Target long track prediction method, equipment, medium and product

Abstract

The invention discloses a target long track prediction method, equipment, a medium and a product, which relate to the field of target long track prediction, and perform error compensation on a prediction result of a main model by utilizing inverse operation of differential and integral through three forms of simultaneously predicting an original value, differential (or difference) and integral (or accumulation) of a target sequence, so as to improve the prediction precision. Different from an existing LSTM model, a triple LSTM model target long track prediction framework provided by the invention performs error compensation by combining inverse operation characteristics of differential and integral. A similar prediction method using differential and integral compensation does not exist in the prior art. According to the method, prediction errors can be effectively reduced, and particularly, the method is excellent in performance when sequence data with complex dynamic characteristics are processed.

Description

Technical Field

[0001] The present invention relates to the field of target long track prediction, and in particular to a target long track prediction method, equipment, medium and product. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.

[0003] Time series forecasting technology plays a key role in fields such as air traffic control and maritime surveillance, particularly in long-trajectory target prediction scenarios, where both short-term dynamic characteristics and long-term trend evolution must be considered. Traditional methods are primarily based on statistical principles and physical motion models, with the most representative being the autoregressive integrated moving average (ARIMA) model and the Kalman filter algorithm. The ARIMA model processes non-stationary sequences through differencing, but its linear assumptions make it difficult to adapt to the nonlinear characteristics of target maneuvers. While the Kalman filter excels at handling noise, it relies on precise system state equations, limiting its adaptability in complex environments.

[0004] With the advancement of deep learning technology, recurrent neural networks (RNNs) and their variant, long short-term memory (LSTM) networks, have gradually become mainstream methods for time series forecasting. LSTMs effectively capture long-term dependencies through a gating mechanism, outperforming traditional methods in trajectory forecasting tasks. However, existing research has largely focused on optimizing single models. Key technical approaches include: 1) increasing network depth to construct a multi-layer LSTM architecture; 2) introducing attention mechanisms to enhance key time-step features; and 3) combining convolutional neural networks to extract spatial features. While these improvements have improved forecasting accuracy to some extent, they are still essentially improvements within the framework of a single model and suffer from two inherent drawbacks. First, a single model struggles to simultaneously balance the transient volatility and long-term trends of sequence data, resulting in a compromise between stability (reflected in trajectory jitter during sudden changes in velocity / acceleration) and trend consistency (reflected in accumulated deviations over long time spans). Second, fixed-weight fusion methods fail to fully account for the propagation characteristics of errors at different forecast stages, which can easily lead to cumulative error amplification.

[0005] Current research on multi-model fusion strategies demonstrates the theoretical value of using a parallel prediction architecture for improving robustness, but significant limitations remain in practical applications: 1) Sub-models are trained on the original sequence, failing to leverage the complementary features introduced by sequence transformations; 2) Weight assignment often relies on empirical values ​​or simple optimization algorithms, lacking mathematical modeling of error propagation mechanisms. Experimental data shows that in scenarios with more than 50 prediction steps, the prediction error of traditional methods exhibits a nonlinear growth trend, highlighting the current state of the art's understanding of error dynamics.

[0006] It's worth noting that differential operations (reflecting the local rate of change of a series) and integral operations (reflecting the global cumulative amount of a series) have been shown to enhance features in traditional time series analysis. For example, differential integration methods can significantly improve the stationarity handling capabilities of ARIMA models, while integral transformations offer unique advantages in trend forecasting. However, within the deep learning framework, how to organically combine differential / integral operations with LSTM models to construct a forecasting system with self-error compensation capabilities remains a technical challenge. Summary of the Invention

[0007] The purpose of the present invention is to address the problems existing in the prior art and provide a target long-track prediction method, device, medium, and product, which simultaneously predicts the original value, differential and integral forms of the target sequence, and uses the inverse operations of differential and integral to dynamically compensate for the prediction results of the main model to improve the prediction accuracy; specifically: first, by establishing a triple LSTM model, it is used to train and predict the original output value sequence, the differential sequence of the original output value, and the integral sequence of the original output value of the sliding window generated data set, wherein the differential and integral prediction sequences are inversely transformed and restored to the 0th order sequence, and finally, by dynamically and reasonably adjusting the weights of the three models according to the sequence order, a good prediction effect can be achieved.

[0008] The technical solutions of the present invention are as follows: A target long track prediction method, comprising: Step S1: Generate a data set containing input data and output data from the original data sequence in a sliding window manner; Step S2: Establish three independent LSTM models, which serve as the original value prediction model, the differential sequence prediction model, and the integral sequence prediction model respectively. The inputs of the three LSTM models are all the input data of the dataset, and the outputs correspond to the original output data, the differential sequence of the original output data, and the integral sequence of the original output data respectively. Step S3: Based on the data set, the three LSTM models are trained separately until the preset convergence conditions are met; Step S4: The three LSTM models perform actual predictions respectively. The output of the original value prediction model is the 0th order prediction sequence. The output of the differential sequence prediction model and the integral sequence prediction model are inversely transformed to restore to the 0th order prediction sequence. Step S5: Dynamically adjust and assign the optimal weights of the three LSTM models according to the order of the predicted sequence; Step S6: Based on the weights adjusted in step S5, perform weighted fusion on the three 0th-order prediction sequences to obtain the final prediction result.

[0009] Furthermore, the original value prediction model directly predicts the target sequence The original value of Differential sequence prediction model predicts target sequence Differential sequence of ; Integral sequence prediction model predicts target sequence The integral sequence of ; The input of the three LSTM models is a sequence ,in is the length of the input sequence; The outputs of the three LSTM models are: Original value prediction model: ;in is the output sequence length; Differential sequence prediction model: ,in ; Integral sequence prediction model: ,in .

[0010] Furthermore, the output results of the differential sequence prediction model are inversely transformed, including: Inverse operation of differential sequence: from recover :

[0011] in: , the initial conditions are .

[0012] Furthermore, the output result of the integral sequence prediction model is inversely transformed, including: Inverse operation of integral sequence: from recover :

[0013] in: , the initial conditions are .

[0014] Furthermore, the weight of the differential sequence prediction model decreases with time steps, and the weight of the integral sequence prediction model increases with time steps.

[0015] Furthermore, the weight distribution method is as follows:

[0016]

[0017]

[0018] in: For the current moment; The weights of the prediction model are the original values; is the weight of the differential sequence prediction model is the weight of the integrated sequence prediction model.

[0019] Furthermore, weighted fusion includes:

[0020] in: Indicates the final prediction result.

[0021] The present invention further provides an electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor executes the above-mentioned method by executing the instructions stored in the memory.

[0022] The present invention also provides a computer-readable storage medium, which is used to store instructions. When the instructions are executed, the above method is implemented.

[0023] The present invention also provides a computer program product, which implements the above method when executed by a processor.

[0024] Compared with the existing technology, the beneficial effects of the present invention are: 1. Existing multi-model systems primarily train and predict multiple models of the original output sequence separately, and then perform a weighted combination to produce a final prediction sequence. This fails to address or balance the volatility and instability of the prediction results. This invention expands the concept and method of long-track target prediction by introducing differential sequence prediction compensation, resulting in more stable prediction results.

[0025] 2. Existing multi-model systems primarily train and predict multiple models of the original output sequence separately, then perform a weighted analysis to produce a final prediction sequence. This fails to address or balance the overall prediction deviation caused by the poor cumulative effect of historical trends. This invention expands the concept and method of long-track target prediction by introducing integral sequence prediction compensation, enabling the prediction results to better reflect the cumulative effect of historical trends.

[0026] 3. Existing multi-model systems primarily train and predict multiple models of the original output sequence separately, then perform weighted calculations to produce a final prediction sequence. Because weighting is always performed using fixed coefficients, it fails to address and balance the problem of error accumulation in the prediction sequence. This invention expands the concept and method of long-range target trajectory prediction by dynamically assigning appropriate weights according to the order of the prediction sequence, resulting in more accurate prediction results.

[0027] 4. Existing multi-models mainly train and predict multiple models of the original output sequence separately, and finally perform weighting to obtain the final prediction sequence. Because the impact of each model error on the overall error is not considered, it cannot solve and balance the problem of minimizing the error of the final prediction result. The present invention dynamically allocates model weights based on the error accumulation and error cancellation rules of the differential sequence and integral sequence prediction values ​​in the process of restoring to the 0th order to minimize the final error. By introducing dynamic weight allocation to reduce the final error, the present invention expands the ideas and methods of target long-track prediction, making the prediction results more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flow chart of a target long track prediction method; Figure 2 The figure is a schematic structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0030] The features and performance of the present invention are further described in detail below with reference to the embodiments.

[0031] Example 1 To facilitate understanding of the technical solution of the present invention, LSTM is now explained as follows.

[0032] LSTM is a special recurrent neural network that effectively solves the vanishing or exploding gradient problems of traditional RNNs by introducing memory units and gating mechanisms. Its basic structure includes an input gate, a forget gate, and an output gate. The principle is as follows: The input gate controls how new input information is added to the cell state. The calculation formula is:

[0033] in, is the current input, is the hidden state of the previous moment, and is the weight matrix, is the bias term, is the sigmoid activation function.

[0034] The forget gate determines how much information in the cell state at the previous moment is retained. The calculation formula is:

[0035] in, is the current input, is the hidden state of the previous moment, and is the weight matrix, is the bias term, is the sigmoid activation function.

[0036] The output gate controls how the information in the cell state is converted into the hidden state. The calculation formula is:

[0037] in, is the current input, is the hidden state of the previous moment, and is the weight matrix, is the bias term, is the sigmoid activation function.

[0038] The candidate cell state is the source of new information and is generated by the hyperbolic tangent function tanh, which is calculated as:

[0039] in, is the current input, is the hidden state of the previous moment, and is the weight matrix, is the bias term.

[0040] Update the cell state. The cell state is updated through the forget gate and input gate. The formula is as follows:

[0041] in, Represents element-wise multiplication.

[0042] Calculate the current hidden state. The hidden state is determined by the output gate and the current cell state. The formula is:

[0043] Generate output, the hidden state is used to generate the final output, usually achieved through a fully connected layer:

[0044] in, is the output weight matrix, is the output bias term.

[0045] See also Figure 1 This embodiment proposes a target long track prediction method, which specifically includes the following steps: Step S1: Generate a data set containing input data and output data from the original data sequence in a sliding window manner; Step S2: Establish three independent LSTM models, which serve as the original value prediction model (0th order), the differential sequence prediction model (1st order), and the integral sequence prediction model (-1st order). The inputs of the three LSTM models are all the input data of the dataset, and the outputs correspond to the original output data, the differential sequence of the original output data, and the integral sequence (or cumulative sequence) of the original output data, respectively. Among them, the original value prediction model serves as the main model. Step S3: Based on the data set, the three LSTM models are trained separately until they meet the preset convergence conditions, such as reaching the number of iterations or reaching the expected accuracy. It should be noted that after training, the three models are used to predict the original value of the future track sequence, the differential value of the future track sequence, and the integral value of the future track sequence, respectively. Step S4: The three LSTM models perform actual predictions respectively. The output of the original value prediction model is the 0th order prediction sequence. The output of the differential sequence prediction model and the integral sequence prediction model are inversely transformed to restore to the 0th order prediction sequence. Step S5: Dynamically adjust and allocate the optimal weights of the three LSTM models according to the order of the prediction sequence; that is, the weight parameters of the three LSTM models need to be appropriately adjusted according to the characteristics of the data sequence to balance the influence of each model on the final prediction result. Only by selecting the optimal parameter value suitable for the data sequence can the best prediction effect be achieved. Step S6: Based on the weights adjusted in step S5, perform weighted fusion on the three 0th-order prediction sequences to obtain the final prediction result.

[0046] In this embodiment, it should be noted that the differential term introduced in the above method is used to maintain the stability and smoothness of the prediction results; In this embodiment, it should be noted that the integral term introduced in the above method is used to capture the long-term trend and cumulative effect of the data.

[0047] The differential and integral terms are further used to compensate for the problems of result fluctuations and long-term cumulative trend deviations in the original value prediction. At the same time, by appropriately adjusting the weight coefficients of the three parts, high-precision prediction results can be obtained.

[0048] In this embodiment, it should be noted that in the long-track target prediction scenario, a differential and integral sequence prediction model is introduced to compensate for the original sequence prediction of the original value prediction model, thereby optimizing the prediction effect. Due to the introduction of differentials and integrals in the prediction, this method is only applicable to multi-step (multi-point) predictions and cannot be used for single-step (single-point) predictions.

[0049] In this embodiment, specifically, the original value prediction model directly predicts the target sequence The original value of Differential sequence prediction model predicts target sequence The differential (difference) sequence of ; Integral sequence prediction model predicts target sequence The integral (accumulation) sequence of ; The input of the three LSTM models is a sequence ,in is the length of the input sequence; The outputs of the three LSTM models are: Original value prediction model: ;in is the output sequence length; Differential sequence prediction model: ,in ; Integral sequence prediction model: ,in .

[0050] In this embodiment, specifically, the output result of the differential sequence prediction model is inversely transformed, including: Inverse operation of differential sequence: from recover :

[0051] in: , the initial conditions are .

[0052] In this embodiment, specifically, the output result of the integral sequence prediction model is inversely transformed, including: Inverse operation of integral sequence: from recover :

[0053] in: , the initial conditions are .

[0054] In this embodiment, it should be noted that the prediction errors of the original value prediction model, the differential sequence prediction model, and the integral sequence prediction model are respectively , ,and ,but: Error propagation of inverse differential operation:

[0055] Error propagation for inverse integral operation:

[0056] Inverse operation of differential sequence: The error will accumulate, the prediction error will be large in the later stage, and the weight should be gradually reduced.

[0057] Inverse operation of the integral sequence: the error can be partially offset and the weight can be gradually increased appropriately.

[0058] In this embodiment, specifically, the weight of the differential sequence prediction model decreases with time steps, and the weight of the integral sequence prediction model increases with time steps; That is, the weight distribution of the differential sequence prediction model should be in the order of the sequence, with the weights becoming smaller and smaller from the beginning to the end to reduce the error accumulation caused by sequence recovery; The weight distribution of the integral sequence prediction model should be in the order of the sequence, with the weight increasing from the front to the back, so as to enhance the error cancellation when subtracting two adjacent items in the sequence recovery process.

[0059] In this embodiment, it should be noted that the inverse operation of the differential sequence will lead to the accumulation of errors, while the inverse operation of the integral sequence can offset the errors by partially differentiating the errors between two adjacent terms. Therefore, due to the different error characteristics of the differential sequence prediction model and the integral sequence prediction model, dynamic weight allocation is performed.

[0060] In this embodiment, the weight allocation method is specifically as follows:

[0061]

[0062]

[0063] in: For the current moment; The weights of the prediction model are the original values; is the weight of the differential sequence prediction model is the weight of the integrated sequence prediction model.

[0064] ,and ; It can dynamically adjust the weights according to the error characteristics. By reasonably selecting the fusion weights , which can effectively reduce the prediction error.

[0065] In this embodiment, specifically, weighted fusion includes:

[0066] in: Indicates the final prediction result.

[0067] In this embodiment, it should be noted that the above-mentioned target long track prediction method combines the original value, differential and integral sequences of the target sequence, and uses the inverse operation of differential and integral to compensate the error of the prediction result of the main model to improve the prediction accuracy.

[0068] Based on the same technical concept, an embodiment of the present invention also provides an electronic device that can implement a target long track prediction method process provided by the above embodiment of the present invention. In one embodiment, the electronic device can be a server, or a terminal device or other electronic device. Figure 2 As shown, the electronic device may include: At least one processor, and a memory connected to the at least one processor. The embodiment of the present invention does not limit the specific connection medium between the processor and the memory. Figure 2 The example in this article is that the processor and memory are connected via a bus. Figure 2 The connections between the other components are shown in bold lines, which are only for illustration and not intended to be limiting. The bus can be divided into address bus, data bus, control bus, etc. Figure 2 The processor is represented by a single thick line, but this does not mean that there is only one bus or only one type of bus. Alternatively, the processor can also be called a controller, without any limitation on the name.

[0069] In an embodiment of the present invention, the memory stores instructions that can be executed by at least one processor, and the at least one processor can execute the target long track prediction method discussed above by executing the instructions stored in the memory. The processor can implement Figure 2 The functions of each module in the device shown.

[0070] Among them, the processor is the control center of the device, which can use various interfaces and lines to connect the various parts of the entire control device, and monitor the device as a whole by running or executing instructions stored in the memory and calling data stored in the memory, the various functions of the device and processing data.

[0071] In an optional design, the processor may include one or more processing units, and the processor may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interface, and application programs, and the modem processor primarily processes wireless communications. It is understood that the modem processor may not be integrated into the processor. In some embodiments, the processor and memory may be implemented on the same chip, or in some embodiments, they may be implemented on separate chips.

[0072] The processor can be a general-purpose processor, such as a CPU, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and can implement or execute the various methods, steps, and logic diagrams disclosed in the embodiments of the present invention. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the target long-track prediction method disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware processor, or by a combination of hardware and software modules within the processor.

[0073] As a non-volatile computer-readable storage medium, memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules. Memory can include at least one type of storage medium, for example, can include flash memory, hard disk, multimedia card, card-type memory, random access memory (Random Access Memory, RAM), static random access memory (Static Random Access Memory, SRAM), programmable read-only memory (Programmable Read Only Memory, PROM), read-only memory (Read Only Memory, ROM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), magnetic memory, disk, optical disk, etc. Memory is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the embodiment of the present invention can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0074] By designing and programming a processor, the code corresponding to the target long-track prediction method described in the aforementioned embodiment can be embedded in the chip, enabling the chip to execute the steps of the method described in the aforementioned embodiment during operation. Designing and programming a processor is well known to those skilled in the art and will not be further described here.

[0075] Based on the same inventive concept, an embodiment of the present invention further provides a storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes a target long track prediction method discussed above.

[0076] In some optional embodiments, the present invention also provides various aspects of a target long track prediction method, which can also be implemented in the form of a program product, which includes program code. When the program product is run on the device, the program code is used to enable the control device to execute the steps of a target long track prediction method according to various exemplary embodiments of the present invention described above in this specification.

[0077] It should be noted that although several units or subunits of the device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of a unit described above can be further divided into multiple units to be embodied. In addition, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0078] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a server, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] Program code for performing the operations of the present invention may be written using any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0081] Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0082] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0084] In addition, in some embodiments, a computer program product is also proposed. When the computer program is executed by a processor, the computer program implements the above-mentioned target long track prediction method.

[0085] The above-described embodiments merely represent specific implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of protection of the present application. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the technical concept of the present application, and all such variations and improvements fall within the scope of protection of the present application.

[0086] The above-described embodiments merely represent specific implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of protection of the present application. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the technical concept of the present application, and all such variations and improvements fall within the scope of protection of the present application.

[0087] This background section is provided to generally present the context of the invention, and the work of the presently named inventors, the work to the extent described in this background section, and aspects of the description in this section that did not constitute prior art at the time of filing are neither explicitly nor implicitly admitted to be prior art to the present invention.

Claims

1. A target long track prediction method, characterized in that: include: Step S1: Generate a data set containing input data and output data from the original data sequence in a sliding window manner; Step S2: Establish three independent LSTM models, which serve as the original value prediction model, the differential sequence prediction model, and the integral sequence prediction model respectively. The inputs of the three LSTM models are all the input data of the dataset, and the outputs correspond to the original output data, the differential sequence of the original output data, and the integral sequence of the original output data respectively. Step S3: Based on the data set, the three LSTM models are trained separately until the preset convergence conditions are met; Step S4: The three LSTM models perform actual predictions respectively. The output of the original value prediction model is the 0th order prediction sequence. The output of the differential sequence prediction model and the integral sequence prediction model are inversely transformed to restore to the 0th order prediction sequence. Step S5: Dynamically adjust and assign the optimal weights of the three LSTM models according to the order of the predicted sequence; Step S6: Based on the weights adjusted in step S5, perform weighted fusion on the three 0th-order prediction sequences to obtain the final prediction result.

2. A target long track prediction method according to claim 1, characterized in that: The original value prediction model directly predicts the target sequence The original value of Differential sequence prediction model predicts target sequence Differential sequence of ; Integral sequence prediction model predicts target sequence The integral sequence of ; The input of the three LSTM models is a sequence ,in is the length of the input sequence; The outputs of the three LSTM models are: Original value prediction model: ;in is the output sequence length; Differential sequence prediction model: ,in ; Integral sequence prediction model: ,in .

3. A target long track prediction method according to claim 2, characterized in that: Perform inverse transformation on the output of the differential sequence prediction model, including: Inverse operation of differential sequence: from recover : in: , the initial conditions are .

4. A target long track prediction method according to claim 3, characterized in that: Perform an inverse transformation on the output of the integral sequence prediction model, including: Inverse operation of integral sequence: from recover : in: , the initial conditions are .

5. A target long track prediction method according to claim 4, characterized in that: The weight of the differential sequence prediction model decreases with time steps, and the weight of the integral sequence prediction model increases with time steps.

6. A target long track prediction method according to claim 5, characterized in that: The weight distribution method is as follows: in: For the current moment; The weights of the prediction model are the original values; is the weight of the differential sequence prediction model is the weight of the integrated sequence prediction model.

7. A target long track prediction method according to claim 6, characterized in that: Weighted fusion, including: in: Indicates the final prediction result.

8. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor executes the method according to any one of claims 1 to 7 by executing the instructions stored in the memory.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images