer terminal for a comprehensive analysis and research method of big data for traffic business management provided by an embodiment of the present invention;

[0042] Figure 3 The flow schematic diagram of a comprehensive analysis and research method of big data for traffic business management provided by an embodiment of the present invention. Specific embodiments

[0043] The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0044] An embodiment of the present invention first provides a comprehensive analysis and research system for big data for traffic business management. Refer to Figure 1 , the system may include:

[0045] An access module 101, configured to, according to traffic service requirements, use distributed data acquisition technology to access multi-source big data streams of traffic business management in real time, generate a standardized data stream, and generate a cleaned real-time data stream based on the standardized data stream;

[0046] A loading module 102, configured to, according to a risk rule library, use dynamic rule loading technology to load predefined risk rules into a rule engine, convert the risk rules into an executable rule model, and dynamically adjust the execution order and priority of the risk rules based on the rule model by using a rule optimization algorithm to generate an initialized rule engine;

[0047] A matching module 103, configured to perform real-time risk identification by using rule matching technology according to the cleaned real-time data stream and the initialized rule engine, perform rule matching on each record in the data stream, and calculate the risk score of each record based on the matching result to generate a risk identification result set;

[0048] An early warning module 104, configured to generate a risk early warning signal by using early warning trigger technology according to the risk identification result set, trigger an early warning for records with a risk score exceeding a preset threshold, and push the corresponding early warning information to a user in real time to implement comprehensive analysis and research of big data for traffic business management.

[0049] It can be seen that, according to the traffic service requirements, a multi-source big data stream for traffic service management is accessed in real time to generate a standardized data stream, and based on the standardized data stream, a cleaned real-time data stream is generated; according to the risk rule library, predefined risk rules are loaded into the rule engine, the risk rules are converted into an executable rule model, and based on the rule model, an initialized rule engine is generated; according to the real-time data stream and the rule engine, real-time risk identification is performed, rule matching is carried out for each record in the data stream, and based on the matching result, the risk score of each record is calculated to generate a risk identification result set; according to the risk identification result set, a risk warning signal is generated by using the warning trigger technology, and the corresponding warning information is pushed to the user in real time, so as to realize the comprehensive analysis and judgment of the big data of traffic service management, thereby being able to effectively analyze and judge the potential risks in the traffic service process and improve the accuracy and timeliness of risk identification. For the detailed explanation of the content steps of each module, see a method for comprehensive analysis and judgment of traffic service management big data described below.

[0050] Correspondingly, another embodiment of the present invention provides a method for comprehensive analysis and judgment of traffic service management big data, and this method can be applied to an electronic device, such as a computer terminal, specifically, such as an ordinary computer, etc.

[0051] The following takes running on a computer terminal as an example to explain it in detail. Figure 2 It is a hardware structure block diagram of a computer terminal for a method for comprehensive analysis and judgment of traffic service management big data provided by an embodiment of the present invention. As Figure 2 shown, this computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the memory can include a non-volatile storage medium and an internal memory.

[0052] The non-volatile storage medium can store an operating system and a computer program. This computer program includes program instructions, and when the program instructions are executed, the processor can execute any method for comprehensive analysis and judgment of traffic service management big data.

[0053] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0054] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When this computer program is executed by the processor, the processor can execute any method for comprehensive analysis and judgment of traffic service management big data.

[0055] This network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 2The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0056] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0057] See Figure 3 , an embodiment of the present invention provides a comprehensive analysis and judgment method for big data of traffic service management, which may include the following steps:

[0058] S301, according to traffic service requirements, use distributed data acquisition technology to real-time access multi-source big data streams of traffic service management, generate a standardized data stream, and based on the standardized data stream, generate a cleaned real-time data stream;

[0059] In the first step of this method, according to traffic service requirements, use distributed data acquisition technology to real-time access multi-source big data streams from multiple traffic-related sources. Specifically, this data includes real-time traffic flow information collected by road sensors, vehicle position and speed data provided by the GPS system, status information of traffic lights, and image data from surveillance cameras, etc. This data comes from different traffic management systems and devices, and has diversity and real-time nature. By standardizing this heterogeneous data, the system can ensure the consistency of various data in format and representation, thus generating a standardized data stream. Based on the standardized data stream, use data cleaning technology to denoise, correct, and format the data, eliminate redundant and error information, and generate a high-quality cleaned real-time data stream. This process not only improves the usability and readability of the data, but also provides a solid foundation for the subsequent risk identification link, ensuring the accuracy and reliability of the analysis results.

[0060] This step is of profound significance for traffic business management. First of all, by accessing traffic big data in real time, the system can obtain instant traffic flow, speed, accident, and signal status information, which provides the necessary basic data support for traffic dispatching, traffic flow management, and emergency response. Secondly, the standardized and cleansed data stream can effectively reduce the analysis errors caused by data quality problems, ensuring that the decisions in the risk identification process are based on accurate information. This high-quality data processing improves the real-time monitoring ability of traffic congestion, accident risks, and abnormal behaviors, helps traffic management departments respond quickly, optimize traffic signal control, dispatch vehicles, and issue warning information, thus ensuring road safety and improving traffic efficiency. Through these means, the traffic management system can better cope with various challenges in a dynamic environment and achieve more intelligent and efficient traffic management.

[0061] Specifically, according to traffic business requirements, multi-source data access interfaces can be configured, parameter configuration and connection tests are performed on the multi-source data access interfaces, and an initialized data access status is generated. Among them, the multi-source data at least includes database log data, API interface data, message queue data, and sensor data;

[0062] In this stage, first, according to specific traffic business requirements, determine the types of data sources to be accessed and design access interfaces. This includes being able to access log data in the database, call API interfaces to obtain real-time data, read asynchronous messages from message queues, and collect sensor data. The access interfaces are set through parameter configuration, including connection strings, access permissions, etc., and connection tests are performed to ensure that data can be successfully read.

[0063] This step ensures that the data acquisition system can reliably access multiple data sources, laying a foundation for the subsequent real-time capture of data streams. In addition, connection tests can promptly detect and solve problems in interface configuration, avoiding data loss or errors in subsequent processes.

[0064] When starting to configure multi-source data access interfaces, first, it is necessary to communicate with the traffic management department to clarify the required data sources and data types. For example, a traffic flow management system may need to access road sensor data (sensor data), traffic signal status (API interface data), vehicle GPS data (message queue data), and traffic accident records (database log data). Then, the development team designs data access interfaces according to these requirements and uses appropriate database driver programs or API request libraries to implement connections with each data source.

[0065] Next, parameter configuration is carried out. For database log data, engineers need to set the database connection string, including information such as host address, port, database name, username, and password, and implement dynamic reading of these parameters in the code. When configuring the API interface, the URL of the API, request method (such as GET or POST), request header information, and required parameters need to be defined. In addition, to improve the security of the interface, an authentication mechanism such as OAuth or API key may also need to be configured. After the configuration is completed, the system will attempt to connect to all data sources to ensure that the connection parameters are valid.

[0066] Finally, connection testing is a crucial step. By writing connection test code, the system will attempt to connect to each data source and obtain some test data to verify the effectiveness of the interface. After a successful connection, the system will record the connection status and generate an initialized data access status report, indicating which data sources are connected successfully, which ones fail, and the reasons for the failures, so that engineers can quickly locate problems and make adjustments.

[0067] According to the initialized data access status, use streaming computing technology to capture multi-source data streams in real time. Among them, through the distributed message queue and data sharding mechanism, the multi-source data streams are sharded by time window or data volume to generate sharded data blocks, and each data block is marked with a data sharding identifier to generate a sharded identifier data set;

[0068] In this stage, the system uses streaming computing technology to capture the data streams transmitted by each data source in real time. By using a distributed message queue (such as Kafka) and a data sharding mechanism, the received data streams are sharded according to a preset time window or data volume. Each generated data block will be marked with a unique sharding identifier for subsequent tracking and processing, and at the same time, a complete sharded identifier data set is formed.

[0069] This process enables data to be processed and analyzed efficiently. By sharding the data stream, not only can data be processed in parallel, but also the processing capacity of the system can be improved under high load conditions, avoiding performance bottlenecks and ensuring data real-time.

[0070] After confirming the data access status, the system will start capturing multi-source data streams in real time through streaming computing technology. Using a distributed message queue such as Apache Kafka or RabbitMQ, the system can asynchronously read data streams from each data source. During this process, the system will create multiple consumer instances to listen to the message topics or queues of each data source respectively to achieve parallel processing of data streams.

[0071] After the data is captured, the system will fragment the received data according to a preset time window (e.g., every 10 seconds) or data volume (e.g., every 1000 records). Through time window processing, the system can aggregate the data generated in each time period into a data block, and through data volume control, it can ensure that each data block is not too large for subsequent processing. For example, if 1500 pieces of data are collected in each 10-second window, these data will be divided into two data blocks, namely the first 1000 and the last 500.

[0072] Each generated data block will be assigned a unique shard identifier, usually composed of the access timestamp and sequence number, so that it can be easily traced and managed during subsequent processing. At the same time, the system aggregates all the sharded data blocks to form a complete shard identifier data set, which lays the foundation for subsequent format unification and cleaning processes.

[0073] According to the shard identifier data set, the multi-source data is unified in format. Among them, through data mapping technology and format conversion algorithms, the original data from different data sources is converted into a unified standardized format to generate a standardized data stream;

[0074] In this step, the original data received from different data sources is unified in format. Through data mapping technology and format conversion algorithms, the data from different sources (such as JSON, XML, CSV, etc.) is converted into a unified standardized structure, which will make subsequent processing more convenient and efficient, thus generating a standardized data stream for further analysis.

[0075] The unification of data format lays the foundation for further data cleaning and analysis, and can effectively avoid errors caused by inconsistent data formats. In addition, the standardized data stream can improve data processing efficiency and simplify the rule application and risk identification processes.

[0076] At this stage, the system will unify the format of the original data received from different data sources. To achieve this goal, using data mapping technology, it is first necessary to define a standard data model, usually based on the data requirements determined by the team during the previous analysis process. The standard model includes necessary field names, data types, and constraint conditions, which enables the subsequent data mapping process to be executed efficiently.

[0077] Taking JSON format as an example, assuming the field name in road sensor data is "sensor_id" and the field name in traffic signal status data is "signal_id", the system unifies these two fields into "device_id". During the data conversion process, the system traverses each record and maps and converts fields from different sources according to predefined rules. At the same time, for unstructured data such as text data, the system may need to use regular expressions or text parsing algorithms to extract and standardize it into a structured format for subsequent processing.

[0078] After data mapping and format conversion, the system will generate standardized data streams. These data streams not only have a consistent format but also facilitate subsequent data cleaning and analysis. The output of the standardized data streams will provide a basis for various data processing and analysis, which is crucial for ensuring the accuracy, authenticity, and effectiveness of risk identification.

[0079] Based on the standardized data streams, data cleaning algorithms are used to remove noise data and redundant information. Among them, through outlier detection techniques and regular expression matching, invalid data, duplicate data, and data with incorrect formats are identified and filtered to generate cleaned real-time data streams.

[0080] At this stage, the system uses data cleaning algorithms to identify and remove noise and redundant information in the standardized data streams. The data is analyzed through outlier detection techniques, and regular expression matching is used to filter out records and duplicate data that do not conform to the format to ensure the data quality of the finally generated real-time data streams. Data cleaning is a key link in improving data quality. Removing invalid information, duplicate records, and format errors in the data not only improves the accuracy of the data but also provides a reliable basis for subsequent risk identification, ensuring the credibility and effectiveness of the results.

[0081] After generating the standardized data streams, data cleaning is carried out next. The data cleaning algorithm first performs noise detection on the standardized data streams. This process is usually achieved through outlier detection techniques. For example, the Z-score method or the IQR method is used to identify and remove outliers to ensure the true reliability of the data. For example, if a record in traffic flow data shows that the traffic volume of a certain section is 100,000 vehicles per hour, while the normal range is between 1,000 and 10,000 vehicles, the system will mark this record as an outlier and filter it.

[0082] In addition to outlier deletion, the system also applies regular expression matching technology to identify records with incorrect data formats. Suppose a certain field should be in date format (such as YYYY-MM-DD). Through regular expressions, the system can quickly locate records that do not conform to this format and further correct or delete them. At the same time, to avoid data redundancy, the system will detect duplicate records in the data stream, usually by maintaining a hash table to store the unique identifiers of all processed records to ensure that they are not processed repeatedly.

[0083] Finally, through the above steps, the system will only retain valid and clean records, generating a cleaned real-time data stream. This data stream will provide a stable and reliable basis for subsequent risk identification and early warning, not only improving the data quality but also enhancing the efficiency and accuracy of subsequent processing.

[0084] S302. According to the risk rule library, use the dynamic rule loading technology to load the predefined risk rules into the rule engine, convert the risk rules into executable rule models, and based on the rule models, use the rule optimization algorithm to dynamically adjust the execution order and priority of the risk rules to generate an initialized rule engine;

[0085] According to the risk rule library, use the dynamic rule loading technology to load the predefined risk rules into the rule engine. This process involves the parsing, conversion, and optimization of risk rules. First, the system extracts relevant risk rules from the rule library storing the risk rules and loads them into the rule engine through the dynamic rule loading technology. Then, the system converts the extracted risk rules into executable rule models to make them suitable for the execution environment of the rule engine. Next, based on the generated rule models, the rule optimization algorithm dynamically adjusts the execution order and priority of the risk rules, comprehensively considering the historical execution frequency, business importance, and its impact on system performance, and finally forms an initialized rule engine, enabling the risk rules to be executed efficiently and precisely.

[0086] The core significance of this step is to ensure that the risk rules in the rule engine can flexibly adapt to the changing traffic business requirements and environmental conditions. Through dynamic loading and optimization, the rule engine can update the risk rules in real time to ensure that the identification and response to potential risks can maintain high efficiency and accuracy. This not only improves the flexibility and intelligence level of risk management but also provides a solid technical foundation for subsequent risk identification and early warning.

[0087] Specifically, according to the risk rule library, use the rule parsing technology to parse the predefined risk rules. Among them, through the syntax analysis technology and the rule description language, convert the rule text in the risk rule library into structured rule objects to generate a set of rule objects;

[0088] At this stage, the system first extracts predefined risk rules from the rule base. These rules are usually stored in a specific text format, such as XML or JSON. Using rule parsing technology, the system performs syntax analysis on this text and converts it into structured rule objects. The core of syntax analysis lies in using a parser to analyze the structure of each component in the text, ensuring that the logical relationships and conditional expressions of each rule are clear and usable.

[0089] For example, assume there is a rule in the rule base: "If the traffic flow on a certain section exceeds 5000 vehicles per hour and the vehicle speed is lower than 20 kilometers per hour, then it is marked as a high risk of congestion." The system will parse this rule, identify the conditions (traffic flow and vehicle speed) and their corresponding logical relationships. After successful parsing, the system will generate structured rule objects, such as an object containing attributes like "conditions", "actions", and "priorities", and organize these objects into a set of rule objects for subsequent processing.

[0090] This set of rule objects not only improves the readability and maintainability of the rules but also lays the foundation for subsequent rule compilation and execution, enabling the rule engine to process and apply these rules in a more efficient manner.

[0091] Based on the set of rule objects, use rule compilation technology to convert the rules into an executable rule model. Among them, through intermediate code generation technology and an optimization compiler, the rule objects are compiled into executable code to generate an executable rule model;

[0092] After the set of rule objects is generated, the system will use rule compilation technology to convert these rule objects into an executable rule model. First, the system will use intermediate code generation technology to convert the structured rule objects into an intermediate representation form. This form usually does not depend on a specific programming language, making the subsequent compilation process more flexible.

[0093] For example, assume a rule object contains a "conditions" part and an "actions" part. After intermediate code generation, the system may generate a form similar to pseudocode: "IF (traffic flow > 5000) AND (vehicle speed < 20) THEN mark as a high risk of congestion." Next, the rule optimization compiler will further analyze and optimize based on this intermediate code and convert it into an executable rule model, usually expressed in a specific machine instruction or high-level language form, to prepare for the subsequent execution of the rule engine.

[0094] This conversion process can not only improve the execution efficiency but also optimize during the execution of the rules, such as by eliminating redundant conditions or simplifying logical judgments, thereby improving the overall performance and response speed of the system, which is particularly important for a real-time risk warning system.

[0095] According to the executable rule model, the rules are loaded into the rule engine using a rule caching mechanism. Among them, through the LRU caching algorithm and distributed caching technology, the frequently used rules are cached into the rule engine memory to generate an optimized rule loading state for caching.

[0096] After the executable rule model is generated, the system loads these rules into the rule engine through the rule caching mechanism. To ensure fast access to frequently used rules, the system uses the LRU (Least Recently Used) caching algorithm to save these rules in memory. The LRU algorithm periodically checks the recent usage records and evicts the rules that have not been used for a long time from the cache to make room for newly loaded rules.

[0097] For example, if a specific risk rule has been called multiple times in the past hour, while another rule has hardly been used during the same period, the system will choose to keep the former in the cache and remove the latter. In this way, the system can reduce the latency in the rule matching process and improve the response speed of the rule engine. In addition, distributed caching technology can be used to achieve cross-node loading and sharing of rules, enabling different rule engine instances to quickly access the same set of rules in a distributed environment and ensuring the high availability of the rules.

[0098] With this optimized rule loading state, the rule engine can execute the rules quickly and effectively, significantly improving the system's performance in complex and large-scale environments to adapt to the growing traffic business needs and risk management challenges.

[0099] Based on the optimized rule loading state for caching, a rule optimization algorithm is used to dynamically adjust the rule execution order. Among them, according to the historical execution frequency and business importance of the rules, the priority weight of each rule is calculated to generate an adjusted rule execution order for priorities.

[0100] Based on the existing optimized state for caching, the system will apply a rule optimization algorithm to dynamically adjust the rule execution order. By analyzing the historical execution frequency, the system can identify which rules have been frequently triggered in the past execution and which have been used less. The results of this analysis will help the system calculate the priority weight of each rule to ensure that more important or more frequently used rules can be executed first.

[0101] For example, assume that Rule A has been triggered 90 times in the past 100 executions, while Rule B has only been triggered 10 times. In this case, the priority weight of Rule A will be significantly higher than that of Rule B. The system will then place Rule A at the front of the execution sequence to ensure that important rules can be processed promptly during risk identification. Additionally, business importance is also a consideration. For example, rules in certain high-risk areas will be assigned higher weights to ensure they are given priority even in resource-constrained situations.

[0102] Through this dynamic adjustment mechanism, the rule engine can continuously optimize its rule execution process at runtime to adapt to changing business scenarios and risk environments, enhancing the flexibility and real-time response capabilities of the system.

[0103] Configure the rule engine according to the adjusted rule execution order based on priorities. Among them, through state management technology and concurrency control mechanisms, ensure that while the rule engine efficiently executes rules, it supports dynamic rule updates and real-time adjustments to generate an initialized rule engine.

[0104] After the priority adjustment is completed, the system will rely on state management technology and concurrency control mechanisms to perform the final configuration of the rule engine. State management technology will help the system track the execution status of each rule in real time during the operation of the rule engine, including information such as successful execution, failure, and discard. This information can help administrators evaluate and optimize the execution effect of the rules.

[0105] For example, when an exception occurs during the execution of a rule, the system can immediately record this status and may trigger an alarm or perform automated adjustments. The concurrency control mechanism ensures that in a multi-threaded or multi-process environment, the rule engine can efficiently and securely handle multiple requests, avoiding data conflicts and resource contention, thus guaranteeing the accurate execution of rules and data consistency.

[0106] Through these configurations, the finally generated initialized rule engine will have high flexibility and scalability, capable of supporting dynamic rule updates and real-time adjustments during operation. This ability enables enterprises to quickly respond to new risk challenges, maintain accurate control over the risk environment, and thus gain a competitive advantage in the complex market environment.

[0107] Based on the initialized rule engine, verify the running state of the rule engine. Among them, through rule coverage analysis and execution log monitoring, ensure that all rules are correctly loaded and executed, and according to the verification results, use the feedback mechanism to dynamically correct the rule loading and running processes to generate the final initialized rule engine state.

[0108] After the rule engine initialization is completed, its running status must be verified to ensure that all loaded rules can be executed correctly. This process is achieved through rule coverage analysis and execution log monitoring. Rule coverage analysis will evaluate whether all predefined risk rules are applied in actual operation, while execution log monitoring tracks the execution of each rule, including the number of executions, execution results, and possible error messages. Through comprehensive analysis of this information, the system can identify rules that are not triggered or executed improperly. According to the verification results, using the feedback mechanism to dynamically correct the rule loading and running processes, the system can update and optimize the rule loading strategy in a timely manner to ensure that the final generated rule engine state is efficient and accurate.

[0109] The significance of this step is to ensure the reliability and accuracy of the risk identification system. By verifying the actual running status of the rule engine, problems in rule loading and abnormalities in the execution process can be discovered in a timely manner, avoiding potential risks not being captured or false alarms being triggered. This process not only helps to improve the overall system performance but also enhances users' trust in the risk warning results, ensuring that in actual applications, the system can respond to various risk scenarios in an efficient and accurate manner, thereby effectively reducing the risk losses in business operations.

[0110] First, the system will deploy automated monitoring tools to collect the execution logs of the rule engine in real time. The execution logs record the execution status of each rule, including information such as whether it is triggered, triggering conditions, execution time, and execution results. For example, if a rule is set to detect sections with high vehicle flow and this rule never appears in the logs, it indicates that the rule has not been triggered in the actual data.

[0111] While collecting the execution logs, the system will conduct rule coverage analysis. This analysis will compare the loaded rules with the risk scenarios involved in the actual transaction data to evaluate which rules are not effectively triggered. If it is found that some key rules are never triggered, the system will actively generate an alarm and extract relevant running data for analysis.

[0112] Then, based on the results of the coverage analysis and execution log monitoring, the system will introduce a feedback mechanism to dynamically correct the rule loading and running processes. For example, for rules that are not triggered, the system may adjust their parameters or re-evaluate their importance and priority to ensure that future data flows can effectively activate these rules. In addition, the system can also update the risk rule library regularly, adding new rules or modifying existing rules to adapt to the changing risk environment.

[0113] Finally, through continuous analysis and adjustment, the system will generate an optimized state of the rule engine, ensuring that it not only maintains high efficiency in practical applications but also accurately identifies and responds to diverse risk scenarios. Such a dynamic correction mechanism ensures the long-term reliability and sustainability of the system.

[0114] S303. Based on the cleaned real-time data stream and the initialized rule engine, use rule matching technology for real-time risk identification. Perform rule matching on each record in the data stream, and based on the matching results, calculate the risk score for each record and generate a risk identification result set.

[0115] In this step, the system uses the cleaned real-time data stream and the initialized rule engine to perform real-time risk identification on each record in the data stream through rule matching technology. This process first involves matching each record in the cleaned data stream with predefined risk rules one by one. The rule engine will evaluate the characteristics and attributes of each record according to the set risk rules and identify potential risks. For example, if the traffic volume on a certain section of a traffic flow record exceeds the set threshold, the rule engine will regard this record as a high-risk section and calculate its risk score. The risk score calculation for each record combines multiple factors, such as traffic volume, vehicle speed, and historical accident rate of the section.

[0116] The implementation of this step greatly improves the efficiency and accuracy of real-time risk identification. By dynamically matching the cleaned real-time data stream with the risk rules in the rule engine, the system can quickly respond to potential risks and generate corresponding risk identification result sets based on specific matching results. This mechanism can not only effectively prevent traffic congestion and accidents but also provide basic data support for subsequent risk assessment and warning triggering, thus optimizing the overall risk management process.

[0117] Specifically, according to the cleaned real-time data stream, the data stream can be secondarily fragmented according to time windows or data volume. Among them, through the hash fragmentation algorithm and the time window division mechanism, the data stream is divided into multiple data fragments, and each data fragment is assigned to different computing nodes to generate a set of fragmentation tasks.

[0118] In this step, the cleaned real-time data stream needs to be secondarily fragmented for subsequent parallel processing. By setting time windows or data volume thresholds, the data stream is effectively divided into multiple smaller data fragments. The application of the hash fragmentation algorithm can ensure that the data is evenly distributed to different computing nodes, which can improve the parallelism and efficiency of processing. Each fragment will be marked for tracking and will ultimately form a set of fragmentation tasks, ready to be distributed to each computing node for subsequent processing.

[0119] This fragmentation process aims to improve the computational efficiency and processing power of the system, enabling the real-time data stream to utilize the advantages of distributed computing during rule matching and quickly respond to potential risk events. Additionally, data fragmentation helps with load balancing, avoiding performance bottlenecks caused by a single node processing excessive data, thus ensuring the stability and efficiency of the entire system.

[0120] In this step, the system first needs to set a time window and data threshold to perform secondary fragmentation on the cleaned real-time data stream. For example, assuming the cleaned data stream adds 10,000 records per minute, the system can set each fragment to contain 500 records, or the time window for each fragment to be 1 minute. Then, the system processes this data through a hash fragmentation algorithm to ensure even distribution of the data. Assuming the unique identifier of a record is ID, by performing a hash operation on ID, it can be determined which fragment this record will be assigned to, effectively avoiding data skew.

[0121] After fragmentation, the system will generate multiple data fragments, and each data fragment will be marked with a unique identifier for convenient subsequent processing. For example, fragment 1 may contain data with record IDs from 1 to 500, and fragment 2 may contain data with record IDs from 501 to 1000. These fragments are then distributed to different computing nodes for parallel processing. Through such a mechanism, the system can improve computational efficiency while ensuring data integrity, thus achieving real-time risk identification.

[0122] In addition, the system will also monitor and record the processing status of each data fragment. By constructing a status management module, the system can track the processing progress of each fragment in real time to ensure no omissions or delays occur. For example, if an exception occurs when computing node 1 is processing fragment 1, the system will immediately detect it and reassign the task of fragment 1 to other normally operating nodes to ensure the stable processing and real-time response of the entire data stream.

[0123] Based on the fragmentation task set and the initialized rule engine, use the multi-pattern matching algorithm to perform rule matching on each data fragment. Among them, through the Aho-Corasick algorithm and parallel computing technology, the rule matching tasks are executed simultaneously on multiple computing nodes to generate a preliminary matching result set;

[0124] Using the prepared fragmentation task set and the initialized rule engine, the system applies the multi-pattern matching algorithm to each data fragment for rule matching. Effective string matching algorithms such as the Aho-Corasick algorithm can find multiple patterns in multiple texts simultaneously, making the risk identification process more efficient. By executing the matching tasks in parallel on multiple computing nodes, the processing speed can be significantly improved to achieve real-time risk identification.

[0125] The implementation of this step can ensure that the system can quickly and effectively identify potential risk events. The combination of multi-mode matching and parallel computing not only improves the efficiency of rule matching but also allows the system to maintain real-time performance when facing large-scale data streams, ensuring timely response to risks.

[0126] In this step, the system docks each data shard with the initialized rule engine for rule matching. First, the system loads predefined risk rules on each computing node. These rules can be descriptions of various risk scenarios such as abnormal traffic flow patterns and frequently accident-prone road sections. By using the Aho-Corasick algorithm to compile multiple rules into an automaton at once, the system can quickly find records that match multiple rules when processing data shards. For example, assume there is a rule for records of traffic flow exceeding 5,000 vehicles per hour on a certain road section and another rule for records of vehicle speed below 20 kilometers per hour on a certain road section. The Aho-Corasick algorithm can identify these records simultaneously, greatly improving the matching efficiency.

[0127] During the data matching process, the system uses parallel computing technology to distribute data shards to different computing nodes for processing. In this way, even if the data volume is extremely large, each computing node can efficiently execute the matching task simultaneously. Each node independently performs rule matching on its own data shard and generates a preliminary matching result set. These result sets will include all the matched high-risk records and their relevant information, such as the matched rule ID and the specific data information of the records.

[0128] Finally, the system will aggregate the matching results of each node to form a preliminary complete matching result set. During this process, the system will also evaluate the processing performance of each node for subsequent resource allocation and optimization. If it is found that there is a bottleneck in the processing of a certain node, then increasing computing resources can be considered to improve its performance and ensure the real-time performance and accuracy of the overall risk control system.

[0129] According to the preliminary matching result set, the matching results of each computing node are aggregated. Among them, through the reduction algorithm and distributed aggregation technology, the scattered matching results are merged into a global matching result set, and based on the global matching result set, the risk score of each record is calculated. Among them, through the weighted summation algorithm and risk level mapping, a risk score data set is generated;

[0130] In this step, the preliminary matching result sets returned by each computing node will be aggregated through a reduction algorithm and distributed aggregation technology. The reduction algorithm merges the returned results to form a unified global matching result set. Then, based on the global matching result set, the system calculates the risk score for each record, integrates the impacts of various risk factors through a weighted summation algorithm, and performs risk level mapping to finally generate a risk score data set. The significance of this process is that it ensures that risk identification is not one-dimensional but comprehensive, incorporating multiple risk factors to form a comprehensive assessment. By calculating the risk score for each record, the system can provide more accurate information support for real-time risk decision-making, thus effectively enhancing the reliability of the risk warning system.

[0131] In this step, the system first needs to aggregate the preliminary matching result sets returned by each computing node to form a unified global matching result set. The system will apply a reduction algorithm, which is an effective method for merging distributed computing results. During this process, the system merges the matching results based on the record ID, that is, merges the same records returned by all computing nodes to ensure that each record has only one entry in the global matching result set. For example, if both Node 1 and Node 2 detect the same high-risk transaction record, only one merged record will be retained in the end.

[0132] After completing the aggregation, the system then needs to calculate the risk score for each record. This risk score will be comprehensively evaluated based on multiple factors, such as traffic flow, vehicle speed, and historical accident rate of the road section. The system will use a weighted summation algorithm to weight each risk factor and assign different weight values according to business rules to obtain the final risk score. For example, in a traffic flow record, if the traffic flow accounts for 70% of the weight and the vehicle speed accounts for 30% of the weight, the system will calculate based on these weights to finally obtain a specific risk value.

[0133] Through risk level mapping, the system can convert the risk score into the corresponding risk level. For example, it is set that a risk score greater than 100 is high risk, 50 to 100 is medium risk, and less than 50 is low risk. Such classification can help the subsequent warning system more quickly identify high-risk records and perform corresponding processing. Therefore, through this process, the system can effectively provide quantitative data support for subsequent decision-making and risk management.

[0134] Based on the risk score data set, a risk identification result set is generated. Among them, through a threshold judgment mechanism and risk classification technology, the records with risk scores exceeding the preset threshold are marked as high risk to generate the final risk identification result set.

[0135] In this step, the system will use the risk score dataset to generate a risk identification result set. By using a threshold judgment mechanism, the system will check whether the risk score of each record exceeds a preset threshold. If it exceeds, the record will be marked as high risk. In addition, the system will also adopt risk classification techniques to classify risks according to different traffic business requirements and generate a final risk identification result set. The implementation of this method can timely and effectively identify high-risk records and provide basic data for subsequent risk control and response measures. Through clear risk classification, decision-makers can quickly focus on high-risk data that may affect system security, thereby improving the efficiency of overall risk management.

[0136] In this step, the system will use the risk score dataset to generate a final risk identification result set. First, the system needs to set one or more preset risk thresholds. For example, set the threshold to 80. If the risk score of a certain record exceeds 80, the record will be marked as high risk. The setting of this threshold can be adjusted according to past historical data analysis and statistical results to ensure that possible risks can be effectively identified.

[0137] Next, the system uses the threshold judgment mechanism to check each record in the risk score dataset one by one. This process will involve simple conditional judgment logic to compare the risk score of each record with the preset threshold. Records that meet the conditions will be marked as "high risk". For example, if the risk score of a certain traffic flow record is 90, the system will mark it as high risk and record it in the risk identification result set.

[0138] Through risk classification techniques, the system will further classify high-risk records. For example, high-risk records can be classified into categories such as "sections with high traffic flow" and "sections with low vehicle speed". Different categories of risk records may require different processing strategies. Finally, the system will generate a result set containing all high-risk records and pass this result set to the subsequent early warning trigger and notification module to quickly respond to potential risk problems. This mechanism not only improves the accuracy of risk identification but also provides effective support for subsequent early warning and processing.

[0139] S304. According to the risk identification result set, use early warning trigger technology to generate risk warning signals, trigger early warnings for records whose risk scores exceed the preset threshold, and push the corresponding warning information to users in real time to achieve comprehensive analysis and judgment of big data in traffic business management.

[0140] This step mainly involves the whole process of generating risk warning signals based on the risk identification result set. First, the system analyzes the risk scores of each record and compares them with the preset risk thresholds to screen out those records whose risk scores exceed the thresholds. This screening process uses conditional judgment logic, enabling the system to quickly identify high-risk behaviors that truly require attention. Then, the system uses warning trigger technology to mark and process these high-risk records, generating corresponding risk warning signals. The warning signals will contain detailed information, such as the specific location of high-risk sections, traffic flow, vehicle speed, and relevant accident information. Finally, these warning signals will be pushed to relevant users in real time to ensure that risk information can be transmitted in a timely manner.

[0141] The implementation of this step greatly enhances the real-time response ability of the system, enabling the traffic management department to immediately respond to potential risk events. This efficient warning mechanism ensures the rapid identification and processing of high-risk records, reducing potential losses caused by delays. In addition, by pushing specific warning information to relevant users, decision-makers can timely understand the risk situation and formulate corresponding risk control measures, thus better ensuring the safety and efficiency of the traffic system.

[0142] Specifically, according to the risk identification result set, the risk scores of each record can be filtered. Among them, through the preset threshold and conditional judgment logic, the records whose risk scores exceed the preset threshold are screened out to generate a high-risk record set.

[0143] In this step, the system first needs to clarify the preset risk threshold, usually based on historical data analysis and risk assessment models. This threshold can be a fixed value, such as 80, or dynamically adjusted according to traffic business requirements. The system will traverse the risk identification result set and check each record one by one. Whenever the system reads a record, it will extract the risk score of the record and compare it with the set threshold. When the system finds that the risk score of a certain record exceeds the threshold, it will add the record to the high-risk record set.

[0144] For example, assume that the risk identification result set of the system contains five records, and their risk scores are 50, 85, 90, 70, and 100 respectively. If the threshold set by the system is 80, the system will first check record 1 (50). Since it does not exceed the threshold, it will continue to check record 2 (85). Finding that its score exceeds 80, it will add it to the high-risk set. Next, record 3 (90) and record 5 (100) also meet the addition conditions, and the finally generated high-risk record set will contain records 2, 3, and 5.

[0145] The key to this filtering process lies in the efficiency and accuracy of the conditional judgment logic. To improve processing efficiency, the system can construct an optimized traversal algorithm, such as using parallel processing technology to check multiple records simultaneously to speed up the generation of the high-risk record set. In this way, the system can analyze a large amount of data in a short time to ensure the timely identification of potential risks.

[0146] Based on the high-risk record set, create warning signals. Among them, through event-driven technology, each high-risk record is converted into a warning event, and the corresponding warning signal is generated, and the warning signals are sorted by priority using an event queue to generate an ordered warning signal queue;

[0147] In this step, the system will construct warning events one by one from the high-risk record set. Each high-risk record will be encapsulated into a warning event object, which contains key information such as record ID, risk type, risk score, and relevant road section information. The system will use event-driven technology, which means that when a high-risk record is identified, the event handler will be immediately triggered. For example, when the risk score of a record is detected to exceed the threshold, the system will automatically create a warning event, such as "The traffic flow on Road Section X triggered two warnings within 10 minutes, and the traffic flow is 6,000 vehicles per hour, exceeding the set threshold". This not only responds quickly to potential risks but also ensures the timely transmission of information.

[0148] Then, these warning events are added to an event queue. Since different high-risk records may have different levels of urgency, the system needs to prioritize these events. A set of rules can be set, for example, setting the priority of records with a high risk score to "high", records with a risk score near the threshold to "medium", and records with the relatively lowest risk score to "low". In this way, the system can effectively distinguish which events need to be processed immediately and which can be processed later, thus optimizing resource allocation.

[0149] Once all high-risk records have been converted into warning signals and sorted by priority, these ordered warning signal queues will provide a clear logical order for the subsequent processing steps. The system can store these events through data structures such as First-In-First-Out (FIFO) or Priority Queue to ensure that the system gives priority to processing the most urgent warning signals, thereby reducing the risks faced by the enterprise.

[0150] According to the ordered warning signal queue, convert the warning signals into standardized warning information. Among them, through the template engine and dynamic data filling technology, the key information in the warning signals is filled into the warning template to generate formatted warning information;

[0151] In this step, the system utilizes the information in the early warning signal queue to generate standardized early warning messages. First, the system predefines a structured early warning message template, which usually includes fields such as "warning type", "related road section", "risk score", "timestamp", etc. By using a template engine, the system can flexibly fill in different early warning event information, ensuring that each early warning message has a consistent format and is easy to understand. For example, the template may be defined as "Warning: There is a risk in the traffic flow of road section {road section ID}, the traffic flow is {traffic flow}, and the risk score is {risk score}."

[0152] The system will traverse the ordered early warning signal queue, extract the necessary information from each early warning signal, and use dynamic data filling technology to fill this information into the early warning template. Suppose the first early warning signal in the queue is "The traffic flow of road section A is 6,000 vehicles per hour, and the risk score is 95". The formatted information generated after filling will be "Warning: There is a risk in the traffic flow of road section A, the traffic flow is 6,000 vehicles per hour, and the risk score is 95." In this way, the system can generate a large number of efficient, accurate, and structured early warning messages.

[0153] The generated formatted early warning messages will be stored in a new collection, ready for subsequent distribution. This standardized early warning information not only improves the accuracy of data processing but also ensures that different users can quickly understand the warning content in the same format, thus enhancing the response efficiency.

[0154] Based on the formatted early warning information, through multi-channel distribution technology and priority scheduling algorithms, according to user preferences and the urgency of the early warning, determine the notification channels and push strategies, and generate real-time push tasks to push the early warning information to relevant users.

[0155] In this step, the system needs to decide how to distribute the early warning information to users based on the formatted early warning information and user preference settings. First, the system will collect user preference information, such as whether they wish to receive early warnings via email, text message, APP push, or other means. This process can be completed through a one-time setting on the user interface or subsequent dynamic updates. Depending on the different needs of users, the system will select different channels to push the same early warning message.

[0156] To ensure that high-priority early warning information can be delivered first, the system will adopt a priority scheduling algorithm. This means that when the system has multiple early warning messages to send, it will give priority to handling high-risk events. For example, if user A receives high-risk early warnings via text message, while user B wishes to receive relatively low-risk warnings via email, the system will schedule according to this setting.

[0157] When finally generating real-time push tasks, the system creates a task queue. Each task includes information such as the content to be sent, target users, receiving methods, and sending times. When the system processes each task in the task queue one by one, it distributes according to the preset sending strategy. By utilizing multi-channel distribution technology, the system can ensure that relevant users can obtain important risk warning information immediately, so as to take necessary actions in the first time and reduce the impact of potential risks.

[0158] It can be seen that according to the traffic business requirements, multi-source big data streams of traffic business management are accessed in real time to generate standardized data streams, and based on the standardized data streams, cleaned real-time data streams are generated; according to the risk rule library, predefined risk rules are loaded into the rule engine, the risk rules are converted into executable rule models, and based on the rule models, the execution order and priority of the risk rules are dynamically adjusted by using a rule optimization algorithm to generate an initialized rule engine; according to the cleaned real-time data stream and the initialized rule engine, real-time risk identification is carried out, rule matching is performed on each record in the data stream, and based on the matching results, the risk scores of each record are calculated to generate a risk identification result set; according to the risk identification result set, risk warning signals are generated by using warning trigger technology, and the corresponding warning information is pushed to users in real time, realizing the comprehensive analysis and judgment of traffic business management big data, so as to effectively analyze and judge potential risks in the traffic business process and improve the accuracy and timeliness of risk identification.

[0159] An embodiment of the present invention also provides a storage medium, in which a computer program is stored. Among them, the computer program is set to execute the steps in any one of the above method embodiments when running.

[0160] Specifically, in this embodiment, the above storage medium can be set to store a computer program for executing the following steps:

[0161] S301, according to the traffic business requirements, utilize distributed data acquisition technology to access multi-source big data streams of traffic business management in real time, generate standardized data streams, and based on the standardized data streams, generate cleaned real-time data streams;

[0162] S302, according to the risk rule library, utilize dynamic rule loading technology to load predefined risk rules into the rule engine, convert the risk rules into executable rule models, and based on the rule models, utilize a rule optimization algorithm to dynamically adjust the execution order and priority of the risk rules to generate an initialized rule engine;

[0163] S303, according to the cleaned real-time data stream and the initialized rule engine, utilize rule matching technology to perform real-time risk identification, perform rule matching on each record in the data stream, and based on the matching results, calculate the risk scores of each record to generate a risk identification result set;

[0164] S304. Generate risk warning signals based on the risk identification result set by using warning trigger technology, trigger warnings for records with risk scores exceeding the preset threshold, and push the corresponding warning information to users in real time to achieve comprehensive analysis and judgment of big data for traffic business management.

[0165] It can be seen that, according to traffic business requirements, multi-source big data streams for traffic business management are accessed in real time by using distributed data collection technology to generate standardized data streams, and based on the standardized data streams, cleaned real-time data streams are generated; according to the risk rule library, predefined risk rules are loaded into the rule engine by using dynamic rule loading technology, the risk rules are converted into executable rule models, and based on the rule models, the execution order and priority of the risk rules are dynamically adjusted by using rule optimization algorithms to generate an initialized rule engine; according to the real-time data stream and the rule engine, real-time risk identification is performed, rule matching is carried out for each record in the data stream, and based on the matching results, the risk scores of each record are calculated to generate a risk identification result set; according to the risk identification result set, risk warning signals are generated by using warning trigger technology, and the corresponding warning information is pushed to users in real time to achieve comprehensive analysis and judgment of big data for traffic business management, so as to effectively analyze and judge potential risks in traffic business processes and improve the accuracy and timeliness of risk identification.

[0166] An embodiment of the present invention also provides an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0167] Specifically, the above electronic device may further include a transmission device and an input / output device, where the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0168] Specifically, in this embodiment, the above processor may be configured to execute the following steps by a computer program:

[0169] S301. According to traffic business requirements, use distributed data collection technology to access multi-source big data streams for traffic business management in real time, generate standardized data streams, and based on the standardized data streams, generate cleaned real-time data streams;

[0170] S302. According to the risk rule library, use dynamic rule loading technology to load predefined risk rules into the rule engine, convert the risk rules into executable rule models, and based on the rule models, use rule optimization algorithms to dynamically adjust the execution order and priority of the risk rules to generate an initialized rule engine;

[0171] S303. Based on the real-time data stream after cleaning and the initialized rule engine, use rule matching technology for real-time risk identification, perform rule matching on each record in the data stream, and based on the matching results, calculate the risk score of each record to generate a risk identification result set.

[0172] S304. According to the risk identification result set, use early warning triggering technology to generate risk warning signals, trigger early warnings for records whose risk scores exceed the preset threshold, and push the corresponding warning information to users in real time to achieve comprehensive analysis and judgment of big data in traffic business management.

[0173] It can be seen that according to the traffic business requirements, multi-source big data streams of traffic business management are accessed in real time to generate a standardized data stream, and based on the standardized data stream, a real-time data stream after cleaning is generated; according to the risk rule library, predefined risk rules are loaded into the rule engine, the risk rules are converted into executable rule models, and based on the rule models, an initialized rule engine is generated; according to the real-time data stream and the rule engine, real-time risk identification is performed, rule matching is performed on each record in the data stream, and based on the matching results, the risk score of each record is calculated to generate a risk identification result set; according to the risk identification result set, risk warning signals are generated by using early warning triggering technology, and the corresponding warning information is pushed to users in real time to achieve comprehensive analysis and judgment of big data in traffic business management, so as to effectively analyze and judge potential risks in the traffic business process and improve the accuracy and timeliness of risk identification.

[0174] The structure, features and function effects of the present invention have been described in detail based on the embodiments shown in the drawings. The above is only the preferred embodiment of the present invention, but the present invention is not limited to the scope shown in the drawings. Any changes made according to the concept of the present invention, or modified into equivalent embodiments with equivalent changes, still within the spirit covered by the description and drawings, shall be within the protection scope of the present invention.

Claims

1. A comprehensive analysis and judgment system for big data in traffic service management, characterized in that The system includes: An access module, which is used to, according to traffic service requirements, utilize distributed data acquisition technology to real-time access multi-source big data streams for traffic service management, generate standardized data streams, and based on the standardized data streams, generate cleaned real-time data streams; A loading module, which is used to, according to a risk rule library, utilize dynamic rule loading technology to load predefined risk rules into a rule engine, convert the risk rules into executable rule models, and based on the rule models, utilize a rule optimization algorithm to dynamically adjust the execution order and priority of the risk rules, generating an initialized rule engine; specifically, the loading module is used for: According to the risk rule library, utilize rule parsing technology to parse the predefined risk rules. Among them, through syntax analysis technology and rule description language, convert the rule text in the risk rule library into structured rule objects, generating a set of rule objects; based on the set of rule objects, utilize rule compilation technology to convert the rules into executable rule models. Among them, through intermediate code generation technology and an optimization compiler, compile the rule objects into execution code, generating executable rule models; according to the executable rule models, utilize a rule caching mechanism to load the rules into the rule engine. Among them, through the LRU caching algorithm and distributed caching technology, cache the frequently used rules into the rule engine memory, generating a rule loading state with optimized caching; Based on the rule loading state with optimized caching, utilize a rule optimization algorithm to dynamically adjust the rule execution order. Among them, calculate the priority weight of each rule according to the historical execution frequency and business importance of the rules, generating an adjusted rule execution order for priorities; according to the adjusted rule execution order for priorities, configure the rule engine. Among them, through state management technology and a concurrency control mechanism, ensure that the rule engine supports dynamic rule updates and real-time adjustments while efficiently executing the rules, generating an initialized rule engine; based on the initialized rule engine, verify the running state of the rule engine. Among them, through rule coverage analysis and execution log monitoring, ensure that all rules are correctly loaded and executed, and according to the verification results, utilize a feedback mechanism to dynamically correct the rule loading and running processes, generating a final initialized rule engine state; A matching module, which is used to, according to the cleaned real-time data streams and the initialized rule engine, utilize rule matching technology to conduct real-time risk identification, perform rule matching on each record in the data streams, and based on the matching results, calculate the risk score of each record, generating a risk identification result set; An early warning module, which is used to, according to the risk identification result set, utilize early warning triggering technology to generate risk early warning signals, trigger early warnings for records with risk scores exceeding a preset threshold, and push the corresponding early warning information to users in real time, realizing the comprehensive analysis and judgment of big data for traffic service management.

2. The system according to claim 1, characterized in that, Specifically, the access module is used for: According to traffic service requirements, configure multi-source data access interfaces, perform parameter configuration and connection testing on the multi-source data access interfaces, and generate the data access status after initialization. Among them, the multi-source data includes at least database log data, API interface data, message queue data, and sensor data; According to the data access status after initialization, use stream computing technology to capture multi-source data streams in real time. Among them, through the distributed message queue and data sharding mechanism, the multi-source data streams are sharded according to time windows or data volume to generate sharded data blocks, and each data block is marked with a data sharding identifier to generate a sharded identification data set; According to the sharded identification data set, unify the formats of multi-source data. Among them, through data mapping technology and format conversion algorithms, the original data from different data sources is converted into a unified standardized format to generate a standardized data stream; Based on the standardized data stream, use data cleaning algorithms to remove noise data and redundant information. Among them, through outlier detection technology and regular expression matching, identify and filter invalid data, duplicate data, and data with format errors to generate a cleaned real-time data stream.

3. A comprehensive analysis and judgment method for big data in traffic business management, characterized in that, The method includes: According to traffic service requirements, use distributed data acquisition technology to access multi-source big data streams for traffic service management in real time, generate a standardized data stream, and based on the standardized data stream, generate a cleaned real-time data stream; According to the risk rule library, use dynamic rule loading technology to load predefined risk rules into the rule engine, convert the risk rules into executable rule models, and based on the rule models, use rule optimization algorithms to dynamically adjust the execution order and priority of the risk rules to generate an initialized rule engine; among them, according to the risk rule library, use rule parsing technology to parse the predefined risk rules. Among them, through syntax analysis technology and rule description language, convert the rule text in the risk rule library into structured rule objects to generate a set of rule objects; based on the set of rule objects, use rule compilation technology to convert the rules into executable rule models. Among them, through intermediate code generation technology and an optimization compiler, compile the rule objects into execution code to generate an executable rule model; according to the executable rule model, use a rule caching mechanism to load the rules into the rule engine. Among them, through the LRU caching algorithm and distributed caching technology, cache the frequently used rules into the rule engine memory to generate a cache-optimized rule loading state; Based on the rule loading status optimized by caching, the rule execution order is dynamically adjusted using a rule optimization algorithm. Among them, according to the historical execution frequency and business importance of the rules, the priority weight of each rule is calculated to generate the rule execution order after priority adjustment; according to the rule execution order after priority adjustment, the rule engine is configured. Among them, through state management technology and concurrent control mechanism, it is ensured that the rule engine supports dynamic rule updates and real-time adjustments while efficiently executing rules, generating an initialized rule engine; based on the initialized rule engine, the running state of the rule engine is verified. Among them, through rule coverage analysis and execution log monitoring, it is ensured that all rules are correctly loaded and executed, and according to the verification results, the rule loading and running processes are dynamically corrected using a feedback mechanism to generate the final initialized rule engine state; According to the cleaned real-time data stream and the initialized rule engine, real-time risk identification is carried out using rule matching technology. Each record in the data stream is matched with the rules, and based on the matching results, the risk score of each record is calculated to generate a risk identification result set; According to the risk identification result set, a risk warning signal is generated using warning trigger technology. Records with risk scores exceeding the preset threshold are triggered for warning, and the corresponding warning information is pushed to users in real time to achieve comprehensive analysis and judgment of big data in traffic business management.

4. The method according to claim 3, wherein According to the traffic business requirements, multi-source big data streams of traffic business management are accessed in real time using distributed data collection technology to generate a standardized data stream, and based on the standardized data stream, a cleaned real-time data stream is generated, including: According to the traffic business requirements, multi-source data access interfaces are configured, and parameter configuration and connection tests are performed on the multi-source data access interfaces to generate an initialized data access state. Among them, the multi-source data at least includes database log data, API interface data, message queue data, and sensor data; According to the initialized data access state, multi-source data streams are captured in real time using streaming computing technology. Among them, through a distributed message queue and data sharding mechanism, the multi-source data streams are sharded according to time windows or data volumes to generate sharded data blocks, and each data block is marked using a data sharding identifier to generate a sharded identifier data set; According to the sharded identifier data set, the formats of the multi-source data are unified. Among them, through data mapping technology and format conversion algorithms, the original data from different data sources is converted into a unified standardized format to generate a standardized data stream; Based on the standardized data stream, noise data and redundant information are removed using data cleaning algorithms. Among them, through outlier detection technology and regular expression matching, invalid data, duplicate data, and data with format errors are identified and filtered to generate a cleaned real-time data stream.

5. The method according to claim 4, wherein According to the cleaned real-time data stream and the initialized rule engine, real-time risk identification is carried out using rule matching technology. Each record in the data stream is matched with the rules, and based on the matching results, the risk score of each record is calculated to generate a risk identification result set, including: According to the cleaned real-time data stream, the data stream is sub-sharded by time window or data volume. Among them, through the hash sharding algorithm and the time window division mechanism, the data stream is divided into multiple data shards, and each data shard is assigned to a different computing node to generate a shard task set; Based on the shard task set and the initialized rule engine, the multi-pattern matching algorithm is used to perform rule matching on each data shard. Among them, through the Aho-Corasick algorithm and parallel computing technology, the rule matching tasks are executed simultaneously on multiple computing nodes to generate a preliminary matching result set; According to the preliminary matching result set, the matching results of each computing node are summarized. Among them, through the reduction algorithm and distributed aggregation technology, the scattered matching results are merged into a global matching result set, and based on the global matching result set, the risk score of each record is calculated. Among them, through the weighted summation algorithm and risk level mapping, a risk score data set is generated; Based on the risk score data set, a risk identification result set is generated. Among them, through the threshold judgment mechanism and risk classification technology, the records with risk scores exceeding the preset threshold are marked as high-risk to generate the final risk identification result set.

6. The method according to claim 5, wherein According to the risk identification result set, the early warning trigger technology is used to generate risk warning signals, trigger warnings for the records with risk scores exceeding the preset threshold, and push the corresponding warning information to users in real time to realize the comprehensive analysis and research of big data in traffic business management, including: According to the risk identification result set, the risk scores of each record are filtered. Among them, through the preset threshold and conditional judgment logic, the records with risk scores exceeding the preset threshold are screened out to generate a high-risk record set; Based on the high-risk record set, warning signals are created. Among them, through the event-driven technology, each high-risk record is converted into a warning event, and the corresponding warning signal is generated, and the warning signals are sorted by priority using an event queue to generate an ordered warning signal queue; According to the ordered warning signal queue, the warning signals are converted into standardized warning information. Among them, through the template engine and dynamic data filling technology, the key information in the warning signals is filled into the warning template to generate formatted warning information; Based on the formatted warning information, through the multi-channel distribution technology and priority scheduling algorithm, according to user preferences and warning urgency, the notification channel and push strategy are determined to generate a real-time push task to push the warning information to relevant users.

7. A storage medium, characterized in that, The computer program is stored in the storage medium, wherein the computer program is set to execute the method described in any one of claims 3-6 when running.

8. An electronic device, comprising a memory and a processor, characterized in that, The computer program is stored in the memory, and the processor is set to run the computer program to execute the method described in any one of claims 4-6.

Citation Information

Patent Citations

  • Cost auditing method and system based on big data

    CN119228420A

  • Intelligent supervision method and system based on big data

    CN119476946A