Tracking Result Prediction Method, Device, Electronic Device, Storage Medium and Program

Abstract

An embodiment of the present invention discloses a tracking result prediction method, device, electronic device, storage medium, and program. The method includes: determining the target actual state data of a target missile at a target moment and an actual motion data set of a target tracking object; determining future predicted state data of the target missile at a future moment based on the target actual state data, the actual motion data set, and a pre-trained state determination model, where the state determination model is a pre-trained neural network model; and determining a predicted tracking result of the target missile for the target tracking object based on the future predicted state data and the actual motion data set. In the technical solution of the embodiment of the present invention, since the neural network model does not need to perform numerical integration calculation and differential calculation, cumulative error is avoided, the calculation amount is reduced, and it is beneficial to improve the efficiency and accuracy of determining the predicted state data.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of aircraft control, and in particular, to a method, device, electronic device, storage medium, and program for predicting tracking results. Background Art

[0002] The analysis of fluid dynamics during missile launch is an important part of missile launch device design. In the prior art, the motion equation is solved by a numerical integration method or a numerical differentiation method, and a simulation framework is built based on the solution result to obtain a missile dynamics model. The tracking result of the missile on the target tracking object during the motion process is predicted through the missile dynamics model.

[0003] However, in the process of implementing the present invention, it is found that the prior art has at least the following technical problems: Solving the motion equation by a numerical integration method leads to the introduction of cumulative errors, resulting in poor accuracy of the predicted tracking result; By the numerical differentiation method, the amount of calculation is large and the efficiency of determining the tracking result is low. Summary of the Invention

[0004] The embodiments of the present invention provide a method, device, electronic device, storage medium, and program for predicting tracking results, so as to achieve the purpose of improving the accuracy of predicting tracking results.

[0005] According to one aspect of the present invention, a method for predicting tracking results is provided, including:

[0006] Determine the target actual state data of the target missile at the target moment and the actual motion data set of the target tracking object;

[0007] Based on the target actual state data, the actual motion data set, and a pre-trained state determination model, determine the future predicted state data of the target missile at a future moment; wherein, the state determination model is a pre-trained neural network model;

[0008] Based on the future predicted state data and the actual motion data set, determine the predicted tracking result of the target missile on the target tracking object.

[0009] According to another aspect of the present invention, a device for predicting tracking results is provided, and the device includes:

[0010] A first data determination module, configured to determine the target actual state data of the target missile at the target moment and the actual motion data set of the target tracking object;

[0011] A second data determination module, configured to determine future predicted state data of the target missile at a future moment based on the target actual state data, the actual motion data set, and a pre-trained state determination model; wherein, the state determination model is a pre-trained neural network model;

[0012] A prediction tracking result determination module, configured to determine a predicted tracking result of the target missile for the target tracking object based on the future predicted state data and the actual motion data set.

[0013] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the tracking result prediction method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the tracking result prediction method according to any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, there is provided a computer program product including a computer program, which implements the tracking result prediction method according to any embodiment of the present invention when executed by a processor.

[0019] The technical solution of the embodiment of the present invention determines the target actual state data of the target missile at the target moment and the actual motion data set of the target tracking object; based on the target actual state data, the actual motion data set, and a pre-trained state determination model, determines the future predicted state data of the target missile at a future moment; wherein, the state determination model is a pre-trained neural network model; since the neural network model does not need to perform numerical integration calculation or numerical differential calculation, cumulative error is avoided, the calculation amount is reduced, which is beneficial to improving the efficiency and accuracy of determining the predicted state data; and, based on the future predicted state data and the actual motion data set, determines the predicted tracking result of the target missile for the target tracking object, thereby achieving the effect of improving the accuracy of the predicted tracking result.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0022] Figure 1 is a flowchart of a method for predicting tracking results provided according to an embodiment of the present invention;

[0023] Figure 2 is a flowchart of another method for predicting tracking results provided according to an embodiment of the present invention;

[0024] Figure 3 is a schematic structural diagram of a device for predicting tracking results provided according to an embodiment of the present invention;

[0025] Figure 4 is a schematic structural diagram of an electronic device for implementing the method for predicting tracking results of the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "including", "etc." and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0028] It should be noted that in the technical solution of the present disclosure, in terms of the collection, gathering, updating, analysis, processing, use, transmission, storage, etc. of the user's personal information, it complies with the provisions of relevant laws and regulations, is used for legal purposes, and does not violate public order and good customs. Necessary measures are taken for the user's personal information to prevent illegal access to the user's personal information data, and to safeguard the security of the user's personal information and network security.

[0029] Figure 1 It is a flowchart of a tracking result prediction method provided according to an embodiment of the present invention. This embodiment is applicable to the situation of predicting the tracking result of a target missile on a target tracking object. This method can be executed by a tracking result prediction device, and the tracking result prediction device can be implemented in the form of hardware and / or software.

[0030] As Figure 1 shown, the method of this embodiment may specifically include:

[0031] S110. Determine the target actual state data of the target missile at the target moment and the actual motion data group of the target tracking object.

[0032] Wherein, the target missile is the missile for which the tracking result needs to be predicted. The target moment can be the moment when the target missile detaches from the launch device. For example, in the scenario of launching a missile by air, the target moment can be the moment when the target missile detaches from the aircraft. In the scenario of launching from a roadbed, the target moment can be the moment when the target missile detaches from the ground launch device. The target actual state data can be at least one of the speed data, position data, and attitude data at the target moment. The actual motion data group can be an array composed of the actual motion point data of the target tracking object at different moments, and the actual motion point data includes position data and speed data. It should be noted that those skilled in the art can preset the target actual motion point data corresponding to the target moment in the actual motion data group according to the actual application situation.

[0033] In specific implementation, the target actual state data of the target missile at the target moment can be determined based on different launch methods of the target missile. Exemplarily, if the launch method is air launch, then according to the pre-set propulsion rules when the aircraft launches the target missile, the speed, position, and attitude of the aircraft at the moment when the target missile detaches from the aircraft can be determined; based on the speed, position, and attitude of the aircraft, the target actual state data of the target missile can be determined. Further, the historical motion data of the target tracking object within the historical time period can be obtained in advance and used as the actual motion data group of the target tracking object.

[0034] S120. Based on the target actual state data, the actual motion data group, and the pre-trained state determination model, determine the future prediction state data of the target missile at the future moment.

[0035] Among them, the state determination model is a pre-trained neural network model. The future predicted state data is the predicted state data of the target missile at future times after the target time. It should be noted that the time interval between the future time and the target time is determined by the trained state determination model.

[0036] In a specific implementation, the method for determining the future predicted state data may be: inputting the target actual state data and the target actual motion point data into the pre-trained state determination model, and the state determination model outputs the future predicted state data at future times.

[0037] S130. Based on the future predicted state data and the actual motion data set, determine the predicted tracking result of the target missile on the target tracking object.

[0038] Optionally, based on the future predicted state data and the actual motion data set, determining the predicted tracking result of the target missile on the target tracking object includes: determining the future actual motion point data based on the actual motion data set; when the future predicted state data and the future actual motion point data meet the preset conditions, determining that the predicted tracking result of the target missile on the target tracking object is tracking successfully; among them, the future predicted state data includes the future predicted position of the target missile at future times; the future actual motion point data includes the future object position of the target tracking object at future times; the preset conditions include that the distance between the future predicted position and the future object position is less than the preset distance threshold.

[0039] In a specific implementation, based on the time interval between the target time and the future time, the actual motion point data that is at the same time interval from the generation time of the target actual motion point data in the actual motion data set can be determined as the future actual motion point data. The future predicted state data and the future actual motion point data can be compared to determine the predicted tracking result based on the comparison result. Among them, the predicted tracking result includes tracking successfully and tracking failed.

[0040] Specifically, the distance between the future predicted position and the future object position can be determined. When this distance is less than the preset distance threshold, it indicates that the target missile catches up with the target tracking object at future times, and then the predicted tracking result is determined as tracking successfully. If this distance is greater than or equal to the preset distance threshold, it indicates that the target missile does not catch up with the target tracking object at future times, and then it can continue to determine whether it can track successfully at other to-be-predicted times in the future time period.

[0041] Furthermore, determine the height of the future predicted position. When this height is less than the preset height threshold, it indicates that the target missile does not catch up with the target tracking object at future times.

[0042] It should be noted that those skilled in the art can determine the specific values of the preset distance threshold and the preset height threshold according to the actual application situation, and this embodiment does not limit this.

[0043] In this embodiment, by comparing the distance between the future predicted position and the future object position with the preset distance threshold, it is quickly determined whether the target navigation is successfully tracked at a future moment.

[0044] Furthermore, the method provided in this embodiment further includes: when the future predicted state data and the future actual motion point data do not meet the preset conditions, determining input data based on the future predicted state data and the actual motion data group, inputting the input data into the state determination model to obtain the latest predicted state data, and updating the future predicted state data based on the latest predicted state data; when the updated future predicted state data meets the preset conditions, determining that the predicted tracking result of the target missile for the target tracking object is successful; when the updated future predicted state data does not meet the preset conditions, repeating the above operations of determining the input data, inputting the input data into the state determination model, and updating the future predicted state data based on the obtained latest predicted state data until the preset stop condition is reached and the repeated execution operation stops.

[0045] To improve the accuracy of the predicted tracking result, it can be determined whether the target missile can be successfully tracked at other moments in the future time period. Specifically, based on the time interval between the future moment and the target moment, the actual motion point data with a time distance from the target actual motion point data equal to this time interval can be determined from the actual motion data group as the future actual motion point data corresponding to the future moment.

[0046] In a specific implementation, the future predicted state data and the future actual motion point data can be used as input data and input into the state determination model to output the latest predicted state data, and the future predicted state data can be updated to the latest predicted state data. To accurately determine the predicted tracking result, it can be determined whether the updated future predicted state data and the future actual motion point data meet the preset conditions. If they meet, it means the tracking is successful. If not, the above steps can be repeated to determine the actual motion point data at the next moment with a time distance from the future moment equal to this time interval, and based on the actual motion point data at the next moment with a time distance from the future moment equal to this time interval and the updated future predicted state data, determine the predicted state data at the next moment with a time distance from the future moment equal to this time interval as the latest predicted state data to update the future predicted state data; and, based on the preset conditions, determine whether the target missile is successfully tracked until the preset stop condition is reached and the repeated execution operation stops.

[0047] In this embodiment, by repeatedly performing operations of determining input data, an input data input status determination model, and updating future prediction status data based on the obtained latest prediction status data, it is possible to determine whether the target navigation tracks the target tracking object at multiple moments in a future time period, so as to improve the accuracy of determining the predicted tracking result.

[0048] Optionally, the preset stop conditions include: the number of executions of the repeated operation reaches a preset number threshold; and / or, the updated future prediction status data meets a preset condition.

[0049] Specifically, in the process of repeatedly performing the above operations of determining input data, an input data input status determination model, and updating future prediction status data based on the obtained latest prediction status data, if it is determined that the updated future prediction status data meets a preset condition, it can be determined that the predicted tracking result is a successful tracking, and the repeated execution of the operation is stopped. If the number of executions of the repeated operation reaches the preset number threshold, the repeated execution of the operation can be stopped, and the predicted tracking result is determined to be a failed tracking.

[0050] In this embodiment, by setting preset stop conditions, the operations of determining input data, an input data input status determination model, and updating future prediction status data based on the obtained latest prediction status data are prevented from being repeatedly executed all the time, which is beneficial to improving the efficiency of determining the predicted tracking result.

[0051] The technical solution of the embodiment of the present invention includes determining the target actual status data of the target missile at the target moment and the actual motion data set of the target tracking object; based on the target actual status data, the actual motion data set, and a pre-trained status determination model, determining the future prediction status data of the target missile at a future moment; wherein, the status determination model is a pre-trained neural network model; since the neural network model does not need to perform numerical integration calculation or numerical differential calculation, cumulative errors are avoided, the calculation amount is reduced, which is beneficial to improving the efficiency and accuracy of determining the prediction status data; and, based on the future prediction status data and the actual motion data set, determining the predicted tracking result of the target missile for the target tracking object, thus achieving the effect of improving the accuracy of the predicted tracking result.

[0052] Figure 2It is a flowchart of another tracking result prediction method provided according to an embodiment of the present invention. On the basis of the above embodiment, optionally, the state determination model includes a state transition network; before determining the future predicted state data of the target missile at a future moment based on the target actual state data, the actual motion data set, and the pre-trained state determination model, it further includes: obtaining the historical operation data set of the target missile; training the to-be-trained state transition network based on the historical operation data set and the reinforcement learning algorithm, and obtaining the state transition network after the training ends as the state determination model. Among them, the explanations of the same or corresponding terms as those in the above embodiments will not be elaborated here. As Figure 2 shown, the method includes:

[0053] S210. Obtain the historical operation data set of the target missile; train the to-be-trained state transition network based on the historical operation data set and the reinforcement learning algorithm, and obtain the state transition network after the training ends as the state determination model.

[0054] Among them, the historical operation data set is composed of historical state data groups generated in multiple historical time periods and multiple historical motion data groups; the historical state data group includes the starting true state data corresponding to the target missile at the starting motion moment and the remaining true state data corresponding to the remaining motion moments, and the historical motion data group includes at least one historical true motion point data of the target tracking object.

[0055] To improve the prediction accuracy, the data in the historical state data group and the historical motion data group can be respectively subjected to data cleaning processing. Among them, the data cleaning operation includes at least one operation of missing value processing, outlier processing, error data processing, and duplicate data processing.

[0056] In this embodiment, the data in the historical state data group and the historical motion data group can be aligned according to the data generation time to establish a data correspondence relationship between the training state data and the training motion point data at different data generation times.

[0057] Optionally, the state transition network is a neural network. The implementation of training the state transition network to be trained based on the historical operation dataset and the reinforcement learning algorithm includes: traversing each starting true state data; for each traversed starting true state data, determining input data based on the starting true state data and the historical motion data group corresponding to the starting true state data, inputting the input data into the state transition network to be trained, outputting historical predicted state data corresponding to the input data, determining the current reward value corresponding to the input data based on the discriminator network to be trained, updating the input data based on the historical predicted state data, and inputting the updated input data value into the state transition network to be trained, outputting historical predicted state data corresponding to the updated input data, repeating the operations of updating the input data based on the historical predicted state data, outputting the historical predicted state data, and determining the current reward value until the preset end condition is met and then stopping the operation, updating the network parameters of the state transition network to be trained based on each current reward value obtained in the current traversal, and updating the network parameters of the discriminator network to be trained based on each historical predicted state data, the remaining true state data corresponding to the starting true state data, and the historical motion data group obtained in the current traversal, so as to determine the next reward value based on the discriminator network with updated network parameters in the next traversal operation until the preset training condition is met and the training ends, and stopping the traversal of the starting true state data; the trajectory determination model is composed of the state transition network after the training ends.

[0058] Among them, the preset training condition includes that the loss function corresponding to the discriminator network converges. The preset end condition includes that the number of repetitions of the operations of updating the input data based on the historical predicted state data, outputting the historical predicted state data, and determining the current reward value reaches a preset number threshold. In this embodiment, the state transition network after the training ends is used as the state determination model.

[0059] Further, the adjustment parameters of the state transition network are determined through the PPO (Proximal Policy Optimization) algorithm and the current reward value, and the network parameters of the state transition network are adjusted based on the adjustment parameters to maximize the cumulative reward.

[0060] In this embodiment, the state determination model is trained by means of reinforcement learning, so that the trained state determination model has stronger generalization.

[0061] S220. Determine the target actual state data of the target missile at the target time and the actual motion data group of the target tracking object.

[0062] In this embodiment, before determining the future predicted state data generated by the target missile after the target moment based on the target actual state data, the actual motion data set, and the pre-trained state determination model, it further includes: determining the target environmental data of the target area where the target missile is located at the target moment; determining the future predicted state data of the target missile at a future moment based on the target actual state data, the actual motion data set, and the pre-trained state determination model, including: obtaining the future predicted state data of the target missile at the future moment based on the target actual state data, the target motion data corresponding to the target moment in the actual motion data set, the target environmental data, and the state determination model.

[0063] Optionally, the target environmental data includes at least one of wind speed data, wind direction data, and temperature data of the target area where the target missile is located at the target moment. The target area is a pre-set flight area of the target missile.

[0064] In a specific implementation, determining the target environmental data of the target area where the target missile is located at the target moment includes: obtaining the weather forecast data of the target area at the target moment, and determining the target environmental data based on the weather forecast data.

[0065] S230. Determine the future predicted state data of the target missile at a future moment based on the target actual state data, the actual motion data set, and the pre-trained state determination model.

[0066] S240. Determine the predicted tracking result of the target missile on the target tracking object based on the future predicted state data and the actual motion data set.

[0067] In this embodiment, when determining the future predicted state data, the influence of environmental factors in the target area is considered, which is beneficial to improving the accuracy of the determined future predicted state data.

[0068] Figure 3 It is a schematic structural diagram of a tracking result prediction device provided according to an embodiment of the present invention. The device is used to execute the tracking result prediction method provided in any of the above embodiments. The device and the tracking result prediction method in the above embodiments belong to the same inventive concept. Details not described in detail in the embodiment of the tracking result prediction device can be referred to the embodiment of the above tracking result prediction method. As Figure 3 shown, the device includes:

[0069] The first data determination module 10 is used to determine the target actual state data of the target missile at the target moment and the actual motion data set of the target tracking object;

[0070] The second data determination module 11 is configured to determine future predicted state data of the target missile at a future moment based on the target actual state data, the actual motion data set, and a pre-trained state determination model; wherein, the state determination model is a pre-trained neural network model;

[0071] The prediction tracking result determination module 12 is configured to determine a prediction tracking result of the target missile for the target tracking object based on the future predicted state data and the actual motion data set.

[0072] Based on any optional technical solution in the embodiments of the present invention, optionally, the device further includes:

[0073] The target environment data determination module is configured to determine target environment data of the target area where the target missile is located at a target moment before determining future predicted state data generated by the target missile after the target moment based on the target actual state data, the actual motion data set, and the pre-trained state determination model;

[0074] The second data determination module 11 includes:

[0075] The future predicted state data determination sub-module is configured to obtain future predicted state data of the target missile at a future moment based on the target actual state data, the target motion data corresponding to the target moment in the actual motion data set, the target environment data, and the state determination model.

[0076] Based on any optional technical solution in the embodiments of the present invention, optionally, the prediction tracking result determination module 12 includes:

[0077] The first tracking result determination sub-module is configured to determine future actual motion point data based on the actual motion data set; and when the future predicted state data and the future actual motion point data meet a preset condition, determine that the prediction tracking result of the target missile for the target tracking object is tracking success;

[0078] Wherein, the future predicted state data includes the future predicted position of the target missile at a future moment; the future actual motion point data includes the future object position of the target tracking object at a future moment; the preset condition includes that the distance between the future predicted position and the future object position is less than a preset distance threshold.

[0079] Based on any optional technical solution in the embodiments of the present invention, optionally, the prediction tracking result determination module 12 further includes:

[0080] The future prediction status data update sub-module is used to determine input data based on the future prediction status data and the actual motion data group when the future prediction status data and the future actual motion point data do not meet the preset conditions, input the input data into the status determination model to obtain the latest prediction status data, and update the future prediction status data based on the latest prediction status data;

[0081] The second tracking result determination sub-module is used to determine that the predicted tracking result of the target missile on the target tracking object is tracking success when the updated future prediction status data meets the preset conditions;

[0082] The repeated execution sub-module is used to repeatedly execute the above operations of determining input data, inputting the input data into the status determination model, and updating the future prediction status data based on the obtained latest prediction status data when the updated future prediction status data does not meet the preset conditions, and stop the repeated execution operation until the preset stop condition is reached.

[0083] Based on any optional technical solution in the embodiment of the present invention, optionally, the preset stop condition includes:

[0084] The execution times of the repeated execution operation reach the preset number threshold; and / or,

[0085] The updated future prediction status data meets the preset conditions.

[0086] Based on any optional technical solution in the embodiment of the present invention, optionally, the status determination model includes a state transition network; the device further includes:

[0087] The historical operation data set acquisition module is used to acquire the historical operation data set of the target missile before determining the future prediction status data of the target missile at a future moment based on the target actual status data, the actual motion data group, and the pre-trained status determination model; wherein, the historical operation data set is composed of historical status data groups generated in multiple historical time periods and multiple historical motion data groups;

[0088] The model training module is used to train the to-be-trained state transition network based on the historical operation data set and the reinforcement learning algorithm, and obtain the state transition network after the training ends as the status determination model.

[0089] The technical solution of the embodiment of the present invention determines the target actual state data of the target missile at the target moment and the actual motion data group of the target tracking object; based on the target actual state data, the actual motion data group and the pre-trained state determination model, determines the future predicted state data of the target missile at the future moment; wherein, the state determination model is a pre-trained neural network model; since the neural network model does not need to perform numerical integration calculation or numerical differentiation calculation, cumulative errors are avoided, the calculation amount is reduced, which is beneficial to improving the efficiency and accuracy of determining the predicted state data; and, based on the future predicted state data and the actual motion data group, determines the predicted tracking result of the target missile for the target tracking object, thereby achieving the effect of improving the accuracy of the predicted tracking result.

[0090] It should be noted that in the embodiments of the above tracking result prediction device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0091] Figure 4 It is a schematic structural diagram of an electronic device for implementing the tracking result prediction method of the embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0092] As Figure 4 shown, the electronic device 20 includes at least one processor 21, and a memory communicatively connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program executable by the at least one processor, and the processor 21 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 into the random access memory (RAM) 23. In the RAM 23, various programs and data required for the operation of the electronic device 20 can also be stored. The processor 21, the ROM 22, and the RAM 23 are connected to each other through a bus 24. The input / output (I / O) interface 25 is also connected to the bus 24.

[0093] Multiple components in the electronic device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 28, such as a magnetic disk, an optical disc, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0094] The processor 21 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 21 executes the various methods and processes described above, such as the tracking result prediction method.

[0095] In some embodiments, the tracking result prediction method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 28. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps of the tracking result prediction method described above can be executed. Alternatively, in other embodiments, the processor 21 can be configured to execute the tracking result prediction method by any other suitable means (e.g., by means of firmware).

[0096] The various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), system-on-chip systems (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] A computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0098] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0100] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0101] A computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0102] This embodiment also provides a computer program product, including a computer program which, when executed by a processor, implements the tracking result prediction method provided in any embodiment of this application.

[0103] In the process of implementing the computer program product, computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0104] It should be understood that the various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0105] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub - combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for predicting tracking results, characterized in that, Including: Determine the actual state data of the target missile at the target moment and the actual motion data group of the target tracking object; Based on the actual state data of the target, the actual motion data group and a pre-trained state determination model, determine the future predicted state data of the target missile at a future moment; wherein, the state determination model is a pre-trained neural network model; Based on the future predicted state data and the actual motion data group, determine the predicted tracking result of the target missile on the target tracking object; The state determination model includes a state transition network; before determining the future predicted state data of the target missile at a future moment based on the actual state data of the target, the actual motion data group and the pre-trained state determination model, it further includes: Obtain the historical operation data set of the target missile; wherein, the historical operation data set is composed of historical state data groups generated by multiple historical time periods and multiple historical motion data groups; Clean the historical state data group and the historical motion data group, and align the data based on the data generation time to establish the corresponding relationship between the training state data and the training motion point data; Based on the historical operation data set and the reinforcement learning algorithm, train the state transition network to be trained, and obtain the state transition network after training as the state determination model.

2. The method according to claim 1, characterized in that Before determining the future predicted state data of the target missile at a future moment based on the actual state data of the target, the actual motion data group and the pre-trained state determination model, it further includes: Determine the target environment data of the target area to which the target missile belongs at the target moment; The determining the future predicted state data of the target missile at a future moment based on the actual state data of the target, the actual motion data group and the pre-trained state determination model includes: Based on the actual state data of the target, the target motion data corresponding to the target moment in the actual motion data group, the target environment data and the state determination model, obtain the future predicted state data of the target missile.

3. The method according to claim 1, wherein The determining the predicted tracking result of the target missile on the target tracking object based on the future predicted state data and the actual motion data group includes: Determine the future actual motion point data based on the actual motion data group; When the future predicted state data and the future actual motion point data meet the preset conditions, determine that the predicted tracking result of the target missile on the target tracking object is successful tracking; Wherein, the future predicted state data includes the future predicted position of the target missile at a future moment; the future actual motion point data includes the future object position of the target tracking object at the future moment; the preset conditions include that the distance between the future predicted position and the future object position is less than a preset distance threshold.

4. The method according to claim 3, wherein It further includes: In the case that the future predicted state data and the future actual motion point data do not meet the preset conditions, input data is determined based on the future predicted state data and the actual motion data set, the input data is input into the state determination model to obtain the latest predicted state data, and the future predicted state data is updated based on the latest predicted state data; In the case that the updated future predicted state data meets the preset conditions, it is determined that the predicted tracking result of the target missile for the target tracking object is successful tracking; In the case that the updated future predicted state data does not meet the preset conditions, the above operations of determining input data, inputting the input data into the state determination model, and updating the future predicted state data based on the obtained latest predicted state data are repeatedly executed until the repeated execution operation stops when the preset stop conditions are reached.

5. The method according to claim 4, wherein The preset stop conditions include: The number of executions of the repeated execution operation reaches the preset number threshold; and / or, The updated future predicted state data meets the preset conditions.

6. A tracking result prediction device, characterized in that, It includes: A first data determination module, configured to determine the target actual state data of the target missile at the target moment and the actual motion data set of the target tracking object; A second data determination module, configured to determine the future predicted state data of the target missile at the future moment based on the target actual state data, the actual motion data set, and a pre-trained state determination model; wherein, the state determination model is a pre-trained neural network model; A predicted tracking result determination module, configured to determine the predicted tracking result of the target missile for the target tracking object based on the future predicted state data and the actual motion data set; The state determination model includes a state transition network; the apparatus further includes: A historical operation data set acquisition module, configured to acquire the historical operation data set of the target missile before determining the future predicted state data of the target missile at the future moment based on the target actual state data, the actual motion data set, and a pre-trained state determination model; wherein, the historical operation data set is composed of a historical state data set generated by multiple historical time periods and a multiple historical motion data sets; data cleaning is performed on the historical state data set and the historical motion data set, and data alignment is performed based on the data generation time to establish a correspondence between the training state data and the training motion point data; A model training module, configured to train the to-be-trained state transition network based on the historical operation data set and a reinforcement learning algorithm, and obtain the state transition network after the training ends as the state determination model.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the tracking result prediction method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for implementing the tracking result prediction method according to any one of claims 1-5 when executed by a processor.

9. A computer program product comprising a computer program which, when executed by a processor, implements the tracking result prediction method according to any one of claims 1-5.

Images