42 results about "Local congestion" patented technology

The invention provides a building interior design layout optimization method, and relates to the technical field of indoor modeling and layout optimization, and the method comprises the steps: obtaining building structure boundary data and current situation layout information, constructing an indoor three-dimensional space model, and completing the marking of node passing attributes and a spatial topological structure. On the basis, crowd behavior data of a daily scene and an emergency scene are collected, behavior characteristics such as walking speed, obstacle avoidance response and congestion sensitivity are extracted, and a walking characteristic model used for simulating the individual motion trend is established. And performing multi-scene simulation under a daily event and an emergency evacuation event by using the walking feature model, calculating performance indexes such as passing time, local congestion degree, key node congestion probability and total evacuation time, and identifying a congestion sensitive area. And further constructing a multi-target evaluation model including traffic efficiency, congestion degree and evacuation performance, and performing global optimization on layout adjustable parameters by adopting an algorithm to obtain a candidate layout scheme set.

The invention provides an urban road network traffic congestion state prediction method and system based on deep learning, and relates to the technical field of intelligent traffic control, and the method comprises the steps: obtaining congestion state image data of an urban road network, and carrying out the preprocessing to extract structured road congestion information; constructing a road network topological graph based on the road congestion information, and performing structure sensing state coding on the road network topological graph to generate a structure sensing state vector fusing local congestion features and global topological position information; and inputting the structure perception state vector into an improved deep learning prediction model, performing feature deepening and enhancement through a graph neural network which dynamically adjusts a graph structure and aggregates node information, and finally outputting road network congestion state prediction results of a plurality of time scales in the future. According to the method, accurate prediction of the urban road network congestion state can be realized, and reliable technical support is provided for intelligent traffic management, resource scheduling optimization, travel path planning and the like.

The invention relates to the technical field of traffic flow control, and provides a multi-mode traffic flow control method and system, and the method comprises the steps: obtaining a traffic capacity parameter of a core traffic node based on the preset core traffic node; obtaining an instantaneous personnel entry rate of the core traffic node; calculating a personnel net accumulation rate according to the instantaneous personnel entry rate and the traffic capacity parameters; performing grading and shunting judgment based on the personnel net accumulation rate to obtain a grading judgment result; when the grading judgment result shows that the personnel net accumulation rate reaches a first preset threshold value, generating an information guide shunting instruction to guide the people stream to actively select an alternative traffic mode; and when the grading judgment result shows that the personnel net accumulation rate reaches a second preset threshold value, generating a physical isolation shunting instruction so as to drive a physical isolation device to change a people flow path. The method has the advantages that the cross-mode congestion transmission chain is accurately identified and cut off, and local congestion is prevented from spreading towards systematic paralysis.

The application discloses a scenic spot tourist navigation method based on a heat map, relates to a scenic spot tourist navigation method, and provides multiple navigation routes for selection for tourists, and generates a heat map by predicting real-time positions of the tourists by using historical data; the predicted heat map is then corrected by a pre-trained convolutional neural network to ensure conformity with actual conditions; when the heat map shows that the crowd density of a certain area is about to exceed a threshold value, the system recommends a navigation route with high uniformity to new tourists to ensure balanced distribution of people flow in the scenic spot. The application solves the problem of possible local congestion of tourists in the scenic spot.

The present application relates to heavy load AGV cooperative control technical field, especially in a kind of heavy load AGV group's cooperative control method, the motion state parameter of each heavy load AGV is collected to construct motion state vector, local traffic congestion parameter is predicted, and then local congestion index is calculated and dynamic coordination trigger threshold is determined;Distributed speed coordination is triggered based on local congestion index and dynamic coordination trigger threshold, to determine the reference coordination speed of each heavy load AGV;The reference coordination speed is passed to relevant heavy load AGV, to generate transmission coordination speed;Based on ground state parameter, the motion state vector of each heavy load AGV and transmission coordination speed, the traffic optimization sorting of each heavy load AGV is determined, to modify transmission coordination speed and determine modified coordination speed;Based on the modified coordination speed of each heavy load AGV, the timing and number of subsequent local traffic congestion are predicted, to determine the effective duration of coordination control.The present application improves the running efficiency and safety of heavy load AGV group in complex traffic environment.

This invention provides a path planning method based on the DYPIBT algorithm, which can effectively solve the problem of path collisions between agents in narrow and busy terrain, reducing ineffective agent movements and chain congestion. It dynamically calculates priorities based on four dimensions: task urgency, remaining distance, local congestion coefficient, and unique ID, ensuring that each agent has a different priority at the same time step. For each location on the map, it performs predictive backtracking judgment, anticipating the next congestion risk before the agent moves and triggering backtracking in advance to reduce ineffective agent movements. To address the path conflict problem, it designs a high-priority priority rule and a priority inheritance rule. After a high-priority agent occupies the target location, a low-priority agent inherits the priority of the high-priority agent, giving agents that have already yielded the right-of-way an opportunity to gain priority in the next path selection, thus reducing ineffective movements for individual agents.

The invention relates to the technical field of circuit board production, and discloses a circuit board production tracking management method and device, equipment and a storage medium, and the method comprises the steps: obtaining the circuit board identity information and fault detection information of a current detection site corresponding to a target circuit board, executing the equipment shutdown processing based on the fault detection information, constructing a candidate recheck option set, and carrying out the detection of the target circuit board. And based on the real-time operation data of each candidate site and the equipment shutdown maintenance information, executing comprehensive cost evaluation to determine an optimal target recheck option, further driving the target detection site to execute recheck on the target circuit board according to the circuit board identity information, and updating the real-time operation data of each detection site at the same time. Therefore, a fusion mechanism that candidate station queue prediction, comprehensive cost evaluation and recheck and maintenance information jointly participate in equipment restart triggering is introduced, the perspectiveness of a recheck decision is improved, it can be avoided that local congestion is expanded into whole-line beat decline, and the production line recovery efficiency and the timeliness of quality control are improved.

The embodiment of the invention discloses a warehouse elevator scheduling method, computer equipment and a computer readable storage medium. The warehouse elevator scheduling method comprises the following steps: constructing a scheduling algorithm to process received task information so as to determine a reservable object; determining a reservation mode according to the task information, and obtaining a reservation form; processing the reservation form according to the reservation mode so as to determine a target object from the reservable objects; and generating and outputting a scheduling queue based on the target object. Therefore, the reservable object can be determined firstly through the scheduling algorithm, so that the workload of the multiple elevators in the warehouse is balanced, the load balance of the elevators is optimized, local congestion and resource idleness are avoided, and the overall scheduling efficiency is improved. The real-time state and resource occupation condition of each connection point can be dynamically reflected by using the reservation form, channel resources are reserved in advance in combination with a pre-locking mechanism, dynamic reservation scheduling and path cooperative control of the elevator are realized, and the response speed and stability of the system are remarkably improved.

The application discloses a kind of AGV cooperative path planning methods for real-time traffic, it is related to AGV path planning technical field, comprising: based on AGV state data constructs global traffic map, and global traffic map is dynamically updated, the dynamic updating includes the weight update based on AGV density value and average speed;Based on the global traffic map after updating, using path planning algorithm generates AGV global optimization cooperative path set;Cooperative path set is converted into control instruction, and control instruction is dynamically compensated by load sensing, and corrected control instruction is obtained and issued to AGV;The application utilizes global traffic dynamic updating to combine cooperative path optimization and the dynamic control of load sensing, realizes the global traffic balance of multiple AGVs and real-time congestion prevention, solves the problem that path conflict is frequent under high load, local congestion cannot be actively adjusted and the overall efficiency is reduced by single AGV optimization.

The application discloses a kind of based on the naming data network hop-by-hop congestion control method of forwarding path number, including router congestion detection and router congestion control;Router calculates the congestion degree of local router by means of active queue management method.Routers determine local congestion state and update the congestion information of data packet.Downstream adjacent router is based on the number of forwarding path and executes multipath forwarding strategy or interest packet sending rate adjustment strategy.When router executes multipath forwarding strategy, the router calculates the shunt proportion of interest packet flow of current interface according to the congestion information of data packet and forwards flow through current or relatively suboptimal interface.When router executes interest packet sending rate adjustment strategy, the router adjusts the interest packet sending rate of same name prefix according to the congestion information of data packet.The application proposes two router control strategies for the characteristics of multiple-source multipath transmission of named data network, to cope with single-path flow and multi-path flow in network.

The invention relates to an elevator collaborative scheduling method and system based on man-machine transport capacity balance, and the method comprises the steps: receiving and analyzing a robot task state packet, and determining the task urgency degree, the task timeliness and the key resource state; building passenger transport state data are collected in real time, and current passenger flow pressure data and elevator system state data are analyzed; carrying out transport capacity balance and scheduling cost decision making, and calculating comprehensive weighted cost of different scheduling strategies based on a robot task state packet and building passenger transport state data; and according to the strategy of the lowest comprehensive weighting cost, differentiated two-way instructions are output, and control instructions are sent to the robot terminal and the elevator control system. According to the scheme provided by the invention, the elevator transport capacity can be dynamically and elastically distributed between the requirements of people and robots, transport capacity waste or local congestion is avoided, the overall vertical transport efficiency of a building is improved, and the problem that the passenger transport service quality is reduced due to improper scheduling of the robots is relieved.

The invention discloses a traffic signal control method based on regional hierarchical multi-agent reinforcement learning, and belongs to the technical field of intelligent traffic systems. According to the method, a target traffic network is divided into a plurality of areas, each area is configured with a management layer agent, each intersection in the area is configured with a control layer agent, and a double-layer layered architecture is constructed; the management layer intelligent agent periodically generates a regional control target based on regional joint state observation, and the target remains unchanged in a plurality of bottom layer control periods; the control layer intelligent agent collects local state observation in each control period, receives the regional control target, dynamically corrects the target based on a local congestion state, and outputs a signal lamp phase control action; the control layer and the management layer respectively calculate level rewards, empirical data are stored in an empirical playback buffer area, and an offline strategy training mode is combined with a double-Q network, Huber loss, delay update and an action entropy regularization mechanism to collaboratively optimize two layers of strategy functions.

The application discloses an unmanned park vehicle remote control scheduling method and system, and belongs to the field of route planning and remote control. By constructing a park space signal strength matrix and adopting an optimized A algorithm to fuse communication quality and vehicle density for path planning, a communication delay and a virtual distance penalty term are calculated according to node signal strength, and are used for an actual cost function; an impedance coefficient is calculated according to regional vehicle density, and is used for a heuristic cost function. Finally, an optimal scheduling path that avoids signal blind areas and balances road network load is generated, effectively reducing remote control delay risk, relieving local congestion, and improving unmanned vehicle operation safety and efficiency.

The embodiment of the invention provides a network slice routing method and device, equipment, a storage medium and a product. The method comprises the following steps: analyzing a received slicing request, and determining a target slice and resource demand information of the target slice; determining a target path and resource allocation information according to the resource demand information and the network state information; the target slice is subjected to routing transmission according to the resource allocation information and the target path, so that the differentiated requirements of the multi-granularity FlexE slice can be accurately responded, the management load of the multi-granularity slice is effectively balanced, and local congestion and resource idleness are avoided; meanwhile, paths and resource allocation information are dynamically determined based on real-time data, dynamic changes of service traffic can be flexibly adapted, deterministic time delay of slice end-to-end transmission is guaranteed, reasonable resource allocation and efficient routing of the multi-granularity FlexE slices are finally achieved, and the overall resource utilization rate, service quality and operation reliability of the network are improved.

The invention discloses an incomplete constraint robot formation-inclusion control method based on preset performance. The method comprises the following steps: selecting a navigator and a follower; constructing a communication network, and ensuring that each follower at least has an information interaction path with one navigator; constructing a nominal formation, so that the followers are uniformly distributed in a convex hull formed by the navigator; calculating the weight of each communication edge; the navigator adopts a distributed preset performance formation control algorithm, and a tracking error is constrained by introducing a monotone management boundary function; the follower adopts a preset performance including control algorithm, and position errors of the follower, the navigator and the neighbors are restrained within a preset performance boundary. By designing the nominal formation and the weight on each communication edge, on one hand, followers are uniformly distributed in a convex hull formed by a navigator, local congestion is prevented, and the collision risk is reduced, and on the other hand, the error can be always maintained in a preset range, and the formation deviation is reduced.

This invention relates to the field of educational resource management technology and discloses an information management method based on an academic affairs management system, including: collecting atomic logs to generate an academic affairs event sequence; comparing frequency distributions to calculate state deviation values; constructing a resource association logic graph and determining business pressure characteristics; calculating the conflict intensity coefficient of each node to identify bottleneck nodes; determining resource constraint release paths and updating node topology relationships based on logical dependency boundaries. This invention effectively avoids the risk of local congestion in static threshold judgment by establishing a mapping mechanism between business load and topology conflict, improves the allocation accuracy of teaching resources in a high-concurrency environment, and achieves stable self-healing of the business architecture by using closed-loop monitoring logic.

The application discloses a time slot scheduling system and method, wherein the system comprises a time slot management module and a weighted polling scheduler; the time slot management module is used for determining the data interaction path delay between a master device and a slave device based on the time sequence delay of a hardware unit in the data transmission path between the master device and the slave device; the data interaction path delay between the master device and each slave device is used for performing the arbitration of the weighted polling scheduling authority, generating a weighted polling request scheduling signal based on the arbitration result, and sending the weighted polling request scheduling signal to the weighted polling scheduler; the weighted polling scheduler is used for polling and selecting the slave device command queue participating in the weighted polling scheduling, and determining the arbitrated slave device command queue; the application can dynamically control the scheduling time slot of the slave device based on the write command length and the data interaction path delay between the master device and the slave device, and inhibit the local congestion caused by the continuous data flow injection into the on-chip interconnection network.

The invention provides a data transmission method and device and related equipment, and the method comprises the steps: responding to a detection result that a to-be-transmitted data packet exists in a transmission buffer region of a transmission channel corresponding to a first protocol, and determining a target transmission channel from the transmission channel; wherein the available credit quota of the target sending channel is greater than zero, and the available credit quota is used for indicating the number of data transactions allowed to be sent by the corresponding sending channel in the current clock period; packaging the to-be-sent data packet of the target sending channel to obtain a to-be-sent transaction layer protocol frame; and the transmission frame of the second protocol definition bearing the transaction layer protocol frame is transmitted to the second equipment, so that semantic fidelity transmission of cross-protocol data is realized, global pause caused by local blockage is avoided through credit-driven channel selection, the problem of head-of-queue blockage is effectively relieved, and the data transmission efficiency is improved. And the bandwidth utilization rate of a physical link and the overall throughput performance of the system are remarkably improved.

This invention discloses a time-space scheduling method for electric vehicles based on dual prediction of SOC (State of Charge) and location, belonging to the technical field of commercial data processing and intelligent transportation systems. The method collects multi-source data and identifies vehicles in fixed or moving scenarios. Then, a dual prediction mechanism is executed: LSTM is used to predict the SOC change trend, SARIMA is used to predict the spatiotemporal location, and a clustering algorithm is used to predict regional charging volume to dynamically calculate the regional saturation threshold. Simultaneously, a two-level optimization mechanism based on a genetic algorithm (global and individual levels) is employed to deeply mine users' personalized preferences for distance and time. Finally, a two-layer collaborative framework of environment and decision-making unit layers is constructed, combining predicted data and preference parameters to calculate scheduling costs, and conflict resolution is performed under dynamic saturation threshold constraints, supplemented by a rolling optimization mechanism to correct decisions in real time. This invention achieves forward-looking, personalized, and globally balanced charging resource scheduling, effectively alleviating local congestion and significantly improving charging efficiency and user satisfaction.

The application provides a kind of city road network traffic congestion state prediction method and system based on deep learning, it is related to intelligent traffic control technical field, the method includes: obtaining the congestion state image data of city road network, and pre-processing is carried out to extract structured road congestion information;Based on the road congestion information, the road network topology graph is constructed, and the structure perception state vector that fuses local congestion feature and global topology position information is generated by carrying out structure perception state coding to the road network topology graph;The structure perception state vector is input to the improved deep learning prediction model, and the graph neural network of dynamic adjustment graph structure and aggregation node information is carried out feature deepening and enhancement, and finally the road network congestion state prediction result of future multiple time scales is output.The application can realize the accurate prediction of city road network congestion state, and provide reliable technical support for intelligent traffic management, resource scheduling optimization, travel path planning and the like.

The invention discloses a satellite optical network load balancing routing and wavelength allocation method, and relates to the field of satellite optical communication. The method comprises the following steps: establishing a dynamic simulation environment of a satellite optical network; defining a node as an agent, for an arriving service request, starting from a source node agent, taking a current node on a path as an active agent, and selecting a next hop node through deep reinforcement learning until a destination node is reached, thereby forming a candidate path and a to-be-allocated wavelength set; and calculating an allocation metric value for each wavelength to be allocated, and selecting the wavelength with the maximum allocation metric value as the optimal wavelength to be allocated to the current service. According to the method, the use condition of the wavelength in the satellite optical network is sensed through the intelligent agent, the path bypassing the blocking area is selected to avoid cascade blocking, the problem of local congestion on the satellite caused by unbalanced distribution of ground services in geography and time can be effectively solved, the service blocking rate is remarkably reduced, and the network load balancing degree is achieved.

The application discloses a three-dimensional (3D) integrated circuit layout method with physical perception incremental partition, comprising the following steps: (1) according to a given netlist, all units are placed on a layer of chips to make global layout to find ideal positions of the units; (2) based on the physical positions of the units, further grid-based minimum cut partition is adopted to distribute the units in the netlist to two chips; (3) incremental half perimeter wire length (HPWL) driven partition and 3D global layout based on electric field energy are adopted to alternately optimize the partition and layout results; (4) sigmoid-based 3D post-global layout is executed to further relieve local congestion; (5) a legalization method is adopted to ensure layout legality; and (6) finally, a detailed layout method is executed to ensure legality and further improve the quality of a solution. The application can quickly obtain a high-quality 3D layout result, effectively reduces wire length and can meet the needs of a super-large-scale three-dimensional integrated circuit layout stage.

This invention discloses a task scheduling method that separates the control plane and data plane, relating to the field of network resource management technology. It addresses the problem that in path calculation based on static link costs, the path selection result does not match the actual runtime carrying capacity of nodes, easily leading to local congestion, decreased scheduling efficiency, and delayed subsequent state updates. The method acquires static network structure information and generates a candidate path set, while simultaneously forming the current cumulative carrying capacity of nodes. Based on the current cumulative carrying capacity and the node's nominal forwarding capacity, it obtains the node's current load occupancy rate, dynamic carrying threshold, and carrying margin. The carrying margin is embedded into path relaxation rules to complete target path selection and flow table distribution. Finally, it performs local feedback updates and local re-comparisons around affected nodes. This invention improves the consistency between path selection and the actual network carrying state, reducing the probability of highly loaded nodes being selected.

The present disclosure provides a data transmission method, device and related equipment, the method comprising: in response to detecting that there is a data packet to be sent in the sending buffer of the sending channel corresponding to the first protocol, determining a target sending channel from the sending channel; wherein the available credit quota of the target sending channel is greater than zero, and the available credit quota is used to indicate the number of data transactions allowed to be sent in the current clock cycle of the corresponding sending channel; encapsulating the data packet to be sent of the target sending channel to obtain a transaction layer protocol frame to be sent; and transmitting a transmission frame defined by the second protocol carrying the transaction layer protocol frame to a second device. Thus, not only is the semantic fidelity transmission of cross-protocol data achieved, but also the global pause caused by local congestion is avoided through credit-driven channel selection, the head-of-line blocking problem is effectively alleviated, and the bandwidth utilization of the physical link and the overall throughput performance of the system are significantly improved.

The invention relates to the technical field of intelligent traffic, in particular to a traffic signal lamp remote control system based on the Internet of Things, which comprises a data collection module, a connection module and a control module, the data collection module comprises an area monitoring module, an area radar scanning module, a network data interaction module, a road data module and a meteorological data collection module; the connection module comprises a signal base station connection module, a network connection module and an electrical connection module; the control module comprises an area processing module and a remote data total processing module; system data acquisition is accurate and comprehensive, and all-scene vehicle, road condition and weather information is obtained through cooperation of area monitoring and millimeter wave radar and combination of road, weather and network interaction modules; intelligent dynamic regulation and control are prominent, an area is linked with a remote total processing module, normal operation is guaranteed, local congestion is dredged, and manual intervention can be performed during full congestion; and the system can interact with the master control and send prompts to guide detour through navigation, so that the passing efficiency and the travel experience are improved.

The application discloses a social distance-based mixed disaster emergency evacuation path simulation planning method and system, and belongs to the technical field of emergency management. The method is aimed at the concurrent scene of major infectious disease epidemic and natural disaster, and proposes a K shortest path capacity planning algorithm with social distance, including a K shortest path generation operator with node capacity constraint, a conflict road section identification operator and a capacity distribution operator with social distance. Under the condition of parameter determination, the evacuation scheme is quickly generated to realize the dynamic balance of evacuation efficiency and infection risk. Further, the above operators are integrated into a simulation optimization framework to construct an alternative scheme library through random sampling and budget allocation under the condition of parameter uncertainty, thereby improving the reliability and robustness of the scheme. The application can quickly develop a flexible and reliable evacuation strategy in a complex disaster environment, avoid local congestion and scheme failure, and enhance the multi-disaster collaborative response capability.

The invention discloses a mixed disaster emergency evacuation path simulation planning method and system based on social distance, and belongs to the technical field of emergency management. According to the method, a K shortest path capacity planning algorithm with a social distance is provided for a serious infectious disease epidemic situation and natural disaster concurrent scene, the algorithm comprises a K shortest path generation operator with node capacity constraint, a conflict road section recognition operator and a capacity distribution operator with the social distance, an evacuation scheme is rapidly generated under the condition of parameter determination, and the evacuation efficiency is improved. And dynamic balance between evacuation efficiency and infection risk is realized. Furthermore, the operators are integrated into a simulation optimization framework, an alternative scheme library is constructed through random sampling and budget allocation under the condition that parameters are uncertain, and the reliability and robustness of the scheme are improved. According to the invention, a flexible and reliable evacuation strategy can be rapidly formulated in a complex disaster environment, local congestion and scheme failure are avoided, and the multi-disaster cooperative response capability is enhanced.

The invention provides a low-altitude logistics dynamic route planning method and system based on demand prediction driving, and belongs to the technical field of low-altitude traffic management and intelligent logistics scheduling. The method comprises the following steps: predicting a logistics demand by using a space-time diagram neural network and generating a virtual task set; constructing a dynamic airspace state model fusing real-time weather, control and monitoring data; by taking the virtual task set as input and the dynamic model as constraint, executing global route planning to generate a preliminary plan; calculating a network congestion risk degree and a planned load balance degree index, triggering feedback adjustment according to an index threshold value, and performing iterative optimization to form a global reference route plan; and in the real-time operation stage, dynamic re-planning is carried out by taking the reference route plan as a baseline and combining a real-time order and the latest airspace state. Through cooperation of prediction, modeling, planning and feedback, conversion from passive response to active scheduling is realized, and the problems of planning lag, local congestion and insufficient global cooperation are solved.

The embodiment of the invention provides an energy transaction method, device and system for a wide-area distributed energy system, and a storage medium, and relates to the technical field of energy internet and intelligent power grids. The method comprises the following steps: obtaining the availability state of a power grid, the energy demand and comfort index of an energy buyer, and the surplus energy and risk type of an energy seller, and directly introducing the personalized comfort preference of the energy buyer and the risk type difference of the energy seller in a transaction process; therefore, the limitation that the energy buyer is regarded as a homogenization main body and the risk preference of the energy seller is ignored is overcome. The coordination of the benefits of the energy buying party, the energy selling party and the power grid is realized, the energy consumption satisfaction degree of the user, the reasonable income of the energy selling party and the economic operation of the power grid are effectively considered in the wide-area distributed energy system, and the problems of unbalanced supply and demand, local congestion and insufficient excitation of participants are improved.