A cloud edge end cooperative urban traffic management data control method, system and electronic device

Abstract

The embodiment of the application discloses a kind of traffic network scheduling control method, system based on space-time big data, electronic equipment, belong to the technical field of electronic data processing, method steps include: the following steps are executed in edge side: receiving and analyzing terminal raw data, filtering and trajectory generation using the rules issued by cloud end;Call fusion engine to perform space-time alignment and matching on multi-source trajectory, generate fusion trajectory;Based on fusion trajectory, traffic flow, average speed are calculated synchronously, and input to event risk assessment model to output risk probability value;After comparing risk probability value with threshold, event level is generated and corresponding alarm is triggered.In cloud side, server converges multi-dimensional information uploaded by each node for macro analysis and model iteration optimization, and periodically issues updated strategy and configuration to edge node to dynamically adjust its processing logic, so as to realize intelligent traffic control from cloud end global optimization to edge real-time execution.

Description

Technical Field

[0001] This application relates to a traffic network scheduling and control method, system, and electronic device based on spatiotemporal big data, belonging to the technical field of electronic data processing. Background Technology

[0002] With the acceleration of urbanization and the continuous growth of motor vehicle ownership, urban transportation systems are facing increasingly severe management pressures. Traditional traffic management models primarily rely on fixed induction coils, video surveillance cameras, and other terminal devices to collect basic data, which is then processed and analyzed centrally through a traffic command center—a traditional architecture of terminal data collection + cloud processing. In this traditional architecture, massive amounts of raw data, such as video streams and radar point clouds, need to be transmitted over long distances via the network to the cloud data center. This can easily lead to data transmission delays, insufficient network bandwidth, and heavy computational loads on cloud servers. When facing application scenarios requiring low-latency decision-making, such as traffic congestion management and rapid accident response, the system's real-time performance shortcomings are particularly prominent, making it difficult to meet the real-time perception, instantaneous analysis, and rapid response requirements of modern intelligent transportation systems.

[0003] To alleviate cloud pressure and improve response speed, edge computing technology has been introduced into the field of intelligent transportation. Existing edge computing solutions typically offload some computing tasks to edge computing nodes closer to the data source, such as offloading structured analysis of video streams, vehicle detection and tracking to roadside units. However, existing technologies are often limited to the independent processing of a single data source, such as analyzing only a single camera video stream. They struggle to effectively process heterogeneous data generated by different terminal devices in terms of format and coordinate system, lacking effective and standardized multi-source data fusion capabilities. This can easily lead to the system repeatedly perceiving the same traffic target, failing to form a unified and continuous trajectory view.

[0004] In other aspects, such as event risk assessment and decision-making, existing risk assessment models are mostly statically deployed, unable to adapt to constantly changing traffic patterns, resulting in a decline in model adaptability and early warning accuracy over time. Furthermore, edge node alarm strategies are typically predefined and rigid, lacking linkage with the global cloud situation. When an event occurs in a certain area, edge nodes often can only issue local independent alarms, failing to achieve cross-node and cross-regional collaborative early warning and linkage control, making it difficult to form a globally optimal control strategy.

[0005] In conclusion, existing technologies can no longer meet people's needs and urgently need to be improved. Summary of the Invention

[0006] The main objective of this application is to provide a traffic network scheduling and control method, system, and electronic device based on spatiotemporal big data, thereby addressing the shortcomings of existing technologies.

[0007] The embodiments of this application are implemented using the following technical solutions: According to one aspect of the embodiments of this application, a cloud-edge-device collaborative urban traffic management data control method is provided, including a cloud server, an edge computing node, and a terminal device: At the edge, the edge computing node establishes a data connection with the terminal device, receives real-time collected raw data streams, parses and preprocesses the raw data streams, and extracts corresponding structured object information; spatially filters the data using preset geofencing rules issued from the cloud server, and generates a target trajectory data stream through edge detection, contour closure, and historical frame tracking; the edge computing node calls its built-in fusion engine based on the target trajectory data stream, and performs spatiotemporal alignment and correlation matching of target trajectory data streams from different sources according to the unified world coordinate system and time reference provided by the cloud server, generating fused trajectory data; based on the fused trajectory data, the edge computing node simultaneously performs traffic parameter calculation and event risk assessment, and, based on virtual detection within a unit of time... The system calculates real-time traffic flow by counting the number of tracks on the monitoring lines, and obtains the average traffic speed by calculating the ratio of track displacement to time interval. The fused track data is then input into an event risk assessment model, which analyzes the spatiotemporal relationships and behavioral patterns between tracks to output an event risk probability value. Edge computing nodes compare the event risk probability value with an event risk threshold in real time, generate an event occurrence probability level based on the comparison results, and trigger an alarm response corresponding to the event occurrence probability level. On the cloud side, the cloud server acquires multi-dimensional traffic operation status information uploaded by each edge computing node. This multi-dimensional traffic operation status information is used for macro-level traffic situation analysis and model iterative optimization. The cloud server periodically distributes updated traffic control strategies and dynamic model configuration information to each edge computing node. The edge computing nodes receive the traffic control strategies and dynamic model configuration information and adjust their local processing logic and alarm strategies accordingly.

[0008] According to at least one specific implementation of the embodiments of this application, when extracting the corresponding structured object information, the structured object information includes the target position, speed, direction, and type, and the generation of the target trajectory data stream specifically involves generating a target trajectory data stream with a unique tracking identifier.

[0009] According to at least one specific embodiment of the present application, the edge computing node invokes its built-in fusion engine based on the target trajectory data stream, and performs spatiotemporal alignment and correlation matching on target trajectory data streams from different sources based on a unified world coordinate system and time reference provided by a cloud server to generate fused trajectory data. This further includes: the edge computing node receiving the target trajectory data stream from a terminal device, performing spatiotemporal alignment on the target trajectory data stream based on a unified world coordinate system reference and high-precision time synchronization service issued from a cloud server, and obtaining an aligned trajectory set with a unified spatiotemporal reference; the edge computing node invokes its built-in multi-source data fusion engine, performs smoothing processing on the trajectory data in the aligned trajectory set using a Kalman filter prediction algorithm deployed on the edge side, performs cross-source correlation matching on the predicted trajectory data based on a Hungarian matching algorithm, calculates the correlation matrix between different trajectory data, and completes trajectory pairing according to a preset correlation threshold; based on the trajectory pairing result, the fusion engine performs weighted fusion and confidence update on multiple trajectory source data belonging to the same traffic object to generate fused trajectory data.

[0010] According to at least one specific embodiment of the present application, based on the fused trajectory data, the edge computing node synchronously performs traffic parameter calculation and event risk assessment, calculates real-time traffic flow based on the number of trajectories passing through the virtual detection line per unit time, and obtains the average traffic speed by calculating the ratio of trajectory displacement to time interval, and: inputs the fused trajectory data into an event risk assessment model, the event risk assessment model outputs an event risk probability value by analyzing the spatiotemporal relationship and behavior pattern between trajectories, further including: the edge computing node starts a traffic parameter calculation thread and an event risk assessment thread based on the received fused trajectory data stream, calculates the real-time traffic flow in the traffic parameter calculation thread, and obtains the calculation result of the average traffic speed of the road network by the ratio of the displacement vector of the fused trajectory data to the corresponding time interval; the edge computing node inputs the fused trajectory data into a locally deployed event risk assessment model, the event risk assessment model constructs a corresponding trajectory interaction relationship map by analyzing the relative spatial distance, the angle of motion direction, and the speed difference between the fused trajectory data, and performs pattern recognition and risk inference on the trajectory interaction relationship map through a neural network; based on the results of the pattern recognition and risk inference, the event risk assessment model generates a corresponding event risk probability value.

[0011] According to at least one specific implementation of the embodiments of this application, a fusion evaluation output of the current road network status is constructed based on the real-time traffic flow, average traffic speed and event risk probability value.

[0012] According to at least one specific embodiment of the present application, the edge computing node compares the event risk probability value with the event risk threshold in real time, generates an event occurrence probability level based on the comparison result, and triggers an alarm response corresponding to the event occurrence probability level. This further includes: the edge computing node, based on the locally obtained event risk probability value, accesses a risk threshold configuration library issued by a cloud server to obtain a multi-dimensional risk threshold corresponding to the current event type; compares the event risk probability value with the multi-dimensional risk threshold level step by step to calculate the risk exceedance level and confidence assessment result; the edge computing node calls a preset level-response mapping strategy to generate a set of response instructions matching the current risk exceedance level, and triggers an alarm response corresponding to the event occurrence probability level through the set of response instructions.

[0013] According to at least one specific embodiment of the present application, the cloud server periodically distributes updated traffic control strategies and model dynamic configuration information to each edge computing node. The edge computing node receives the traffic control strategies and model dynamic configuration information and adjusts its local processing logic and alarm strategy. Further, the cloud server, based on analysis of the running data and historical event cases provided to the edge computing nodes, periodically executes model retraining and strategy optimization algorithms to generate updated traffic control strategies and model dynamic configuration information. The model dynamic configuration information encapsulates neural network model parameters, a multi-level risk threshold matrix, and an event processing rule set. The cloud server distributes the traffic control strategies and model dynamic configuration information to the edge computing nodes through a secure communication link. The edge computing nodes, through a configuration management service, complete the parameter loading, threshold table replacement, and new rule engine deployment of the event risk assessment model in their local environment, forming a new version model, and switch to the new version model through a hot-switching mechanism.

[0014] According to another aspect of the embodiments of this application, a cloud-edge-device collaborative urban traffic management data control system is provided, used to implement the cloud-edge-device collaborative urban traffic management data control method, including: a target trajectory data stream generation module, on the edge side, an edge computing node establishes a data connection with a terminal device, receives real-time collected raw data streams, parses and preprocesses the raw data streams, extracts corresponding structured object information; uses preset geofencing rules issued from a cloud server to spatially filter the data, and generates a target trajectory data stream through edge detection, contour closure, and historical frame tracking processing; a fusion trajectory data generation module, where the edge computing node calls a built-in fusion engine based on the target trajectory data stream, and performs spatiotemporal alignment and correlation matching of target trajectory data streams from different sources according to a unified world coordinate system and time reference provided by the cloud server, generating fused trajectory data; and an event risk probability value output module, where, based on the fused trajectory data, the edge computing node simultaneously performs traffic parameter calculation and event risk assessment, based on a unit time... The system calculates real-time traffic flow by counting the number of virtual detection lines and obtains average traffic speed by calculating the ratio of trajectory displacement to time interval. It also inputs the fused trajectory data into an event risk assessment model, which analyzes the spatiotemporal relationships and behavioral patterns between trajectories to output an event risk probability value. A traffic event occurrence probability level alarm response module is used where edge computing nodes compare the event risk probability value with an event risk threshold in real time, generate an event occurrence probability level based on the comparison result, and trigger an alarm response corresponding to the event occurrence probability level. An edge computing node local processing module is used where, on the cloud side, the cloud server acquires multi-dimensional traffic operation status information uploaded by each edge computing node. This multi-dimensional traffic operation status information is used for macro-level traffic situation analysis and model iterative optimization. The cloud server periodically distributes updated traffic control strategies and model dynamic configuration information to each edge computing node, which receives the traffic control strategies and model dynamic configuration information and adjusts its local processing logic and alarm strategies accordingly.

[0015] According to another aspect of the embodiments of this application, an electronic device is provided, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method.

[0016] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided that stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method.

[0017] The beneficial technical effects of the embodiments of this application are: The cloud-edge-device collaborative urban traffic management data control method and system provided in this application adopts a collaborative architecture that combines cloud-based optimized training with edge-distributed real-time execution. By completing the efficient fusion of multi-source data, real-time calculation of traffic parameters, and local event risk assessment and graded response based on the intelligent model distributed from the cloud at the edge, and by using cloud-based aggregation of network data to iteratively optimize the model and strategy and dynamically distribute it to the edge, the goal of integrating global intelligence with local real-time computing capabilities is achieved. This improves the real-time enhancement of traffic situation awareness, enables intelligent traffic event risk assessment, and increases the adaptive capability of the traffic control system.

[0018] This application's embodiments address the problems of high data processing latency in the centralized architecture of existing technologies and the lack of fusion and intelligent decision-making capabilities of existing edge computing nodes. It avoids the shortcomings of slow system response caused by the inability of static models to adapt to dynamic and complex traffic environments, improves the accuracy of traffic event early warning, and has broad application prospects. Attached Figure Description

[0019] To more clearly illustrate the specific implementation methods of the embodiments of this application or the technical solutions in the prior art, the drawings used in the description of the specific implementation methods or the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of steps S1 to S6 in an embodiment of this application.

[0021] Figure 2 This is a flowchart of the optimization technical solutions provided in steps S21 to S23.

[0022] Figure 3 This is a flowchart of the optimization technical solutions provided in steps S31 to S33.

[0023] Figure 4 This is a flowchart of the optimization technical solution provided in steps S41 to S42.

[0024] Figure 5 This is a flowchart of the optimization technical solution provided in steps S61 to S62.

[0025] Figure 6 This is a system architecture diagram of an embodiment of this application.

[0026] Figure 7 This is a schematic diagram of the electronic device. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this application, and not all embodiments. Based on the specific implementation methods in the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of the embodiments of this application.

[0028] like Figure 1 The cloud-edge-device collaborative urban traffic management data control method shown includes a cloud server, edge computing nodes, and terminal devices, and includes the following steps: Step S1: On the edge side, the edge computing node establishes a data connection with the terminal device, receives the raw data stream collected in real time, parses and preprocesses the raw data stream, and extracts the corresponding structured object information; spatial filtering of the data is performed using preset geofencing rules issued from the cloud server, and target trajectory data stream is generated through edge detection, contour closure, and historical frame tracking. For example, when extracting the corresponding structured object information, the structured object information includes the target location, speed, direction, and type; specifically, generating the target trajectory data stream involves generating a target trajectory data stream with a unique tracking identifier.

[0029] Step S2: The edge computing node calls the built-in fusion engine based on the target trajectory data stream, and performs spatiotemporal alignment and correlation matching on the target trajectory data streams from different sources according to the unified world coordinate system and time reference provided by the cloud server, to generate fused trajectory data.

[0030] Step S3: Based on the fused trajectory data, the edge computing nodes simultaneously perform traffic parameter calculations and event risk assessments. Real-time traffic flow is calculated based on the number of trajectories passing through the virtual detection line per unit time, and the average traffic speed is obtained by calculating the ratio of trajectory displacement to time interval. The fused trajectory data is then input into the event risk assessment model, which analyzes the spatiotemporal relationships and behavioral patterns between trajectories to output an event risk probability value. In this step, the event risk assessment model is trained by a cloud server and distributed to the edge computing nodes.

[0031] Step S4: The edge computing node compares the event risk probability value with the event risk threshold in real time, generates an event occurrence probability level based on the comparison result, and triggers an alarm response corresponding to the event occurrence probability level. In this step, the event risk threshold is stored on a cloud server, and the comparison result also includes a preset level relationship between the event risk probability value and the event risk threshold. The alarm response includes generating visual alarm information and activating audible and visual alarm devices.

[0032] Step S5: On the cloud side, the cloud server acquires multi-dimensional traffic operation status information uploaded by each edge computing node. This multi-dimensional traffic operation status information is used for macro-level traffic situation analysis and model iterative optimization. In this step, the multi-dimensional traffic operation status information includes: traffic data, event cases, and model feedback information.

[0033] In step S6, the cloud server periodically sends the updated traffic control strategy and model dynamic configuration information to each edge computing node. The edge computing node receives the traffic control strategy and model dynamic configuration information and adjusts its local processing logic and alarm strategy.

[0034] Definitions: Raw data stream: refers to the initial sensing signal sequence collected by terminal devices (such as cameras and radar) without processing, such as video frames and radar point clouds. The raw data stream contains underlying information, but it is heterogeneous in format and highly redundant, and it is the data raw material for all subsequent intelligent processing.

[0035] Structured object information (SIE) refers to traffic element descriptions with clear semantics and a unified format, parsed and extracted from raw data streams. SIE typically includes attributes such as the category of traffic targets (e.g., pedestrians, vehicles, etc.), location coordinates, instantaneous speed, direction of movement, and confidence level. It serves as intermediate data for computer understanding and processing.

[0036] Preset geofencing rules: A spatial constraint strategy defined in the cloud and distributed to the edge, explicitly defining the region of interest (ROI) that the system needs to process, in the form of polygonal geographic coordinates or logical regions. Preset geofencing rules are mainly used in the data preprocessing stage to filter out sensing targets that are not within the scope of interest, reducing unnecessary computational load.

[0037] Spatial filtering: A data cleaning operation based on preset geofencing rules. During the data cleaning process, the spatial relationship between the target's coordinate information and the fence boundary is determined (e.g., the point is inside the polygon). Only the target data located within the area of ​​interest is retained, thereby achieving preliminary location-based data filtering and noise reduction.

[0038] Edge detection, contour closure, and historical frame tracking: The above three concepts are used in the image processing and data association process to generate continuous target trajectories from the perceived data. By detecting the boundaries of the targets in the image, they are connected into complete contours, and cross-frame target matching and state association are performed in the time series based on motion consistency, outputting trajectory data with spatiotemporal continuity.

[0039] Fusion Engine: A core software module deployed in edge computing nodes, responsible for integrating and optimizing heterogeneous trajectory data from different sensing sources. The fusion engine outputs fused trajectory data through algorithms such as unified spatiotemporal benchmarks, correlation matching, and confidence weighting.

[0040] Spatiotemporal alignment: a preprocessing step before multi-source data fusion, used to solve the problem of data incomparability caused by inconsistent spatial coordinate systems and asynchronous timestamps of different sensing devices. Through coordinate transformation and time interpolation, all data are mapped to a unified spatiotemporal reference system.

[0041] Virtual detection line: A logical detection section without a physical entity, defined in a digital map or image coordinate system, typically a line segment. Used to count parameters such as traffic flow, the system completes the counting by determining the intersection relationship between the target trajectory and the virtual detection line (e.g., moving from side A to side B).

[0042] The technical solutions provided in steps S1 to S6 realize a control method and system that integrates cloud optimization and edge computing. Steps S1 to S4 enable local perception, decision-making, and response at edge nodes. Edge nodes are responsible for processing raw data, integrating multi-source information, and using models and thresholds distributed from the cloud for real-time risk assessment and response, ensuring the traffic management system's low-latency handling capability for traffic incidents. Steps S5 to S6 construct a cloud-optimized handling system. By aggregating experience data from edge nodes across the entire network, conducting in-depth analysis and model iteration, and then re-injecting the optimized strategies and intelligent models into the edge nodes, the traffic management system achieves continuous evolution and adaptive capabilities.

[0043] In steps S1 to S4, the rapid response and data processing capabilities of the local traffic network formed by the design computing nodes are enhanced. Furthermore, the pre-built intelligence in the cloud is utilized to complete the basic data processing functions—from acquiring sensor signals to providing early warning information—near the data source. This reduces the latency caused by network transmission and centralized processing, ensuring the immediacy of responses to critical events. Steps S5 to S6, based on the basic data processing functions provided in steps S1 to S4, continuously optimize and learn from the execution results of all edge nodes in the cloud, iteratively updating the model and its corresponding strategies. This not only updates its own strategy output capabilities but also updates the capabilities of edge nodes in real time, enabling the entire traffic control system to adapt to changes in traffic flow patterns. This avoids the degradation of static system performance and periodically synchronizes the unified and optimized control strategies and model configurations to all edge nodes, ensuring the consistency of the traffic network's overall control standards and intelligence level.

[0044] like Figure 2As shown, preferably, in step S2, the edge computing node invokes its built-in fusion engine based on the target trajectory data stream, and performs spatiotemporal alignment and correlation matching on target trajectory data streams from different sources according to the unified world coordinate system and time reference provided by the cloud server, generating fused trajectory data, further including: Step S21: The edge computing node receives the target trajectory data stream from the terminal device, and performs a spatiotemporal alignment operation on the target trajectory data stream based on the unified world coordinate system reference and high-precision time synchronization service issued from the cloud server to obtain an aligned trajectory set with a unified spatiotemporal reference.

[0045] In step S22, the edge computing node calls its built-in multi-source data fusion engine, uses the Kalman filter prediction algorithm deployed on the edge to smooth the trajectory data in the aligned trajectory set, performs cross-source association matching on the predicted trajectory data based on the Hungarian matching algorithm, calculates the association degree matrix between different trajectory data, and completes trajectory pairing according to the preset association threshold.

[0046] Step S23: Based on the trajectory pairing results, the fusion engine performs weighted fusion and confidence updates on multiple trajectory source data belonging to the same traffic object to generate fused trajectory data. This fused trajectory data is used to support subsequent real-time traffic parameter calculations and event risk assessments.

[0047] The optimization techniques provided in steps S21 to S23 transform multi-source heterogeneous raw data into structured data with a unified standard, providing a reliable data foundation for subsequent steps. Through the spatiotemporal alignment operation in step S21, based on the benchmark data provided in the cloud, all input data are unified under the same spatiotemporal framework, eliminating data structure inconsistencies caused by device differences, clock drift, and coordinate deviations, ensuring that all subsequent data processing is performed on the same benchmark. Step S22 achieves algorithmic collaboration by smoothing the trajectory and predicting its state using the Kalman filter algorithm. This not only filters out noise but, more importantly, provides stable trajectory state estimates for the subsequent Hungarian matching algorithm, improving the accuracy and robustness of cross-source trajectory association. The trajectory pairing results output in step S22 provide the basis for weighted fusion and confidence updates in step S23. Step S23 completes the data fusion calculation at the edge, achieving the dual goals of improving data quality and ensuring system real-time performance. It avoids the bandwidth consumption and excessive latency caused by uploading massive amounts of raw trajectory data to the cloud for fusion, enabling the generated high-quality fused trajectory data to be used in real time and without delay by subsequent data analysis modes on the same node. This forms an efficient data processing chain from data fusion to decision-making applications, meeting the stringent requirements of intelligent transportation for data real-time performance.

[0048] In summary, the optimization solutions provided in steps S21 to S23 transform fragmented target trajectory data from different sensing terminals into unified and continuous fused trajectory data, laying a solid data foundation for the application of this data in subsequent steps.

[0049] like Figure 3 As shown, preferably, in step S3, based on the fused trajectory data, the edge computing node synchronously performs traffic parameter calculation and event risk assessment, calculates real-time traffic flow based on the number of trajectories passing through the virtual detection line per unit time, and obtains the average traffic speed by calculating the ratio of trajectory displacement to time interval; and: inputs the fused trajectory data into the event risk assessment model, the event risk assessment model outputs an event risk probability value by analyzing the spatiotemporal relationship and behavioral patterns between trajectories, further including: In step S31, the edge computing node, based on the received fused trajectory data stream, initiates a traffic parameter calculation thread and an event risk assessment thread. The traffic parameter calculation thread calculates the real-time traffic flow, and the average traffic speed of the road network is obtained by calculating the ratio of the displacement vector of the fused trajectory data to the corresponding time interval. In this step, the real-time traffic flow is calculated by statistically analyzing the number of fused trajectories crossing the virtual detection line within a preset time window. Based on the real-time traffic flow, average traffic speed, and event risk probability value, a fused assessment output of the current road network state can be constructed to support subsequent hierarchical decision-making and response control.

[0050] In step S32, the edge computing node inputs the fused trajectory data into a locally deployed event risk assessment model. The event risk assessment model constructs a corresponding trajectory interaction relationship graph by analyzing the relative spatial distance, angle of motion direction, and speed differences between the fused trajectory data. A neural network then performs pattern recognition and risk inference on the trajectory interaction relationship graph. In this step, the neural network is a pre-trained neural network in the cloud.

[0051] Step S33: Based on the results of pattern recognition and risk reasoning, the event risk assessment model generates corresponding event risk probability values. The event risk probability value characterizes the likelihood of potential conflicts, abnormal clustering, or violations occurring, providing a quantitative analysis of traffic events.

[0052] Definitions: Pattern recognition refers to the process of automatically discovering, extracting, and classifying statistically regular or typical interaction structures, behavioral sequences, or abnormal patterns from an input trajectory interaction graph. The core of pattern recognition is identifying interaction pattern categories with specific risk implications, such as close following, sudden lane changes, and intersection conflicts, providing understandable intermediate features for risk assessment.

[0053] Risk reasoning refers to the process of inferring the likelihood, severity, and timing of potential traffic incidents based on pattern recognition, identified interaction patterns, and contextual information (such as vehicle speed, road type, and weather), using knowledge or statistical models. Risk reasoning deduces the possible consequences of patterned behavior and the probability of those consequences occurring, rather than making causal judgments, and outputs corresponding quantitative risk probability values.

[0054] The optimization solutions provided in steps S31 to S33 employ a dual-thread parallel processing approach for the fused trajectory data, simultaneously extracting macroscopic statistical features (traffic parameters) and mining microscopic interactive risks (event probabilities) to construct a comprehensive quantitative assessment result. This comprehensive quantitative assessment result can reflect both the overall operational status of the current traffic situation and provide early warnings for specific local risks, including: Step S31 enables multi-dimensional and highly efficient concurrent mining of the same data source. Through the traffic parameter calculation thread established in step S31, the traffic management system can continuously output core indicators reflecting the overall load and efficiency of the road network with relatively low computational overhead. Simultaneously, by establishing independent event risk assessment threads in steps S32 and S33, neural network models are invoked to deeply analyze the interactions between trajectories, uncover potential safety risks, and form corresponding fused trajectory data streams. This allows the traffic management system to simultaneously analyze both current road conditions and potential traffic risks within a single data processing cycle, improving data utilization efficiency and the comprehensiveness of system assessment.

[0055] It is worth noting that step S31 employs a rule-based algorithm, primarily involving statistical counting and algebraic ratio operations. The output of step S31 is relatively stable, intuitive, and interpretable, and can be considered basic data for traffic management. Steps S32 and S33, on the other hand, utilize a neural network model capable of handling high-dimensional, non-linear data relationships and uncovering hidden risk patterns within the basic traffic management data. Through the synergy of steps S31 and S33, the data output of step S31 provides context for the risk probability value output by step S33, making step S3 both interpretable and capable of predicting high-dimensional, non-linear data relationships. For example, the high-risk probability under high traffic volume differs significantly in urgency and possible causes from the high-risk probability under low traffic volume. By constructing a fusion assessment output from both, the decision-making system can obtain accurate traffic risk warnings and conduct comprehensive judgments based on intuitive statistical parameters. The purpose of step S32 is to deploy the pre-trained neural network model on the edge computing node and perform data analysis locally on the edge computing node, thus completing the corresponding calculation work on the edge side and avoiding the computational delay caused by uploading massive amounts of trajectory interaction data to the cloud.

[0056] like Figure 4 As shown, preferably, in step S4, the edge computing node compares the event risk probability value with the event risk threshold in real time, generates an event occurrence probability level based on the comparison result, and triggers an alarm response corresponding to the event occurrence probability level, further including: Step S41: Based on the locally obtained event risk probability value, the edge computing node obtains the multi-dimensional risk threshold corresponding to the current event type by accessing the risk threshold configuration library issued by the cloud server, and compares the event risk probability value with the multi-dimensional risk threshold level by level to calculate the risk exceedance level and confidence assessment result.

[0057] In step S42, the edge computing node invokes a preset level-response mapping strategy to generate a set of response instructions that matches the current risk exceedance level, and triggers an alarm response corresponding to the event occurrence probability level through the set of response instructions.

[0058] For example, the response instruction set includes alarm information generation instructions, device control instructions, and data reporting instructions. The response instruction set encapsulates execution priority and timing logic. A visual alarm interface is generated through a graphics rendering engine and pushed to the monitoring terminal. The visual alarm interface includes event location, risk level, and handling suggestions. The visual alarm interface sends control signals to the on-site audible and visual alarm devices to trigger the audible and visual alarm mode corresponding to the risk exceeding the limit level.

[0059] The optimization solutions provided in steps S41 to S42 transform abstract risk probability values ​​into a set of specific control instructions through a strategy-driven decision engine. This process involves dynamic threshold matching and risk rating, as well as strategy mapping and instruction generation, achieving an automated and intelligent process from risk perception to instruction control. This ensures the matching of response measures with risk levels and the controllability of instruction execution. Step S41 accesses the multi-dimensional risk threshold database bound to event types, distributed from the cloud, compares risk probability values, and further calculates the corresponding risk exceedance level and confidence assessment results reflecting the reliability of the judgment. This refined classification provides a decision-making basis for the response in step S42, enabling subsequent responses to be differentiated based on different risks, reducing false alarms and alarm fatigue. Step S42, based on the level classification determined in step S41, invokes a preset level-response mapping strategy to generate a set of response instructions encapsulated with execution priorities and timing logic. This allows the risk level output in step S41 to drive the corresponding response action in step S42. For example: first, a high-priority visual alarm is pushed to the traffic control center; simultaneously, a medium-priority instruction activates the traffic scene's audible and visual alarm to warn surrounding vehicles and personnel; then, a low-priority data recording and reporting process is initiated. By handling different events through instructions of different priorities, the system's handling capabilities are enhanced.

[0060] It can be seen that both the risk threshold configuration library in step S41 and the level-response mapping strategy in step S42 are uniformly distributed and maintained by the cloud. This enables the risk rating standards and response rules in step S4 to achieve global unified management and dynamic updates. After obtaining the risk threshold configuration library and the level-response mapping strategy, all decision-making and execution actions, such as threshold comparison, strategy matching, instruction generation, and driving devices, are completed in real time by edge computing nodes on the edge side. Therefore, the work of steps S41 and S42, under the collaborative cooperation between the cloud and the edge, can strictly follow the global control will defined by the cloud and achieve real-time response on the edge side, balancing the needs of centralized control and distributed real-time execution.

[0061] like Figure 5 As shown, preferably, in step S6, the cloud server periodically sends the updated traffic control strategy and model dynamic configuration information to each edge computing node. The edge computing node receives the traffic control strategy and model dynamic configuration information, adjusts its local processing logic and alarm strategy, and further includes: In step S61, the cloud server periodically executes model retraining and strategy optimization algorithms based on the analysis of the running data and historical event cases provided by the edge computing nodes, and generates updated traffic control strategies and model dynamic configuration information. The model dynamic configuration information encapsulates neural network model parameters, multi-level risk threshold matrices, and event processing rule sets.

[0062] In step S62, the cloud server distributes the traffic control strategy and dynamic model configuration information to the edge computing node via a secure communication link. The edge computing node, through a configuration management service, completes parameter loading, threshold table replacement, and deployment of the new rule engine for the event risk assessment model in its local environment. This forms a new version of the model, which is then switched to via a hot-swapping mechanism. This achieves seamless online upgrades to processing and decision-making capabilities and global policy synchronization. The dynamic model configuration information includes model parameters, risk thresholds, and processing rules.

[0063] The optimization solutions provided in steps S61 to S62 are data-driven and centered on transforming the static edge-side intelligence of traditional technologies into a mechanism that can be updated online and optimized in the cloud, enabling multi-level collaboration between the cloud, edge, and terminal. This involves building a technology that learns from the operational experience of the entire transportation network in the cloud and deploys the learning results to edge nodes, including: In step S61, the cloud server actively collects operational data and historical traffic event data from the edge nodes of the traffic network for periodic analysis and executes model retraining and strategy optimization algorithms. This enables the neural network model to learn the latest traffic patterns, the risk threshold to be automatically calibrated based on historical performance, and the processing rules to be improved based on real traffic conditions.

[0064] Step S62 upgrades and synchronizes the model parameters, threshold matrix, and event processing rules from step S61. It unifies these elements in the cloud and provides standardized configuration management services to edge nodes, updating model parameters, risk thresholds, and the rule engine locally on the edge nodes. Step S62 introduces a hot-switching mechanism, enabling capability upgrades without interrupting real-time services. This allows edge nodes to upgrade their running decision logic from the old version to the new version of the model and strategy generated in step S61 without restarting or stopping the current traffic data processing business, achieving seamless upgrades and switching without requiring downtime maintenance.

[0065] In summary, step S61, through its collaboration with step S62, ensures that the decision-making logic and judgment criteria used by all edge nodes can be upgraded simultaneously and uniformly to the latest version generated by global optimization in the cloud, thus avoiding differences in traffic management decisions caused by inconsistent node versions and preventing traffic control loopholes.

[0066] like Figure 6 As shown in the embodiments, this application also discloses a cloud-edge-device collaborative urban traffic management data control system, used to implement the cloud-edge-device collaborative urban traffic management data control method described in any specific embodiment of this application, including: The target trajectory data stream generation module establishes a data connection between the edge computing node and the terminal device on the edge side, receives the raw data stream collected in real time, parses and preprocesses the raw data stream, and extracts the corresponding structured object information; it uses preset geofencing rules issued from the cloud server to perform spatial filtering on the data, and generates the target trajectory data stream through edge detection, contour closure and historical frame tracking processing. The fusion trajectory data generation module involves edge computing nodes calling the built-in fusion engine based on the target trajectory data stream. According to the unified world coordinate system and time reference provided by the cloud server, the module performs spatiotemporal alignment and correlation matching on target trajectory data streams from different sources to generate fusion trajectory data. The event risk probability value output module, based on the fused trajectory data, performs traffic parameter calculation and event risk assessment simultaneously on the edge computing node, calculates real-time traffic flow based on the number of trajectories passing through the virtual detection line per unit time, and obtains average traffic speed by calculating the ratio of trajectory displacement to time interval, and inputs the fused trajectory data into the event risk assessment model, which outputs the event risk probability value by analyzing the spatiotemporal relationship and behavior pattern between trajectories. The traffic incident probability level alarm response module uses edge computing nodes to compare the event risk probability value with the event risk threshold in real time, generate the event occurrence probability level based on the comparison result, and trigger an alarm response corresponding to the event occurrence probability level. The edge computing node local processing module, on the cloud side, the cloud server obtains multi-dimensional traffic operation status information uploaded by each edge computing node. The multi-dimensional traffic operation status information is used for macro-analysis of traffic situation and iterative optimization of model. The cloud server periodically sends the updated traffic control strategy and model dynamic configuration information to each edge computing node. The edge computing node receives the traffic control strategy and model dynamic configuration information and adjusts its local processing logic and alarm strategy.

[0067] The implementation methods of the system described above are merely illustrative. For example, the various functional modules, units, or subsystems within the system may or may not be physically separate, or they may or may not be physical units; that is, they may be located in the same place or distributed across multiple different systems and their subsystems or modules. Those skilled in the art can select some or all of the functional modules, units, or subsystems to achieve the objectives of the embodiments of the present invention according to actual needs. Those skilled in the art can understand and implement the above-described situations without any creative effort.

[0068] like Figure 7 As shown, this application embodiment, in addition to providing a cloud-edge-device collaborative urban traffic management data control method and system, also provides corresponding electronic devices and storage media: An electronic device includes: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the method.

[0069] A computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method.

[0070] Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 7 As shown, device 800 includes a processor 801, a memory 802, a communication interface 803, and a bus 804. The processor 801, memory 802, and communication interface 803 communicate via bus 804, or via other means such as wireless transmission. The memory 802 stores instructions, and the processor 801 executes the instructions stored in the memory 802. The memory 802 stores program code 8021, and the processor 801 can call the program code 8021 stored in the memory 802 to execute the steps of the cloud-edge-device collaborative urban traffic management data control method.

[0071] It should be understood that in the embodiments of this application, processor 801 may be a CPU, or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors may be microprocessors or any conventional processors, etc.

[0072] The memory 802 may include read-only memory (ROM) and random access memory (RAM), and provides instructions and data to the processor 801. The memory 802 may also include non-volatile random access memory. The memory 802 may be volatile memory or non-volatile memory, or may include both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0073] In addition to the data bus, bus 804 may also include a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as bus 804 in the diagram.

[0074] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive (SSD).

[0075] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the specification of the embodiments of this application.

[0076] In the description of the embodiments of this application, the reference to terms such as "an embodiment," "example," "specific example," etc., means that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0077] Furthermore, the technical solutions of the various implementation methods in this application can be combined with each other, but only if they are based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the embodiments of this application.

[0078] All features disclosed in the embodiments of this application, or all steps in the disclosed methods or processes, may be combined in any way, except for mutually exclusive features and / or steps. Any feature disclosed in the specification of the embodiments of this application, unless specifically stated otherwise, may be replaced by other equivalent or similar alternative features. That is, unless specifically stated otherwise, each feature is merely one example of a series of equivalent or similar features. Throughout the specification, the same reference numerals indicate the same elements.

[0079] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification of embodiments (including the corresponding claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification of embodiments (including the corresponding claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of this application, and are not intended to limit them. Although the embodiments of this application have been described in detail with reference to the foregoing specific embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing specific embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this invention.

Claims

1. A cloud-edge-device collaborative urban traffic management data control method, comprising a cloud server, edge computing nodes, and terminal devices, characterized in that: At the edge, edge computing nodes establish data connections with terminal devices, receive raw data streams collected in real time, parse and preprocess the raw data streams, and extract the corresponding structured object information. The data is spatially filtered using preset geofencing rules issued from the cloud server, and a target trajectory data stream is generated through edge detection, contour closure and historical frame tracking. The edge computing node calls the built-in fusion engine based on the target trajectory data stream, and performs spatiotemporal alignment and correlation matching on the target trajectory data streams from different sources according to the unified world coordinate system and time reference provided by the cloud server, to generate fused trajectory data; Based on the fused trajectory data, the edge computing node synchronously performs traffic parameter calculation and event risk assessment, calculates real-time traffic flow based on the number of trajectories passing through the virtual detection line per unit time, and obtains the average traffic speed by calculating the ratio of trajectory displacement to time interval. The fused trajectory data is then input into the event risk assessment model, which outputs an event risk probability value by analyzing the spatiotemporal relationship and behavior patterns between trajectories. The edge computing node compares the event risk probability value with the event risk threshold in real time, generates an event occurrence probability level based on the comparison result, and triggers an alarm response corresponding to the event occurrence probability level. On the cloud side, the cloud server acquires multi-dimensional traffic operation status information uploaded by each edge computing node. This multi-dimensional traffic operation status information is used for macro-analysis of traffic conditions and iterative optimization of models. The cloud server periodically distributes updated traffic control strategies and dynamic model configuration information to each edge computing node. The edge computing node receives the traffic control strategies and dynamic model configuration information and adjusts its local processing logic and alarm strategies accordingly.

2. The cloud-edge-device collaborative urban traffic management data control method according to claim 1, characterized in that, When extracting the corresponding structured object information, the structured object information includes the target position, velocity, direction, and type. Specifically, generating the target trajectory data stream involves generating a target trajectory data stream with a unique tracking identifier.

3. The cloud-edge-device collaborative urban traffic management data control method according to claim 1, characterized in that, The edge computing node invokes its built-in fusion engine based on the target trajectory data stream, and performs spatiotemporal alignment and correlation matching on target trajectory data streams from different sources according to the unified world coordinate system and time reference provided by the cloud server, generating fused trajectory data, which further includes: Edge computing nodes receive target trajectory data streams from terminal devices and perform spatiotemporal alignment operations on the target trajectory data streams based on a unified world coordinate system reference and high-precision time synchronization service issued from a cloud server to obtain a set of aligned trajectories with a unified spatiotemporal reference. The edge computing node calls its built-in multi-source data fusion engine, uses the Kalman filter prediction algorithm deployed on the edge to smooth the trajectory data in the aligned trajectory set, performs cross-source association matching on the predicted trajectory data based on the Hungarian matching algorithm, calculates the association degree matrix between different trajectory data, and completes trajectory pairing according to the preset association threshold. Based on the trajectory pairing results, the fusion engine performs weighted fusion and confidence updates on multiple trajectory source data belonging to the same traffic object to generate fused trajectory data.

4. The cloud-edge-device collaborative urban traffic management data control method according to claim 1, characterized in that, Based on the fused trajectory data, edge computing nodes simultaneously perform traffic parameter calculations and event risk assessments. Real-time traffic flow is calculated based on the number of trajectories passing through the virtual detection line per unit time, and the average traffic speed is obtained by calculating the ratio of trajectory displacement to time interval. Furthermore, the fused trajectory data is input into an event risk assessment model, which analyzes the spatiotemporal relationships and behavioral patterns between trajectories to output an event risk probability value. Based on the received fused trajectory data stream, the edge computing node starts a traffic parameter calculation thread and an event risk assessment thread. In the traffic parameter calculation thread, the real-time traffic flow is calculated, and the average traffic speed of the road network is obtained by the ratio of the displacement vector of the fused trajectory data to the corresponding time interval. The edge computing node inputs the fused trajectory data into a locally deployed event risk assessment model. The event risk assessment model constructs a corresponding trajectory interaction relationship map by analyzing the relative spatial distance, the angle of motion direction, and the speed difference between the fused trajectory data. A neural network performs pattern recognition and risk reasoning on the trajectory interaction relationship map. Based on the results of pattern recognition and risk reasoning, the event risk assessment model generates a corresponding event risk probability value.

5. The cloud-edge-device collaborative urban traffic management data control method according to claim 4, characterized in that, Based on the real-time traffic flow, average traffic speed, and event risk probability value, a fusion assessment output of the current road network status is constructed.

6. The cloud-edge-device collaborative urban traffic management data control method according to claim 1, characterized in that, The edge computing node compares the event risk probability value with the event risk threshold in real time, generates an event occurrence probability level based on the comparison result, and triggers an alarm response corresponding to the event occurrence probability level, further including: Based on the event risk probability value obtained locally, the edge computing node accesses the risk threshold configuration library issued by the cloud server to obtain the multi-dimensional risk threshold corresponding to the current event type, compares the event risk probability value with the multi-dimensional risk threshold level by level, and calculates the risk exceedance level and confidence assessment result. The edge computing node invokes a preset level-response mapping strategy to generate a set of response instructions that matches the current risk exceedance level, and triggers an alarm response corresponding to the probability level of the event occurrence through the set of response instructions.

7. The cloud-edge-device collaborative urban traffic management data control method according to claim 1, characterized in that, The cloud server periodically distributes updated traffic control strategies and model dynamic configuration information to each edge computing node. The edge computing nodes receive the traffic control strategies and model dynamic configuration information and adjust their local processing logic and alarm strategies, further including: The cloud server periodically executes model retraining and strategy optimization algorithms based on the analysis of operational data and historical event cases provided by edge computing nodes, generating updated traffic control strategies and dynamic model configuration information. The dynamic model configuration information encapsulates neural network model parameters, multi-level risk threshold matrices, and event processing rule sets. The cloud server distributes the traffic control strategy and model dynamic configuration information to the edge computing node through a secure communication link. The edge computing node completes the parameter loading, threshold table replacement and new rule engine deployment of the event risk assessment model in the local environment through the configuration management service, forming a new version model, and switches itself to the new version model through a hot switching mechanism.

8. A cloud-edge-device collaborative urban traffic management data control system, used to implement the cloud-edge-device collaborative urban traffic management data control method according to any one of claims 1 to 7, characterized in that, include: The target trajectory data stream generation module establishes a data connection between the edge computing node and the terminal device on the edge side, receives the raw data stream collected in real time, parses and preprocesses the raw data stream, and extracts the corresponding structured object information. The data is spatially filtered using preset geofencing rules issued from the cloud server, and a target trajectory data stream is generated through edge detection, contour closure and historical frame tracking. The fusion trajectory data generation module involves edge computing nodes calling the built-in fusion engine based on the target trajectory data stream. According to the unified world coordinate system and time reference provided by the cloud server, the module performs spatiotemporal alignment and correlation matching on target trajectory data streams from different sources to generate fusion trajectory data. The event risk probability value output module, based on the fused trajectory data, performs traffic parameter calculation and event risk assessment simultaneously on the edge computing node, calculates real-time traffic flow based on the number of trajectories passing through the virtual detection line per unit time, and obtains average traffic speed by calculating the ratio of trajectory displacement to time interval, and inputs the fused trajectory data into the event risk assessment model, which outputs the event risk probability value by analyzing the spatiotemporal relationship and behavior pattern between trajectories. The traffic incident probability level alarm response module uses edge computing nodes to compare the event risk probability value with the event risk threshold in real time, generate the event occurrence probability level based on the comparison result, and trigger an alarm response corresponding to the event occurrence probability level. The edge computing node local computing processing module, on the cloud side, the cloud server obtains multi-dimensional traffic operation status information uploaded by each edge computing node, the multi-dimensional traffic operation status information is used for macro-analysis of traffic situation and model iterative optimization; The cloud server periodically distributes updated traffic control strategies and dynamic model configuration information to each edge computing node. The edge computing node receives the traffic control strategies and dynamic model configuration information and adjusts its local processing logic and alarm strategies accordingly.

9. An electronic device, characterized in that, include: The system includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method according to any one of claims 1 to 7.

Images