147 results about "Traffic model" patented technology

In various examples, a traffic model including one or more traffic scenarios may be generated and / or updated based on using human feedback. Human feedback may be provided indicating a preference for various traffic scenarios to identify which scenarios in a model are more realistic. A reward model may capture the preference information and rank the realism of one or more traffic scenarios.

The embodiment of the invention discloses a dynamic traffic signal control method and device based on data fusion and a medium, belongs to the technical field of intelligent traffic, and solves the problem that the existing traffic signal control is difficult to make effective response when an accident occurs. Performing data fusion on first traffic data acquired by a road monitoring and shooting device and second traffic data acquired by a positioning device of the floating car through a multi-head attention mechanism at the edge node to obtain multi-source traffic characteristic data; the cloud end inputs the multi-source traffic characteristic data into a preset signal optimization model every first preset duration; the preset signal optimization model is updated and optimized through a PPO algorithm and a federated average method, and a global traffic model is generated; and through knowledge distillation, compressing the global traffic model, and migrating an edge traffic model obtained after compression to a corresponding edge node so as to carry out traffic signal strategy output on a corresponding road section through the edge traffic model.

The invention relates to reinforcement learning for traffic simulation. In various examples, a traffic model including one or more traffic scenes may be generated and / or updated based on the use of human feedback. Human feedback may be provided indicating preferences for various traffic scenes to determine which scenes in the model are more realistic. The reward model may capture preference information and rank the authenticity of one or more traffic scenes.

The invention discloses a dynamic model detection method based on an AI algorithm, and relates to the field of AI algorithms, and the method can monitor and collect network abnormal data in real time by installing a network monitoring tool in a monitoring network environment. And preprocessing the network abnormal data to generate a standardized data set, and storing the standardized data set in a MySQL relational database. The data sets are extracted in real time through SQL query, and a network anomaly feature vector Ft is generated by using a feature extraction formula. Then constructing a network flow dynamic model, inputting the historical network anomaly feature vector Ft into a long short-term memory (LSTM) network of an AI algorithm for preliminary training to obtain a network flow dynamic model M0, and dynamically updating the input of the network anomaly feature vector Ft extracted in real time to obtain an updated network flow model Mt; the dynamic model can capture tiny changes in network traffic, and potential abnormal behaviors can be effectively identified.

The invention discloses a software and hardware decoupling analogue simulation test system, belongs to the technical field of vehicle analogue simulation test, and solves the technical problem that a traditional test system often neglects the actual situation in the operation process due to excessive consideration from the theoretical perspective. The system comprises an environment simulation module which is used as an integrated tool and platform for realizing automobile virtual research and development through an analog simulation technology, integrates an automobile driving environment model, a vehicle-mounted environment sensing model and a traffic model, and provides a three-dimensional digital virtual test scene modeling and editing function; the vehicle dynamics simulation module is used for providing vehicle dynamics simulation, scene construction, sensor construction and data interface construction; and the evaluation index and evaluation software module is used for receiving results output by the environment simulation module and the vehicle dynamics simulation module and outputting a report. The invention focuses on simulating the working condition, road condition and scene of a real vehicle to test the designed algorithm model, software and hardware, so as to find and solve problems as soon as possible.

The invention discloses an urban traffic intelligent management method based on multi-source data, and relates to the technical field of traffic data management, and the method comprises the steps: collecting multi-source traffic data, firstly carrying out the preprocessing, then carrying out the matching and integration, and building a unified traffic data warehouse; carrying out batch processing and stream processing on warehouse data by applying a distributed computing framework and a stream processing technology; on the basis of multi-source data, various traffic models are constructed and optimized, and a visual tool is developed to visually display an analysis result; by combining real-time traffic data, a model prediction result and historical data, traffic signals are dynamically adjusted, route planning and navigation services are provided for users, and routes and scheduling of public traffic are optimized; a traffic monitoring center is constructed, and real-time monitoring and timely early warning are carried out based on the traffic signal dynamic adjustment result and the real-time traffic data; establishing an emergency plan; and establishing a data sharing platform, and sharing the related traffic data. The system is used for monitoring, analyzing, managing and applying the traffic data.

The invention discloses a multi-target path planning method for ship surface motion of multi-heterogeneous unmanned equipment. The method comprises the following steps: establishing a multi-agent traffic model based on a common evolution principle; a certain area weighted network diagram based on traffic flow, user distribution and power grid load is constructed, nodes in the network represent positions of potential charging stations, side weights reflect path time or cost, the number of potential places of the charging stations in the weighted network diagram and the capacity of the potential places are determined based on a multi-objective evolutionary algorithm, and the charging stations in the weighted network diagram are calculated. Site selection and capacity configuration of the charging station are optimized through simulation selection, crossing and mutation operation; based on the multi-objective evolutionary algorithm, optimizing the site selection condition of the charging station through non-dominated sorting and congestion degree distance, and obtaining a plurality of Pareto optimal solutions; according to the method, the result obtained through the multi-target method is analyzed and researched, the optimal solution of the two multi-target performance indexes is solved through the NSGA-II algorithm, and an important means is provided for solving the problem of the evolutionary algorithm in the multi-target electric vehicle charging station.

The invention relates to the field of industrial automation and intelligent logistics, and discloses a vision-based operation management system, which comprises a visual perception module, a traffic modeling module, a path optimization module, a scheduling optimization module and a feedback adjustment module, the visual perception module obtains image or video data in the operation area and extracts the dynamic state of the target equipment; the traffic modeling module constructs a dynamic weighted graph model based on the equipment state data; the path optimization module generates an optimal path of the equipment by solving a dynamic Hamiltonian path problem; the scheduling optimization module optimizes the passing sequence and speed of the equipment based on a game theory model; and the feedback adjustment module monitors the running state of the equipment in real time, detects abnormal conditions and dynamically adjusts modeling and optimization results. The method can effectively solve the problems of path conflict and traffic jam in multi-device collaborative operation, improves the operation efficiency and the resource utilization rate, has high real-time performance and adaptability, and is suitable for various scenes such as logistics storage, industrial production and intelligent transportation.

The invention relates to the technical field of flow forwarding, in particular to a controllable flow forwarding method. The method comprises the following steps: S1, demand analysis, S2, traffic model construction, S3, equipment initial configuration, S4, traffic monitoring and evaluation, S5, traffic classification and priority setting, S6, bandwidth limitation and rate control, S7, load balancing, S8, resource reservation, S9, security encryption and verification of a data packet, S10, traffic caching and data loss prevention, and S11, dynamic adjustment of a forwarding strategy. According to the method, accurate control and management of network traffic are realized through traffic model construction, traffic monitoring and evaluation, traffic classification and priority setting, bandwidth limitation and rate control, load balancing and resource reservation, the security of data in a forwarding process is improved through security encryption and verification of a data packet, log recording and performance monitoring, and the data forwarding efficiency is improved. And data loss is avoided through flow caching, data loss prevention and dynamic adjustment of a forwarding strategy.

The invention discloses a train communication network intrusion detection method based on a multi-scale residual network, and the method comprises the following steps: building a train communication network topological structure model, and building a traffic model for the mixed transmission of normal traffic and intrusion traffic; collecting a flow data packet in a link as an original data sample in the intrusion detection data set, and performing preprocessing to obtain a data sample containing statistical characteristics; a train communication network intrusion detection MSRNet-GLAM model is constructed, and the performance of the train communication network intrusion detection MSRNet-GLAM model is checked and evaluated, so that the MSRNet-GLAM model can learn key feature information of a data sample in a multi-scale manner; and training and optimizing the MSRNet-GLAM model by using the improved focus loss function, and performing intrusion detection on the traffic data of the train communication network to be detected to obtain a traffic detection result of the train communication network. The method can effectively solve the problems of low security and difficulty in detection of intrusion traffic under the trend of mass data communication of the train communication network, and ensures the security of the train network.

The invention discloses a cross-domain time-sensitive satellite network traffic scheduling method based on a TSN and MF-TDMA, and the method comprises the steps: a cross-domain controller collects network topology information, builds a satellite cluster global network model, carries out the collection of data and task demands, and a user controller collects an intra-domain sending end traffic access request, the traffic demand is reported to the cross-domain controller and the in-satellite controller; the cross-domain controller performs flow characteristic analysis and establishes a flow model; the in-satellite controller evaluates the network load, constructs a dynamic network resource state information base, and determines the traffic scheduling granularity according to the long-time stable service; according to the positions of the source node and the destination node of the service flow, the cross-domain controller and the in-satellite controller respectively calculate the scheduling paths of the cross-domain flow and the single-domain flow; and according to the routing result of each flow, based on the scheduling decision variable, establishing a wireless and wired joint scheduling constraint and optimization target, generating an integer linear equation, and solving an optimal solution to generate a scheduling scheme.

The invention relates to the technical field of intelligent traffic, in particular to a multi-modal traffic large model staged training method and system based on a WSD learning rate scheduler, and the method comprises the steps: carrying out the enhancement and extension of an original traffic scene data set through a data enhancement method based on a man-machine cooperation program; obtaining a plurality of downstream task data sets suitable for different levels of training targets in the field of traffic violation scene perception and analysis; and combining a WSD learning rate scheduler and task objectives of different downstream tasks to formulate a staged training strategy. According to the method, limited original data in a low-resource scene in the traffic field is expanded into downstream task data sets oriented to different training targets through a data enhancement method of a man-machine collaboration program, and a WSD learning rate scheduler is introduced to split a fine adjustment process of a traditional multi-modal large language model into different training stages; and different downstream task data sets are put in different training stages in a targeted manner, so that a training process which better fits a model learning rule is realized.

The invention provides a traffic signal period duration dynamic adjustment method based on trajectory data. The method comprises the following steps: step 1, determining a data source; step 2, data integration and standardization; 3, traffic flow characteristics are extracted; and 4, constructing a dynamic traffic model, and dynamically adjusting the period duration of the traffic signal. According to the method, the traffic flow efficiency can be improved, the traffic flow change can be more accurately predicted by utilizing real-time data analysis, and the signal period can be dynamically adjusted, so that the vehicle waiting time is shortened, and the overall road traffic capacity is improved. According to the method, big data analysis and an artificial intelligence algorithm are combined, automation and intelligence of traffic signal control are achieved, and dependence on manual intervention is reduced.

The invention relates to the field of urban public transport deployment, and provides a public transport network matching method and system based on an urban space structure, which divides urban areas by constructing a traffic model, identifies areas with dense demands on the basis of power consumption density, and provides a public transport network matching method and system based on the urban space structure. And the coverage condition of the existing public transport network on the areas with dense demands is evaluated, and uncovered areas are identified. For the uncovered areas, the information of stores and companies in the map data is used to subdivide the uncovered areas into a plurality of types of areas. A bus rapid transit system is additionally arranged in a commercial district to improve transportation efficiency, a peak period special line is additionally arranged in an office building area to meet commuting requirements, a customized bus special line is provided in an industrial district to meet requirements of specific periods and routes, and a conventional bus route is additionally arranged in a residential district to improve daily travel. Accurate matching between the urban space structure and the public transport demand is realized, and the coverage rate and efficiency of public transport service are improved.

The invention relates to the technical field of network security, in particular to a computer network security analysis method and system based on big data, and the method comprises the following steps: firstly, collecting network flow data through multiple nodes, preprocessing the data, then extracting the time sequence characteristics of the flow, constructing a time sequence behavior model through a long and short-term memory network, and constructing a time sequence behavior model; the method comprises the following steps: acquiring a real-time traffic model, identifying a behavior mode of normal traffic based on the model, judging whether the traffic is abnormal by comparing a time sequence characteristic of the real-time traffic with the normal traffic model, performing deviation scoring, performing abnormal traffic clustering on the detected abnormal traffic by adopting a K-means clustering algorithm, identifying a potential attack type, and according to a deviation scoring result, determining whether the traffic is abnormal or not. Defense response is automatically triggered, and the security of the network is ensured; according to the invention, through the adaptive defense strategy and the efficient flow analysis method, the real-time response capability, accuracy and adaptability of network security are improved.

The invention discloses a vehicle state sensing method and system in a vehicle-road cooperation environment, and relates to the technical field of intelligent traffic, and the method comprises the steps: collecting the real-time traffic data of a target intersection; establishing a temporary V2X communication link; receiving real-time traffic data and K pieces of real-time vehicle state information of K running vehicles; if the one-dimensional risk detection results of the roadside edge computing device on the real-time traffic data and the K pieces of real-time vehicle state information are set to be 0, compensating the K pieces of real-time vehicle state information by adopting the real-time traffic data to obtain K pieces of compensated vehicle state information, constructing a global dynamic traffic model, and performing track conflict prediction and potential collision risk positioning; and according to the risk avoidance priority, broadcasting the potential collision risk to K running vehicles through a V2X communication link. The technical problems of inaccurate traffic modeling and untimely collision risk identification caused by incomplete vehicle-mounted sensing information in the prior art are solved, and the technical effects of improving the vehicle state sensing accuracy and the collision risk early warning timeliness are achieved.

The invention discloses a large traffic model intelligent traffic event identification method based on cross-modal retrieval. The method comprises the following steps: inputting an image of a traffic event to be identified and text description thereof into a traffic event identification network model; a visual feature extraction module is used for extracting visual features in the image; the text feature extraction module is used for extracting text features in the text description; the visual selective filtering module is used for selectively filtering the irrelevant visual extraction features to obtain visual filtering features; the text selective filtering module is used for selectively filtering unnecessary text extraction features to obtain text filtering features; the cross-modal selective alignment module is used for performing cross-modal alignment on the visual and text extraction features to obtain visual alignment features and text alignment features; and the calculation module is used for fusing the visual filtering features and the visual alignment features as well as the text filtering features and the text alignment features to determine an identification result. According to the invention, the accuracy and efficiency of retrieval identification are improved.

The invention relates to the technical field of data transmission, in particular to an ink-jet printing data transmission system based on a TSN and an ink-jet printing system.The ink-jet printing data transmission system comprises a time-sensitive network switch used for receiving flow data frames sent by an upper computer; the time-sensitive network gateway is used for receiving the traffic data frame transmitted by the time-sensitive network switch, determining a transmission sequence of all traffic data in a preset transmission time window, and transmitting all processed traffic data; wherein the time-sensitive network gateway mathematical model is constructed based on the flow distribution balance optimization target and the system flow priority distribution optimization target by taking the total size of the flow data received by each electronic control unit as a constraint. According to the invention, the TSN technology is introduced, so that low-delay and high-determinacy data transmission under the condition of high bandwidth is realized in an ink-jet printing system; based on traffic optimization scheduling, a TSN traffic model is designed, a data transmission sequence is determined, and the flexibility and reliability of the system in the data transmission process are improved.

The invention discloses a traffic state completion prediction method based on multi-source data pre-training, belongs to the technical field of deep learning algorithms, solves the problem of how to improve the complex data processing capability of a traditional traffic model, integrates data in multiple fields, clusters the data through a k-means algorithm, and improves the traffic state completion prediction efficiency. The data in each cluster is ensured to be numerically similar, adjacent data pairs are selected from each cluster according to a time sequence so as to capture relevance in the time dimension, the data pairs are subsequently used as input of the model, multiple data types are used in the pre-training stage, and the formal training stage focuses on traffic data, so that the data in the pre-training stage and the data in the formal training stage are used as input of the model. According to the method, rich features and modes learned from different data sources in the pre-training stage are fully utilized to achieve zero-start training of traffic data, the understanding and prediction ability of the model for traffic data characteristics can be remarkably improved, and especially in the face of sparse data or new field tasks, the learning and adaptation process of the model can be accelerated.

The invention relates to the field of intelligent traffic systems, in particular to an intelligent intersection multi-vehicle cooperative control method. The method comprises the following steps: S1, sensing a vehicle state and sharing vehicle node information by adopting a dual-mode communication mechanism; s2, fusing state data at edge computing nodes; establishing a dynamic traffic model according to the fused state data; s3, acquiring node data of the edge calculation node, calculating a vehicle passing priority index according to the node data, and performing vehicle priority decision according to the passing priority index; s4, performing grading processing on the vehicles with the overlapped tracks; s5, the RSU device broadcasts the control instruction, and if the vehicle-mounted unit receives the control instruction within the set time, an execution report is transmitted back to the RSU device; and if the vehicle-mounted unit does not receive the control instruction within the set time, a redundancy execution mechanism is started to detect and control the running state of the vehicle. According to the invention, millisecond-level synchronous transmission and high-precision perception of information are realized, and the real-time performance and accuracy of traffic environment modeling are improved.

The invention provides an electric vehicle energy assessment method based on dynamic wireless charging, and the method comprises the following steps: S1, determining a target road network, and constructing a microscopic traffic simulation model with the same geometric condition as the target road network on traffic simulation software; s2, calibrating the microscopic traffic model based on traffic flow data, link flow data and travel data in the field annular detector; s3, based on the total power loss of the generator efficiency and an electric vehicle battery charge calculation method, obtaining an improved SOC model of the electric vehicle; s4, taking the improved SOC model of the electric vehicle proposed in the S3 as a simulation software plug-in, and constructing a heuristic framework; s5, determining the DWC length through the set alpha and beta values and the calculated SOC value; and S6, evaluating the energy demand of the electric vehicles according to the average driving time of the charging road section and the total number of the electric vehicles within the given time based on the bidirectional lane changing behavior. According to the invention, optimization of the layout of the electric road system is facilitated, and the requirements of traffic flow and energy are better met.

A user equipment information prediction method and apparatus and a network element. The method in embodiments of this application includes: obtaining, by a first network element, user equipment location data of a first time period using a location service LCS architecture; and inputting, by the first network element, the user equipment location data of the first time period into a traffic model or a supervised learning model, and obtaining user equipment prediction information of a second time period output by the traffic model or the supervised learning model.

The invention discloses an urban multi-layer traffic network modeling and toughness analysis method under the influence of rainstorm, and relates to the technical field of traffic control, a rainstorm ponding model is built based on historical rainfall information, and a runoff depth and a ponding depth are simulated based on the rainstorm ponding model; building a multi-mode traffic model based on SUMO software; a rainstorm ponding model and a multi-mode traffic model are integrated to construct a coupling model, ponding information is matched to a corresponding road through a road ID, failure mechanisms of different traffic modes under rainstorm ponding are obtained, ponding influences are considered for road traffic and rail traffic respectively, and corresponding influence parameters are set. Adjusting the road speed limit in real time and updating the route in real time; the SUMO simulation output result is utilized, the toughness index change in different scenes is calculated, the comprehensive traffic network toughness in different rainstorm scenes is analyzed from the four dimensions of topology, convenience, service and safety, the comprehensive traffic network toughness is evaluated, the dynamic capture of traffic characteristics is realized, and the analysis depth and breadth are improved.

The invention discloses a high-concurrency scene-oriented government affair system automation performance test method and system, and the method comprises the steps: deploying test nodes in a government affair system, and constructing a distributed pressure test cluster; constructing a system flow model of a mixed load mode containing an instantaneous peak value and continuous pressure; collecting a resource index set and an application performance index set of the tested system in real time; according to the dynamic capacity expansion and contraction test, comparing the real-time monitoring index data with the system flow model data in the test process, and automatically triggering a horizontal expansion test scene; injecting three types of abnormal events into the system, and recording the self-healing time and the abnormal propagation path of the system; and constructing an intelligent analysis model, identifying a performance inflection point based on an anomaly detection algorithm of a time sequence, and generating a test result. The method has the advantages that the hybrid load model is constructed through the historical business data, the fault injection and intelligent analysis model is combined, real-time monitoring and dynamic capacity expansion and contraction testing are carried out, and the performance of the government affair system in a high-concurrency scene is comprehensively evaluated.

The invention provides a traffic model construction method and system based on fluid mechanics, and relates to the technical field of traffic model construction.Traffic flow data are collected in real time, the characteristic speed and congestion wave propagation speed in the fluid mechanics are combined, dynamic and fine division of traffic light road sections is achieved, and the traffic flow data are acquired in real time. The spatial mutation of the traffic state is effectively captured, and the accuracy of traffic flow state recognition is improved; based on the divided road section intervals, a multi-model strategy is adopted to match different traffic states, vehicle flow characteristics under smooth, slight congestion and serious congestion are comprehensively reflected, and the adaptability and physical rationality of the model are enhanced; through combination of the vehicle dynamics safety constraint and the signal lamp control period, collaborative optimization of the optimal vehicle speed and the optimal vehicle distance is realized, coordination of vehicle safe passing and signal lamps is guaranteed, and the road passing efficiency and the driving safety are improved.

The invention discloses a semantic parameter calibration method for an urban cross-domain multi-mode space, and belongs to the technical field of traffic simulation. In order to realize semantic parameter calibration of the city cross-domain multi-mode space, the method comprises the following steps: constructing the city cross-domain multi-mode space based on BIM; performing multi-mode traffic network semantic parameter calibration, including self-driving traffic network characteristic parameter calibration, walking traffic network characteristic parameter calibration, bus traffic network characteristic parameter calibration, rail traffic network characteristic parameter calibration and hub space characteristic parameter calibration; the method comprises the following steps: performing simulation deduction on a traffic state, restoring a multi-mode traffic network operation state, performing statistics on traffic flow, travel distance, travel time and transfer frequency indexes, and comparing with actual geomagnetic data, checkpoint data, video monitoring data, vehicle GPS track data and rail bus card swiping data to complete multi-mode traffic network semantic parameter checking. The prediction capability and decision support capability of the traffic model are improved.

A system receives GPS data and on-board sensor data from several connected vehicles indicating locations of nearby vehicles and objects. The system processes the data to create a shared-world model that includes locations and velocities of the connected vehicles and nearby vehicles and objects, and the system determines whether driving hazards exist, such as potential collisions. The system may transmit an alert to at least one of the connected vehicles, to cause the connected vehicle or a mobile device to present a warning message to a driver, such as a visual, audio, or haptic message, or to cause the connected vehicle to implement an action to avoid the driving hazard, such as activating emergency braking or altering course. The system may create, and transmit to a connected vehicle or mobile device, a lane-level traffic model indicating traffic density, traffic speed, and traffic throughput.

The present invention relates to a method for planning new transportation energy facilities on highways, including determining basic parameters of electric vehicles and highways; simulating electric vehicle travel on highways through dynamic traffic models; simulating the spatiotemporal distribution of electric vehicle charging loads using the Monte Carlo method; evaluating the utilization potential and complementarity of wind and solar energy in highway service areas; establishing a new transportation energy facility planning model, including: establishing an objective function and constraint conditions; and solving the new transportation energy facility planning scheme using an improved genetic algorithm based on the spatiotemporal distribution of electric vehicle charging loads and the new transportation energy facility planning model. Compared with the prior art, the present invention improves the existing site selection and sizing methods from the aspects of electric vehicle parameter characterization, dynamic traffic simulation, wind and solar energy evaluation, and provides guidance for the site selection and sizing of new transportation energy facilities on highways.

The application provides a power deterministic network routing and packet scheduling method and system, the method comprising: determining the feasible path set from the source to the destination node for each deterministic flow according to the network and traffic model; constructing the three-dimensional scheduling variable consisting of the path, time offset and CSQF period specification set for each flow; jointly solving the three-dimensional variable of each flow to obtain the routing and packet scheduling scheme satisfying the resource, sending, delay and period constraint with the minimum objective function, the objective function being used to realize the double load balancing of the link and period window; and calculating the network remaining resource based on the obtained scheme and allocating the transmission resource for the non-deterministic flow according to the network remaining resource. Through the three-dimensional joint scheduling of the routing, time and period and the double load balancing of the link and window, the application can significantly reduce the jitter under the strict delay constraint, effectively improve the network resource utilization and the reliability of the deterministic service.

The invention relates to the field of computer network optimization and controller load balancing, and discloses a controller load balancing method based on hierarchical load awareness and adaptive heredity, which comprises the following steps: S1, constructing an SDN network model, establishing a mapping matrix of a switch and a controller, establishing a switch flow model, and establishing a flow model of the controller; s2, establishing a load model of the controller, setting a dynamic load formula and a static load formula of the controller, and calculating the total load of the controller; s3, establishing a layered load sensing model, and determining whether to trigger load balancing or not according to a preset threshold value; s4, optimizing a mapping relation between the switch and the controller by using an adaptive genetic algorithm to realize dynamic load balancing; and S5, setting an algorithm ending condition, outputting an optimal mapping scheme, and carrying out load balancing according to the scheme.