13results about How to "Lower average wait time" patented technology

The invention discloses an urban traffic optimization and planning system based on reinforcement learning, and relates to the technical field of computer information, and the system comprises a traffic data acquisition unit, a reinforcement learning processing unit and a traffic planning unit. The traffic data acquisition unit is used for regarding target urban traffic as a network and regarding each intersection as a node, and constructing a nonlinear traffic flow dynamic model to update a multi-dimensional tensor at each time step; the reinforcement learning processing unit is used for taking a signal timing matrix of a signal lamp of a road section between every two nodes of target urban traffic as a state space and calculating a corresponding action space when a target reward function is a maximum value; and the traffic planning unit is used for finishing the traffic planning of the target city according to the action space of each road section. According to the method, the global optimization capability, the multi-objective optimization capability, the adaptive learning capability, the data processing capability, the safety and the interpretability of traffic signal control are remarkably improved.

The invention relates to the field of earth-rock engineering, and discloses an organization design optimization method for improving the work efficiency of earth-rock engineering machinery, and the method comprises the following steps: S1, carrying out the modeling of each process in the earth-rock engineering through a directed acyclic graph; s2, calculating the earliest starting time and the latest starting time of each process by using a critical path method based on the process relation model, identifying a critical path of the project, and determining a critical process which affects the project construction period; s3, on the basis of the identified key process, performing process scheduling optimization by using mixed integer linear programming to ensure that the project period is minimized under resource limitation, and generating an optimized process scheduling scheme; and S4, based on the optimized process scheduling scheme, establishing a multi-stage queuing theory model, and optimizing the scheduling of the mechanical equipment. By optimizing procedure scheduling and mechanical equipment scheduling, the construction efficiency of earth-rock engineering is remarkably improved, the construction period and resource waste are reduced, and it is ensured that a project is efficiently completed on schedule.

The invention provides a charging scheduling method based on a potential game, and the method comprises the steps: providing a charging relation network of an electric vehicle, and building a market competition framework of a charging station operator based on the network; based on the market competition framework of the charging station operators, a game model among the power grid, the charging station operators and the electric vehicle users is constructed, the optimal pricing of the charging station operators is obtained, the number and distribution of the charging piles and / or the load of the power grid are dynamically adjusted, and the charging of the electric vehicle users is scheduled. Meanwhile, the invention provides a corresponding system, a terminal and a medium. According to the method, the total revenue of the charging station can be improved, the average waiting time of the user can be reduced, the charging station can be fully utilized while the benefit of a charging station operator is improved, the regional crowding condition of the charging station is improved while the benefit of the charging station is maximized, and the number and distribution of the charging piles of the charging station and the load of a power grid are optimized.

The invention discloses an intelligent stereo garage scheduling method and system based on garage location energy efficiency and time length prediction, and the method comprises the steps: dividing all storage berths into three energy efficiency regions based on the storage time of a vehicle from an entrance to the storage berths, namely a high-efficiency region, a middle-efficiency region and a low-efficiency region; sorting the vehicle storage duration from small to large, and dividing the vehicle storage duration into three intervals which correspond to different energy efficiency areas for storing the vehicles respectively; and after a to-be-parked vehicle arrives at the entrance of the intelligent stereo garage, the predicted vehicle parking duration is obtained by using the trained XGBoost algorithm according to the historical parking data of the vehicle, and then the vehicle is automatically parked at the allocated storage berth. The invention provides an effective scheduling scheme, so that the full library rate is relatively balanced, the extreme full library rate condition is avoided, and the scheduling is more scientific and reasonable.

The invention discloses an elevator passenger traffic planning method and device, and aims to solve the problems that passengers are crowded and the operation efficiency is low in the peak period of an elevator. In the aspect of equipment, the elevator control calculation processing equipment covers a display module, a voice module and other modules and various interfaces, can cooperate with a group control system and other systems, realizes the functions of people flow data acquisition, elevator dispatching optimization, station planning and display and the like, and is provided with a self-adaptive lift car grid division and background management module. According to the method, an intelligent indication system is designed, dynamic guidance is provided for passengers in combination with floor areas and personnel distribution, communication linkage of all the systems is constructed, the indication system has real-time interactivity, and a display module is arranged outside a hall to guide the elevator calling passengers to queue up. The elevator running efficiency can be remarkably improved, the elevator taking experience of passengers is optimized, and the method is suitable for elevator systems of various high-rise buildings such as commercial mansions and residential buildings and has wide application prospects and practical value.

The present application relates to the technical field of password cards, and in particular to a method and system for centralized management of multiple password cards. The method includes: obtaining the device parameters of each physical password card, generating multiple virtual password cards according to the device parameters of a single physical password card; establishing a virtual password card resource library, storing all virtual password cards in the virtual password card resource library, and establishing a calling program to generate a virtual password card calling instruction; obtaining the virtual password card operation parameters corresponding to the target physical password card according to the preset monitoring node, and judging whether to modify the number of virtual password cards of the target physical password card according to the operation parameters. By establishing multiple sub-password card resource libraries, storing multiple virtual password cards corresponding to different physical password cards, and adding a calling program and a password card association model, the virtual password card can be quickly called according to different user needs, thereby improving the operation efficiency, realizing the simultaneous processing of multiple user needs, and improving the quality of password services.

The invention discloses a double-elevator group control scheduling method and system based on scene self-adaption and machine learning, and belongs to the technical field of intelligent building control. In order to solve the problems that an existing double-elevator system is lagged in response in a non-peak period and low in peak period transport capacity matching degree, full-floor balanced response is achieved by monitoring the elevator state in real time, controlling double elevators to stop at the bottom layer in an idle mode and calculating a middle floor through a weighted gravity center method; in the peak mode, differentiated directional elevator parking strategies are executed according to building types, and the up-down tidal passenger flow of morning and evening peaks is accurately adapted. In addition, the system introduces a machine learning module, and dynamically updates a peak time window based on historical data by using a time sequence density detection algorithm. According to the method, the average waiting time is effectively shortened, the carrying efficiency in the peak period is improved, and the elevator system is endowed with the self-evolution ability adapting to the flow change of building personnel.

The application provides a simulation running time prediction method and system, a storage medium and a program product, and relates to the technical field of model training. The original running time is logarithmically transformed to compress the time data into a smooth numerical space that is easier for model learning. Data cleaning provides a clean and representative data basis for model training. Standardization processing avoids interference of different parameter dimension differences on model weight learning. The convolutional neural network model has local perception ability and can automatically capture and learn deep patterns of strongly coupled parameter combinations from the standardized feature vector. Finally, the introduction of the Huber loss function ensures that the model can accurately fit normal samples and resist the interference of residual noise during the training process, and finally obtains a highly robust and generalizable prediction model.

The invention discloses a distributed database data synchronization method, which relates to the technical field of data synchronization. A distributed database synchronization platform is set; files that each customer needs to synchronize are uploaded to the distributed database synchronization platform; queue information of files to be synchronized of the distributed database synchronization platform is generated; an execution priority is set for each file in the queue of files to be synchronized; library priority is set for the distributed database at the same time; time slices of different lengths are set for each distributed database according to the library priority size; each file is allocated to a distributed database with different library priorities for synchronization according to the execution priority of each file; a data synchronization exception record table is created; and abnormal data information after data synchronization is completed is recorded. The invention uses a distributed database for data synchronization, so that the resources of each distributed database middleware node are reasonably utilized, and the waiting time for user data synchronization is reduced.

A biochemical sensing system uses a sensor device to sense an interaction between a molecular entity and a nanopore, the sensor device comprising an array of sensor elements supporting the nanopore. A switch arrangement selectively connects a detection channel for amplifying a sensed electrical signal to a corresponding sensor element. Based on an analysis of the amplified electrical signal output from the detection channel, the completion of the interaction at the sensor element is detected. In response thereto, the switch arrangement is controlled to connect the detection channel connected to the sensor element in which the completion of the interaction has been detected to another sensor element.

The application discloses a kind of based on multi-objective optimization's charging cabinet resource scheduling system, system includes data perception layer, intelligent decision-making layer and execution control layer, the intelligent decision-making layer integrates demand prediction unit, multi-objective optimization unit and reinforcement learning dynamic adjustment unit, form " perception-prediction-static optimization-dynamic adjustment-execution-feedback " intelligent closed loop, wherein, demand prediction unit adopts space-time convolutional neural network, realizes accurate space-time prediction to charging demand;Multi-objective optimization unit constructs and solves multi-objective model, cooperatively optimizes charging cabinet utilization, user waiting time and power grid load fluctuation, generates Pareto optimal scheduling scheme set;Through deep reinforcement learning intelligent agent, online fine-tuning is carried out to basic scheme, to deal with emergency situation.The application realizes the forward-looking planning of charging resource scheduling, multi-objective balance and dynamic robustness adaptation, can significantly improve the overall operation efficiency of charging network, user experience and power grid compatibility.

This invention provides a single-channel video carousel method, apparatus, electronic device, and storage medium. The single-channel video carousel method includes: determining that the channel bandwidth is k times the video playback bitrate, where k ≥ 1, based on the available video carousel bandwidth and the playback bitrate of the target video; using a video segmentation algorithm to simultaneously determine the number of video segments N, where N ≥ k, and the position of each segment in the channel, based on k; and dividing the video into N equal-length video segments, S... i Let S be the i-th video segment, 1≤i≤N, and let S be the total number of video segments. i A complete video is formed by concatenating the segments in ascending order of their sequence numbers. Based on a video segmentation scheme, corresponding segments are deployed at the corresponding positions on the channel for cyclical transmission, achieving video data rotation. The video data reception method includes: assuming the client user requests video playback at time t... a Based on the client receiving algorithm according to t a Determine the reception time and video playback time for each segment.

The present invention relates to the technical field of financial technology (Fintech), and discloses a task scheduling method, including: receiving an execution request for a first task, obtaining the service time of the first task and the service time of each task to be executed in a task scheduling queue; based on the service time of the first task and the service time of each task to be executed, sorting the first task and each task to be executed according to the size of the service time to obtain a new task scheduling queue, and executing the tasks in the new task scheduling queue in sequence according to the size of the service time, and the smaller the service time, the closer the task is to the head of the new task scheduling queue. When a new task arrives, the execution order of the tasks is rearranged according to the service time of the tasks, and the tasks are arranged from the head to the tail of the task scheduling queue in the order of the service time from small to large, so as to ensure that the task with the shortest service time is executed first, thereby reducing the average waiting time of the task.