508 results about "Arrival time" patented technology

The invention discloses a micro-seismic signal arrival time pickup method based on fuzzy clustering and variational mode decomposition. The method comprises the following steps: firstly, calculating characteristic functions of attribute characteristics such as a micro-seismic signal mean value, power and kurtosis and normalizing the characteristic functions to obtain a characteristic matrix, then primarily picking up a micro-seismic P-wave initial movement position and a first arrival moment through a fuzzy clustering algorithm, and extracting an effective time window by taking the first arrival moment as a reference point; a variational mode decomposition algorithm is utilized to decompose signals in a time window into K intrinsic mode function components, AIC function values of the components are calculated by means of an akaike information criterion algorithm, a minimum value point is picked up to serve as first arrival time, energy ratios of all the components are calculated, and final micro-seismic P-wave first arrival time is obtained through weighted calculation. The method effectively deals with the low signal-to-noise ratio environment of the underground coal mine, has higher pickup precision and reliability compared with a traditional pickup method, can provide accurate micro-seismic occurrence time and position information for mine safety early warning, and powerfully guarantees the safety production of the coal mine.

The invention discloses a container port berth and storage yard allocation combined planning operation method and system based on a cluster strategy, and the method comprises the steps: collecting the information of ships, container trucks and storage yards in a target time period, including the planned arrival time of the ships, the number and types of containers carried by the ships, the stockpiling state of the storage yards, and the planned arrival time of outer container trucks; the collected information is input into a pre-constructed multi-target mixed integer programming model, and an optimal programming strategy is calculated and comprises berth plans of all ships in a specified time period and loading and unloading operation plans of container batches; wherein the pre-established multi-target mixed integer programming model comprises three target functions, and the targets are the shortest ship berthing deviation expected turnover time, the minimum container transportation total distance between a berth and a storage yard container area and the minimum workload imbalance of the storage yard container area respectively; and executing ship and storage yard operation according to the optimal planning strategy. The overall operation efficiency of the wharf can be improved.

Techniques for managing pickup orders are discussed herein. A managing computing device can receive first and second pickup orders made at different time points associated with a first user. The pickup orders can be directed to the same store. The managing computing device can group the first and the second pickup orders as a batched order which can update a priority of the first or second pickup order. The managing computing device can receive location data from a computing device associated with the first user or a third party. The managing computing device can determine an estimated arrival time of the first user or the third party based on the location data. The managing computing device can send a message to a store computing device associated with the store, indicating the estimated arrival time and the batched order associated with the first user.

The invention provides a ship lockage appointment scheduling optimization method, system, equipment and medium, and belongs to the field of shipping traffic scheduling, and the method comprises the steps: based on an arrival time prediction model, according to the planned arrival time, historical actual arrival time and ship attribute data of at least two appointment ships, obtaining a ship lockage appointment scheduling optimization model; generating a mean value and a standard deviation of the estimated arrival time corresponding to each reserved ship; based on the mean value and the standard deviation of the estimated arrival time, constructing a multi-target optimization model meeting a preset optimization target and a preset constraint condition; calculating corresponding scheduling reference time according to the mean value and the standard deviation of the estimated arrival time, and creating an initial scheduling scheme population according to the scheduling reference time; and based on a non-dominated sorting genetic algorithm and a variable neighborhood search algorithm, solving the multi-objective optimization model according to the initial scheduling scheme population to obtain a final scheduling scheme. According to the invention, the traffic jam of the hub is effectively relieved, and the lockage efficiency of the ship is improved.

The invention provides a high-speed rail emergency train number matching optimization method and system based on timeliness guarantee, and belongs to the field of logistics distribution scheme optimization. According to the method, the set business process comprises customer delivery, goods pickup and delivery, inter-station transportation and goods pickup and delivery; according to the order data and the rider data, the taking and delivering service time distribution of the two links of taking goods to the station and taking goods and delivering goods is constructed, and then the goods waiting time, the latest arrival time of the day and the goods arrival time meeting the maximum delay time are determined; taking the smaller value of the latest arrival time of the day and the cargo arrival time meeting the maximum delay time as the latest arrival time of the cargo; determining a train alternative set according to cargo time limit requirements and cargo OD stations; and based on the timeliness guarantee and the operation cost, constructing a high-speed rail emergency train number matching optimization model based on the timeliness guarantee, and solving the model to obtain an optimized train number matching result. According to the invention, the punctuality and reliability of transportation are improved, and the overall operation efficiency and economic benefits are improved.

The invention discloses a driver side navigation switching management method and system. The invention relates to the field of intelligent traffic and mobile application development. Passenger order information (such as new order generation and order state change) from a scheduling system is continuously monitored; acquiring the current navigation state (destination, route planning, driving state and the like) of the driver in real time; switching condition judgment is carried out; if the driver is in common navigation and receives a passenger order, calling a preset judgment table based on the order emergency degree and the predicted arrival time of the driver, and if judging that a switching condition is met, triggering a navigation switching process; according to the system, the navigation switching response time is compressed from the second level to the millisecond level through an active mechanism of order triggering and state sensing, and a driver can complete switching without manual operation. A map SDK asynchronous calling technology is adopted, parameter transmission and state cleaning are completed in the background, and the switching success rate is increased.

The invention relates to the technical field of intelligent prediction, and discloses an emergency resource reserve intelligent prediction system and method based on a graph neural network, and the system comprises a space-time diagram construction module which collects port, berth, channel segment, emergency warehouse and ship information, passing time window information and emergency information, and constructs an event flow heterogeneous space-time diagram; the backbone screening module is used for screening backbone sub-graphs and setting a relation feature conversion rule and a time feature representation rule; the graph memory updating module is used for updating node and edge features; the multi-task prediction module is used for outputting quantile demand prediction, reachability scores, transportation timeliness and safety stock threshold values; the consistency constraint training module is used for executing consistency constraint training; the inventory allocation decision-making module is used for generating allocation distribution quantity and outputting predicted arrival time; and the berth time window recharging module is used for generating a berth operation time window and recharging the actual arrival time. According to the invention, emergency resource demand prediction, inventory threshold calculation and allocation and berth operation linkage decision are realized.

A method for routing an autonomous vehicle from a start location to a target destination location via a set of road segments is provided. The method includes determining at least two candidate routes comprising a respective subset of the set of road segments. Each of the at least two candidate routes indicates how the autonomous vehicle shall travel from the start location, to arrive at the target destination location within a time interval of a target time of arrival. The method determines a flexibility metric for each of the at least two candidate routes indicative of a possible time adjustment when adjusting a speed of the autonomous vehicle. The method selects a route based on the determined flexibility metrics.

The invention discloses a time management optimization method and a display device for an ambulance, and belongs to the technical field of medical first aid management. The method comprises the steps of obtaining an exclusive data set and multi-dimensional dynamic data of a target patient in real time, calling a preset demand rule base, calculating the emergency degree of the target patient in combination with the exclusive data set, and performing emergency level division; constructing a transfer planning model, screening a resource-adaptive target hospital for a target patient, synchronously planning a global optimal driving path, calculating predicted arrival time, and generating an individual transfer plan; global summarization is carried out on target patients to be transferred to form a matrix to be transferred, resource adaptation verification is carried out on the basis of a target hospital, an actual target transfer set is generated, and the transfer process is monitored in real time to update the predicted arrival time in real time; and after the transfer is completed, obtaining the actual arrival time, calculating the predicted deviation value, marking the deviation reason, forming an optimized data set, shortening the transfer time efficiency, and reducing the treatment delay risk.

The invention discloses an online car-hailing order allocation method and system based on an artificial intelligence algorithm, and relates to the technical field of intelligent scheduling, and the method comprises the steps: obtaining to-be-allocated order data and driver data; determining a candidate driver set by adopting a dynamic search radius and a multi-state driver screening strategy, and calculating an estimated arrival time in combination with a real-time traffic condition; establishing a multi-factor order receiving willingness evaluation model, and calculating the order receiving probability of each order-driver combination; constructing a comprehensive matching degree evaluation model, calculating the matching degree of all order-driver combinations, and generating a matching degree matrix; processing the matching degree matrix by adopting a global optimization algorithm, and outputting an order-driver allocation result; and pushing an order to a driver in the order-driver allocation result, monitoring a response state, and performing reallocation processing on a non-response condition. Through the multi-factor order receiving willingness evaluation and the global optimization algorithm, the success rate and matching precision of order allocation are improved, the order waiting time is shortened, and the overall allocation efficiency is improved.

The invention relates to the technical field of server hardware fault diagnosis, in particular to an intelligent fault diagnosis method and system for a server mainboard and a storage medium. The method comprises the following steps: configuring monitoring parameters in a bus link controller of a server mainboard, and setting an undisturbed sampling window as a training sequence time period and an idle symbol time period in a bus physical layer data transmission process; periodically reading a link adaptive equalization parameter, an error count value and symbol arrival time through a bus link controller register, and simultaneously collecting a temperature parameter and a voltage parameter at the current moment; and combining the link adaptive equalization parameter, the error count value, the symbol arrival time, the temperature parameter and the voltage parameter at the same sampling moment as a signal quality vector at the moment. According to the method, two data transmission-free windows of the training sequence time period and the idle symbol time period are identified and utilized, so that the monitoring operation and the service data are staggered, and the sampling operation is ensured not to interfere with normal data transmission.

A mine earthquake positioning method based on an improved pigeon inspired optimization algorithm comprises the following steps: 1) preprocessing original mine earthquake waveform data by using ACF to obtain an ACF sequence; 2) performing first arrival time pickup on the processed data by using a long and short time window algorithm STA / LTA; (3) storing the station coordinates and the first arrival time picked in the step (2) into a file according to the format of station coordinates X, station coordinates Y, station coordinates Z and first arrival time; 4) reading the file generated in the step 3), and setting an upper boundary and a lower boundary of a search space; 5) selecting a combination of a time-of-arrival method and a variance function as a target function; and 6) using the improved pigeon inspired optimization algorithm FC-PIO to carry out seismic source positioning operation: minimizing the target function in the step 5) through the improved pigeon inspired optimization algorithm FC-PIO, finding an optimal solution, and obtaining the occurrence position of a mine earthquake event. Through the method, the mine earthquake positioning precision and efficiency can be remarkably improved in practical application, and the reliability of mine safety monitoring is ensured.

The invention belongs to the technical field of port operation management, and provides a port project whole-process decision management system based on big data analysis, which comprises the steps of performing verification analysis on a plurality of historical predicted port arrival time through hypothetical moving windows, determining an optimal moving window by using a moving window averaging method and an Euclidean calculation model, and determining the port arrival time according to the optimal moving window; obtaining a model correction factor according to historical predicted time and actual time, obtaining predicted port arriving time, comparing the predicted port arriving time with to-be-loaded departure time, if the predicted port arriving time is not matched with the to-be-loaded departure time, rejecting original stable connection ships, reselecting the ships according to a connection matching degree, and performing re-evaluation until the ships with time dimension connection matching are found from a connection ship sequence, by optimizing a moving window and introducing a correction factor, the port arrival time prediction accuracy is improved, the problem that the port ship scheduling efficiency is effectively improved due to loading and unloading caused by time mismatching is avoided, and the problems of how to accurately predict the port arrival time of the stably connected ship and how to judge whether the port arrival time is matched with the to-be-loaded departure time or not are solved.

Systems and methods for predicting an estimated time of arrival for an equipment at a destination location are disclosed. The method includes inputting to a trained machine learning model a starting location, the destination location and at least one event data, generated in response to an event during a trip of the equipment via the railroad from the starting location to the destination location. The machine learning model is trained using a plurality of historical shipment route data. A particular historical shipment route data comprises at least a location and a corresponding timestamp. The method includes predicting, using the trained machine learning model, the estimated time of arrival of the equipment at the destination location.

The invention discloses a logistics arrival time forecasting system and method based on multi-data fusion, relates to the technical field of logistics arrival time forecasting, and aims to solve the technical problem that the deviation between the forecasting result of an existing logistics arrival time forecasting system and the actual arrival time is large. The system comprises a data acquisition module, a path planning module, a time calculation module and an early warning and output module. The output end of the data acquisition module is connected with the path planning module and the time calculation module, and the data acquisition module is used for acquiring multi-source data. The multi-source data comprises historical logistics data, order and delivery information data, weather data, real-time road condition data, map data, transportation tool characteristic data, cargo special demand data, transportation tool connection hidden loss data and transportation tool collaborative delay association data; and the output end of the path planning module is connected with the time calculation module. The method has the advantage of improving the accuracy of the arrival time forecast in the multimodal transport scene.

The invention discloses an equipment distance measurement method, electronic equipment, a storage medium and a product, and relates to the technical field of equipment distance measurement, the disclosed equipment distance measurement method comprises the following steps: sending an ultrasonic signal to slave equipment, and receiving a response signal replied by the slave equipment; performing interference elimination processing on the response signal to obtain a pure response signal; and determining the arrival time of the signal direct path from the pure response signal, and determining the distance between the master device and the slave device according to the arrival time. According to the invention, the distance measurement precision in a multi-device distance measurement scene can be improved.

The invention discloses a ship arrival time segmented prediction method and system based on a complex network, and the method comprises the following steps: taking the AIS data, channel features and traffic environment features of a ship as feature data, calculating the importance scores of all feature data, taking the feature data of which the importance score is greater than a set importance threshold as important features; weighting the important features according to the importance scores to obtain a complexity score of each track point in the AIS data; traversing all the track points, if the difference value of the complexity scores of two adjacent track points is smaller than a set threshold value, dividing the two track points into the same leg, otherwise, dividing the two track points into different legs; and marking the important features according to a leg division result, training a prediction model by using the marked important features, and realizing segmented prediction of the arrival time of the ship by using the trained prediction model.

The invention belongs to the field of intelligent transportation, and discloses a bus lane sharing control method based on the optimal bus speed, which comprises the following steps: S1, bus position monitoring and planning speed acquisition; s2, predicting predicted arrival time and stop time; s3, calculating the time for closing the bus lane; s4, calculating the time of reopening the bus lane; and S5, sending an instruction to the lane signal lamp. According to the method, conflicts between the buses and the social vehicles are reduced through reasonable space-time resource dynamic allocation, so that the influence on the passing efficiency of the social vehicles is reduced while the priority passing of the buses is ensured. According to the method, the passing efficiency and the punctuality rate of the bus can be improved, the reliability of a bus system is improved, the safety and smoothness of an urban traffic system can be ensured, energy consumption and tail gas emission are reduced, and meanwhile the riding experience and satisfaction degree of passengers are improved.

The invention discloses a charging pile dynamic distribution method in a multi-forklift collaborative operation scene, and relates to the technical field of intelligent logistics dispatch, and the method comprises the steps: S1, based on a current traffic flow prediction result, generating the predicted arrival time of a forklift at each charging pile, and S2, according to the predicted arrival time, determining the charging pile according to the predicted arrival time. The method comprises the steps of S1, calculating the actual waiting duration and the corresponding priority weight of each forklift, S3, dynamically regulating and controlling the charging queuing sequence of the forklifts based on the priority weights, and S4, sending the regulated queuing sequence to a target forklift to guide the target forklift to complete charging pile distribution. According to the charging pile dynamic allocation method in the multi-forklift collaborative operation scene, the charging queuing sequence is regulated and controlled according to the current traffic flow prediction result, so that the problems of congestion and overlong waiting time are solved.

The invention discloses an inventory management method, and the method comprises a time-sharing arrival planning step which comprises the steps: obtaining an order demand of a manufacturer, and making a time-sharing arrival plan according to the order demand and corresponding supplier distribution; and the warehouse layout optimization step comprises the steps of obtaining warehouse-out frequency and order quantity information of each cargo in the warehouse, sorting and classifying the cargo according to the sales volume or the sales volume, dividing the warehouse space into a plurality of storage areas according to the classification, and placing the cargo in the storage area corresponding to the classification where the cargo is located. According to the inventory management method, the arrival time of the goods is reasonably distributed, so that the goods arrive at different time periods, and the pressure of the warehouse space is reduced. Through the step of optimizing the warehouse layout, the most suitable storage position of the goods is determined according to the goods order and the circulation frequency, and the overall operation efficiency is improved.

The invention discloses a communication method and device, and relates to the field of communication. The method comprises the following steps: receiving first configuration information from access network equipment, wherein the first configuration information is used for indicating a first time-frequency resource; when there is uplink data to be transmitted, and the position distance between the first position of the terminal device at the first moment and the second position corresponding to the service cell is less than a first distance threshold, and / or the signal strength of the service cell is greater than a first signal strength threshold, sending the uplink data on a first time-frequency resource; the first moment is the arrival moment of the uplink data or the first target time corresponding to the first time-frequency resource. According to the invention, the terminal equipment does not carry out random access, and uses the first time-frequency resource indicated by the access network equipment to send the uplink data, so that the signaling overhead and the transmission delay are reduced, and the uplink data capacity is enhanced. The first time-frequency resource is a shared common time-frequency resource for different terminal devices, the resource utilization rate is high, and the transmission capacity of the communication system can be enhanced.

The present invention relates to an intelligent berthing method for inland anchorages, comprising the following steps: S1: a ship sends a berth application and obtains the ship's current information; S2: using the ship information to predict the ship's arrival time at each available anchorage; S3: collecting information on all currently moored ships at the anchorage and allocating berths to incoming ships based on the current berthing situation at the anchorage; S4: after a ship has moored, checking whether it has moored at the designated location as required; S5: after receiving a departure information, collecting the ship's departure time for use in allocating berths to subsequent incoming ships; and S6: upon reaching the scheduled departure time, the ship performs the departure operation. This method can predict ship arrival times and intelligently allocate berths to incoming ships, thereby reducing anchorage management costs, improving anchorage operation efficiency, and enhancing the intelligent construction of anchorages.

The invention discloses a pre-hospital emergency unified scheduling decision-making method and system. The method comprises the steps that S1, a unified scheduling center obtains an accident occurrence place, a trauma type and the number of trauma people; s2, the number of wounded persons is judged, if one person enters S3, and if multiple persons enter S6; s3, if the wounds are serious wounds, entering S4, and if the wounds are non-serious wounds, entering S5; s4, selecting the hospital with the shortest time for arriving at the hospital at present from the hospitals with the wound type treatment scores reaching the preset value as a target hospital; s5, selecting the hospital which is predicted to reach the hospital for the shortest time as a target hospital; s6, judging the number of severely-wounded people, if one person enters the step S4, if multiple persons exist, selecting hospitals with the wound type treatment scores reaching a preset value, sorting the selected hospitals from short to long according to the current predicted shortest time for reaching the hospitals, selecting target hospitals according to the sequence, judging the number of non-severely-wounded people, if one person enters the step S5, judging the number of non-severely-wounded people, and if the number of non-severely-wounded people enters the step S5; and if multiple persons sort the hospitals from short to long according to the current predicted shortest time of reaching the hospitals, selecting target hospitals in sequence.

The invention discloses a civil aviation cargo tracking method, and relates to the technical field of logistics transportation, and the method comprises the steps: collecting cargo data information, and carrying out the whole-process information monitoring in real time; monitoring data information is obtained, a comprehensive evaluation result is obtained according to the comprehensive evaluation model, the predicted value of the cargo arrival time is dynamically adjusted, and an overall process analysis report is generated; according to the overall process analysis report, obtaining the transportation completion degree and the error time value corresponding to each transportation path and the actual transportation time of each transportation node, and dynamically planning the transportation paths according to an optimization mechanism; through setting cargo transportation whole process information monitoring, transparency and traceability of cargo transportation can be effectively improved. By establishing the comprehensive evaluation model and monitoring and analyzing the change data source, the extended time is obtained and the arrival time is predicted, so that a user can obtain the cargo state information in time, and the effects of information transparency, dynamic adjustment, real-time monitoring and timely feedback are achieved.

The invention relates to a medical-seeking registration appointment method and system and a medium, and relates to the technical field of medical information services. The method comprises the following steps: recommending a doctor and a corresponding doctor-seeing date to a user on the basis of registration information including a doctor-seeing department and the severity of an illness state of the user, determining doctor-seeing time and hospital arrival time of the user on the doctor-seeing date on the basis of the doctor-seeing date selected by the user and a doctor-seeing time determination condition preset by a system, and sending doctor-seeing information to a user terminal. In the process, the doctor is recommended based on the severity of the illness state, so that the waste of doctor resources can be reduced, and the doctor-seeing time and the hospital arrival time of the user at the doctor-seeing date are determined based on the doctor-seeing, the doctor-seeing date and the doctor-seeing time determination condition, so that the doctor-seeing efficiency is improved, and the doctor-seeing queuing time is reduced.

The elevator waiting time estimation device of the present invention includes: a queuing start measurement unit that measures the situation where the user of the elevator arrives at a set position, a boarding measurement unit that measures the situation where the user of the elevator enters the car, a storage unit that stores the arrival time measured by the queuing start measurement unit and the boarding time measured by the boarding measurement unit, and a waiting time calculation unit that calculates the waiting time required until the user of the elevator enters the car based on the arrival time and the boarding time stored in the storage unit. Thus, the waiting time at the landing can be calculated with simple processing and structure.

The invention discloses an intelligent shipping method for a port ship. The intelligent shipping method comprises the following steps: acquiring information data; dynamically predicting the arrival time of the ship in real time; building a port berth real-time dynamic distribution model based on ship arrival time prediction; solving a port berth real-time dynamic distribution model; and outputting a real-time dynamic port ship berthing result. According to the method, whether the tide and the berthing position meet the ship draft and other constraints are considered in berth dynamic allocation, the berth allocation strategy of the optimal berthing position is designed, the berth utilization rate is increased, the port efficiency is improved, and the method has the advantages of being high in universality and wide in coverage; according to the method, the complex relation between the latitude, the longitude, the COG, the SOG and other characteristics and the arrival time is directly estimated through the machine learning model, real-time prediction of the arrival time is achieved by inputting AIS data of the latest period of time, therefore, dynamic characteristic changes are captured more efficiently, prediction precision is high, convergence is fast, and the workload is small.

The invention provides a ship lock intelligent scheduling method and system considering ship classification and dangerous goods isolation, and the method comprises the steps: S1, obtaining the information of a to-be-scheduled ship and the information of a lock chamber, and constructing a conventional ship information list ListN and a dangerous ship information list ListD based on the danger level of the to-be-scheduled ship; s2, according to the management method of the hydro-junction where the lock chamber is located, the danger level of independent lockage is obtained, and the safety size of the ship needing independent lockage in the ListD is modified so that the lock chamber can be fully occupied by the ship; and S3, respectively taking the ListN and the ListD as an input list ListI, calculating a global highest scheduling score of the ListI based on the safety size, the arrival time and the type of the ship, and selecting a global optimal scheduling scheme corresponding to the higher global highest scheduling score in the ListN and the ListD as a final scheduling scheme. The united targets of improving the utilization rate of the lock chamber, reducing the waiting time of the ship, weighing the priority of the ship and isolating the dangerous goods ship are achieved.

The invention relates to the technical field of heterogeneous traffic analysis, in particular to a heterogeneous traffic analysis method, device and system driven by an intelligent large model, and the method comprises the steps: collecting the side channel characteristics of encrypted traffic, and obtaining the side channel characteristics of the encrypted traffic based on the length of each data packet in a single session, the traffic direction and the arrival timestamp relative to the session starting time; correcting a static position coding mode of the Transform model, and performing dynamic position coding on the side channel characteristics to obtain a first characteristic vector of each data packet; constructing a second feature vector, a third feature vector and a fourth feature vector; distributing learnable deviation vectors for each feature vector to form a modal deviation matrix which is used as learnable parameters in the training process of the Transform model, and correcting an attention mechanism in the Transform model; and obtaining a fusion feature vector of all the feature vectors, and carrying out attack detection on the input traffic. Therefore, the accuracy of flow detection is improved.

The invention discloses a crowdsourcing task processing method and system based on multi-agent cooperation, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving a user order which comprises a service type, a starting point address, an end point address and the arrival time; decomposing all user orders according to a preset rule to generate a task package; determining the predicted arrival time of each task package according to the pickup address and the delivery address, and generating an optimal allocation scheme according to the real-time state of the worker and the predicted arrival time of each task package; and performing task pushing according to the optimal allocation scheme. Intelligent decomposition and dynamic allocation of tasks are achieved through cooperation of large language model agents, the completion efficiency and quality of crowdsourcing tasks are remarkably improved, predicted arrival time is dynamically calculated through path planning agents, execution of time-sensitive tasks is optimized, and delay is reduced.