Multi-granularity simulation model scheduling method and apparatus, device, medium, and product

Abstract

The present application relates to the technical field of multi-granularity simulation models, and discloses a multi-granularity simulation model scheduling method and apparatus, a device, a medium, and a product. The multi-granularity simulation model scheduling method comprises: on the basis of a plurality of trajectory data collected by a plurality of sensors, analyzing a relationship between current collection times of a plurality of first sensors and a queue time interval corresponding to a second sensor; on the basis of a relationship analysis result, performing synchronization processing on the plurality of trajectory data to obtain a plurality of first target trajectory data; performing density distribution analysis on historical trajectory data to obtain cost factors; on the basis of the cost factors, adjusting the plurality of first target trajectory data to obtain a plurality of second target trajectory data; and in response to a trigger of a simulation execution instruction, performing synchronous simulation on the basis of obtained timestamps and the plurality of second target trajectory data. The present application improves the simulation synchronization among a plurality of multi-granularity simulation models by performing synchronous processing on trajectory data and adjusting the trajectory data by means of cost factors.

Description

Scheduling methods, devices, equipment, media, and products for multi-granularity simulation models

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202510145312.X, filed on February 10, 2025, entitled “Scheduling Method, Apparatus, Device, Medium and Product for Multi-Granularity Simulation Model”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of multi-granularity simulation model technology, specifically to scheduling methods, devices, equipment, media, and products for multi-granularity simulation models. Background Technology

[0004] In a distributed environment, multiple multi-granularity simulation models of a radar system are used to comprehensively and accurately simulate the performance and behavior of the radar system under different scenarios. Given the different simulation step sizes of these multi-granularity simulation models, synchronization is required to ensure accurate data exchange between them during co-simulation, and to ensure that the simulation of radar system behavior is continuous and conforms to actual logic.

[0005] Currently, there are two methods for synchronizing multi-granularity simulation models with different simulation step sizes. The first method is waiting for synchronization. Specifically, during simulation, all multi-granularity simulation models are paused until the slowest model completes its current simulation step size, then the others are started. The second method is simple interpolation. Specifically, when one multi-granularity simulation model has a larger simulation step size than another, at the moment the smaller model needs synchronization, linear interpolation is performed on adjacent time points of the larger model to approximate the moment the smaller model needs synchronization.

[0006] However, the first method leads to the multi-granularity simulation model being idle, resulting in low simulation efficiency; the accuracy of the second method depends on the changes in the state of the multi-granularity simulation model, and this method will be distorted in nonlinear changes, resulting in low reliability of simulation results. Summary of the Invention

[0007] In view of this, this application provides a scheduling method, apparatus, device, medium and product for multi-granularity simulation models to solve the problems of low simulation efficiency and low reliability of simulation results caused by synchronous processing methods for multi-granularity simulation models in related technologies.

[0008] In a first aspect, this application provides a method for synchronous processing of multi-granularity simulation models, comprising: analyzing the relationship between the current acquisition time of multiple first sensors and the queue time interval corresponding to the data acquisition queue of the second sensor based on multiple trajectory data of a target object collected by multiple sensors, and obtaining a relationship analysis result; the first data acquisition rate of multiple first sensors is less than a preset acquisition rate, the second data acquisition rate of the second sensors is greater than or equal to the preset acquisition rate, the data acquisition queue is a trajectory data queue arranged by the second sensors according to the acquisition time order, and the multiple sensors include multiple first sensors and second sensors; synchronously processing the multiple trajectory data according to the relationship analysis result to obtain multiple first target trajectory data; performing density distribution analysis on the historical trajectory data of multiple sensors to obtain a cost factor corresponding to each sensor; adjusting the multiple first target trajectory data according to the cost factor corresponding to each sensor to obtain multiple second target trajectory data; acquiring the timestamps of multiple multi-granularity simulation models, and controlling the multiple multi-granularity simulation models to perform synchronous simulation in response to the triggering of the simulation run command, based on the timestamps and the multiple second target trajectory data.

[0009] This application analyzes the relationship between the current acquisition time of multiple first sensors with acquisition rates lower than a preset acquisition rate and the queue time interval corresponding to the data acquisition queue of second sensors with acquisition rates greater than or equal to the preset acquisition rate. It effectively integrates multiple trajectory data collected by sensors at different acquisition rates to obtain relationship analysis results. Based on these results, the multiple trajectory data are synchronized to obtain multiple first target trajectory data. This application achieves accurate temporal correspondence between different trajectory data by precisely synchronizing trajectory data collected by different sensors. This application performs density distribution analysis on historical trajectory data from multiple sensors to obtain a cost factor for each sensor. Based on the cost factor for each sensor, it adjusts the multiple first target trajectory data to obtain multiple second target trajectory data. By mining the characteristics of the trajectory data collected by multiple sensors using historical data, cost factors are obtained, enabling the cost factors to accurately reflect the characteristics of multiple trajectory data. Adjusting the multiple first target trajectory data using cost factors improves the synchronization and reliability of the multiple second target trajectory data. After obtaining the timestamps of multiple multi-granularity simulation models, this application responds to the triggering of simulation run commands and controls multiple multi-granularity simulation models to perform synchronous simulation based on the timestamps and multiple second target trajectory data. This application improves the synchronization and reliability of trajectory data by synchronously processing multiple trajectory data to obtain multiple first target trajectory data, and then adjusting the multiple first target trajectory data according to a cost factor to obtain multiple second target trajectory data. This improves the accuracy of simulation results obtained by controlling multiple multi-granularity simulation models to perform synchronous simulation based on timestamps and multiple second target trajectory data, making the simulation results more consistent with reality. Since this application directly processes multiple trajectory data and obtains the timestamps of multiple multi-granularity simulation models, the multiple multi-granularity simulation models do not need to wait for each other to synchronize, thereby improving the simulation efficiency of multiple multi-granularity simulation models.

[0010] In one optional implementation, based on multiple trajectory data of the target object collected by multiple sensors, the relationship between the current acquisition time of multiple first sensors and the queue time interval corresponding to the data acquisition queue of the second sensor is analyzed to obtain the relationship analysis result. This includes: selecting multiple first trajectory data collected by the second sensor from the multiple trajectory data; arranging the multiple first trajectory data in the order of acquisition time to obtain a data acquisition queue; obtaining the queue time interval corresponding to the data acquisition queue; obtaining the current acquisition time of each first sensor, comparing the current acquisition time with the queue time interval to obtain the relationship analysis result; wherein the relationship analysis result includes the current acquisition time being less than or equal to the first endpoint time of the queue time interval, the current acquisition time being greater than the first endpoint time and less than the second endpoint time, and the current acquisition time being greater than or equal to the second endpoint time of the queue time interval; the first endpoint time being less than the second endpoint time.

[0011] In one optional implementation, multiple trajectory data are synchronously processed based on the relationship analysis results to obtain multiple first target trajectory data, including: when the current acquisition time is greater than a first endpoint time and less than a second endpoint time, in the data acquisition queue, query the third target trajectory data corresponding to the first target time whose first time difference with the current acquisition time is less than a first preset value and the fourth target trajectory data corresponding to the second target time; using the first time interval between the first target time and the second target time as a first interpolation interval, interpolate the current acquisition time, the third target trajectory data, and the fourth target trajectory data to obtain the first target trajectory data corresponding to each sensor; when the current acquisition time is less than or equal to the first endpoint time of the queue time interval, determine the second time difference between the first endpoint time and the current acquisition time; obtain the third target time based on the sum of the first endpoint time and the second time difference; in the data acquisition queue, query the third target time whose third time difference with the third target time is less than a first preset value and the fourth target trajectory data corresponding to the first target time. The fourth target time corresponds to the fifth target trajectory data with two preset values; the second time interval between the first endpoint time and the fourth target time is used as the second interpolation interval, and the sixth target trajectory data corresponding to the current acquisition time, the first endpoint time, and the fifth target trajectory data are interpolated to obtain the first target trajectory data corresponding to each sensor; when the current acquisition time is greater than or equal to the second endpoint time of the queue time interval, the fourth time difference between the second endpoint time and the current acquisition time is determined; the fifth target time is obtained based on the difference between the second endpoint time and the fourth time difference; in the data acquisition queue, the sixth target time corresponding to the seventh target trajectory data whose fifth time difference with the fifth target time is less than the third preset value is queried; the third time interval between the first endpoint time and the sixth target time is used as the third interpolation interval, and the eighth target trajectory data corresponding to the current acquisition time, the second endpoint time, and the seventh target trajectory data are interpolated to obtain the first target trajectory data corresponding to each sensor.

[0012] Based on different relationship analysis results, this application obtains different interpolation intervals and uses interpolation processing to obtain multiple first target trajectory data, which can effectively fill data gaps or correct time differences, and can handle data synchronization problems more precisely, thereby improving the accuracy of data synchronization.

[0013] In one optional implementation, density distribution analysis is performed on historical trajectory data from multiple sensors to obtain a cost factor for each sensor. This includes: acquiring historical trajectory data from multiple sensors and a preset fusion function; the preset fusion function includes a cost factor; performing a normal distribution transformation on the preset fusion function based on the historical trajectory data to obtain a normal distribution function; performing density distribution analysis on the normal distribution function to obtain a density distribution function; determining a first normal distribution relation corresponding to the density distribution function; introducing a correction function into the normal distribution relation, solving for the correction parameters in the correction function to obtain a second normal distribution relation; and solving for the cost factor based on the first and second normal distribution relations to obtain the cost factors for multiple sensors.

[0014] This application employs a pre-defined fusion function and performs a series of operations, including normal distribution transformation and density distribution analysis, to solve for the cost factor, making its determination more scientific and accurate. This application introduces a correction function into the normal distribution formula and solves for the correction parameters, enabling the determined cost factor to better adapt to different application scenarios and data characteristics. This precise cost factor allows for a more reasonable balance of the weights of trajectory data collected by different sensors when adjusting trajectory data, reducing the impact of data errors and interference, and improving the overall accuracy of data processing.

[0015] In one optional implementation, multiple first target trajectory data are adjusted according to the cost factor corresponding to each sensor to obtain multiple second target trajectory data, including: obtaining multiple second target trajectory data by multiplying the cost factor corresponding to each sensor with the first target trajectory data corresponding to each sensor.

[0016] In one optional implementation, multiple multi-granularity simulation models are controlled to perform synchronous simulation based on timestamps and multiple second target trajectory data, including: controlling multiple computing nodes and multiple simulation nodes in the multiple multi-granularity simulation models to run synchronously based on timestamps and multiple second target trajectory data.

[0017] Secondly, this application provides a scheduling device for a multi-granularity simulation model, comprising: a relation analysis result determination module, used to analyze the relationship between the current acquisition time of multiple first sensors and the queue time interval corresponding to the data acquisition queue of the second sensor based on multiple trajectory data of a target object collected by multiple sensors, and obtain a relation analysis result, wherein the first data acquisition rate of the multiple first sensors is less than a preset acquisition rate, the second data acquisition rate of the second sensors is greater than or equal to the preset acquisition rate, the data acquisition queue is a trajectory data queue arranged by the second sensors according to the acquisition time order, and the multiple sensors include multiple first sensors and second sensors; a trajectory data synchronization processing module, used to synchronize the multiple trajectory data according to the relation analysis result to obtain multiple first target trajectory data; a density distribution analysis module, used to perform density distribution analysis on the historical trajectory data of multiple sensors to obtain the cost factor corresponding to each sensor; a target trajectory data adjustment module, used to adjust the multiple first target trajectory data according to the cost factor corresponding to each sensor to obtain multiple second target trajectory data; and a synchronous simulation module, used to acquire the timestamps of multiple multi-granularity simulation models, and in response to the triggering of the simulation run command, control the multiple multi-granularity simulation models to perform synchronous simulation according to the timestamps and multiple second target trajectory data.

[0018] Thirdly, this application provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the scheduling method of the multi-granularity simulation model described in the first aspect or any corresponding embodiment.

[0019] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the scheduling method of the multi-granularity simulation model described in the first aspect or any corresponding embodiment.

[0020] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute a scheduling method for a multi-granularity simulation model described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this application, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 is a flowchart illustrating the scheduling method of a multi-granularity simulation model according to an embodiment of this application.

[0023] Figure 2 is a flowchart illustrating a method for determining multiple first target trajectory data according to an embodiment of this application.

[0024] Figure 3 is a schematic diagram of the interpolation interval selection process according to an embodiment of this application.

[0025] Figure 4 is a flowchart illustrating another method for determining the trajectory data of a plurality of first targets according to an embodiment of this application.

[0026] Figure 5 is a flowchart illustrating the method for determining the cost factor according to an embodiment of this application.

[0027] Figure 6 is a flowchart illustrating another method for determining a cost factor according to an embodiment of this application.

[0028] Figure 7 is a structural block diagram of a scheduling device for a multi-granularity simulation model according to an embodiment of this application.

[0029] Figure 8 is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0031] In a distributed environment, multiple multi-granularity simulation models of a radar system are used to comprehensively and accurately simulate the performance and behavior of the radar system under different scenarios. Given the different simulation step sizes of these multi-granularity simulation models, synchronization is required to ensure accurate data exchange between them during co-simulation, and to ensure that the simulation of radar system behavior is continuous and conforms to actual logic.

[0032] There are many methods for synchronizing multi-granularity simulation models with different simulation step sizes, such as waiting synchronization or simple interpolation. Waiting synchronization involves pausing all multi-granularity simulation models during the simulation and waiting until the slowest model completes its current simulation step before resuming. This method ensures accurate synchronization between the multi-granularity simulation models at the same point in time. However, this synchronization method can lead to faster multi-granularity simulation models being idle, thus reducing overall simulation efficiency.

[0033] Simple interpolation is a method for cross-step-size synchronization that uses numerical interpolation to estimate the state of a multi-granularity simulation model. For example, when one multi-granularity simulation model has a large step size and another has a small step size, at the moment when synchronization is needed for the smaller step-size model, linear interpolation is performed on adjacent time points of the larger step-size model to obtain an approximate state at the synchronization point. The accuracy of this method depends on the changes in the state of the multi-granularity simulation models; it works well with linear changes but may distort the results with nonlinear changes, leading to low simulation efficiency.

[0034] This application provides a scheduling method for multi-granularity simulation models. By synchronizing trajectory data and adjusting the trajectory data through a cost factor, the simulation synchronization of multiple multi-granularity simulation models can be improved.

[0035] According to an embodiment of this application, a scheduling method for a multi-granularity simulation model is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] This embodiment provides a scheduling method for a multi-granularity simulation model, which can be used in a computer device equipped with a scheduling host. This embodiment applies to the scheduling host. Figure 1 is a flowchart of the scheduling method for a multi-granularity simulation model according to this embodiment. As shown in Figure 1, the process includes the following steps:

[0037] Step S101: Based on multiple trajectory data of the target object collected by multiple sensors, analyze the relationship between the current acquisition time of multiple first sensors and the queue time interval corresponding to the data acquisition queue of the second sensor, and obtain the relationship analysis result; the first data acquisition rate of multiple first sensors is less than the preset acquisition rate, the second data acquisition rate of the second sensor is greater than or equal to the preset acquisition rate, the data acquisition queue is the trajectory data queue arranged by the second sensor according to the acquisition time order, and the multiple sensors include multiple first sensors and second sensors.

[0038] The target object refers to the object detected and tracked by the radar in the radar system, such as an aircraft or a drone. Multiple trajectory data are data collected by multiple sensors reflecting the target object's movement path and state in space.

[0039] In some optional implementations, the scheduling method for the multi-granularity simulation model further includes a process for distinguishing multiple sensors. The process for distinguishing multiple sensors involves comparing the data acquisition rates of multiple sensors, identifying sensors with data acquisition rates greater than or equal to a preset acquisition rate as second sensors, and identifying multiple sensors with data acquisition rates less than the preset acquisition rate as multiple second sensors. The preset acquisition rate is set according to the actual situation. In this embodiment, the preset acquisition rate is set as high as possible to ensure that the second sensor is the sensor with the highest data acquisition rate.

[0040] In some optional implementations, the relationship analysis results include the current acquisition time being less than or equal to the first endpoint time of the queue time interval, the current acquisition time being greater than the first endpoint time and less than the second endpoint time, and the current acquisition time being greater than or equal to the second endpoint time of the queue time interval; the first endpoint time being less than the second endpoint time.

[0041] The first endpoint time is the minimum time in the queue time interval, and the second endpoint time is the maximum time in the queue time interval.

[0042] Step S102: Based on the relationship analysis results, multiple trajectory data are processed synchronously to obtain multiple first target trajectory data.

[0043] In some optional implementations, multiple trajectory data are processed synchronously based on the relationship analysis results to obtain multiple first target trajectory data, including: determining the interpolation interval of multiple trajectory data based on the relationship analysis results, and interpolating the multiple trajectory data according to the interpolation interval to obtain the first target trajectory time corresponding to each sensor.

[0044] Specifically, when the current acquisition time is greater than the first endpoint time and less than the second endpoint time, the third target trajectory data corresponding to the first target time and the fourth target trajectory data corresponding to the second target time are queried in the data acquisition queue when the first time difference between the current acquisition time and the first target time is less than the first preset value. The first time interval between the first target time and the second target time is used as the first interpolation interval, and the current acquisition time, the third target trajectory data and the fourth target trajectory data are interpolated to obtain the first target trajectory data corresponding to each sensor.

[0045] The first preset value is set according to the actual situation. In this embodiment, the first preset value is set as small as possible to ensure that the trajectory data corresponding to the first target time and the trajectory data corresponding to the second target time are two adjacent data points in the data acquisition queue. For example, the first preset value can be the average acquisition time corresponding to the data acquisition queue.

[0046] When the current acquisition time is less than or equal to the first endpoint time of the queue time interval, determine the second time difference between the first endpoint time and the current acquisition time; obtain the third target time based on the sum of the first endpoint time and the second time difference; in the data acquisition queue, query the fourth target time corresponding to the fifth target trajectory data whose third time difference with the third target time is less than the second preset value; take the second time interval between the first endpoint time and the fourth target time as the second interpolation interval, and perform interpolation processing on the current acquisition time, the sixth target trajectory data corresponding to the first endpoint time, and the fifth target trajectory data to obtain the first target trajectory data corresponding to each sensor.

[0047] The second preset value is set according to the actual situation. In this embodiment, the second preset value is set as small as possible to ensure that the fourth target time corresponding to the fifth target trajectory data is the time point closest to the third target time.

[0048] When the current acquisition time is greater than or equal to the second endpoint time of the queue time interval, determine the fourth time difference between the second endpoint time and the current acquisition time; based on the difference between the second endpoint time and the fourth time difference, obtain the fifth target time; in the data acquisition queue, query the sixth target time corresponding to the seventh target trajectory data whose fifth time difference with the fifth target time is less than the third preset value; take the third time interval between the first endpoint time and the sixth target time as the third interpolation interval, and perform interpolation processing on the current acquisition time, the eighth target trajectory data corresponding to the second endpoint time, and the seventh target trajectory data to obtain the first target trajectory data corresponding to each sensor.

[0049] The third preset value is set according to the actual situation. In this embodiment, the third preset value is set as small as possible to ensure that the sixth target time corresponding to the seventh target trajectory data is the time point closest to the fifth target time.

[0050] Step S103: Perform density distribution analysis on the historical trajectory data of multiple sensors to obtain the cost factor corresponding to each sensor.

[0051] The cost factor is a quantitative indicator used to characterize the features and data quality of each sensor, obtained by density distribution analysis of historical trajectory data from multiple sensors.

[0052] In some optional implementations, density distribution analysis is performed on historical trajectory data from multiple sensors to obtain a cost factor for each sensor, including:

[0053] The process involves acquiring historical trajectory data from multiple sensors and a preset fusion function, which includes a cost factor. A normal distribution transformation is applied to the preset fusion function based on the historical trajectory data to obtain a normal distribution function. Density distribution analysis is performed on the normal distribution function to obtain a density distribution function. A first normal distribution relation corresponding to the density distribution function is determined. A correction function is introduced into the normal distribution relation, and the correction parameters in the correction function are solved to obtain a second normal distribution relation. Based on the first and second normal distribution relations, the cost factors are solved to obtain the cost factors for multiple sensors.

[0054] Step S104: Adjust the multiple first target trajectory data according to the cost factor corresponding to each sensor to obtain multiple second target trajectory data.

[0055] In some optional implementations, multiple first target trajectory data are adjusted according to the cost factor corresponding to each sensor to obtain multiple second target trajectory data, including: obtaining multiple second target trajectory data by multiplying the cost factor corresponding to each sensor with the first target trajectory data corresponding to each sensor.

[0056] Step S105: Obtain the timestamps of multiple multi-granularity simulation models. In response to the triggering of the simulation run command, control the multiple multi-granularity simulation models to perform synchronous simulation based on the timestamps and multiple second target trajectory data.

[0057] In some optional implementations, multiple multi-granularity simulation models are controlled to perform synchronous simulation based on timestamps and multiple second target trajectory data, including: controlling multiple computing nodes and multiple simulation nodes in multiple multi-granularity simulation models to run synchronously based on timestamps and multiple second target trajectory data.

[0058] Each multi-granularity simulation model comprises multiple simulation nodes and multiple computing nodes. The scheduling host coordinates and manages these multiple simulation nodes and computing nodes. Computing nodes are nodes that undertake specific computational tasks. Simulation nodes are computing nodes used to perform simulation tasks. Simulation nodes switch between different states based on the scheduling host's settings and the second target trajectory data, such as initializing simulation tasks, running simulation programs, and pausing simulation programs. All computing nodes are synchronously started and run under the control of the scheduling host's clock.

[0059] In some optional implementations, the simulation node is equipped with a time controller that periodically acquires the simulation node's timestamp using UDP (User Datagram Protocol). The simulation step size of the simulation node is an integer multiple (e.g., m times) of the frame period length of the multi-granularity simulation model, and is initialized to 0 as the logical time. After each synchronization operation is completed, the logical time of the computing node is incremented by m, and the logical time of the scheduling host is incremented by 1 after the current operation is completed.

[0060] In this embodiment, after receiving the timestamp and multiple second target trajectory data, the computing node switches between initialization, running, and pause states in response to different instructions. In the initialization state, for the simulation node, initial conditions are loaded, simulating the initial position, velocity, and flight parameters of the target object; for the computing node, the required matrix, vector, and other data structures are initialized. When the simulation node receives the simulation run instruction from the scheduling host and meets the running conditions, it enters the running state and simulates the flight trajectory of the target object at different times based on the second target trajectory data. When the scheduling host receives the user's pause instruction, it sends a pause instruction to both the computing node and the simulation node.

[0061] The scheduling method for the multi-granularity simulation model provided in this embodiment analyzes the relationship between the current acquisition time of multiple first sensors with acquisition rates less than a preset acquisition rate and the queue time interval corresponding to the data acquisition queue of second sensors with acquisition rates greater than or equal to the preset acquisition rate. This effectively integrates multiple trajectory data collected by sensors with different acquisition rates, obtaining relationship analysis results. Based on these results, the multiple trajectory data are synchronized to obtain multiple first target trajectory data. This embodiment performs precise synchronization processing on trajectory data collected by different sensors, achieving accurate temporal correspondence between different trajectory data. Furthermore, this embodiment performs density distribution analysis on historical trajectory data from multiple sensors to obtain a cost factor corresponding to each sensor. Based on the cost factor corresponding to each sensor, the multiple first target trajectory data are adjusted to obtain multiple second target trajectory data. By mining the features of trajectory data collected by multiple sensors using historical data, cost factors are obtained, enabling the cost factors to accurately reflect the characteristics of multiple trajectory data. Adjusting the multiple first target trajectory data using cost factors improves the synchronization and reliability of the multiple second target trajectory data. This application embodiment obtains the timestamps of multiple multi-granularity simulation models and, in response to the triggering of the simulation run command, controls multiple multi-granularity simulation models to perform synchronous simulation based on the timestamps and multiple second target trajectory data. This application embodiment obtains multiple first target trajectory data by synchronizing multiple trajectory data, and then adjusts these first target trajectory data according to a cost factor to obtain multiple second target trajectory data. This improves the synchronization and reliability of the trajectory data, thereby improving the accuracy of the simulation results obtained by controlling multiple multi-granularity simulation models to perform synchronous simulation based on the timestamps and multiple second target trajectory data. The simulation results are more consistent with reality. Because this application embodiment directly processes multiple trajectory data and obtains the timestamps of multiple multi-granularity simulation models, the multiple multi-granularity simulation models do not need to wait for each other to synchronize, thus improving the simulation efficiency of the multiple multi-granularity simulation models.

[0062] This embodiment provides a scheduling method for a multi-granularity simulation model, which can be used in computer equipment. Figure 2 is a flowchart of a method for determining multiple first target trajectory data according to an embodiment of this application. As shown in Figure 2, the process includes the following steps:

[0063] Step S201: Select multiple first trajectory data collected by the second sensor from multiple trajectory data.

[0064] Among them, multiple first trajectory data are selected in addition to the current trajectory data collected by the second sensor.

[0065] Step S202: Arrange multiple first trajectory data in the order of acquisition time to obtain a data acquisition queue.

[0066] Step S203: Obtain the queue time interval corresponding to the data acquisition queue.

[0067] In some alternative implementations, suppose the data acquisition queue contains n first trajectory data, let α be the time interval threshold, and let τ be the time difference between adjacent first trajectory data, then τ≥α; for sensors with an acquisition period T less than α, it indicates that the sensor's data acquisition rate is high. In order to avoid the first trajectory data in the data acquisition queue being too dense, let τ=α; for sensors with an acquisition period T greater than α, the sensor's data acquisition rate is low. In order to keep the first trajectory data reasonably distributed, let τ=T.

[0068] Step S204: Obtain the current acquisition time of each first sensor, compare the current acquisition time with the queue time interval, and obtain the relationship analysis results.

[0069] Step S205: Based on the relationship analysis results, multiple trajectory data are processed synchronously to obtain multiple first target trajectory data.

[0070] The relationship analysis results include the current collection time being less than or equal to the first endpoint time of the queue time interval, the current collection time being greater than the first endpoint time and less than the second endpoint time, and the current collection time being greater than or equal to the second endpoint time of the queue time interval; the first endpoint time being less than the second endpoint time.

[0071] When the current acquisition time is greater than the first endpoint time and less than the second endpoint time, in the data acquisition queue, query the third target trajectory data corresponding to the first target time whose first time difference with the current acquisition time is less than the first preset value, and the fourth target trajectory data corresponding to the second target time; take the first time interval between the first target time and the second target time as the first interpolation interval, and perform interpolation processing on the current acquisition time, the third target trajectory data and the fourth target trajectory data to obtain the first target trajectory data corresponding to each sensor.

[0072] When the current acquisition time is less than or equal to the first endpoint time of the queue time interval, determine the second time difference between the first endpoint time and the current acquisition time; obtain the third target time based on the sum of the first endpoint time and the second time difference; in the data acquisition queue, query the fourth target time corresponding to the fifth target trajectory data whose third time difference with the third target time is less than the second preset value; take the second time interval between the first endpoint time and the fourth target time as the second interpolation interval, and perform interpolation processing on the current acquisition time, the sixth target trajectory data corresponding to the first endpoint time, and the fifth target trajectory data to obtain the first target trajectory data corresponding to each sensor.

[0073] When the current acquisition time is greater than or equal to the second endpoint time of the queue time interval, determine the fourth time difference between the second endpoint time and the current acquisition time; based on the difference between the second endpoint time and the fourth time difference, obtain the fifth target time; in the data acquisition queue, query the sixth target time corresponding to the seventh target trajectory data whose fifth time difference with the fifth target time is less than the third preset value; take the third time interval between the first endpoint time and the sixth target time as the third interpolation interval, and perform interpolation processing on the current acquisition time, the eighth target trajectory data corresponding to the second endpoint time, and the seventh target trajectory data to obtain the first target trajectory data corresponding to each sensor.

[0074] The time of the first endpoint can be t. min The time of the second endpoint can be t. max The first target time can be t. j The second objective time can be t. j+1 The current data collection time is t, and the second time difference is d. a The third objective time is t. min +d a The fourth objective time is t. n The fourth time difference is d b The fifth objective has a time limit of t. max -d b The sixth objective has a time of t. m .

[0075] For example, as shown in Figure 3, which is a schematic diagram of the interpolation interval selection process, the high-rate sensor is the second sensor and the low-rate sensor is the first sensor. When t min <t<t max At that time, select two adjacent time points t in the queue time interval of the high-speed sensor. j With t j+1 , will [t j , t j+1 ] as the first interpolation interval; when t≤t min Calculate the second time difference d. a =t min -t, assuming the upper limit of the time difference is β, if d a If d > β, then it exceeds the reasonable interpolation range, and no interpolation processing is performed. a ≤β, select the time interval with respect to t in the queue. min +d a The closest point t n , will [t min , t n [This is] used as the second interpolation interval; when t ≥ t max Calculate the time difference d b =tt maxLet the upper limit of the time difference be β, if d b If d > β, then it exceeds the reasonable interpolation range, and no interpolation processing is performed. b ≤β, select the time interval with respect to t in the queue. max -d b The closest point t m , will [t m , t max [This is] used as the third interpolation interval.

[0076] In this embodiment of the application, the formula for interpolation is:

[0077] Where X(t), Y(t), and Z(t) are the values ​​of the first target trajectory data in spatial coordinates, and t is the current acquisition time. a t is the lower limit of the interpolation interval. a+1 X is the lower limit of the interpolation interval. a Y a Z a For t a The corresponding spatial coordinates of the target trajectory data, X a+1 Y a+1 Z a+1 For t a+1 The spatial coordinates of the corresponding target trajectory data.

[0078] For example, as shown in Figure 4, there is a flowchart of another method for determining multiple first target trajectory data, which includes: establishing a historical wake queue; determining the master source; selecting an interpolation interval; and determining the first target trajectory data.

[0079] In some optional implementations, a historical wake queue is established, including: acquiring multiple trajectory data corresponding to each sensor and maintaining the multiple trajectory data corresponding to each sensor in a historical wake queue.

[0080] In some alternative implementations, determining the master source includes comparing the data acquisition rates of each sensor and selecting the sensor with the highest acquisition rate as the master source, i.e., the second sensor.

[0081] In some optional implementations, an interpolation interval is selected; the first target trajectory data is determined. For details, please refer to step S205 of the embodiment shown in Figure 2, which will not be repeated here.

[0082] The method for determining multiple first target trajectory data in this application embodiment obtains different interpolation intervals based on different relationship analysis results. By using interpolation processing to obtain multiple first target trajectory data, it can effectively fill data gaps or correct time differences, and can handle data synchronization problems more precisely, thereby improving the accuracy of data synchronization.

[0083] This embodiment provides a scheduling method for a multi-granularity simulation model, which can be used in computer equipment. Figure 5 is a flowchart of a method for determining the cost factor according to an embodiment of this application. As shown in Figure 5, the process includes the following steps:

[0084] Step S501: Obtain historical trajectory data from multiple sensors and a preset fusion function; the preset fusion function includes a cost factor.

[0085] The expression for the preset fusion function is: y = WX = [w1, w2, ..., w n [x1,x2,…,x] n ] T ;

[0086] Where y is the preset fusion function, W is the cost factor, X is the historical trajectory data, and w i Let x be the cost factor corresponding to the i-th sensor. i This represents the historical trajectory data corresponding to the i-th sensor.

[0087] In some alternative implementations, x i N(μ) follows a normal distribution i ,σ i 2 ). Where μ i The expected value, σ, includes information about the measured parameter and the constant deviation of the sensor. i σ represents the mean square error, indicating the accuracy of the sensor. i The larger the value, the greater the dispersion of the sensor's measurement data for the same parameter, meaning the lower the sensor's accuracy. i The smaller the value, the higher the accuracy of the sensor.

[0088] Step S502: Perform a normal distribution transformation on the preset fusion function based on the historical trajectory data to obtain the normal distribution function.

[0089] The preset fusion function y is transformed into a standard normally distributed random vector Z = A(XU) through the following transformation: x =WU+WA -1 Z;

[0090] Where Z = [z1, z2, ..., z n ], U = [μ1, μ2, ..., μ n ] T .

[0091] Where Z is a vector, A is a diagonal matrix, X is historical trajectory data, U is the mean vector, W is the cost factor, and Z = [z1, z2, ..., zn ] is a component of the standard normally distributed random vector obtained after transformation, σ i For the mean squared error, μ i Let y be the expected value. x The normal distribution function is obtained by performing a normal distribution transformation on the preset fusion function y.

[0092] Step S503: Perform density distribution analysis on the normal distribution function to obtain the density distribution function.

[0093] y x The probability density function is:

[0094] Where, f(y) x ) is the preset fusion function y x The probability density function, where n is the total number of historical trajectory data, w i Let σ be the cost factor corresponding to the i-th sensor. i Let μ be the mean square error corresponding to the i-th sensor. i Let be the expected value corresponding to the i-th sensor.

[0095] Step S504: Determine the first normal distribution relationship corresponding to the density distribution function.

[0096] f(y x It follows a normal distribution.

[0097] in, The first normal distribution relationship is given by w. i Let σ be the cost factor corresponding to the i-th sensor, n be the total number of historical trajectory data collected by the i-th sensor, and σ be the cost factor. i Let be the mean square error corresponding to the i-th sensor.

[0098] Step S505: Introduce a correction function into the normal distribution equation, solve for the correction parameter in the correction function, and obtain the second normal distribution equation.

[0099] The corrected function relation is:

[0100] Where F is the correction function, w i Let σ be the cost factor corresponding to the i-th sensor, n be the total number of historical trajectory data collected by the i-th sensor, and σ be the cost factor. i Let be the mean squared error corresponding to the i-th sensor.

[0101] Known For w i Differential calculation yields when At that time, σy The fusion accuracy is highest when the minimum value is reached.

[0102] The second normal distribution relationship is:

[0103] in, The second normal distribution relationship is given, where n is the total number of historical trajectory data collected by the i-th sensor, and σ i Let be the mean squared error corresponding to the i-th sensor.

[0104] Step S506: Solve for the cost factors based on the first normal distribution formula and the second normal distribution formula to obtain the cost factors of multiple sensors.

[0105] Substituting the first normal distribution equation into the second normal distribution equation yields the cost factor, which is... Substitution Obtain the cost factor.

[0106] The expression for calculating the cost factor is:

[0107] Among them, w i Let σ be the cost factor corresponding to the i-th sensor. i Let be the mean squared error corresponding to the i-th sensor, and n be the total number of historical trajectory data collected by the i-th sensor.

[0108] For example, as shown in Figure 6, there is a flowchart of another method for determining the cost factor, which includes: modeling simulation model data and calculating the cost factor; calculating the cost factor includes transforming the standard normal distribution; solving for the highest fusion accuracy; and calculating the cost factor.

[0109] In some alternative implementations, simulation model data modeling includes: assuming n sensors measure a certain parameter, and the i-th sensor outputs historical trajectory data X. i＝ [x1,x2,…,x n ] T , where i = 1, 2, ..., n. In the actual measurement process, X i N(μ) follows a normal distribution i ,σ i 2 ). Where μ i The expected value, σ, includes information about the measured parameter and the constant deviation of the sensor. i σ represents the mean square error, indicating the accuracy of the sensor. i The larger the value, the greater the dispersion of the sensor's measurement data for the same parameter, meaning the lower the sensor's accuracy. i The smaller the value, the higher the accuracy of the sensor.

[0110] In some optional implementations, calculating the cost factor includes transforming the standard normal distribution; solving for the highest fusion accuracy; and calculating the cost factor. For details, please refer to steps S502 to S506 of the embodiment shown in Figure 5, which will not be repeated here.

[0111] The cost factor determination method provided in this embodiment utilizes a preset fusion function and performs a series of operations such as normal distribution transformation and density distribution analysis to solve for the cost factor, making the determination of the cost factor more scientific and accurate. This application introduces a correction function into the normal distribution formula and solves for the correction parameters, enabling the determined cost factor to better adapt to different application scenarios and data characteristics. This precise cost factor can more reasonably balance the weights of trajectory data collected by different sensors when adjusting trajectory data, reducing the impact of data errors and interference, and improving the overall accuracy of data processing.

[0112] This embodiment also provides a scheduling device for a multi-granularity simulation model, which is used to implement the above embodiments and optional implementations; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0113] This embodiment provides a scheduling device for a multi-granularity simulation model, as shown in Figure 7, including:

[0114] The relationship analysis result determination module 701 is used to analyze the relationship between the current acquisition time of multiple first sensors and the queue time interval corresponding to the data acquisition queue of the second sensor based on multiple trajectory data of the target object collected by multiple sensors, and obtain the relationship analysis result. The first data acquisition rate of multiple first sensors is less than the preset acquisition rate, the second data acquisition rate of the second sensor is greater than or equal to the preset acquisition rate, and the data acquisition queue is the trajectory data queue arranged by the second sensor according to the acquisition time order. The multiple sensors include multiple first sensors and multiple second sensors.

[0115] The trajectory data synchronization processing module 702 is used to synchronize multiple trajectory data according to the relationship analysis results to obtain multiple first target trajectory data.

[0116] The density distribution analysis module 703 is used to perform density distribution analysis on the historical trajectory data of multiple sensors to obtain the cost factor corresponding to each sensor.

[0117] The target trajectory data adjustment module 704 is used to adjust multiple first target trajectory data according to the cost factor corresponding to each sensor to obtain multiple second target trajectory data.

[0118] The synchronous simulation module 705 is used to acquire the timestamps of multiple multi-granularity simulation models. In response to the triggering of the simulation run command, it controls multiple multi-granularity simulation models to perform synchronous simulation based on the timestamps and multiple second target trajectory data.

[0119] In some optional implementations, the relationship analysis result determination module 701 includes:

[0120] The first trajectory data selection unit is used to select multiple first trajectory data collected by the second sensor from multiple trajectory data.

[0121] The data acquisition queue determination unit is used to arrange multiple first trajectory data according to the acquisition time order to obtain the data acquisition queue.

[0122] The queue time interval acquisition unit is used to obtain the queue time interval corresponding to the data acquisition queue.

[0123] The relationship analysis result determination unit is used to obtain the current acquisition time of each first sensor, compare the current acquisition time with the queue time interval, and obtain the relationship analysis result. The relationship analysis result includes the current acquisition time being less than or equal to the first endpoint time of the queue time interval, the current acquisition time being greater than the first endpoint time and less than the second endpoint time, and the current acquisition time being greater than or equal to the second endpoint time of the queue time interval; the first endpoint time is less than the second endpoint time.

[0124] In some alternative implementations, the trajectory data synchronization processing module 702 includes:

[0125] The first trajectory data synchronization processing unit is used to query the data acquisition queue for the third target trajectory data corresponding to the first target time and the fourth target trajectory data corresponding to the second target time, based on the fact that the current acquisition time is greater than the first endpoint time and less than the second endpoint time. The first time interval between the first target time and the second target time is used as the first interpolation interval to perform interpolation processing on the current acquisition time, the third target trajectory data and the fourth target trajectory data to obtain the first target trajectory data corresponding to each sensor.

[0126] The second trajectory data synchronization processing unit is used to determine the second time difference between the first endpoint time and the current acquisition time when the current acquisition time is less than or equal to the first endpoint time of the queue time interval; to obtain the third target time based on the sum of the first endpoint time and the second time difference; to query the fourth target time corresponding to the fifth target trajectory data in the data acquisition queue whose third time difference with the third target time is less than the second preset value; and to use the second time interval between the first endpoint time and the fourth target time as the second interpolation interval, and to interpolate the current acquisition time, the sixth target trajectory data corresponding to the first endpoint time, and the fifth target trajectory data to obtain the first target trajectory data corresponding to each sensor.

[0127] The third trajectory data synchronization processing unit is used to determine the fourth time difference between the second endpoint time and the current acquisition time when the current acquisition time is greater than or equal to the second endpoint time of the queue time interval; based on the difference between the second endpoint time and the fourth time difference, the fifth target time is obtained; in the data acquisition queue, the sixth target time corresponding to the seventh target trajectory data whose fifth time difference with the fifth target time is less than the third preset value is queried; the third time interval between the first endpoint time and the sixth target time is used as the third interpolation interval, and the eighth target trajectory data corresponding to the current acquisition time and the second endpoint time, as well as the seventh target trajectory data, are interpolated to obtain the first target trajectory data corresponding to each sensor.

[0128] In some optional implementations, the density distribution analysis module 703 includes:

[0129] The function acquisition unit is used to acquire historical trajectory data from multiple sensors and a preset fusion function; the preset fusion function includes a cost factor.

[0130] The normal distribution transformation unit is used to perform a normal distribution transformation on a preset fusion function based on historical trajectory data to obtain a normal distribution function.

[0131] The density analysis unit is used to perform density distribution analysis on the normal distribution function to obtain the density distribution function.

[0132] The first normal distribution relationship determination unit is used to determine the first normal distribution relationship corresponding to the density distribution function.

[0133] The correction function solving unit is used to introduce a correction function into the normal distribution relation, solve for the correction parameters in the correction function, and obtain the second normal distribution relation.

[0134] The cost factor determination unit is used to solve the cost factors according to the first normal distribution relationship and the second normal distribution relationship to obtain the cost factors of multiple sensors.

[0135] In some alternative implementations, the target trajectory data adjustment module 704 includes:

[0136] The target trajectory data adjustment unit is used to obtain multiple second target trajectory data based on the product of the cost factor corresponding to each sensor and the first target trajectory data corresponding to each sensor.

[0137] In some alternative implementations, the synchronous simulation module 705 includes:

[0138] The synchronous simulation unit is used to control the operation of multiple computing nodes and multiple simulation nodes in multiple multi-granularity simulation models to perform synchronous simulation based on timestamps and multiple second target trajectory data.

[0139] The optional functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0140] In this embodiment, the scheduling device of the multi-granularity simulation model is presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0141] This application also provides a computer device having a scheduling device with the multi-granularity simulation model shown in FIG7 above.

[0142] Please refer to Figure 8, which is a schematic diagram of the structure of a computer device provided in an optional embodiment of this application. As shown in Figure 8, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be installed on a common motherboard or otherwise as needed. The processor can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 uses one processor 10 as an example.

[0143] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Optionally, processor 10 may also include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GPRS), or any combination thereof.

[0144] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0145] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0146] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0147] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0148] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; optionally, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0149] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0150] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A scheduling method for a multi-granularity simulation model, characterized in that, The method includes: Based on multiple trajectory data of the target object collected by multiple sensors, the relationship between the current acquisition time of multiple first sensors and the queue time interval corresponding to the data acquisition queue of the second sensor is analyzed to obtain the relationship analysis results; the first data acquisition rate of the multiple first sensors is less than the preset acquisition rate, the second data acquisition rate of the second sensors is greater than or equal to the preset acquisition rate, the data acquisition queue is the trajectory data queue arranged by the second sensors according to the acquisition time order, and the multiple sensors include multiple first sensors and second sensors. Based on the relationship analysis results, the multiple trajectory data are synchronized to obtain multiple first target trajectory data; Density distribution analysis is performed on the historical trajectory data of the multiple sensors to obtain the cost factor corresponding to each sensor. The multiple first target trajectory data are adjusted according to the cost factor corresponding to each sensor to obtain multiple second target trajectory data; The timestamps of multiple multi-granularity simulation models are obtained, and in response to the triggering of the simulation run command, the multiple multi-granularity simulation models are controlled to perform synchronous simulation based on the timestamps and the multiple second target trajectory data.

2. The method according to claim 1, characterized in that, The method involves analyzing the relationship between the current acquisition time of multiple first sensors and the queue time interval corresponding to the data acquisition queue of the second sensors based on multiple trajectory data of the target object collected by multiple sensors, and obtaining the relationship analysis results, including: From the plurality of trajectory data, select a plurality of first trajectory data collected by the second sensor; The plurality of first trajectory data are arranged in the order of acquisition time to obtain the data acquisition queue; Obtain the queue time interval corresponding to the data acquisition queue; The current acquisition time of each first sensor is obtained, and the current acquisition time is compared with the queue time interval to obtain the relationship analysis result; wherein, the relationship analysis result includes the current acquisition time being less than or equal to the first endpoint time of the queue time interval, the current acquisition time being greater than the first endpoint time and less than the second endpoint time, and the current acquisition time being greater than or equal to the second endpoint time of the queue time interval; the first endpoint time is less than the second endpoint time.

3. The method according to claim 2, characterized in that, The process of synchronizing the multiple trajectory data based on the relationship analysis results to obtain multiple first target trajectory data includes: When the current acquisition time is greater than the first endpoint time and less than the second endpoint time, in the data acquisition queue, query the third target trajectory data corresponding to the first target time whose first time difference with the current acquisition time is less than a first preset value and the fourth target trajectory data corresponding to the second target time; use the first time interval between the first target time and the second target time as the first interpolation interval, and perform interpolation processing on the current acquisition time, the third target trajectory data and the fourth target trajectory data to obtain the first target trajectory data corresponding to each sensor; When the current acquisition time is less than or equal to the first endpoint time of the queue time interval, a second time difference between the first endpoint time and the current acquisition time is determined; a third target time is obtained based on the sum of the first endpoint time and the second time difference; in the data acquisition queue, a fourth target time is queried corresponding to the fifth target trajectory data whose third time difference with the third target time is less than a second preset value; the second time interval between the first endpoint time and the fourth target time is used as a second interpolation interval, and the current acquisition time, the sixth target trajectory data corresponding to the first endpoint time, and the fifth target trajectory data are interpolated to obtain the first target trajectory data corresponding to each sensor; When the current acquisition time is greater than or equal to the second endpoint time of the queue time interval, a fourth time difference between the second endpoint time and the current acquisition time is determined; based on the difference between the second endpoint time and the fourth time difference, a fifth target time is obtained; in the data acquisition queue, a sixth target time corresponding to the seventh target trajectory data whose fifth time difference with the fifth target time is less than a third preset value is queried; the third time interval between the first endpoint time and the sixth target time is used as the third interpolation interval, and the eighth target trajectory data corresponding to the current acquisition time, the second endpoint time, and the seventh target trajectory data are interpolated to obtain the first target trajectory data corresponding to each sensor.

4. The method according to any one of claims 1 to 3, characterized in that, The density distribution analysis of the historical trajectory data from the multiple sensors to obtain the cost factor for each sensor includes: The historical trajectory data from the multiple sensors and a preset fusion function are acquired; the preset fusion function includes a cost factor. The preset fusion function is transformed into a normal distribution function based on the historical trajectory data to obtain the normal distribution function; Density distribution analysis is performed on the normal distribution function to obtain the density distribution function; Determine the first normal distribution relationship corresponding to the density distribution function; A correction function is introduced into the normal distribution relationship, and the correction parameters in the correction function are solved to obtain the second normal distribution relationship; The cost factors of the plurality of sensors are obtained by solving the first normal distribution formula and the second normal distribution formula.

5. The method according to any one of claims 1 to 3, characterized in that, The step of adjusting the plurality of first target trajectory data according to the cost factor corresponding to each sensor to obtain a plurality of second target trajectory data includes: The plurality of second target trajectory data are obtained by multiplying the cost factor corresponding to each sensor with the first target trajectory data corresponding to each sensor.

6. The method according to any one of claims 1 to 3, characterized in that, The step of controlling the multiple multi-granularity simulation models to perform synchronous simulation based on the timestamp and the multiple second target trajectory data includes: The system controls the operation of multiple computing nodes and multiple simulation nodes in the multiple multi-granularity simulation models based on the timestamp and the multiple second target trajectory data to perform synchronous simulation.

7. A scheduling device for a multi-granularity simulation model, characterized in that, The device includes: The relationship analysis result determination module is used to analyze the relationship between the current acquisition time of multiple first sensors and the queue time interval corresponding to the data acquisition queue of the second sensor based on multiple trajectory data of the target object collected by multiple sensors, and obtain the relationship analysis result. The first data acquisition rate of the multiple first sensors is less than the preset acquisition rate, the second data acquisition rate of the second sensor is greater than or equal to the preset acquisition rate, the data acquisition queue is the trajectory data queue arranged by the second sensor according to the acquisition time order, and the multiple sensors include multiple first sensors and second sensors. The trajectory data synchronization processing module is used to synchronize the multiple trajectory data according to the relationship analysis results to obtain multiple first target trajectory data. The density distribution analysis module is used to perform density distribution analysis on the historical trajectory data of the multiple sensors to obtain the cost factor corresponding to each sensor. The target trajectory data adjustment module is used to adjust the plurality of first target trajectory data according to the cost factor corresponding to each sensor to obtain a plurality of second target trajectory data; The synchronous simulation module is used to acquire the timestamps of multiple multi-granularity simulation models, and in response to the triggering of the simulation run command, control the multiple multi-granularity simulation models to perform synchronous simulation based on the timestamps and the multiple second target trajectory data.

8. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the scheduling method of the multi-granularity simulation model according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the scheduling method of the multi-granularity simulation model according to any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the scheduling method for the multi-granularity simulation model according to any one of claims 1 to 6.

Images