A traffic law enforcement resource scheduling method and system based on multi-source real-time data

Abstract

The application discloses a traffic law enforcement resource scheduling method and system based on multi-source real-time data, which comprises the following steps: acquiring multi-source real-time data, wherein the multi-source real-time data at least comprises law enforcement task data, law enforcement resource data and environmental support data; pre-processing and fusing the multi-source real-time data to construct a standardized scheduling data resource pool; based on the scheduling data resource pool, structurally analyzing the law enforcement task and determining a task priority sequence; based on the scheduling data resource pool, constructing a dynamic portrait of law enforcement resources; inputting the task priority sequence and the dynamic portrait into a preset intelligent scheduling decision model, and performing multi-objective optimization calculation combined with law enforcement compliance constraint conditions to generate a target scheduling scheme; and outputting the target scheduling scheme to perform dynamic scheduling of law enforcement resources. The traffic law enforcement resource is accurately matched, quickly responded and compliantly scheduled in a dynamic scene, and the law enforcement disposal efficiency and resource utilization rate are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of resource scheduling technology, and in particular to a method and system for scheduling traffic law enforcement resources based on multi-source real-time data. Background Technology

[0002] The scheduling of traffic enforcement resources is a crucial link in ensuring the efficiency and standardization of law enforcement. Current technologies primarily employ fixed-area divisions and fixed-shift scheduling, or pre-allocation of resources based on static statistical data of enforcement needs. Their core principle is static planning based on experience or historical data, typically assigning enforcement resources through manual scheduling or simple rule matching. However, this scheduling method based on static data and simple rules is ill-suited to the unique demands of traffic enforcement operations, such as their high degree of unpredictability, specialized nature, and strict compliance constraints. This results in the scheduling mechanism failing to achieve optimal resource allocation in dynamically changing enforcement scenarios. Due to the lack of integrated processing and dynamic profiling of multi-source real-time data, existing technologies exhibit delayed response times to sudden enforcement events. Furthermore, relying solely on single-dimensional matching such as distance ignores the professional skills and real-time workload of enforcement personnel, leading to low accuracy in resource and task matching. Additionally, the failure to embed compliance rules such as continuous duty hours of enforcement personnel into the decision-making logic easily introduces the risk of illegal scheduling. Therefore, existing technologies urgently need a scheduling method that can integrate multi-source real-time data, comprehensively consider task priorities and dynamic resource profiles, and make intelligent decisions under compliance constraints, in order to solve the technical problem that static scheduling mechanisms cannot adapt to dynamic law enforcement scenarios. Summary of the Invention

[0003] In view of this, the present invention proposes a method and system for scheduling traffic enforcement resources based on multi-source real-time data, which can realize accurate matching, rapid response, and compliant scheduling of traffic enforcement resources in dynamic scenarios. The present invention provides the following technical solution: A method for scheduling traffic enforcement resources based on multi-source real-time data includes: Acquire multi-source real-time data, which includes at least law enforcement task data, law enforcement resource data, and environmental support data; The multi-source real-time data is preprocessed and fused to construct a standardized scheduling data resource pool; Based on the aforementioned scheduling data resource pool, law enforcement tasks are structurally parsed and a task priority sequence is determined. Based on the aforementioned scheduling data resource pool, a dynamic profile of law enforcement resources is constructed; The task priority sequence and the dynamic profile are input into a preset intelligent scheduling decision model, and multi-objective optimization calculations are performed in combination with law enforcement compliance constraints to generate a target scheduling scheme. Output the target scheduling scheme to execute the dynamic scheduling of law enforcement resources.

[0004] Optionally, acquiring multi-source real-time data includes: Data is collected in real time through law enforcement terminals, vehicle-mounted equipment, roadside sensing devices and related systems at the terminal layer; Data transmission uses the MQTT protocol, with a priority transmission mechanism for law enforcement task data with a preset high priority level, prioritizing transmission bandwidth and low latency.

[0005] Optionally, the preprocessing and fusion of the multi-source real-time data includes: A time-series sliding window mechanism is used to filter abnormal data, including abnormal location data of law enforcement personnel and abnormal values ​​of road condition sensors. The data is standardized by converting location data into a preset spatial coordinate standard and time data into a preset time format standard. The scheduling data resource pool is stored in a memory-cached database to ensure low-latency data access.

[0006] Optionally, the step of performing structured parsing of law enforcement tasks and determining a task priority sequence specifically includes: Text analysis algorithms are used to extract core information from unstructured emergency descriptions to obtain structured task attribute fields. Pre-set structured fields are directly extracted for early warning tasks and routine patrol tasks. Construct a task priority evaluation index system for transportation law enforcement scenarios. The evaluation index system shall include at least three criteria-level indicators: urgency, risk level, and scope of impact. A multi-level weighted evaluation method is adopted to assign preset weights to the three criteria-level indicators, and the comprehensive score of the task is calculated by combining the scores of each criteria-level indicator. Based on the correspondence between the comprehensive task score and the preset grading threshold, law enforcement tasks are divided into multiple priority levels, and the task priority sequence is generated.

[0007] Optionally, the construction of dynamic profiles of law enforcement resources specifically includes: Construct a profile of law enforcement personnel, calculate skill proficiency scores based on historical law enforcement data, and embed compliance status indicators, which include at least continuous duty duration and current task load; Construct a resource aggregation profile, divide the pre-defined spatial grid units according to the law enforcement jurisdiction, count the quantity and type of law enforcement resources in each grid unit, calculate the resource redundancy, and generate a resource distribution heat map; The dynamic profile is updated in real time according to a preset update frequency to reflect the real-time status changes of law enforcement resources.

[0008] Optionally, the intelligent scheduling decision model has a built-in multi-objective optimization function, which at least covers response time, resource matching degree, resource load balance degree and processing success rate; The law enforcement compliance constraints include constraints on the continuous duty time of law enforcement personnel, current task load constraints, and the matching constraints between high-priority tasks and highly skilled personnel. An iterative optimization algorithm is used to solve the multi-objective optimization function under the premise of satisfying the law enforcement compliance constraints, so as to generate the target scheduling scheme.

[0009] This invention further discloses a traffic enforcement resource scheduling system based on multi-source real-time data, comprising: The data acquisition module is used to acquire multi-source real-time data, which includes at least law enforcement task data, law enforcement resource data, and environmental support data. The data processing module is used to preprocess and fuse the multi-source real-time data to build a standardized scheduling data resource pool. The task parsing module is used to perform structured parsing of law enforcement tasks and determine the task priority sequence based on the scheduling data resource pool. The resource profiling module is used to construct a dynamic profile of law enforcement resources based on the scheduling data resource pool. The intelligent decision-making module is used to input the task priority sequence and the dynamic profile into the preset intelligent scheduling decision model, and perform multi-objective optimization calculations in combination with law enforcement compliance constraints to generate a target scheduling scheme. The scheduling execution module is used to output the target scheduling scheme to execute the dynamic scheduling of law enforcement resources.

[0010] The present invention further discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0011] The present invention further discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method.

[0012] The present invention further discloses a computer program product, including a computer program that implements the above-described method when executed by a processor.

[0013] According to the technical solution of this invention, by acquiring and preprocessing and fusing multi-source real-time data, including law enforcement tasks, resources, and environmental support, a standardized scheduling data resource pool is constructed. This overcomes the shortcomings of single scheduling basis, which cannot adapt to dynamic scenarios, and achieves real-time and dynamic scheduling decisions. On this basis, by performing structured analysis on law enforcement tasks to determine the task priority sequence, and constructing a dynamic profile of law enforcement resources including skill proficiency and compliance status, this profile is input into a preset intelligent scheduling decision model. Combined with law enforcement compliance constraints, multi-objective optimization calculations are performed. This not only ensures accurate matching of high-priority tasks with highly skilled personnel, significantly improving the success rate of task handling and resource utilization, but also embeds compliance rules such as continuous duty duration into the decision logic, effectively avoiding the risk of illegal scheduling. Finally, a target scheduling plan is generated to execute the dynamic scheduling of law enforcement resources. Thus, while ensuring the standardization of law enforcement, the response time for emergency tasks is greatly shortened, and the overall efficiency and resource coordination capabilities of transportation law enforcement are improved. Attached Figure Description

[0014] For illustrative and not limiting purposes, the present invention will now be described in conjunction with embodiments and accompanying drawings, wherein: Figure 1 This is a flowchart illustrating the traffic enforcement resource scheduling method based on multi-source real-time data in an embodiment of the present invention. Figure 2 This is a schematic diagram of the constituent modules of the traffic law enforcement resource scheduling system based on multi-source real-time data in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device in an embodiment of the present invention. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0016] It should be noted that, where there is no conflict, the embodiments and features of the embodiments in this application can be combined with each other. The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0017] refer to Figure 1 This embodiment discloses a traffic enforcement resource scheduling method based on multi-source real-time data, including: S100: Acquire multi-source real-time data, which includes at least law enforcement task data, law enforcement resource data, and environmental support data.

[0018] For the acquisition of multi-source real-time data, raw data is collected in real time through various sensing and interactive devices deployed at the terminal layer. The terminal layer devices include, but are not limited to: law enforcement terminals handheld or worn by law enforcement officers, vehicle-mounted equipment in law enforcement vehicles, roadside / shore-based sensing devices deployed on key road sections or waterways, and external system interfaces associated with transportation law enforcement operations.

[0019] In this embodiment, the collected multi-source real-time data specifically includes the following three categories: Law enforcement task data includes real-time early warning tasks, emergency law enforcement incidents, and routine patrol tasks. For real-time early warning tasks, the collected fields include violation type, geographical coordinates, risk level, and urgency; for emergency law enforcement incidents, the collected fields include event type, scope of impact, and required response time; for routine patrol tasks, the collected fields include patrol area and duration requirements.

[0020] Law enforcement resource data includes data on law enforcement personnel, vehicles, and equipment. For law enforcement personnel data, the collected fields include real-time location information, skill level identifier, current task load status, on-duty status, and cumulative duty duration. For law enforcement vehicle data, the collected fields include real-time location information, vehicle condition, load capacity, and equipment configuration. For law enforcement equipment data, the collected fields include equipment type, availability, and storage location.

[0021] Environmental support data includes meteorological data, road condition data, and waterway navigation data. Specifically, real-time meteorological data is acquired via the meteorological platform API interface, with a collection frequency set to once every 5 minutes; real-time road traffic condition data is acquired via the road condition API interface; and waterway navigation flow and status data are collected through the waterway electronic checkpoint system.

[0022] The collected raw data is transmitted to the edge layer and cloud processing center via a communication network. In this embodiment, the data transmission uses the MQTT protocol to ensure low latency and high reliability.

[0023] To further ensure the response speed of emergency law enforcement tasks, this implementation method adopts a priority transmission mechanism during data transmission. Specifically, law enforcement task data is classified by priority level. For law enforcement task data with a preset high priority level, such as urgency level 1 or 2, the priority transmission mechanism is used for processing. This mechanism prioritizes the allocation of transmission bandwidth and low-latency transmission for such high-priority task data, ensuring that emergency task data can reach the data processing center first, providing data timeliness assurance for subsequent rapid scheduling decisions.

[0024] Through the above steps, the comprehensive collection and initial transmission of multi-source heterogeneous real-time data in the context of transportation law enforcement were completed, laying the data foundation for subsequent data processing and scheduling decisions.

[0025] S200: Preprocess and fuse the multi-source real-time data to construct a standardized scheduling data resource pool. This is achieved through collaborative processing at the edge layer and cloud layer. This eliminates noise and heterogeneity in the original data, ensuring data consistency, accuracy, and timeliness, providing a high-quality data foundation for subsequent task analysis and intelligent decision-making.

[0026] Specifically, after receiving the raw multi-source real-time data collected in step S100, preprocessing operations are first performed. These include: Temporal sliding window anomaly filtering: A temporal sliding window mechanism is used to clean the data stream in real time. In this embodiment, the window size of the temporal sliding window mechanism is set to 5 seconds. Within this sliding window, the continuity and rationality of the data are detected, and abnormal data is filtered. This abnormal data includes abnormal data from law enforcement personnel location and abnormal values ​​from road condition sensors. For abnormal data from law enforcement personnel location, the judgment logic is: if the position change of three consecutive sampling points is greater than 50m and the calculated speed is greater than 120km / h, it is judged as location drift data and filtered. For abnormal values ​​from road condition sensors, the judgment logic is: if the traffic speed reported by the sensor is less than 0 or greater than 150km / h, it is judged as a sensor abnormal value and filtered. For missing data, a neighborhood interpolation method is used to supplement it. For example, if road condition data is missing at a certain moment, the average of the data from the two moments before and after that moment is used to fill it in, ensuring data continuity.

[0027] Data standardization: The filtered data is standardized to unify the data format and dimensions. Specifically, spatial coordinate standardization: Location data is uniformly converted to a preset spatial coordinate standard. In this embodiment, the preset spatial coordinate standard is the WGS-84 latitude and longitude coordinate system, with coordinate accuracy retained to ±0.0001°, ensuring that all resource and task locations are comparable under the same spatial reference; Time format standardization: Time data is unified to a preset time format standard. In this embodiment, the preset time format standard is a UTC timestamp, accurate to the second, ensuring time synchronization of multi-source data; Scoring data normalization: Heterogeneous scoring data such as skill scores and vehicle condition scores are normalized to a preset score range. In this embodiment, the preset score range is 0-10 points, facilitating unified calculation by subsequent algorithms.

[0028] After preprocessing, the multi-source data is fused to construct multi-dimensional data associations. Specifically, this includes: Time-series alignment and fusion: A time-series alignment and fusion algorithm is employed to align various data types based on standardized timestamps. In this implementation, time synchronization accuracy is controlled within ±1 second. Through time alignment, it is ensured that the task status, resource location, and environmental parameters at the same moment are correlated.

[0029] Spatial location association: Based on standardized spatial coordinates, task data is spatially associated with surrounding resource and environmental data. For example, the enforcement task for a certain road segment is associated with the locations of law enforcement personnel around that road segment and the real-time traffic congestion coefficient of that road segment.

[0030] Construction of a four-dimensional data matrix: Through the alignment and association described above, a four-dimensional data matrix of "task ID-resource ID-environmental parameters-time" is constructed. This matrix fully describes the state relationship between a specific task and a specific resource at a specific point in time, under a specific environment, providing comprehensive data support for subsequent scheduling decisions.

[0031] This implementation method, tailored to the specific characteristics of transportation law enforcement operations, embeds compliance data verification logic during the data fusion phase to proactively mitigate the risk of unauthorized dispatching. Specifically, it includes: Continuous duty duration verification: The system automatically retrieves the continuous duty duration field from law enforcement resource data. In this implementation, the preset compliance duration threshold is 4 hours. If a law enforcement officer is detected to have been on duty continuously for more than 4 hours, the officer's data is automatically filtered, and their status is marked as "unschedulable".

[0032] On-duty status verification: Synchronously verify the on-duty status of personnel. If the status is "offline" or "on leave", they are directly excluded from the schedulable resource pool.

[0033] High-quality data, after preprocessing, fusion, and verification, forms a unified scheduling data resource pool and is stored at high speed to support real-time queries. The storage medium is a memory-based cache database. In this embodiment, the memory-based cache database is specifically a Redis database. Its in-memory storage characteristics ensure fast data access. Further optimization of data structures and indexes ensures low-latency data access. In this embodiment, query latency is controlled within 50ms to meet the high real-time requirements of the intelligent scheduling decision model (decision response latency <1s).

[0034] Through the above steps, the construction of a standardized, compliant, and real-time accessible scheduling data resource pool was completed, transforming raw heterogeneous data into such a pool.

[0035] S300: Based on the scheduling data resource pool, perform structured parsing of law enforcement tasks and determine the task priority sequence.

[0036] Specifically, the system first extracts the law enforcement task data to be processed from the scheduling data resource pool. For unstructured emergency event descriptions, natural language processing algorithms are used to extract core information. For example, the description information "There is a truck suspected of being overloaded on XX road section, causing congestion" is automatically extracted into structured task attribute fields such as task type "early warning and handling", location "coordinates of XX road section", and required skill "overload detection". For early warning tasks and routine patrol tasks, preset structured fields are directly extracted to complete the structured parsing of the tasks.

[0037] Based on this, a task priority evaluation index system for transportation law enforcement scenarios is constructed. This system includes three criterion-level indicators: urgency, risk level, and scope of impact. An improved analytic hierarchy process (AHP) tailored to transportation law enforcement scenarios is used to assign preset weights to these three criterion-level indicators. Specifically, the rationality of the matrices is ensured by constructing pairwise comparison matrices at the criterion level and performing consistency checks. For example, the weight ω1 for urgency is set to 0.4 to align with the core requirement of rapid response to sudden law enforcement tasks, while the weights ω2 for risk level and ω3 for scope of impact are both set to 0.3.

[0038] Subsequently, the comprehensive task score is calculated by combining the scores of the indicators at each criterion level. In this implementation, each criterion level indicator adopts a 10-point scoring system, and the scoring criteria are formulated based on the type of transportation law enforcement task. The urgency scoring criteria are: 10 points for emergencies, 8 points for real-time early warning tasks, and 3 points for routine patrol tasks; the risk level scoring criteria are: 10 points for Level 1 risk, 7 points for Level 2 risk, and 3 points for Level 3 risk; and the impact scope scoring criteria are: 10 points for large-scale impact, 6 points for local impact, and 2 points for small-scale impact. The comprehensive task score is calculated according to the comprehensive scoring formula S=a·S1+b·S2+c·S3, where S1, S2, and S3 are the scores for urgency, risk level, and impact scope, respectively, and a, b, and c are the weighting coefficients corresponding to urgency, risk level, and impact scope, respectively. Finally, based on the correspondence between the comprehensive task score and the preset grading threshold, the law enforcement tasks are divided into multiple priority levels. For example, they are specifically divided into 5 priority levels: Level 1 (highest priority) with a comprehensive score of 9 or higher, Level 2 (7 to 9), Level 3 (5 to 7), Level 4 (3 to 5), and Level 5 (less than 3). This generates the task priority sequence and outputs it to the intelligent scheduling decision model, providing accurate priority input for subsequent resource matching.

[0039] S400: Based on the aforementioned scheduling data resource pool, construct a dynamic profile of law enforcement resources.

[0040] Specifically, the process begins by extracting historical enforcement data, real-time location information, and status information of law enforcement personnel from the scheduling data resource pool to construct a profile of each officer. The core of this process involves calculating a skill proficiency score based on historical enforcement data, using a weighted average method. The formula is Sp = α × Ss + β × Se, where Ss is the success rate score and Se is the efficiency correction score. Ss = (number of successful handlings / total number of handlings) × 10. If the total number of handlings is 0, then Ss = 5 (initial base score). Se is the efficiency correction score, calculated as Se = [1 - (actual handling time - average handling time of similar tasks in the region) / average handling time of similar tasks in the region] × 10. The result is 0 when < 0 and 10 when > 10. For example, if a law enforcement officer handles an over-limit detection task 20 times, with 18 successful handlings, an actual handling time of 40 minutes, and an average handling time of 50 minutes in the region, then Ss = (18 / 20) × 10 = 9 points. =[1-(40-50) / 50]×10=12 points (take 10 points), final proficiency score Sp =0.6×9+0.4×10=9.4 points; Real-time updates of personnel location, current load (number of tasks undertaken / maximum workload, maximum workload defaults to 2 items), and continuous duty duration, ultimately calculating the proficiency score. At the same time, compliance status indicators are embedded in this profile. The compliance status indicators include at least continuous duty duration and current task load. Real-time monitoring is conducted to see if the continuous duty duration of law enforcement personnel exceeds 4 hours and if the current load exceeds the maximum workload. The status that meets the compliance requirements is updated to the profile in real time.

[0041] Based on this, a resource aggregation profile is constructed. Pre-defined spatial grid units are divided according to law enforcement jurisdiction areas; in this embodiment, the grid is specifically 1km × 1km. The quantity and type of law enforcement resources within each grid unit are statistically analyzed, including the number of law enforcement personnel, vehicles, and equipment types. Resource redundancy, i.e., the difference between the actual resource quantity and the predicted demand, is calculated to generate a resource distribution heatmap. The dynamic profile is updated in real-time according to a preset update frequency; in this embodiment, it is updated every 30 seconds to reflect the real-time status changes of law enforcement resources, thereby providing accurate resource status input for the intelligent scheduling decision model.

[0042] S500: Input the task priority sequence and the dynamic profile into the preset intelligent scheduling decision model, and perform multi-objective optimization calculations in combination with law enforcement compliance constraints to generate a target scheduling scheme.

[0043] Specifically, the task priority sequence generated in step S300 and the dynamic profile of law enforcement resources constructed in step S400 are first used as input data, and an improved genetic algorithm is used to solve the problem. The encoding method adopts a real number encoding of "task number-person number-task priority" triplets, adapted to the differentiated scheduling requirements of traffic law enforcement task priorities. The encoding length is the total number of tasks N, and the encoding format is... ,in, For task sequence number, For personnel serial numbers, Task priority is determined by directly embedding priority information through encoding to ensure matching weights for high-priority tasks during genetic operations.

[0044] Furthermore, the fitness function is calculated using a multi-objective weighted summation formula, and the weight parameters are dynamically calibrated based on the needs of traffic enforcement scenarios. The formula is as follows: ,in, For response time weighting, As the resource matching degree weight, As the weight for resource load balancing, To weight the success rate, the standardized values ​​of each sub-objective function range from 0 to 1. The sub-objective functions are optimized based on the characteristics of traffic enforcement scenarios, including the response time function. Introducing real-time traffic congestion coefficient The arrival time has been corrected, and the formula has been optimized to: ,in Based on arrival time, The congestion coefficient, To determine the maximum allowed arrival time, 10 minutes are used for Level 1 and Level 2 tasks, and 30 minutes are used for Level 3 to Level 5 tasks; Matching degree function Introducing task type adaptation coefficient The formula is optimized to ,in Skill fit scoring; load balancing function Introducing a continuous duty duration correction factor The formula is optimized to ,in To correct for the afterload variance, For the current load, As a correction factor for continuous duty duration, The maximum load is set to 2; the success rate function is... Introducing task difficulty coefficient The formula is optimized to ,in This represents the historical success rate.

[0045] Enforcement compliance constraints strictly adhere to traffic enforcement management regulations, including a maximum continuous duty time of 4 hours for enforcement personnel, a current workload not exceeding the maximum capacity (default 2 items), and prioritizing the matching of high-priority tasks with highly skilled personnel (i.e., level 1 and 2 tasks are matched with personnel with a skill level score of at least 8). These specific settings can be modified according to application scenarios. Genetic operations are optimized to address the suddenness, priority differentiation, and dynamic resource status of traffic enforcement tasks. Population initialization uses priority-oriented initialization, prioritizing the allocation of suitable personnel for level 1 and 2 high-priority tasks; crossover operations use priority-retaining crossover, with the crossover probability set to... During crossover, the matching relationships of high-priority tasks are preserved, and crossover is only performed on the encoding fragments of low-priority tasks from level 3 to 5. The mutation operation uses an adaptive mutation probability, which is dynamically adjusted based on the population fitness variance. When the variance is less than 0.1, the mutation probability is... When the variance is greater than or equal to 0.1, the probability of variation is The selection operation employs a hybrid approach of elite retention and roulette wheel selection, retaining the top 10% of fittest individuals in each generation, while the remaining individuals are selected using roulette wheel selection. The final output is the optimal scheduling scheme with the highest fitness function score, serving as the target scheduling scheme. This scheme prioritizes the allocation of personnel for level 1 and level 2 high-priority tasks and route planning based on real-time traffic conditions from the map API, while also including dynamic adjustment instructions.

[0046] S600: Output the target scheduling scheme to execute the dynamic scheduling of law enforcement resources.

[0047] Specifically, the target scheduling plan generated in step S500 is first distributed through multiple channels, including law enforcement officers' handheld or vehicle-mounted law enforcement apps and the command center's monitoring screen. The distributed scheduling instructions include task details, matched personnel information, routes planned based on real-time traffic conditions using map APIs, and handling requirements, ensuring that law enforcement officers clearly understand the task content and action path. For high-priority tasks of levels 1 and 2, the instructions prioritize the personnel allocation results and route planning to avoid congested sections. After the instructions are issued, the real-time execution tracking phase begins. The movement trajectory of law enforcement officers and the task execution progress are collected in real time through law enforcement recorders and vehicle-mounted devices. The task execution progress status includes not yet departed, en route, in progress, and completed. Anomalies are monitored during the execution process. If anomalies such as timeout failure or obstruction are detected, a secondary scheduling reminder is automatically triggered, and the intelligent scheduling decision model is re-invoked to generate an adjustment plan to ensure the continuity of task handling.

[0048] Simultaneously, a scheduling execution dashboard is constructed for status monitoring, displaying core indicators in real time, including task completion rate, average response time, personnel resource utilization rate, and anomaly handling rate. In this embodiment, the specific requirements for core indicators are: average response time for Level 1 tasks less than 5 minutes, average response time for Level 2 tasks less than 10 minutes, and personnel resource utilization rate greater than or equal to 60%. The indicator data is updated every 10 seconds so that the command center can grasp the scheduling efficiency in real time. In addition, data is collected based on the scheduling execution results to support dynamic optimization. The collected task handling results include success, failure, or partial success, as well as the satisfaction with the actual response time and resource matching. An online learning algorithm is used to adjust the weight parameters of the intelligent scheduling decision model and update the proficiency score and handling efficiency indicators in the resource profile, forming a closed-loop optimization mechanism. For example, if the road conditions in a certain area are complex, the response time weight is increased; if a law enforcement officer has high handling efficiency, their proficiency score is updated, thereby continuously improving the adaptability and scientific nature of the scheduling plan and realizing the dynamic scheduling of law enforcement resources.

[0049] In this embodiment, to achieve continuous evolution and adaptive adjustment of the scheduling system, the method further includes: S700: Feedback optimization based on scheduling execution results. Task handling result data is collected, including task handling status, actual response time, resource matching satisfaction score, and subjective feedback information from law enforcement personnel. Based on the collected handling result data, an online learning algorithm is used to dynamically adjust the weight parameters of the intelligent scheduling decision model. For example, if the road condition complexity in a certain area during a specific time period causes the actual response time to be generally higher than the predicted value, the weight coefficient of the response time function in the fitness function is automatically increased; if the historical handling success rate of a certain type of task is consistently low, the weight of the task difficulty coefficient or the matching degree function is adjusted. Simultaneously, the indicators in the resource profile are updated using the handling result data. For example, if a law enforcement officer's handling efficiency in this task is significantly higher than the average level, the handling efficiency correction score in their skill proficiency score is updated; if a law enforcement officer's continuous duty time is close to the compliance threshold, the compliance status marker is strengthened in their profile. Through the above feedback optimization mechanism, a closed loop of "data collection - intelligent decision-making - execution monitoring - feedback optimization" is formed, continuously improving the adaptability and scientific nature of the scheduling scheme.

[0050] refer to Figure 2 This embodiment further discloses a dynamic scheduling system for transportation law enforcement resources based on multi-source real-time data. The system includes a data acquisition module 21, a data processing module 22, a task parsing module 23, a resource profiling module 24, an intelligent decision-making module 25, a scheduling execution module 26, and a feedback optimization module 27.

[0051] The data acquisition module 21 is configured to collect multi-source real-time data in real time through law enforcement terminals, vehicle-mounted equipment, roadside sensing equipment and related systems at the terminal layer. The multi-source real-time data includes at least law enforcement task data, law enforcement resource data and environmental support data, and uses the MQTT protocol for data transmission. A priority transmission mechanism is used for preset high-level law enforcement task data.

[0052] The data processing module 22 is configured to preprocess and fuse the multi-source real-time data, filter abnormal data using a time-series sliding window mechanism, standardize the data, verify compliance data, and build a standardized scheduling data resource pool.

[0053] The task parsing module 23 is configured to perform structured parsing of law enforcement tasks based on the scheduling data resource pool, construct a task priority evaluation index system, calculate the comprehensive score of tasks using a multi-level weighted evaluation method, and determine the task priority sequence.

[0054] The resource profiling module 24 is configured to construct law enforcement personnel profiles and resource aggregation profiles based on the scheduling data resource pool, calculate skill proficiency scores, count the number and type of resources within the grid unit, and generate a resource distribution heatmap.

[0055] The intelligent decision-making module 25 is configured to input the task priority sequence and the dynamic profile into a preset intelligent scheduling decision model, and perform multi-objective optimization calculations in combination with law enforcement compliance constraints to generate a target scheduling scheme.

[0056] The scheduling execution module 26 is configured to output the target scheduling scheme, issue scheduling instructions through multiple channels, track the task execution progress in real time, and trigger secondary scheduling in case of abnormal situations.

[0057] The feedback optimization module 27 is configured to collect and process data based on the scheduling execution results, adjust the weight parameters of the intelligent scheduling decision model using an online learning algorithm, and update the resource profile indicators.

[0058] The modules are connected via a data bus or communication interface to work together to achieve dynamic scheduling of transportation law enforcement resources.

[0059] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 3 As shown, the electronic device 50 includes: a processor 501, a memory 502, and a bus 503; The processor 501 and the memory 502 communicate with each other via the bus 503; the processor 501 is used to call the program instructions in the memory 502 to execute the methods provided in the above-described embodiments.

[0060] This embodiment provides a non-transitory computer-readable storage medium that stores computer instructions that cause a computer to execute the methods provided in the above-described embodiments.

[0061] Those skilled in the art will understand that all or part of the steps of the above-described method implementation can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above-described method implementation. The aforementioned storage medium includes various storage media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.

[0062] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0063] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0064] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for scheduling traffic enforcement resources based on multi-source real-time data, characterized in that, include: Acquire multi-source real-time data, which includes at least law enforcement task data, law enforcement resource data, and environmental support data; The multi-source real-time data is preprocessed and fused to construct a standardized scheduling data resource pool; Based on the aforementioned scheduling data resource pool, law enforcement tasks are structurally parsed and a task priority sequence is determined; Based on the aforementioned scheduling data resource pool, a dynamic profile of law enforcement resources is constructed; The task priority sequence and the dynamic profile are input into a preset intelligent scheduling decision model, and multi-objective optimization calculations are performed in combination with law enforcement compliance constraints to generate a target scheduling scheme. Output the target scheduling scheme to execute the dynamic scheduling of law enforcement resources.

2. The traffic enforcement resource scheduling method according to claim 1, characterized in that, The acquisition of multi-source real-time data includes: Data is collected in real time through law enforcement terminals, vehicle-mounted equipment, roadside sensing devices and related systems at the terminal layer; Data transmission uses the MQTT protocol, with a priority transmission mechanism for law enforcement task data with a preset high priority level, prioritizing transmission bandwidth and low latency.

3. The traffic enforcement resource scheduling method according to claim 1, characterized in that, The preprocessing and fusion of the multi-source real-time data includes: A time-series sliding window mechanism is used to filter abnormal data, including abnormal location data of law enforcement personnel and abnormal values ​​of road condition sensors. The data is standardized by converting location data into a preset spatial coordinate standard and time data into a preset time format standard. The scheduling data resource pool is stored in a memory-cached database to ensure low-latency data access.

4. The traffic enforcement resource scheduling method according to claim 1, characterized in that, The structured analysis of law enforcement tasks and the determination of task priority sequences specifically include: Text analysis algorithms are used to extract core information from unstructured emergency descriptions to obtain structured task attribute fields. Pre-set structured fields are directly extracted for early warning tasks and routine patrol tasks. Construct a task priority evaluation index system for transportation law enforcement scenarios. The evaluation index system shall include at least three criteria-level indicators: urgency, risk level, and scope of impact. A multi-level weighted evaluation method is adopted to assign preset weights to the three criteria level indicators, and the comprehensive score of the task is calculated by combining the scores of each criteria level indicator. Based on the correspondence between the comprehensive task score and the preset grading threshold, law enforcement tasks are divided into multiple priority levels, generating the task priority sequence.

5. The traffic enforcement resource scheduling method according to claim 1, characterized in that, The construction of dynamic profiles of law enforcement resources specifically includes: Construct a profile of law enforcement personnel, calculate skill proficiency scores based on historical law enforcement data, and embed compliance status indicators, which include at least continuous duty duration and current task load; Construct a resource aggregation profile, divide the pre-defined spatial grid units according to the law enforcement jurisdiction, count the quantity and type of law enforcement resources in each grid unit, calculate the resource redundancy, and generate a resource distribution heat map; The dynamic profile is updated in real time according to a preset update frequency to reflect the real-time status changes of law enforcement resources.

6. The traffic enforcement resource scheduling method according to claim 1, characterized in that, The intelligent scheduling decision model has a built-in multi-objective optimization function, which at least covers response time, resource matching degree, resource load balance and processing success rate. The law enforcement compliance constraints include constraints on the continuous duty time of law enforcement personnel, current task load constraints, and the matching constraints between high-priority tasks and highly skilled personnel. An iterative optimization algorithm is used to solve the multi-objective optimization function under the premise of satisfying the law enforcement compliance constraints, so as to generate the target scheduling scheme.

7. A traffic enforcement resource scheduling system based on multi-source real-time data, characterized in that, include: The data acquisition module is used to acquire multi-source real-time data, which includes at least law enforcement task data, law enforcement resource data, and environmental support data. The data processing module is used to preprocess and fuse the multi-source real-time data to build a standardized scheduling data resource pool. The task parsing module is used to perform structured parsing of law enforcement tasks and determine the task priority sequence based on the scheduling data resource pool. The resource profiling module is used to construct a dynamic profile of law enforcement resources based on the scheduling data resource pool. The intelligent decision-making module is used to input the task priority sequence and the dynamic profile into the preset intelligent scheduling decision model, and perform multi-objective optimization calculations in combination with law enforcement compliance constraints to generate a target scheduling scheme. The scheduling execution module is used to output the target scheduling scheme to execute the dynamic scheduling of law enforcement resources.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method of any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the method of any one of claims 1-6.

Images