Method and device for determining motion trail of target object, computer equipment and medium

Abstract

The invention relates to a target object motion track determination method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: fitting three-dimensional coordinate data of a target object at a plurality of historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data; under the condition that the coordinate system where the three-dimensional coordinate data is located is a target coordinate system matched with the trajectory prediction platform, determining the three-dimensional coordinate data as target three-dimensional data; based on the fitting model and the target three-dimensional data, predicting the three-dimensional coordinate data of the target object at a plurality of to-be-predicted time points through a trajectory prediction platform to obtain predicted three-dimensional coordinates of the target object at each to-be-predicted time point; and determining a predicted motion track of the target object in a geographic scene based on the geographic scene configured in the track prediction platform and the predicted three-dimensional coordinate of each to-be-predicted time point. By adopting the method, the obtaining efficiency of the predicted motion trail can be improved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and geographic information technology, and in particular to a method, device, computer equipment, storage medium and computer program product for determining a motion trajectory of a target object. Background Art

[0002] With the development of science and technology, more and more computer platforms can be used to realize the motion trajectory demonstration of target objects. At present, the motion trajectory simulation of target objects is mainly based on image recognition and three-dimensional positioning platform to obtain geographical environment information, establish corresponding target objects, generate corresponding geographical information digital models based on captured images and satellite remote sensing systems, and build customized three-dimensional space models and dynamic demonstrations.

[0003] Then, the existing technical solutions involve a large number of developers, and adopt image recognition methods and data from remote sensing satellite geographic information platforms. The logic of information processing is relatively complex, and there are many customized operations, which can easily lead to a decrease in real-time processing performance and is not conducive to real-time restoration of geographic information scenes, thereby reducing the efficiency of demonstrating the motion trajectory of the target object in a specific geographic scene. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining a motion trajectory of a target object, which can improve the efficiency of obtaining a predicted motion trajectory, in order to address the above technical problems.

[0005] In a first aspect, the present application provides a method for determining a motion trajectory of a target object, the method comprising:

[0006] Performing fitting processing on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data;

[0007] In a case where the coordinate system where the three-dimensional coordinate data resides is a target coordinate system matched by the trajectory prediction platform, determining the three-dimensional coordinate data as target three-dimensional data;

[0008] Based on the fitting model and the target three-dimensional data, the three-dimensional coordinate data of the target object at multiple time points to be predicted are predicted by the trajectory prediction platform to obtain the predicted three-dimensional coordinates of the target object at each of the time points to be predicted;

[0009] Based on the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each of the time points to be predicted, the predicted motion trajectory of the target object in the geographical scene is determined.

[0010] In one embodiment, the method further comprises:

[0011] When there is a difference between the coordinate system where the three-dimensional coordinate data resides and the target coordinate system, obtaining a transformation matrix corresponding to the target coordinate system;

[0012] The three-dimensional coordinate data is transformed using the transformation matrix to obtain target three-dimensional data whose coordinate system is the target coordinate system.

[0013] In one embodiment, the fitting process is performed on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data, including:

[0014] Acquire three-dimensional coordinate data of a target object at multiple historical time points, and determine an initial fitting model for fitting the three-dimensional coordinate data;

[0015] Based on the initial fitting model, determining a model loss corresponding to the three-dimensional coordinate data;

[0016] Parameters in the initial fitting model are optimized based on the model loss to obtain a fitting model.

[0017] In one embodiment, determining the predicted motion trajectory of the target object in the geographic scene based on the geographic scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each of the time points to be predicted includes:

[0018] Obtaining a trajectory display request; the trajectory display request carries a scenario requirement for displaying the predicted motion trajectory of the target object;

[0019] Filtering out a geographical scene matching the scene requirement from a plurality of geographical scenes configured in the trajectory prediction platform;

[0020] Based on the geographical scene and the predicted three-dimensional coordinates of the target object at each of the to-be-predicted time points, a predicted motion trajectory of the target object in the geographical scene is determined, and the predicted motion trajectory is displayed.

[0021] In one embodiment, before fitting the three-dimensional coordinate data of the target object at multiple historical time points, the process includes:

[0022] Acquire initial three-dimensional coordinate data of the target object at multiple historical time points;

[0023] Performing missing detection on the initial three-dimensional coordinate data to obtain a detection result;

[0024] Based on the detection result, a plurality of three-dimensional coordinate data satisfying a target condition at a historical time point are screened out from the initial three-dimensional coordinate data.

[0025] In one of the embodiments, the number of the target objects is multiple;

[0026] The method further comprises:

[0027] Determine the aggregation point of each of the target objects in the geographic scene based on the predicted motion trajectory of each of the target objects in the geographic scene;

[0028] The aggregation point is determined as the target point for each target object to handle business.

[0029] In a second aspect, the present application provides a device for determining a motion trajectory of a target object, the device comprising:

[0030] A fitting module, used to perform fitting processing on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data;

[0031] A data determination module, configured to determine the three-dimensional coordinate data as target three-dimensional data when the coordinate system where the three-dimensional coordinate data resides is a target coordinate system matched by a trajectory prediction platform;

[0032] A data prediction module, used to predict the three-dimensional coordinate data of the target object at multiple time points to be predicted through the trajectory prediction platform based on the fitting model and the target three-dimensional data, so as to obtain the predicted three-dimensional coordinates of the target object at each of the time points to be predicted;

[0033] The trajectory determination module is used to determine the predicted motion trajectory of the target object in the geographic scene based on the geographic scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each of the time points to be predicted.

[0034] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0036] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0037] The above-mentioned method, device, computer equipment, storage medium and computer program product for determining the motion trajectory of the target object can obtain a fitting model for predicting the coordinate data of the target object by performing fitting processing based on the three-dimensional coordinate data of the target object at multiple historical time points; by determining the three-dimensional coordinate data as target three-dimensional data when the coordinate system where the three-dimensional coordinate data is located is a target coordinate system that matches the trajectory prediction platform, the target three-dimensional data can be made recognizable by the trajectory prediction platform, thereby improving the accuracy of the predicted three-dimensional coordinates, thereby improving the accuracy of the predicted motion trajectory of the final output; by determining the predicted motion trajectory of the target object in the geographical scene according to the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, the geographical information in the geographical scene can be restored in real time, so that the predicted motion trajectory of the target object in the geographical scene can be quickly obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A diagram of an application environment of a method for determining a motion trajectory of a target object in one embodiment;

[0039] Figure 2 A schematic diagram of a flow chart of a method for determining a motion trajectory of a target object in one embodiment;

[0040] Figure 3 A schematic flow chart of a target point determination step in one embodiment;

[0041] Figure 4 is a structural block diagram of a device for determining a motion trajectory of a target object in one embodiment;

[0042] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] The method for determining the motion trajectory of a target object provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 fits the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data. When the coordinate system where the three-dimensional coordinate data is located is the target coordinate system matched by the trajectory prediction platform, the server 104 directly determines the acquired three-dimensional coordinate data as the target three-dimensional data. Based on the fitting model and the target three-dimensional data, the server 104 predicts the three-dimensional coordinate data of the target object at multiple time points to be predicted through the trajectory prediction platform, thereby obtaining the predicted three-dimensional coordinates of the target object at each time point to be predicted. The server 104 determines the predicted motion trajectory of the target object in the geographic scene according to the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0045] In one embodiment, Figure 2 As shown, a method for determining the motion trajectory of a target object is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0046] Step 202 , performing fitting processing on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data.

[0047] Among them, fitting processing refers to finding a model or formula that can represent the change of three-dimensional coordinate data over time based on the three-dimensional coordinate data of the target object at different historical time points, that is, taking the changing historical time points as independent variables, fitting according to the three-dimensional coordinate data, and analyzing whether the fitted model converges after fitting, and if the fitting model does not converge, continuously optimizing and adjusting the parameters in the model so that the model converges, thereby obtaining the final fitting model. The fitting model can also be understood as a fitting formula. The fitting model can be a model that can be used for coordinate prediction, such as a Kriging model and a differential prediction model.

[0048] Optionally, the server obtains the three-dimensional coordinate data of the target object at multiple historical time points, and then optimizes the parameters in the Kriging model according to the three-dimensional coordinate data of the target object at different historical time points to obtain an optimized Kriging model, that is, taking the changing historical time points as independent variables and the three-dimensional coordinate data as dependent variables, analyzing whether the fitted Kriging model has reached convergence, and if the Kriging model has not converged, continuously optimizing and adjusting the parameters in the Kriging model to make the model converge, thereby obtaining the final Kriging model.

[0049] Step 204 , when the coordinate system where the three-dimensional coordinate data is located is the target coordinate system matched by the trajectory prediction platform, the three-dimensional coordinate data is determined as the target three-dimensional data.

[0050] Among them, the trajectory prediction platform refers to a platform that can predict and display the trajectory of the target object, and when displaying the predicted motion trajectory of the target object, it can also be displayed in combination with a specific scene. For example, the trajectory prediction platform can be a Cesium platform. The Cesium platform is a map engine written in JavaScript and uses WebGL (Web Graphics Library). It uses a cross-platform and cross-browser JavaScript library to display the three-dimensional earth geographical environment, and uses the Web interactive three-dimensional painting standard for hardware-accelerated graphics presentation. The Cesium platform is an open source program licensed under Apache2.0 (open source protocol), supporting multi-mode map displays such as 3D (3-dimensional), 2.5D (2.5-dimensional) and 2D (2-dimensional), and can draw various plane graphics, geometric bodies, import layers, and even light and shadow scenes, 3D models and other data visualization displays.

[0051] The language format of the Cesium platform is CZML (Cesium Language). The CZML format can accurately describe the process of how the definition values ​​of various graphics elements change over time. Even the description values ​​of each internal corner in a complex three-dimensional model can be defined one by one by this format, so as to achieve subtle changes of various graphics elements in the dynamic time series presentation of the three-dimensional model and accurately control variables. The Cesium platform has a set of client APIs (Application Programming Interface). Through CZML, a data-driven approach is adopted, and rich scenes can be built using the general Cesium viewer without writing code.

[0052] The target coordinate system matched by the trajectory prediction platform refers to the coordinate system of the three-dimensional coordinate data that can be recognized by the trajectory prediction platform. For example, the data that the Cesium platform can recognize is the three-dimensional coordinate data based on the world coordinate system, so the world coordinate system is the target coordinate system.

[0053] Optionally, the server detects the coordinate system where the three-dimensional coordinate data is located, and when the coordinate system detection result represents the coordinate system where the three-dimensional coordinate data is located, and it is the same as the target coordinate system matched by the trajectory prediction platform, the three-dimensional coordinate data is directly determined as the target three-dimensional data.

[0054] In a specific application, the server detects the coordinate system where the three-dimensional coordinate data is located, and obtains the coordinate system detection results that all the three-dimensional coordinate data are based on the world coordinate system. If the server obtains the data that the Cesium platform can recognize based on the world coordinate system, it can determine that the coordinate system where the three-dimensional coordinate data is located is the same as the target coordinate system where the data that the Cesium platform can recognize is located, that is, both are world coordinate systems, and the server determines the three-dimensional coordinate data as the target three-dimensional data.

[0055] Step 206 , based on the fitting model and the target three-dimensional data, the three-dimensional coordinate data of the target object at multiple time points to be predicted are predicted through the trajectory prediction platform to obtain the predicted three-dimensional coordinates of the target object at each time point to be predicted.

[0056] The time point to be predicted refers to the time point at which the three-dimensional coordinate data of the target object needs to be predicted. For example, there is the three-dimensional coordinate data of the target object for each day in July, and the three-dimensional coordinate data of the target object for each day in August is unknown and needs to be predicted. It is necessary to use the three-dimensional coordinate data of July to predict the coordinate data of August. Then each day in July is a historical time point, and each day in August is a time point to be detected.

[0057] Optionally, the server inputs the fitting model and target three-dimensional data into the trajectory prediction platform through an interface for the trajectory prediction platform to interact with the outside world, and then predicts the three-dimensional coordinate data of the target object at multiple time points to be predicted based on the fitting model and the target three-dimensional data through the trajectory prediction platform, thereby obtaining the predicted three-dimensional coordinates of the target object at each time point to be predicted.

[0058] Step 208 , based on the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, determine the predicted motion trajectory of the target object in the geographical scene.

[0059] Among them, multiple geographical scenes are configured in the trajectory prediction platform, and the geographical scene used to display the predicted motion trajectory is determined according to the trajectory display request. If the trajectory prediction platform is pre-configured with a geographical scene that matches the scene requirements carried in the trajectory display request, then this geographical scene is directly used to display the predicted motion trajectory; if the trajectory prediction platform is not pre-configured, then it is necessary to first determine the geographical information of the geographical scene indicated by the scene requirements, and then build the corresponding geographical scene inside the trajectory prediction platform according to the geographical information, or after the trajectory prediction platform has built the geographical scene, then input the built geographical scene into the trajectory prediction platform, so that the geographical scene that matches the scene requirements carried in the trajectory display request can be obtained in the trajectory prediction platform.

[0060] Optionally, the server obtains a geographical scene that matches the scene requirement carried in the trajectory display request from multiple geographical scenes in the trajectory prediction platform, and then obtains the predicted motion trajectory of the target object in the geographical scene based on the matched geographical scene and the predicted coordinate data of each predicted time point, and displays it on the trajectory prediction platform.

[0061] In the above-mentioned method for determining the motion trajectory of the target object, by performing fitting processing based on the three-dimensional coordinate data of the target object at multiple historical time points, a fitting model for predicting the coordinate data of the target object can be obtained; by determining the three-dimensional coordinate data as target three-dimensional data when the coordinate system where the three-dimensional coordinate data is located is a target coordinate system that matches the trajectory prediction platform, the target three-dimensional data can be made recognizable by the trajectory prediction platform, thereby improving the accuracy of the predicted three-dimensional coordinates, thereby improving the accuracy of the predicted motion trajectory of the final output; by determining the predicted motion trajectory of the target object in the geographical scene according to the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, the geographical information in the geographical scene can be restored in real time, so that the predicted motion trajectory of the target object in the geographical scene can be quickly obtained.

[0062] In one embodiment, the method for determining the motion trajectory of the target object further includes:

[0063] When the coordinate system where the three-dimensional coordinate data resides is different from the target coordinate system, a transformation matrix corresponding to the target coordinate system is obtained.

[0064] The three-dimensional coordinate data is transformed using a transformation matrix to obtain target three-dimensional data whose coordinate system is the target coordinate system.

[0065] The difference means that the coordinate system where the three-dimensional coordinate data is located is not the same as the target coordinate system matched by the trajectory prediction platform. For example, the three-dimensional coordinate data is based on the Cartesian coordinate system, while the data that the trajectory prediction platform can recognize is based on the world coordinate system. In this case, the coordinate system where the three-dimensional coordinate data is located is different from the target coordinate system matched by the trajectory prediction platform.

[0066] The transformation matrix is ​​obtained through the rotation matrix and rotation vector, mainly using the rotation of the Euler angle, first rotating about the z-axis, then rotating about the y-axis, and then rotating about the x-axis to obtain the rotation angles respectively, and then using the angle vector to obtain the corresponding transformation matrix.

[0067] The transformation process is to apply the transformation matrix to each three-dimensional coordinate data, for example, multiply the transformation matrix and the three-dimensional coordinate data to obtain the target three-dimensional data.

[0068] Optionally, when the server detects that the coordinate system of the three-dimensional coordinate data of the target object at a historical time point is different from the target coordinate system, it uses Euler angle rotation to first rotate about the z-axis, then about the y-axis, and then about the x-axis to obtain the rotation angles respectively, and then uses the angular vector to obtain the transformation matrix corresponding to the target coordinate system, and then applies the transformation matrix to each three-dimensional coordinate data, transforms the three-dimensional coordinate data, and thus obtains the target three-dimensional data whose coordinate system is the target coordinate system.

[0069] In this embodiment, the target three-dimensional data whose coordinate system differs from the target coordinate system is transformed by using a transformation matrix, so that the transformed target three-dimensional data can be quickly recognized by the trajectory prediction platform, thereby improving the accuracy and efficiency of the predicted three-dimensional coordinates output by the trajectory prediction platform, thereby improving the accuracy and efficiency of the predicted motion trajectory finally output.

[0070] In one embodiment, fitting processing is performed on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data, including:

[0071] The three-dimensional coordinate data of the target object at multiple historical time points are obtained, and an initial fitting model for fitting the three-dimensional coordinate data is determined.

[0072] Based on the initial fitting model, the model loss corresponding to the three-dimensional coordinate data is determined.

[0073] The parameters in the initial fitting model are optimized based on the model loss to obtain the fitting model.

[0074] The initial fitting model refers to a model that has not been optimized, and the initial fitting model refers to a prediction model used for trajectory prediction, such as a Kriging model or a differential prediction model.

[0075] Model loss refers to the difference between the predicted value and the true value. For example, the predicted coordinates at each historical time point are calculated based on the initial fitting model, and then the difference between the predicted coordinates and the three-dimensional coordinate data is calculated based on the loss function to obtain the model loss corresponding to the three-dimensional coordinate data. Model loss can be obtained using loss functions such as mean square error loss function, mean absolute error loss function, and quantile loss function.

[0076] Optionally, the server first collects the three-dimensional coordinate data of the target object at multiple historical time points, and selects an initial fitting model for fitting the three-dimensional coordinate data from multiple models. The server inputs the three-dimensional coordinate data and the corresponding historical time points into the initial fitting model, and uses a loss function to calculate the loss corresponding to the model three-dimensional coordinate data according to the prediction results of the initial fitting model for the three-dimensional coordinate data. The server optimizes the parameters in the initial fitting model according to the model loss until the initial fitting model converges, and then outputs the final fitting model.

[0077] In this embodiment, by using the initial fitting model, the model loss corresponding to the three-dimensional coordinate data of the target object at multiple historical time points is determined, and the parameters in the initial fitting model are optimized according to the model loss, so that the initial fitting model can converge, so that the fitting model finally output can be the optimal model, so that when the coordinate prediction is performed based on the fitting model, the accuracy of the predicted three-dimensional coordinates can be improved.

[0078] In one embodiment, based on the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, determining the predicted motion trajectory of the target object in the geographical scene includes:

[0079] Get a trajectory display request. The trajectory display request carries the scenario requirement of displaying the predicted motion trajectory of the target object.

[0080] From the multiple geographic scenarios configured in the trajectory prediction platform, select the geographic scenarios that match the scenario requirements.

[0081] Based on the predicted three-dimensional coordinates of the geographic scene and the target object at each predicted time point, the predicted motion trajectory of the target object in the geographic scene is determined and displayed.

[0082] The trajectory display request refers to a request to display the predicted motion trajectory of the target object on the trajectory prediction platform. The trajectory display request also carries the scene requirements for displaying the predicted motion trajectory of the target object. For example, if the scene requirements specify that the predicted motion trajectory of the target object is to be displayed in geographic scene A, then the predicted motion trajectory that is finally displayed is the predicted motion trajectory in geographic scene A.

[0083] The geographical scenes in the trajectory prediction platform can be pre-configured or configured in real time. For example, when the geographical scenes currently configured in the trajectory prediction platform do not meet the scene requirements, the geographical scenes that match the scene requirements can be built outside the trajectory prediction platform, and then the built geographical scenes can be input into the trajectory prediction platform, so that the geographical scenes that match the scene requirements can be screened out from the multiple geographical scenes configured in the trajectory prediction platform. For another example, if there are geographical scenes that match the scene requirements in the trajectory prediction platform, only the geographical scenes that match the scene requirements need to be screened out.

[0084] The display of the predicted motion trajectory can be displayed on the trajectory prediction platform. When the predicted motion trajectory of the target object in the geographic scene is determined, the predicted motion trajectory of the target object can be displayed on the trajectory prediction platform.

[0085] Optionally, the server obtains a trajectory display request, and extracts the scene requirement for displaying the predicted motion trajectory of the target object carried in the trajectory display requirement to obtain the scene requirement. The server screens multiple geographic scenes configured in the trajectory prediction platform according to the scene requirement to obtain a geographic scene that matches the scene requirement. The server combines the geographic scene and the predicted three-dimensional coordinates of the target object at each time point to be predicted, obtains the predicted motion trajectory of the target object in the geographic scene through the trajectory prediction platform, and displays it on the trajectory prediction platform.

[0086] In this embodiment, by screening out geographic scenes matching the scene requirements from the geographic scenes configured in the trajectory prediction platform according to the scene requirements carried by the trajectory display requirements, and then based on the predicted three-dimensional coordinates of each time point to be predicted and the geographic scene, the predicted three-dimensional coordinates are combined with the geographic information in the geographic scene in real time, so that the predicted motion trajectory of the target object in the geographic scene can be quickly obtained.

[0087] In one embodiment, before fitting the three-dimensional coordinate data of the target object at multiple historical time points, the process includes:

[0088] Obtain the initial three-dimensional coordinate data of the target object at multiple historical time points.

[0089] Perform missing detection on the initial three-dimensional coordinate data to obtain the detection result.

[0090] Based on the detection results, multiple three-dimensional coordinate data that meet the target conditions at the historical time point are screened out from the initial three-dimensional coordinate data.

[0091] The initial three-dimensional coordinate data refers to coordinate data that has not been screened, and the three-dimensional coordinate data refers to coordinate data that has been screened. Missing detection refers to detection based on the continuity between historical time points of each initial three-dimensional coordinate data.

[0092] The target condition refers to the condition that the continuity between the historical time points where the initial three-dimensional coordinate data is located must meet. For example, if we want to predict the movement trajectory of the target object based on the 20 coordinate data of the target object within a month, we obtain the initial three-dimensional coordinate data of the target object in July and August and find that the data in July only has 10 days of initial three-dimensional coordinate data, one data per day, while the data in August has 20 days of initial three-dimensional coordinate data, one data per day. This means that the data in August is more complete than the data in July, and the continuity of historical time points is also better. Therefore, when the final fitting process is performed, the initial three-dimensional data in August will be determined as the three-dimensional coordinate data and fitted.

[0093] Optionally, the server acquires the initial three-dimensional coordinate data of the target object at multiple historical time points, and then performs missing detection on the acquired initial three-dimensional coordinate data, thereby obtaining a detection result that characterizes the continuity between the historical time points where each initial three-dimensional coordinate data is located. Based on the continuity characterized by the detection result, the server selects multiple three-dimensional coordinate data whose continuity between the historical time points meets the target condition from the initial three-dimensional coordinate data.

[0094] In this embodiment, by performing missing detection on the acquired initial three-dimensional coordinate data, and based on the detection results, filtering out the three-dimensional coordinate data at the historical time point that meets the target conditions from the initial three-dimensional coordinate data, the three-dimensional coordinate data finally obtained can be made reliable, thereby improving the reliability of the fitting model obtained based on the three-dimensional coordinate data.

[0095] In one embodiment, Figure 3 As shown, there are multiple target objects. The method for determining the motion trajectory of the target object also includes:

[0096] Step 302: Determine the aggregation point of each target object in the geographic scene based on the predicted motion trajectory of each target object in the geographic scene.

[0097] The aggregation point can be understood as the point where the predicted motion trajectories of multiple target objects overlap, that is, the location with a large flow of people. For example, in the next month, based on the predicted motion trajectories of multiple target objects, it can be known that position A belongs to the location covered by the predicted motion trajectories of most or all target objects, then position A can be used as the aggregation point.

[0098] Optionally, the server determines a position that can be covered by the predicted motion trajectories of most or all target objects based on the predicted motion trajectories of each target object in the geographic scene, and then uses the position as an aggregation point of each target object in the geographic scene.

[0099] Step 304, determining the aggregation point as the target point for each target object to handle business.

[0100] Among them, the business is provided by business processing personnel such as marketing personnel. The target point refers to the location where the business processing personnel carry out business activities. By using the aggregation point as the target point, the business processing personnel can make the business carried out at the target point known or understood by more target objects, thereby expanding the influence of the activity and improving the conversion rate of the activity.

[0101] In this embodiment, by determining the aggregation point based on the predicted movement trajectory of each target object and using the aggregation point as the target point, the business conducted at the target point can be known or understood by more target objects, thereby expanding the influence of the activity and improving the conversion rate of the activity.

[0102] The present application also provides an application scenario, which applies the above-mentioned method for determining the motion trajectory of a target object. Specifically, the application of the method for determining the motion trajectory of a target object in the application scenario is as follows:

[0103] The server acquires the initial three-dimensional coordinate data of the target object at multiple historical time points, and then performs missing detection on the acquired initial three-dimensional coordinate data, thereby obtaining a detection result representing the continuity between the historical time points where each initial three-dimensional coordinate data is located. Based on the continuity represented by the detection result, the server selects multiple three-dimensional coordinate data whose continuity between the historical time points meets the target condition from the initial three-dimensional coordinate data.

[0104] The server selects an initial fitting model for fitting the three-dimensional coordinate data from multiple models. The server inputs the three-dimensional coordinate data and the corresponding historical time points into the initial fitting model, and uses the loss function to calculate the loss corresponding to the model three-dimensional coordinate data according to the prediction results of the initial fitting model for the three-dimensional coordinate data. The server optimizes the parameters in the initial fitting model according to the model loss until the initial fitting model converges, and then outputs the final fitting model.

[0105] When the server detects that the coordinate system of the three-dimensional coordinate data of the target object at a historical time point is different from the target coordinate system, it uses Euler angle rotation to first rotate about the z-axis, then about the y-axis, and then about the x-axis to obtain the rotation angles respectively, and then uses the angular vector to obtain the transformation matrix corresponding to the target coordinate system, and then applies the transformation matrix to each three-dimensional coordinate data, transforms the three-dimensional coordinate data, and thus obtains the target three-dimensional data whose coordinate system is the target coordinate system.

[0106] The server inputs the fitting model and target three-dimensional data into the trajectory prediction platform through the interface for data interaction between the trajectory prediction platform and the outside world. Then, the trajectory prediction platform predicts the three-dimensional coordinate data of the target object at multiple time points to be predicted based on the fitting model and the target three-dimensional data, thereby obtaining the predicted three-dimensional coordinates of the target object at each time point to be predicted.

[0107] The server obtains the trajectory display request and extracts the scene requirements for displaying the predicted motion trajectory of the target object carried in the trajectory display requirement to obtain the scene requirements. According to the scene requirements, the server screens multiple geographic scenes configured in the trajectory prediction platform to obtain a geographic scene that matches the scene requirements. The server combines the geographic scene and the predicted three-dimensional coordinates of the target object at each time point to be predicted, obtains the predicted motion trajectory of the target object in the geographic scene through the trajectory prediction platform, and displays it on the trajectory prediction platform.

[0108] The server determines the location that can be covered by the predicted movement trajectory of most or all target objects based on the predicted movement trajectory of each target object in the geographic scene, and then determines the location as the aggregation point of each target object in the geographic scene. The server uses the aggregation point as the target point for business processing personnel to carry out business activities.

[0109] In the above embodiment, by performing fitting processing based on the three-dimensional coordinate data of the target object at multiple historical time points, a fitting model for predicting the coordinate data of the target object can be obtained; by determining the three-dimensional coordinate data as target three-dimensional data when the coordinate system where the three-dimensional coordinate data is located is a target coordinate system that matches the trajectory prediction platform, the target three-dimensional data can be made recognizable by the trajectory prediction platform, thereby improving the accuracy of the predicted three-dimensional coordinates, thereby improving the accuracy of the predicted motion trajectory of the final output; by determining the predicted motion trajectory of the target object in the geographic scene according to the geographic scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, the geographic information in the geographic scene can be restored in real time, so that the predicted motion trajectory of the target object in the geographic scene can be quickly obtained.

[0110] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0111] Based on the same inventive concept, the embodiment of the present application also provides a target object motion trajectory determination device for implementing the target object motion trajectory determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the target object motion trajectory determination device provided below can refer to the limitations of the target object motion trajectory determination method above, and will not be repeated here.

[0112] In one embodiment, Figure 4 As shown, a device for determining a motion trajectory of a target object is provided, comprising:

[0113] The fitting module 402 is used to perform fitting processing on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data.

[0114] The data determination module 404 is used to determine the three-dimensional coordinate data as target three-dimensional data when the coordinate system where the three-dimensional coordinate data is located is the target coordinate system matched by the trajectory prediction platform.

[0115] The data prediction module 406 is used to predict the three-dimensional coordinate data of the target object at multiple time points to be predicted through the trajectory prediction platform based on the fitting model and the target three-dimensional data, and obtain the predicted three-dimensional coordinates of the target object at each time point to be predicted.

[0116] The trajectory determination module 408 is used to determine the predicted motion trajectory of the target object in the geographic scene based on the geographic scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted.

[0117] In the above embodiment, by performing fitting processing based on the three-dimensional coordinate data of the target object at multiple historical time points, a fitting model for predicting the coordinate data of the target object can be obtained; by determining the three-dimensional coordinate data as target three-dimensional data when the coordinate system where the three-dimensional coordinate data is located is the target coordinate system that matches the trajectory prediction platform, the target three-dimensional data can be made recognizable by the trajectory prediction platform, thereby improving the accuracy of the predicted three-dimensional coordinates, thereby improving the accuracy of the predicted motion trajectory of the final output; by determining the predicted motion trajectory of the target object in the geographical scene according to the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, the geographical information in the geographical scene can be restored in real time, so that the predicted motion trajectory of the target object in the geographical scene can be quickly obtained.

[0118] In one embodiment, the target object's motion trajectory determination device further includes:

[0119] The matrix determination unit is used to obtain a transformation matrix corresponding to the target coordinate system when there is a difference between the coordinate system where the three-dimensional coordinate data is located and the target coordinate system.

[0120] The data transformation unit is used to transform the three-dimensional coordinate data using a transformation matrix to obtain target three-dimensional data whose coordinate system is the target coordinate system.

[0121] In one embodiment, the fitting module includes:

[0122] The model determination unit is used to obtain the three-dimensional coordinate data of the target object at multiple historical time points and determine an initial fitting model for fitting the three-dimensional coordinate data.

[0123] The loss determination unit is used to determine the model loss corresponding to the three-dimensional coordinate data based on the initial fitting model.

[0124] The model optimization unit is used to optimize the parameters in the initial fitting model based on the model loss to obtain the fitting model.

[0125] In one embodiment, the trajectory determination module includes:

[0126] The request acquisition unit is used to acquire a trajectory display request. The trajectory display request carries a scenario requirement for displaying a predicted motion trajectory of a target object.

[0127] The scene determination unit is used to filter out a geographical scene that matches the scene requirements from multiple geographical scenes configured in the trajectory prediction platform.

[0128] The trajectory determination unit is used to determine the predicted motion trajectory of the target object in the geographical scene based on the predicted three-dimensional coordinates of the geographical scene and the target object at each predicted time point, and display the predicted motion trajectory.

[0129] In one embodiment, the fitting module includes:

[0130] The data acquisition unit is used to acquire the initial three-dimensional coordinate data of the target object at multiple historical time points.

[0131] The missing detection unit is used to perform missing detection on the initial three-dimensional coordinate data to obtain a detection result.

[0132] The data screening unit is used to screen out a plurality of three-dimensional coordinate data that meet the target conditions at the historical time point from the initial three-dimensional coordinate data based on the detection result.

[0133] In one embodiment, there are multiple target objects. The target object motion trajectory determination device further includes:

[0134] The aggregation point determination unit is used to determine the aggregation point of each target object in the geographical scene based on the predicted motion trajectory of each target object in the geographical scene.

[0135] The target point unit is used to determine the aggregation point as the target point for each target object to handle business.

[0136] Each module in the above-mentioned target object motion trajectory determination device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0137] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store three-dimensional coordinate data of historical time points, fitting models, target three-dimensional data, predicted three-dimensional coordinates, geographic scenes, and predicted motion trajectories. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining the motion trajectory of a target object is implemented.

[0138] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0139] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0140] The three-dimensional coordinate data of the target object at multiple historical time points are fitted to obtain a fitting model corresponding to the three-dimensional coordinate data. When the coordinate system where the three-dimensional coordinate data is located is the target coordinate system matched by the trajectory prediction platform, the three-dimensional coordinate data is determined as the target three-dimensional data. Based on the fitting model and the target three-dimensional data, the three-dimensional coordinate data of the target object at multiple time points to be predicted are predicted through the trajectory prediction platform to obtain the predicted three-dimensional coordinates of the target object at each time point to be predicted. Based on the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, the predicted motion trajectory of the target object in the geographical scene is determined.

[0141] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0142] When the coordinate system where the three-dimensional coordinate data is located is different from the target coordinate system, a transformation matrix corresponding to the target coordinate system is obtained. The three-dimensional coordinate data is transformed using the transformation matrix to obtain target three-dimensional data whose coordinate system is the target coordinate system.

[0143] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0144] The three-dimensional coordinate data of the target object at multiple historical time points are obtained, and an initial fitting model for fitting the three-dimensional coordinate data is determined. Based on the initial fitting model, the model loss corresponding to the three-dimensional coordinate data is determined. Based on the model loss, the parameters in the initial fitting model are optimized to obtain a fitting model.

[0145] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0146] Get a trajectory display request. The trajectory display request carries the scenario requirement for displaying the predicted motion trajectory of the target object. From the multiple geographic scenarios configured in the trajectory prediction platform, select the geographic scenario that matches the scenario requirement. Based on the geographic scenario and the predicted three-dimensional coordinates of the target object at each predicted time point, determine the predicted motion trajectory of the target object in the geographic scenario, and display the predicted motion trajectory.

[0147] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0148] Obtain the initial three-dimensional coordinate data of the target object at multiple historical time points. Perform missing detection on the initial three-dimensional coordinate data to obtain detection results. Based on the detection results, select multiple three-dimensional coordinate data that meet the target conditions at the historical time points from the initial three-dimensional coordinate data.

[0149] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0150] Based on the predicted movement trajectory of each target object in the geographical scene, the aggregation point of each target object in the geographical scene is determined, and the aggregation point is determined as the target point for each target object to handle business.

[0151] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0152] The three-dimensional coordinate data of the target object at multiple historical time points are fitted to obtain a fitting model corresponding to the three-dimensional coordinate data. When the coordinate system where the three-dimensional coordinate data is located is the target coordinate system matched by the trajectory prediction platform, the three-dimensional coordinate data is determined as the target three-dimensional data. Based on the fitting model and the target three-dimensional data, the three-dimensional coordinate data of the target object at multiple time points to be predicted are predicted through the trajectory prediction platform to obtain the predicted three-dimensional coordinates of the target object at each time point to be predicted. Based on the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, the predicted motion trajectory of the target object in the geographical scene is determined.

[0153] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0154] When the coordinate system where the three-dimensional coordinate data is located is different from the target coordinate system, a transformation matrix corresponding to the target coordinate system is obtained. The three-dimensional coordinate data is transformed using the transformation matrix to obtain target three-dimensional data whose coordinate system is the target coordinate system.

[0155] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0156] The three-dimensional coordinate data of the target object at multiple historical time points are obtained, and an initial fitting model for fitting the three-dimensional coordinate data is determined. Based on the initial fitting model, the model loss corresponding to the three-dimensional coordinate data is determined. Based on the model loss, the parameters in the initial fitting model are optimized to obtain a fitting model.

[0157] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0158] Get a trajectory display request. The trajectory display request carries the scenario requirement for displaying the predicted motion trajectory of the target object. From the multiple geographic scenarios configured in the trajectory prediction platform, select the geographic scenario that matches the scenario requirement. Based on the geographic scenario and the predicted three-dimensional coordinates of the target object at each predicted time point, determine the predicted motion trajectory of the target object in the geographic scenario, and display the predicted motion trajectory.

[0159] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0160] Obtain the initial three-dimensional coordinate data of the target object at multiple historical time points. Perform missing detection on the initial three-dimensional coordinate data to obtain detection results. Based on the detection results, select multiple three-dimensional coordinate data that meet the target conditions at the historical time points from the initial three-dimensional coordinate data.

[0161] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0162] Based on the predicted movement trajectory of each target object in the geographical scene, the aggregation point of each target object in the geographical scene is determined, and the aggregation point is determined as the target point for each target object to handle business.

[0163] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0164] The three-dimensional coordinate data of the target object at multiple historical time points are fitted to obtain a fitting model corresponding to the three-dimensional coordinate data. When the coordinate system where the three-dimensional coordinate data is located is the target coordinate system matched by the trajectory prediction platform, the three-dimensional coordinate data is determined as the target three-dimensional data. Based on the fitting model and the target three-dimensional data, the three-dimensional coordinate data of the target object at multiple time points to be predicted are predicted through the trajectory prediction platform to obtain the predicted three-dimensional coordinates of the target object at each time point to be predicted. Based on the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each time point to be predicted, the predicted motion trajectory of the target object in the geographical scene is determined.

[0165] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0166] When the coordinate system where the three-dimensional coordinate data is located is different from the target coordinate system, a transformation matrix corresponding to the target coordinate system is obtained. The three-dimensional coordinate data is transformed using the transformation matrix to obtain target three-dimensional data whose coordinate system is the target coordinate system.

[0167] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0168] The three-dimensional coordinate data of the target object at multiple historical time points are obtained, and an initial fitting model for fitting the three-dimensional coordinate data is determined. Based on the initial fitting model, the model loss corresponding to the three-dimensional coordinate data is determined. Based on the model loss, the parameters in the initial fitting model are optimized to obtain a fitting model.

[0169] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0170] Get a trajectory display request. The trajectory display request carries the scenario requirement for displaying the predicted motion trajectory of the target object. From the multiple geographic scenarios configured in the trajectory prediction platform, select the geographic scenario that matches the scenario requirement. Based on the geographic scenario and the predicted three-dimensional coordinates of the target object at each predicted time point, determine the predicted motion trajectory of the target object in the geographic scenario, and display the predicted motion trajectory.

[0171] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0172] Obtain the initial three-dimensional coordinate data of the target object at multiple historical time points. Perform missing detection on the initial three-dimensional coordinate data to obtain detection results. Based on the detection results, select multiple three-dimensional coordinate data that meet the target conditions at the historical time points from the initial three-dimensional coordinate data.

[0173] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0174] Based on the predicted movement trajectory of each target object in the geographical scene, the aggregation point of each target object in the geographical scene is determined, and the aggregation point is determined as the target point for each target object to handle business.

[0175] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0176] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0177] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0178] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a motion trajectory of a target object, characterized in that: The method comprises: Performing fitting processing on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data; In a case where the coordinate system where the three-dimensional coordinate data resides is a target coordinate system matched by the trajectory prediction platform, determining the three-dimensional coordinate data as target three-dimensional data; Based on the fitting model and the target three-dimensional data, the three-dimensional coordinate data of the target object at multiple time points to be predicted are predicted by the trajectory prediction platform to obtain the predicted three-dimensional coordinates of the target object at each of the time points to be predicted; Based on the geographical scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each of the time points to be predicted, the predicted motion trajectory of the target object in the geographical scene is determined.

2. The method according to claim 1, characterized in that The method further comprises: When there is a difference between the coordinate system where the three-dimensional coordinate data resides and the target coordinate system, obtaining a transformation matrix corresponding to the target coordinate system; The three-dimensional coordinate data is transformed using the transformation matrix to obtain target three-dimensional data whose coordinate system is the target coordinate system.

3. The method according to claim 1, characterized in that The fitting process is performed on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data, including: Acquire three-dimensional coordinate data of a target object at multiple historical time points, and determine an initial fitting model for fitting the three-dimensional coordinate data; Based on the initial fitting model, determining a model loss corresponding to the three-dimensional coordinate data; Parameters in the initial fitting model are optimized based on the model loss to obtain a fitting model.

4. The method according to claim 1, characterized in that: The step of determining the predicted motion trajectory of the target object in the geographic scene based on the geographic scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each of the to-be-predicted time points includes: Obtaining a trajectory display request; the trajectory display request carries a scenario requirement for displaying the predicted motion trajectory of the target object; Filtering out a geographical scene matching the scene requirement from a plurality of geographical scenes configured in the trajectory prediction platform; Based on the geographical scene and the predicted three-dimensional coordinates of the target object at each of the to-be-predicted time points, a predicted motion trajectory of the target object in the geographical scene is determined, and the predicted motion trajectory is displayed.

5. The method according to claim 1, characterized in that Before the fitting process is performed on the three-dimensional coordinate data of the target object at multiple historical time points, the process includes: Acquire initial three-dimensional coordinate data of the target object at multiple historical time points; Performing missing detection on the initial three-dimensional coordinate data to obtain a detection result; Based on the detection result, a plurality of three-dimensional coordinate data satisfying a target condition at a historical time point are screened out from the initial three-dimensional coordinate data.

6. The method according to claim 1, characterized in that The number of the target objects is multiple; The method further comprises: Determine the aggregation point of each of the target objects in the geographic scene based on the predicted motion trajectory of each of the target objects in the geographic scene; The aggregation point is determined as the target point for each target object to handle business.

7. A device for determining a motion trajectory of a target object, characterized in that: The device comprises: A fitting module, used to perform fitting processing on the three-dimensional coordinate data of the target object at multiple historical time points to obtain a fitting model corresponding to the three-dimensional coordinate data; A data determination module, configured to determine the three-dimensional coordinate data as target three-dimensional data when the coordinate system where the three-dimensional coordinate data resides is a target coordinate system matched by a trajectory prediction platform; A data prediction module, used to predict the three-dimensional coordinate data of the target object at multiple time points to be predicted through the trajectory prediction platform based on the fitting model and the target three-dimensional data, so as to obtain the predicted three-dimensional coordinates of the target object at each of the time points to be predicted; The trajectory determination module is used to determine the predicted motion trajectory of the target object in the geographic scene based on the geographic scene configured in the trajectory prediction platform and the predicted three-dimensional coordinates of each of the time points to be predicted.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images