High-speed toll station traffic efficiency evaluation system and method based on multi-source time-series data

Abstract

The application relates to the technical field of intelligent transportation, and discloses a high-speed toll station traffic efficiency evaluation system and method based on multi-source time sequence data. The system comprises a data analysis module, a preprocessing module, a feature processing module, a double-model evaluation module and a hierarchical evaluation module. The method is applied to the system. The application focuses on the traffic efficiency evaluation of a high-speed toll station, a double-index evaluation system driven by multi-source time sequence data is formed, real-time and accurate evaluation of the operation state of the toll station is realized, scientific and data-based decision-making basis is provided for operation management, and problems such as insufficient data fusion and monotonous evaluation standards of traditional manual monitoring are effectively solved.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, specifically a highway toll station traffic efficiency evaluation system and method based on multi-source time-series data. Background Technology

[0002] With the continuous growth of traffic volume and the increasing complexity of road network structures, the high-density traffic flow and the massive demands of road network operation and management have placed higher requirements on highway network toll collection operators. How to achieve efficient monitoring of toll station operation status and build an objective and accurate traffic evaluation system has become crucial for promoting the digital transformation of road network operation services and improving traffic efficiency and service quality.

[0003] Currently, traditional methods for assessing the operational status of toll stations mainly rely on monitoring centers built by road management units and manual monitoring. This presents significant technical bottlenecks: First, insufficient data fusion capabilities, relying solely on single video data sources or individual auxiliary data from different road sections, making it difficult to effectively integrate multi-dimensional information such as equipment status, traffic flow data, and transaction records, thus failing to comprehensively reflect the true operational status of toll stations. Second, a lack of objectivity in evaluation standards, excessive reliance on manual experience and the absence of a quantitative and scientific scoring system, leading to subjective biases in the assessment results. Third, limited monitoring timeliness and coverage, making it difficult to achieve 24 / 7 real-time monitoring across all scenarios, and weak capabilities for retrospective analysis of historical operational data, failing to meet the needs of rapid fault diagnosis and long-term operational optimization.

[0004] Therefore, there is an urgent need for a technology that can achieve real-time and accurate assessment of the operational status of toll stations. Summary of the Invention

[0005] The purpose of this application is to provide a system and method for evaluating the traffic efficiency of highway toll stations based on multi-source time-series data, so as to solve the technical problems mentioned in the background.

[0006] To achieve the above objectives, this application discloses the following technical solutions:

[0007] Firstly, this application discloses a highway toll station traffic efficiency evaluation system based on multi-source time-series data, the system comprising:

[0008] The data parsing module is configured to: collect multi-dimensional time-series data from multiple toll stations, and transmit, parse, and monitor the quality of the collected time-series data to obtain standardized structured data;

[0009] The preprocessing module is configured to: perform timestamp alignment and device operating status transformation on the structured data to obtain structured time-series data with device operating status identifiers;

[0010] The feature processing module is configured to: extract pressure parameter feature vectors and service parameter feature vectors based on the structured time-series data;

[0011] The dual-model evaluation module is configured to: based on the constructed stress index model and service index model, respectively input the stress parameter feature vector and the service parameter feature vector, and output the stress index prediction value and the service index prediction value;

[0012] The graded evaluation module is configured to: output the corresponding traffic pressure evaluation result based on the pressure index prediction value according to the preset graded mapping relationship, and output the corresponding service quality evaluation result based on the service index prediction value.

[0013] Preferably, the data parsing module includes:

[0014] The data transmission service unit is configured to transmit the multi-dimensional time-series data through a hybrid transmission processing mechanism, wherein the hybrid transmission processing mechanism includes asynchronous transmission via message queues and real-time processing of streaming data, and the multi-dimensional time-series data is unstructured or semi-structured data.

[0015] The file parsing service unit is configured to convert the multi-dimensional time-series data into structured data using regular expressions and heterogeneous data format parsing tools.

[0016] The data quality monitoring unit is configured to: assess the integrity of the structured data through a data volume statistical monitoring benchmark model and non-empty rate analysis of key business fields; assess the accuracy of the structured data through a business rule engine and outlier detection algorithm; assess the consistency of the structured data through a cross-data source alignment and verification mechanism; assess the timeliness of the structured data through an end-to-end latency indicator and a tiered alarm mechanism; and assess the effectiveness of the structured data through data usage frequency and demand matching degree analysis.

[0017] Preferably, the multi-dimensional time-series data includes vehicle transaction logs, real-time vehicle passage monitoring data, device monitoring heartbeat data, and lane log data, wherein:

[0018] The transaction log for passing vehicles includes lane code, universal unique identifier, transaction time, license plate number, toll vehicle type, entrance information, toll gantry identification, and exit information;

[0019] The real-time vehicle passage monitoring data includes lane code, license plate number, entry time into lane, exit time into lane, passage duration, average speed, transaction time, and special situation type;

[0020] The device monitors heartbeat data including lane code, upload time, entry time, device ID, status code, response delay, and fault marker.

[0021] The lane log data includes lane code, software version, upload time, data entry time, data version, number of incidents, and incident type.

[0022] Preferably, the preprocessing module includes:

[0023] The timestamp alignment unit is configured to align all data sources with a time window of S seconds, and to fill missing values ​​using a regular linear interpolation method. The filling formula is:

[0024]

[0025] in, These are the missing values ​​at the target time point t to be filled. The observation value is from the previous valid time point t-1. For the observation value at the next valid time point t+1, The time interval between the valid time point t+1 and the valid time point t-1. Let be the time interval between the target time point t and the effective time point t-1, and ;

[0026] The device status conversion unit is configured to convert device heartbeat data into device operating status data. If a device records fewer than a dynamic threshold x heartbeats within a time window of S seconds, it is marked as a device fault. The conversion formula is as follows:

[0027]

[0028] in, The result is the equipment fault marking result. When the value is 1, it means that the equipment is judged to be in a fault state. When the value is 0, it means that the equipment is judged to be in a normal state. This represents the number of valid heartbeats recorded at time point t. A value of 1 indicates that there is a valid heartbeat record at the corresponding time point, while a value of 0 indicates that there is no valid heartbeat record at the corresponding time point. This represents the total number of valid heartbeat data records within a time window of S seconds.

[0029] Preferably, the calculation formula for the pressure index model is as follows:

[0030]

[0031] in, The predicted pressure index value for the i-th sample output by the model at time t; Let be the dimension of the pressure parameter feature vector. The value of the eigenvector of the k-th pressure parameter. The weights of the eigenvectors for the k-th pressure parameter are... For pressure bias term;

[0032] The calculation formula for the service index model is as follows:

[0033]

[0034] in, The predicted service index value of the i-th sample output by the model at time t; The dimension of the service parameter feature vector. The value of the feature vector of the k-th service parameter. The weights of the feature vector of the k-th service parameter are... For service bias terms.

[0035] Preferably, the pressure parameter feature vector Including the idle time of lane i during time period t Number of idle times Real-time traffic flow Traffic saturation Total number of equipment Number of devices with abnormal heartbeats Equipment failure ratio Failure rate sliding window statistics and moving average of traffic flow index .

[0036] Preferably, the service parameter feature vector Including the actual average travel time of lane i during time period t Theoretical benchmark travel time Travel time deviation Vehicle speed fluctuation rate Continuous trouble-free duration Transaction success rate smoothing value And the efficiency ratio of lane toll collection method at toll station j during time period t .

[0037] Preferably, the dual-model evaluation module is further configured to: train and optimize the model using mean squared error and L2 regularization as loss functions, and update the model parameters using backpropagation and gradient descent algorithms; wherein:

[0038] The loss function of the stress index model is:

[0039]

[0040] The loss function of the service index model is:

[0041]

[0042] The formula for updating model parameters is:

[0043]

[0044]

[0045] in, This is the training sample size; This is the labeled stress index value of the i-th sample in the training dataset at time t; The label service index value of the i-th sample in the training dataset at time t; For the regularization parameters of the pressure index model; Regularization parameters for the service index model; The learning rate; For loss function right The gradient; For loss function right The gradient.

[0046] Preferably, the hierarchical mapping relationship includes:

[0047] When the predicted pressure index value is in the range of [0,5), the corresponding traffic pressure assessment result is smooth; when the predicted pressure index value is in the range of [5,7), the corresponding traffic pressure assessment result is basically smooth; when the predicted pressure index value is in the range of [7,8), the corresponding traffic pressure assessment result is slightly congested; when the predicted pressure index value is in the range of [8,9), the corresponding traffic pressure assessment result is moderately congested; when the predicted pressure index value is in the range of [9,10], the corresponding traffic pressure assessment result is severely congested.

[0048] When the predicted service index value is in the range [0,2], the corresponding service quality evaluation result is poor; when the predicted service index value is in the range (2,4], the corresponding service quality evaluation result is poor; when the predicted service index value is in the range (4,6], the corresponding service quality evaluation result is average; when the predicted service index value is in the range (6,8], the corresponding service quality evaluation result is good; when the predicted service index value is in the range (8,10], the corresponding service quality evaluation result is excellent.

[0049] Secondly, this application discloses a method for evaluating the traffic efficiency of highway toll stations based on multi-source time-series data, applied to the highway toll station traffic efficiency evaluation system based on multi-source time-series data as described above. The method includes:

[0050] Data parsing steps: Collect multi-dimensional time-series data from multiple toll stations, and transmit, parse, and monitor the quality of the collected time-series data to obtain standardized structured data;

[0051] Preprocessing steps: The structured data is timestamped and transformed to reflect the device operating status to obtain structured time-series data with device operating status identifiers;

[0052] Feature processing steps: Extract pressure parameter feature vectors and service parameter feature vectors based on the structured time-series data;

[0053] Dual-model evaluation steps: Based on the constructed stress index model and service index model, input the stress parameter feature vector and the service parameter feature vector respectively, and output the stress index prediction value and the service index prediction value.

[0054] The graded evaluation steps are as follows: According to the preset graded mapping relationship, the corresponding traffic pressure evaluation result is output based on the predicted value of the pressure index, and the corresponding service quality evaluation result is output based on the predicted value of the service index.

[0055] Beneficial Effects: The highway toll station traffic efficiency evaluation system and method based on multi-source time-series data in this application collects multi-dimensional time-series data from multiple toll stations, and after transmission, parsing, and quality monitoring, obtains standardized structured data that comprehensively and accurately reflects the overall operational information such as toll station equipment status, traffic flow changes, and transaction status. Secondly, by extracting feature vectors of pressure and service parameters and combining them with dual-model evaluation to output quantitative pressure and service indices, and then outputting evaluation results through hierarchical mapping relationships, a scientific and objective quantitative evaluation system is constructed, reducing evaluation bias. At the same time, based on real-time data processing, timestamp alignment processing, and real-time output capabilities, real-time monitoring of the entire scenario can be achieved, and the standardized structured data facilitates the retrospective analysis of historical operational data, meeting the needs of rapid fault diagnosis and long-term operational optimization, and improving the monitoring coverage and depth. In addition, through the output pressure index prediction value, service index prediction value, and efficiency level evaluation results, accurate and dynamic evaluation results are provided to highway operation and management units, promoting the transformation of road network operation services from manual monitoring to data-driven and intelligent systems, and providing scientific decision support for improving traffic efficiency and service quality. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 A structural block diagram of a highway toll station traffic efficiency evaluation system based on multi-source time-series data provided in this application embodiment;

[0058] Figure 2 A flowchart illustrating the method for evaluating the traffic efficiency of highway toll stations based on multi-source time-series data, provided in this application embodiment. Detailed Implementation

[0059] The technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0060] In this document, the term "comprising" is intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0061] This embodiment provides a first aspect such as Figure 1 The highway toll station traffic efficiency evaluation system based on multi-source time-series data shown includes:

[0062] The data parsing module is configured to: collect multi-dimensional time-series data from multiple toll stations, and transmit, parse, and monitor the quality of the collected time-series data to obtain standardized structured data;

[0063] The preprocessing module is configured to: perform timestamp alignment and device operating status transformation on the structured data to obtain structured time-series data with device operating status identifiers;

[0064] The feature processing module is configured to: extract pressure parameter feature vectors and service parameter feature vectors based on the structured time-series data;

[0065] The dual-model evaluation module is configured to: based on the constructed stress index model and service index model, respectively input the stress parameter feature vector and the service parameter feature vector, and output the stress index prediction value and the service index prediction value;

[0066] The graded evaluation module is configured to: output the corresponding traffic pressure evaluation result based on the pressure index prediction value according to the preset graded mapping relationship, and output the corresponding service quality evaluation result based on the service index prediction value.

[0067] Based on this, the highway toll station traffic efficiency evaluation system based on multi-source time-series data in this embodiment integrates multi-dimensional time-series data through a data parsing module, solving the limitations of traditional assessments that rely on a single data source and achieving data comprehensiveness. A preprocessing module ensures the temporal consistency and integrity of the data, laying the foundation for subsequent analysis. A feature processing module and a dual-model evaluation module output quantitative indices, replacing traditional manual experience-based judgments and constructing an objective dual-indicator evaluation system. Finally, a hierarchical evaluation module outputs intuitive evaluation results, achieving real-time and accurate assessment of the toll station's operational status. This effectively solves the problems of insufficient data integration, subjective evaluation, and poor timeliness in traditional assessments, providing data-driven decision support for operation management.

[0068] In this embodiment, the data parsing module includes:

[0069] The data transmission service unit is configured to transmit the multi-dimensional time-series data through a hybrid transmission processing mechanism, wherein the hybrid transmission processing mechanism includes asynchronous transmission via message queues and real-time processing of streaming data (such as Apache Flink), and the multi-dimensional time-series data is unstructured or semi-structured data.

[0070] The file parsing service unit is configured to: convert the multi-dimensional time-series data into structured data using regular expressions and heterogeneous data format parsing tools; wherein, the heterogeneous data format parsing tools include an XML parser or a JSON parser;

[0071] The data quality monitoring unit is configured to: assess the integrity of the structured data through a data volume statistical monitoring benchmark model and non-empty rate analysis of key business fields; assess the accuracy of the structured data through a business rule engine and outlier detection algorithm; assess the consistency of the structured data through a cross-data source alignment and verification mechanism; assess the timeliness of the structured data through an end-to-end latency indicator and a tiered alarm mechanism; and assess the effectiveness of the structured data through data usage frequency and demand matching degree analysis.

[0072] Through the above-described data parsing module setup, the three units of the data parsing module work together: the data transmission service unit adopts a hybrid transmission mechanism, which not only ensures the stability of unstructured / semi-structured data transmission but also enables real-time processing, solving the problems of latency or instability in traditional data transmission; the file parsing service unit standardizes the data through regular expressions and XML / JSON parsers, providing a unified format for subsequent processing and overcoming the shortcomings of traditional data formats being chaotic and difficult to integrate; the data quality monitoring unit evaluates data quality from five dimensions, ensuring that the data is complete, accurate, consistent, timely, and effective, avoiding evaluation bias caused by data quality issues, and providing data assurance for the reliability of the entire system.

[0073] Feasibly, the multi-dimensional time-series data includes vehicle transaction logs, real-time vehicle passage monitoring data, equipment monitoring heartbeat data, and lane log data, wherein:

[0074] The transaction log for passing vehicles includes lane code, universal unique identifier, transaction time, license plate number, toll vehicle type, entrance information, toll gantry identification, and exit information;

[0075] The real-time vehicle passage monitoring data includes lane code, license plate number, entry time into lane, exit time into lane, passage duration, average speed, transaction time, and special situation type;

[0076] The device monitors heartbeat data including lane code, upload time, entry time, device ID, status code, response delay, and fault marker.

[0077] The lane log data includes lane code, software version, upload time, data entry time, data version, number of incidents, and incident type.

[0078] By designing the multi-dimensional time series data as described above, the types and key fields of the multi-dimensional time series data were clarified, the data sources and core information were accurately defined, and the comprehensiveness and relevance of data collection were ensured. This provided reliable and standardized raw data for subsequent data analysis, preprocessing and feature extraction, avoiding analytical biases caused by missing or unclear data fields, and further ensuring the effectiveness of the entire evaluation system.

[0079] In this embodiment, the preprocessing module includes:

[0080] The timestamp alignment unit is configured to align all data sources with a time window of S seconds, and to fill missing values ​​using a regular linear interpolation method. The filling formula is:

[0081]

[0082] in, These are the missing values ​​at the target time point t to be filled. The observation value is from the previous valid time point t-1. For the observation value at the next valid time point t+1, The time interval between the valid time point t+1 and the valid time point t-1. Let be the time interval between the target time point t and the effective time point t-1, and ;

[0083] The device status conversion unit is configured to convert device heartbeat data into device operating status data. If a device records fewer than a dynamic threshold x heartbeats within a time window of S seconds, it is marked as a device fault. The conversion formula is as follows:

[0084]

[0085] in, The result is the equipment fault marking result. When the value is 1, it means that the equipment is judged to be in a fault state. When the value is 0, it means that the equipment is judged to be in a normal state. This represents the number of valid heartbeats recorded at time point t. A value of 1 indicates that there is a valid heartbeat record at the corresponding time point, while a value of 0 indicates that there is no valid heartbeat record at the corresponding time point. This represents the total number of valid heartbeat data records within a time window of S seconds.

[0086] Based on the above preprocessing module settings, the timestamp alignment unit aligns data using an S-second time window, fills missing values ​​with a linear interpolation formula, and estimates missing values ​​by using effective observations before and after the target time point and by the time interval ratio, ensuring time consistency across different data sources, filling in data gaps, and avoiding analysis errors caused by time misalignment or data gaps. The equipment status conversion unit compares the heartbeat count with a dynamic threshold, using heartbeat frequency to reflect equipment activity, accurately identifying equipment fault status, providing a reliable basis for subsequent pressure and service index analysis, and solving the problem of fuzzy traditional equipment status judgment.

[0087] In this embodiment, the calculation formula for the pressure index model is as follows:

[0088]

[0089] in, The predicted pressure index value for the i-th sample output by the model at time t; Let be the dimension of the pressure parameter feature vector. The value of the eigenvector of the k-th pressure parameter. The weights of the eigenvectors for the k-th pressure parameter are... This is the pressure bias term.

[0090] The calculation formula for the service index model is as follows:

[0091]

[0092] in, The predicted service index value of the i-th sample output by the model at time t; The dimension of the service parameter feature vector. The value of the feature vector of the k-th service parameter. The weights of the feature vector of the k-th service parameter are... For service bias terms.

[0093] Based on the aforementioned stress index model and service index model, by linearly combining feature vectors and quantifying the impact of each feature on stress / service quality through weighting, multi-dimensional features are integrated into a single index. This transforms complex multi-dimensional data into intuitive and comparable quantitative indicators, thereby achieving a quantitative assessment of traffic stress and service quality. This solves the problem of the lack of unified quantitative standards in traditional evaluations, making the evaluation results more objective and comparable.

[0094] It is feasible that the pressure parameter feature vector Including the idle time of lane i during time period t Number of idle times Real-time traffic flow Traffic saturation Total number of equipment Number of devices with abnormal heartbeats Equipment failure ratio Failure rate sliding window statistics and moving average of traffic flow index .

[0095] By designing the aforementioned pressure parameter feature vectors, the key factors affecting traffic pressure are comprehensively captured, providing multi-dimensional and targeted input features for the pressure index model. This ensures that the model can accurately depict changes in traffic pressure, solves the problem of the single dimension in traditional pressure assessment, and improves the comprehensiveness and accuracy of pressure evaluation.

[0096] Secondly, the service parameter feature vector Including the actual average travel time of lane i during time period t Theoretical benchmark travel time Travel time deviation Vehicle speed fluctuation rate Continuous trouble-free duration Transaction success rate smoothing value And the efficiency ratio of lane toll collection method at toll station j during time period t Among them, the lane toll collection methods include ETC or MTC.

[0097] By designing the service parameter feature vectors mentioned above, the core indicators of service quality are comprehensively covered, providing multi-dimensional feature support for the service index model. This enables the model to accurately quantify service quality, solves the problem of the one-sidedness of traditional service evaluation indicators, and improves the accuracy of service quality evaluation.

[0098] Furthermore, the dual-model evaluation module is also configured to: train and optimize the model using mean squared error and L2 regularization as loss functions, and update the model parameters using backpropagation and gradient descent algorithms; wherein:

[0099] The loss function of the stress index model is:

[0100]

[0101] The loss function of the service index model is:

[0102]

[0103] The formula for updating model parameters is:

[0104]

[0105]

[0106] in, This refers to the number of training samples (i.e., the total number of samples used in model training). The labeled pressure index value (i.e. the actual observed pressure index) of the i-th sample in the training dataset at time t. The labeled service index value (actually observed service index) of the i-th sample in the training dataset at time t. This is a regularization parameter for the pressure index model, used to reduce model complexity and prevent overfitting; Regularization parameters for the service index model are used to reduce model complexity and prevent overfitting. and Used for L2 regularization calculation; The learning rate is used to control the step size for parameter updates in the gradient descent algorithm. For loss function Yes gradient, For loss function pairs The gradient reflects the parameters and The trend and extent of the impact of small changes on the value of the loss function.

[0107] Based on the above, the loss function for model training and optimization employs mean squared error and L2 regularization. Mean squared error measures the error by calculating the squared difference between the predicted and true values, ensuring the accuracy of model predictions. L2 regularization, by weighting the sum of squared parameters, limits the parameters from becoming too large and prevents model overfitting. The parameter update formula iteratively optimizes the parameters along the gradient of the loss function to minimize the loss. This improves the model's prediction accuracy and generalization ability, avoids practical application deviations caused by overfitting the training data, and ensures stable output of the two models in different scenarios.

[0108] In this embodiment, the hierarchical mapping relationship includes:

[0109] When the predicted pressure index value is in the range of [0,5), the corresponding traffic pressure assessment result is smooth; when the predicted pressure index value is in the range of [5,7), the corresponding traffic pressure assessment result is basically smooth; when the predicted pressure index value is in the range of [7,8), the corresponding traffic pressure assessment result is slightly congested; when the predicted pressure index value is in the range of [8,9), the corresponding traffic pressure assessment result is moderately congested; when the predicted pressure index value is in the range of [9,10], the corresponding traffic pressure assessment result is severely congested.

[0110] When the predicted service index value is in the range [0,2], the corresponding service quality evaluation result is poor; when the predicted service index value is in the range (2,4], the corresponding service quality evaluation result is poor; when the predicted service index value is in the range (4,6], the corresponding service quality evaluation result is average; when the predicted service index value is in the range (6,8], the corresponding service quality evaluation result is good; when the predicted service index value is in the range (8,10], the corresponding service quality evaluation result is excellent.

[0111] Based on the above-mentioned hierarchical mapping relationship, the quantitative index is mapped to a specific level by a preset interval, which realizes the transformation of the abstract quantitative index into an easy-to-understand evaluation conclusion. This enables operators to quickly grasp the traffic pressure and service quality status of toll stations, solves the problem of the obscure and difficult-to-apply traditional evaluation results, and improves decision-making efficiency.

[0112] In summary, the highway toll station traffic efficiency evaluation system based on multi-source time-series data in this embodiment focuses on evaluating the traffic efficiency of highway toll stations. With a dual-indicator evaluation system driven by multi-source time-series data, it achieves real-time and accurate assessment of the toll station's operating status, providing a scientific and data-driven basis for operation management and effectively solving problems such as insufficient data integration and monotonous evaluation standards in traditional manual monitoring.

[0113] In a second aspect, this embodiment provides a method such as Figure 2The highway toll station traffic efficiency evaluation method based on multi-source time series data, as shown, is applied to the highway toll station traffic efficiency evaluation system based on multi-source time series data as described above. The method includes the following steps:

[0114] The processor architecture consists of an ARM processor and an FPGA module. The ARM processor performs system management, edge computing task scheduling and northbound interface docking, while the FPGA module performs protocol conversion and real-time data stream processing.

[0115] In the protocol conversion of the FPGA module, different IoT protocols are efficiently converted through parallel processing. The IoT protocols include several of the following protocols: Zigbee, LoRa, Modbus, MQTT, CoAP, and Matter.

[0116] A hybrid task scheduling algorithm based on genetic algorithm and Petri net is adopted to dynamically allocate cross-protocol task resources and optimize task execution paths;

[0117] A unified security framework module integrating protocol-agnostic key management, cross-protocol security mechanisms, and zero-trust architecture is used to achieve unified management of symmetric and asymmetric encryption.

[0118] Based on the edge computing module, local data analysis is performed, and task priorities are dynamically adjusted according to the analysis results.

[0119] It should be noted that the highway toll station traffic efficiency evaluation method based on multi-source time-series data in this embodiment corresponds to the aforementioned highway toll station traffic efficiency evaluation system based on multi-source time-series data. Therefore, for the parts not specifically described in the highway toll station traffic efficiency evaluation method based on multi-source time-series data in this embodiment (including but not limited to specific implementation techniques and effects), please refer to the relevant records in the aforementioned highway toll station traffic efficiency evaluation system based on multi-source time-series data. This text will not elaborate further here.

[0120] In the embodiments provided in this application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For hardware implementation, the processor may be implemented in one or more of the following: application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGA modules), processors, controllers, microcontrollers, microprocessors, other electronic units designed to implement the functions described herein, or combinations thereof. For software implementation, some or all of the processes of the embodiments may be performed by a computer program instructing the associated hardware. During implementation, the program may be stored in a computer-readable storage medium or transmitted as one or more instructions or code on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein communication media include any medium that facilitates the transfer of a computer program from one place to another. Storage media may be any available medium accessible to a computer. Computer-readable storage media may include, but are not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code having the form of instructions or data structures and accessible to a computer.

[0121] Finally, it should be noted that the above description is only a preferred embodiment of this application and is not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A high-speed toll station passage efficiency evaluation system based on multi-source time series data, characterized in that, The system comprises: a data analysis module configured to collect multi-dimensional time series data of multiple toll stations, and to transmit, analyze and monitor the quality of the collected time series data to obtain standardized structured data; a preprocessing module configured to perform timestamp alignment and device operating state conversion processing on the structured data to obtain structured time series data with device operating state identification; a feature processing module configured to extract pressure parameter feature vectors and service parameter feature vectors based on the structured time series data; a dual-model evaluation module configured to input the pressure parameter feature vectors and the service parameter feature vectors into a constructed pressure index model and a constructed service index model respectively, and output pressure index prediction values and service index prediction values; a hierarchical evaluation module configured to output corresponding traffic pressure evaluation results based on the pressure index prediction values and corresponding service quality evaluation results based on the service index prediction values according to a preset hierarchical mapping relationship; the calculation formula of the pressure index model is: ； wherein, is the predicted stress index value for the i-th sample of the model output at time instant t; is the dimension of the stress parameter feature vector, is the value of the k-th stress parameter feature vector, is the k-th stress parameter feature vector weight, is the stress bias term; the calculation formula of the service index model is: ； wherein, is a predicted service index value for the i-th sample of the model output at time instant t; is a dimension of the service parameter feature vector, is a value of the k-th service parameter feature vector, is a weight of the k-th service parameter feature vector, is a service bias term; The pressure parameter feature vector The idle time of the lane i at the t period The idle frequency The real-time traffic flow The traffic flow saturation The total number of devices The number of devices with heartbeat abnormalities The device failure ratio The failure rate sliding window statistics And the traffic flow index moving average ​ The service parameter feature vector The actual average travel time of the lane i in the t period The theoretical reference travel time The travel time deviation degree The vehicle speed fluctuation rate The continuous fault-free duration The transaction success rate smooth value And the lane toll mode efficiency ratio of the toll station j in the t period . 2.The system of claim 1, wherein, the data analysis module comprises: a data transmission service unit configured to transmit the multi-dimensional time series data through a hybrid transmission processing mechanism, wherein the hybrid transmission processing mechanism comprises message queue asynchronous transmission and real-time processing of streaming data, and the multi-dimensional time series data is unstructured or semi-structured data; a file analysis service unit configured to convert the multi-dimensional time series data into structured data through regular expressions and heterogeneous data format analysis tools; a data quality monitoring unit configured to perform integrity evaluation on the structured data through a data volume statistical monitoring benchmark model and a key business field non-empty rate analysis, accuracy evaluation on the structured data through a business rule engine and an outlier detection algorithm, consistency evaluation on the structured data through a cross-data source alignment verification mechanism, timeliness evaluation on the structured data through an end-to-end delay indicator and a hierarchical alarm mechanism, and effectiveness evaluation on the structured data through data usage frequency and demand matching degree analysis. 3.The system of claim 2, wherein, The multi-dimensional time series data comprises traffic vehicle transaction flow, real-time vehicle monitoring data, device monitoring heartbeat data and lane log data, wherein: The traffic vehicle transaction flow comprises lane code, universal unique identification, transaction time, license plate number, toll vehicle type, entry information, toll gate identification and exit information; The real-time vehicle monitoring data comprises lane code, license plate number, lane entry time, lane exit time, vehicle passing time, vehicle average speed, transaction time consumption and special situation type; The device monitoring heartbeat data comprises lane code, upload time, storage time, device ID, status code, response delay and fault flag; The lane log data comprises lane code, software version, upload time, storage time, data version, special situation number and special situation type.

4. The multi-source timing data based express toll plaza throughput evaluation system of claim 1, wherein, The preprocessing module comprises: a timestamp alignment unit configured to align all data sources with a time window of S seconds, and to fill in missing values using a regular linear method, with a filling formula of: ； wherein is the missing value for the target time point t to be filled in, is the observation value of the preceding valid time point t-1, is the observation value of the following valid time point t+1, is the time interval between the valid time point t+1 and the valid time point t-1, is the time interval between the target time point t and the valid time point t-1, and ; A device state conversion unit is configured to convert device heartbeat data into device running state data, mark a device as faulty if the device has less than a dynamic threshold x times of heartbeat data records in a time window S seconds, and convert the formula as follows: ； wherein, is a device fault flag result, when the value is 1, it indicates that the device is determined to be in a fault state, when the value is 0, it indicates that the device is determined to be in a normal state; is the number of valid heartbeat data recorded at time point t, when the value is 1, it indicates that there is valid heartbeat record at the corresponding time point, when the value is 0, there is no valid heartbeat record at the corresponding time point; is the total number of valid heartbeat data records within a time window of S seconds.

5. The multi-source timing data based express toll plaza throughput evaluation system of claim 1, wherein, The double model evaluation module is further configured to perform model training and optimization by taking mean square error and L2 regularization as a loss function, and update model parameters by a back propagation algorithm and a gradient descent algorithm. The loss function of the pressure index model is as follows: ； The loss function of the service index model is as follows: ； The formula for updating the model parameters is as follows: ； ； wherein, is the number of training samples; is the labeled stress index value of the i-th sample in the training dataset at time t; is the labeled service index value of the i-th sample in the training dataset at time t; is the regularization parameter of the stress index model; is the regularization parameter of the service index model is the learning rate; is the loss function the gradient of with respect to is the loss function the gradient of with respect to 6. The multi-source timing data based express toll plaza throughput evaluation system of claim 1, wherein, The hierarchical mapping relationship includes: When the pressure index prediction value is in the interval [0, 5), the corresponding traffic pressure evaluation result is smooth; when the pressure index prediction value is in the interval [5, 7), the corresponding traffic pressure evaluation result is basically smooth; when the pressure index prediction value is in the interval [7, 8), the corresponding traffic pressure evaluation result is slight congestion; when the pressure index prediction value is in the interval [8, 9), the corresponding traffic pressure evaluation result is moderate congestion; and when the pressure index prediction value is in the interval [9, 10], the corresponding traffic pressure evaluation result is severe congestion. When the service index prediction value is in the interval [0, 2], the corresponding service quality evaluation result is poor; when the service index prediction value is in the interval (2, 4], the corresponding service quality evaluation result is relatively poor; when the service index prediction value is in the interval (4, 6], the corresponding service quality evaluation result is general; when the service index prediction value is in the interval (6, 8], the corresponding service quality evaluation result is good; and when the service index prediction value is in the interval (8, 10], the corresponding service quality evaluation result is excellent.

7. A method for evaluating the efficiency of a highway toll station based on multi-source time-series data, applied to the system for evaluating the efficiency of a highway toll station based on multi-source time-series data according to any one of claims 1-6, characterized in that, The method comprises: A data analysis step of collecting multi-dimensional time series data of multiple toll stations, and transmitting, analyzing and quality monitoring the collected time series data to obtain standardized structured data; A preprocessing step of performing timestamp alignment and device running state conversion processing on the structured data to obtain structured time series data with device running state identification; A feature processing step of extracting a pressure parameter feature vector and a service parameter feature vector based on the structured time series data; A double model evaluation step of inputting the pressure parameter feature vector and the service parameter feature vector into the pressure index model and the service index model respectively, and outputting a pressure index prediction value and a service index prediction value; A hierarchical evaluation step of outputting a corresponding traffic pressure evaluation result based on the pressure index prediction value and a corresponding service quality evaluation result based on the service index prediction value according to a preset hierarchical mapping relationship.

Images