Pose prediction method, device and equipment

Abstract

The invention discloses a pose prediction method, device and equipment, and relates to the technical field of data processing. The method comprises the following steps: acquiring a historical pose sequence, wherein the historical pose sequence comprises a plurality of historical pose data arranged according to a time sequence; decomposing the historical pose sequence according to a data decomposition algorithm to obtain k'sub-modal components corresponding to the historical pose sequence; for any sub-mode component, generating a pose prediction subsequence according to the pose prediction model corresponding to the sub-mode component; and fusing the pose prediction subsequences corresponding to the k'sub-modal components according to a fusion model to obtain a pose prediction sequence. The method is a novel pose prediction method capable of predicting a more accurate pose prediction sequence.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and more specifically, to a pose prediction method, apparatus, and device. Background Art

[0002] Currently, in order to reduce the display latency and stuttering of a head-mounted display device, and thus enhance the user experience of the head-mounted display device, etc., an early rendering technology is usually adopted. Specifically, a pose prediction model is used to predict the pose of the head-mounted display device, and the image is rendered according to the predicted pose, so as to early render the image to be displayed by the head-mounted display device.

[0003] However, the existing pose prediction models usually adopt linear networks and only predict based on historical pose data, which makes it difficult for the pose prediction model to learn complex non-linear relationships, and thus unable to accurately predict the pose. Therefore, a new pose prediction method is urgently needed to be proposed. Summary of the Invention

[0004] An object of the present application is to provide a new technical solution for pose prediction.

[0005] According to a first aspect of the present application, there is provided a pose prediction method, the method including:

[0006] Obtain a historical pose sequence, where the historical pose sequence includes a plurality of historical pose data arranged in time sequence;

[0007] Decompose the historical pose sequence according to a data decomposition algorithm to obtain k' sub-modal components corresponding to the historical pose sequence;

[0008] For any sub-modal component, generate a pose prediction subsequence according to the pose prediction model corresponding to the sub-modal component;

[0009] Fuse the pose prediction subsequences corresponding to the k' sub-modal components according to a fusion model to obtain a pose prediction sequence.

[0010] Optionally, the decomposing the historical pose sequence according to a data decomposition algorithm to obtain k' sub-modal components corresponding to the historical pose sequence includes:

[0011] Obtain the number of hippopotamus individuals in a hippopotamus population and the iteration cut-off condition of the hippopotamus population;

[0012] For any individual hippopotamus, perform the fitness value determination step to obtain the current individual fitness value of the hippopotamus individual. The fitness value determination step includes: determining a data decomposition algorithm according to the initial position of the hippopotamus individual, determining k sub-modal components for the historical pose sequence according to the data decomposition algorithm, and determining the current individual fitness value of the hippopotamus individual according to the k sub-modal components. The initial position of the hippopotamus individual is used to represent the parameter value of the data decomposition algorithm, and the parameter value includes at least k;

[0013] Determine the current relative speed change rate of the hippopotamus individual according to the current individual fitness value of the hippopotamus individual and the number of times of repeating the fitness value determination step;

[0014] Update the initial position of the hippopotamus individual according to the current relative speed change rate of the hippopotamus individual to obtain the updated position of the hippopotamus individual;

[0015] Update the initial position of the hippopotamus individual to the updated position of the hippopotamus individual, and repeat the fitness value determination step until the iteration cut-off condition of the hippopotamus population is reached;

[0016] Output the k sub-modal components corresponding to the optimal current individual fitness value among the current individual fitness values of the latest obtained hippopotamus individual as the k' sub-modal components corresponding to the historical pose sequence.

[0017] Optionally, the iteration cut-off condition of the hippopotamus population includes:

[0018] Repeat the fitness value determination step until the iteration number of the hippopotamus population is reached;

[0019] Or, the error between the reconstructed data corresponding to the k sub-modal components and the historical pose sequence is less than a preset error.

[0020] Optionally, the determining the current individual fitness value of the hippopotamus individual according to the k sub-modal components includes:

[0021] Determine the reconstructed data according to the k sub-modal components;

[0022] Determine the Euclidean distance between the reconstructed data and the historical pose sequence as the current individual fitness value of the hippopotamus individual;

[0023] Or, determine the sum of the fuzzy entropies corresponding to the k sub-modal components according to the k sub-modal components, and determine the sum of the fuzzy entropies as the current individual fitness value of the hippopotamus individual.

[0024] Optionally, before determining the data decomposition algorithm according to the initial position of the hippopotamus individual, the method further includes:

[0025] Determine the random mapping value of the hippopotamus individual according to the random mapping;

[0026] Determine the chaotic mapping value of the hippopotamus individual according to the random mapping value and the chaotic mapping;

[0027] Determine the initial position of the hippopotamus individual according to the chaotic mapping value of the hippopotamus individual and the initial position constraint condition of the hippopotamus individual.

[0028] Optionally, the determining the current relative speed change rate of the hippopotamus individual according to the current individual fitness value of the hippopotamus individual and the number of times of repeating the fitness value determination step includes:

[0029] When the number of times of repeating the fitness value determination step is 0, determine that the current relative speed change rate of the hippopotamus individual is infinite;

[0030] When the number of times of repeating the fitness value determination step is greater than 0, determine the current optimal fitness value according to the current individual fitness value of each hippopotamus individual;

[0031] Determine the historical optimal fitness value according to the historical fitness value obtained by each hippopotamus individual in the previous execution of the fitness value determination step;

[0032] Obtain the historical individual fitness value obtained by the hippopotamus individual in the previous execution of the fitness value determination step;

[0033] Determine the current relative speed change rate of the hippopotamus individual according to the historical individual fitness value, the current individual fitness value, the historical optimal fitness value and the current optimal fitness value.

[0034] Optionally, the updating the initial position of the hippopotamus individual according to the current relative speed change rate of the hippopotamus individual to obtain the updated position of the hippopotamus individual includes:

[0035] When the current relative speed change rate of the hippopotamus individual is greater than the preset change rate, update the initial position of the hippopotamus individual according to the position update method in the first exploration stage of the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual;

[0036] When the current relative speed change rate of the hippopotamus individual is less than or equal to the preset change rate, update the initial position of the hippopotamus individual according to the position update method in the second exploration stage of the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual;

[0037] For any one of the above-mentioned hippopotamus individuals, update the updated intermediate position of the hippopotamus individual according to the position update method in the development stage of the hippopotamus optimization algorithm to obtain the updated position of the hippopotamus individual.

[0038] Optionally, the step of updating the initial position of the hippopotamus individual according to the position update formula in the first exploration stage of the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual includes:

[0039] Determine the adaptive weight of each hippopotamus individual according to the current individual fitness value of each hippopotamus individual;

[0040] Update the position update formula in the first exploration stage of the hippopotamus optimization algorithm according to the adaptive weight to obtain the updated position update method in the first exploration stage;

[0041] Update the initial position of the hippopotamus individual according to the updated position update method in the first exploration stage, which is the updated intermediate position of the hippopotamus individual.

[0042] According to the second aspect of the present application, a pose prediction device is provided, and the device includes:

[0043] An acquisition module, configured to acquire a historical pose sequence, where the historical pose sequence includes a plurality of historical pose data arranged in time sequence;

[0044] A decomposition module, configured to decompose the historical pose sequence according to a data decomposition algorithm to obtain k' sub-modal components corresponding to the historical pose sequence;

[0045] A generation module, configured to generate a pose prediction subsequence for any one of the sub-modal components according to the pose prediction model corresponding to the sub-modal component;

[0046] A fusion module, configured to fuse the pose prediction subsequences corresponding to the k' sub-modal components according to a fusion model to obtain a pose prediction sequence.

[0047] According to the third aspect of the present application, an electronic device is provided, and the electronic device includes the device as described in the second aspect;

[0048] Alternatively, the electronic device includes a memory and a processor, the memory is configured to store computer instructions, and the processor is configured to call the computer instructions from the memory to execute the method as described in any item of the first aspect.

[0049] According to the fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the method as described in any item of the first aspect.

[0050] The present application provides a pose prediction method, which includes: obtaining a historical pose sequence, where the historical pose sequence includes a plurality of historical pose data arranged in time sequence; decomposing the historical pose sequence according to a data decomposition algorithm to obtain k' sub-modal components corresponding to the historical pose sequence; for any sub-modal component, generating a pose prediction subsequence according to the pose prediction model corresponding to the sub-modal component; and fusing the pose prediction subsequences corresponding to the k' sub-modal components according to a fusion model to obtain a pose prediction sequence. This method can accurately predict the corresponding pose prediction sequence for the historical pose sequence. That is, the present application provides a new pose prediction method that can predict a more accurate pose prediction sequence.

[0051] Other features and advantages of the present application will become clear through the following detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The drawings incorporated in the specification and constituting a part of the specification illustrate embodiments of the present application and, together with the description, are used to explain the principles of the present application.

[0053] Figure 1 is a block diagram of the hardware configuration of an electronic device for implementing a pose prediction method according to an embodiment of the present application Figure 1 ;

[0054] Figure 2 is a flowchart showing the implementation of a pose prediction method according to an embodiment of the present application Figure 1 ;

[0055] Figure 3 is a flowchart showing the implementation of a pose prediction method according to an embodiment of the present application Figure 2 ;

[0056] Figure 4 is a schematic diagram of the distribution structure of a random mapping and a chaotic mapping according to an embodiment of the present application;

[0057] Figure 5 is a schematic diagram showing the values of the tanh function when a takes different values according to an embodiment of the present application;

[0058] Figure 6 is a schematic diagram of the structure of an apparatus for implementing a pose prediction method according to an embodiment of the present application;

[0059] Figure 7 is a block diagram of the hardware configuration of an electronic device for implementing a pose prediction method according to an embodiment of the present application Figure 2 。 DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present application.

[0061] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way a limitation on the present application or its application or use.

[0062] Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, methods, and devices should be regarded as part of the specification.

[0063] In all examples shown and discussed herein, any specific values should be construed as merely exemplary and not as a limitation. Thus, other examples of exemplary embodiments may have different values.

[0064] It should be noted that: like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, further discussion thereof is not required in subsequent drawings.

[0065] Figure 1 is a block diagram of the hardware configuration of an electronic device for implementing a pose prediction method according to an embodiment of the present application Figure 1 .

[0066] The electronic device 1000 can be a terminal or a server. Further, the terminal can be a head-mounted device (such as an AR device, an MR device, and a VR device), a portable computer, a tablet computer, a handheld computer, etc. The server can be a cloud server, etc.

[0067] The electronic device 1000 may include a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and so on. Among them, the processor 1100 can be a central processing unit CPU, a microprocessor MCU, etc. The memory 1200 includes, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 1300 includes, for example, a USB interface, a headphone interface, etc. The communication device 1400 can perform wired or wireless communication, for example. The display device 1500 is, for example, a liquid crystal display screen, a touch display screen, etc. The input device 1600 can include, for example, a touch screen, a keyboard, etc. The user can input / output voice information through the speaker 1700 and the microphone 1800.

[0068] Although in Figure 1In the figure, multiple devices are shown for the electronic device 1000. However, this application may only relate to some of the devices. For example, the electronic device 1000 only relates to the memory 1200 and the processor 1100.

[0069] In the embodiments of the present application, the memory 1200 of the electronic device 1000 is used to store instructions for controlling the processor 1100 to execute the pose prediction method provided by the embodiments of the present application.

[0070] In the above description, those skilled in the art can design instructions according to the solutions disclosed in the present application. How the instructions control the processor to operate is well known in the art, so it will not be described in detail here.

[0071] The present application provides a pose prediction method applied to an electronic device as Figure 1 shown. As Figure 2 shown, the pose prediction method provided by the present application includes the following steps S2100 to step S2400.

[0072] Step S2100, obtain a historical pose sequence.

[0073] Among them, the historical pose sequence includes a plurality of historical pose data arranged in time sequence.

[0074] In this embodiment, the historical pose sequence is used to predict a pose prediction sequence, where the pose prediction sequence includes a plurality of future pose data at future moments arranged in time sequence.

[0075] A pose is usually represented by position data and attitude data. In one example, a pose can be represented as a seven-dimensional data: p_RS_R_x[M], p_RS_R_y[M], p_RS_R_z[M], q_RS_w[], q_RS_x[], q_RS_y[] and q_RS_z[]. Among them, p_RS_R_x[M], p_RS_R_y[M] and p_RS_R_z[M] represent three-dimensional position data, and q_RS_w[], q_RS_x[], q_RS_y[] and q_RS_z[] represent quaternion attitude data. On this basis, a historical pose data included in the historical pose sequence is composed of at least one of p_RS_R_x[M], p_RS_R_y[M], p_RS_R_z[M], q_RS_w[], q_RS_x[], q_RS_y[] and q_RS_z[] corresponding to the historical moment. That is to say, in this embodiment, the historical pose data may not represent a complete pose.

[0076] In an embodiment of the present application, the historical pose sequence can be represented as [x1, x2,..., x M .

[0077] Step S2200: Decompose the historical pose sequence according to the data decomposition algorithm to obtain k' sub-modal components corresponding to the historical pose sequence.

[0078] In this embodiment, the specific implementation of the above step S2200 can be as Figure 3 shown. Input the historical pose sequence into the data decomposition algorithm, and the data decomposition algorithm outputs k' sub-modal components.

[0079] In an embodiment of the present application, the data decomposition algorithm in the above step S2200 can be a traditional data decomposition algorithm, such as a traditional VMD algorithm or a traditional Oneshot STL decomposition algorithm.

[0080] When the data decomposition algorithm in the above step S2200 is a traditional Oneshot STL decomposition algorithm, k' is equal to 3, and the k' sub-modal components in the above step S2200 are respectively the trend component, the seasonal component, and the residual component corresponding to the historical pose sequence.

[0081] It should be noted that the k' sub-modal components decomposed by the data decomposition algorithm in the above step S2200 are arranged in the order of decreasing or increasing frequency.

[0082] Step S2300: For any sub-modal component, generate a pose prediction subsequence according to the pose prediction model corresponding to the sub-modal component.

[0083] In this embodiment, the specific implementation of the above step S2300 can be as Figure 3 shown. For any sub-modal component, input the sub-modal component into the corresponding pose prediction model, and the pose prediction model outputs the pose prediction subsequence corresponding to the sub-modal component. Among them, the pose prediction subsequence includes the pose prediction component corresponding to the corresponding sub-modal component.

[0084] Among them, taking the first sub-modal component among the k' sub-modal components as an example, the training process of the corresponding pose prediction model is specifically as follows: Obtain a plurality of training samples; train the pose prediction model to be trained according to the plurality of training samples to obtain a trained pose training model. Among them, the acquisition method of a training sample is specifically as follows: Taking a group of pose sequences as [x1, x2,..., x n , the input step number of the pose prediction model is 5, the prediction step number is 3, and the prediction start step is 3 steps after the last step of the input step number as an example, extract [x1, x2, x3, x4, x5] and [x8, x9, x n from the pose sequence [x1, x2,..., x 10; For [x1, x2, x3, x4, x5], k' sub-modal components are obtained through the data decomposition method in step S2200 above; for [x8, x9, x 10 , k' sub-modal components are obtained through the data decomposition method in step S2200 above; the first sub-modal component corresponding to [x1, x2, x3, x4, x5] is used as a sample in the training sample, and the first sub-modal component corresponding to [x8, x9, x 10 is used as the label of the aforementioned sample.

[0085] Step S2400, fuse the pose prediction subsequences corresponding to k' sub-modal components according to the fusion model to obtain a pose prediction sequence.

[0086] In an embodiment of the present application, the pose prediction sequence can be represented as [x M+i , x M+i+1 , …, x M+i+J . And, the fusion model can specifically be a linear layer model, such as a linear layer.

[0087] In this embodiment, the specific implementation of the above step S2400 is: the fusion model adds the pose prediction components belonging to the same dimension in the pose prediction subsequences corresponding to k' sub-modal components to obtain a pose prediction sequence.

[0088] Based on the above, it can be known that in the present application, through the above step S2300, the historical pose sequence used to determine the pose prediction sequence can be decomposed into k' sub-modal components, which can reduce the non-linear complexity of the historical pose sequence, that is, reduce the non-stationarity and distribution shift of the historical pose sequence. On this basis, after obtaining the pose prediction components for each sub-modal component obtained by decomposing the historical pose sequence into k sub-modal components through the above step S2400, the accurate pose prediction sequence can be obtained through the above step S2500. That is to say, the present application can accurately predict the corresponding pose prediction sequence for the historical pose sequence. That is, the present application provides a new pose prediction method that can predict a more accurate pose prediction sequence.

[0089] The present application provides a pose prediction method, which includes: obtaining a historical pose sequence including a plurality of historical pose data arranged in time sequence; decomposing the historical pose sequence according to a data decomposition algorithm to obtain k' sub-modal components corresponding to the historical pose sequence; for any sub-modal component, generating a pose prediction subsequence according to the pose prediction model corresponding to the sub-modal component; and fusing the pose prediction subsequences corresponding to the k' sub-modal components according to a fusion model to obtain a pose prediction sequence. This method can accurately predict the corresponding pose prediction sequence for the historical pose sequence. That is, the present application provides a new pose prediction method that can predict a more accurate pose prediction sequence.

[0090] In an embodiment of the present application, the data decomposition algorithm in the above step S2200 may specifically be an improved VMD algorithm. The values of k and alpha in the traditional VMD algorithm are set according to experience. This results in a large difference between the reconstructed signal corresponding to the sub-modal components decomposed by the traditional VMD algorithm and the historical pose sequence (i.e., the input signal of the traditional VMD algorithm). To address this, the values of k and alpha of the VMD algorithm are determined by the hippopotamus optimization algorithm to obtain an improved VMD algorithm. In this embodiment, the specific value of k in the VMD algorithm determined by the hippopotamus optimization algorithm is denoted as k'.

[0091] In another embodiment of the present application, the specific implementation of the above step S2200 may also be the following steps S2210 to S2260.

[0092] Step S2210, obtaining the number of hippopotamus individuals in the hippopotamus population and the iteration termination condition of the hippopotamus population.

[0093] The number of hippopotamus individuals is the number of candidate solutions in the search space. In this embodiment, the number of hippopotamus individuals is the number of groups of parameter values in the data decomposition algorithm. In an example, the data decomposition algorithm is the VMD algorithm. Based on this, the number of hippopotamus individuals is the number of groups of the k value and the alpha value in the VMD algorithm.

[0094] The iteration termination condition of the hippopotamus population represents the convergence condition for updating the positions of the hippopotamus individuals.

[0095] Step S2220, for any hippopotamus individual, performing a fitness value determination step to obtain the current individual fitness value of the hippopotamus individual.

[0096] In this embodiment, the fitness value determination step in step S2220 is implemented by the following steps S2221 to S2223.

[0097] Step S2221, determining the data decomposition algorithm according to the initial position of the hippopotamus individual.

[0098] Among them, the initial position of the hippopotamus individual is used to represent the parameter values of the data decomposition algorithm, and the parameter values include at least k.

[0099] Taking the VMD algorithm as an example of the data decomposition algorithm, the initial position of the hippopotamus individual is the value of k and alpha in the VMD algorithm in the initial state. The specific implementation of the above step S2210 is: setting both k and alpha in the VMD algorithm to the values in the initial state to obtain the VMD algorithm, where k in the VMD algorithm represents the number of sub-modal components included in the data decomposition result obtained by decomposition.

[0100] It should be noted that when the above step S2221 is executed for the first time, the parameter values of the data decomposition algorithm represented by the initial position of the hippopotamus individual are specifically the parameter values of the data decomposition algorithm in the initial state, that is, an initial parameter value. And, the values of k and alpha are updated through the following steps S2230 to S2240, and the finally updated k is denoted as k'.

[0101] In an embodiment of the present application, the initial position of the hippopotamus individual can be determined by means of random mapping as in the traditional hippopotamus optimization algorithm.

[0102] Due to the large randomness of random mapping, the random values determined by random mapping are unevenly distributed. This further leads to the problem of unstable optimization convergence speed in the subsequent traditional hippopotamus optimization algorithm. Therefore, in an embodiment of the present application, the data decomposition method provided in the present application further includes the steps of determining the initial position of the hippopotamus individual shown in steps S2221-1 to S2221-3 before the above step S2221.

[0103] Step S2221-1: Determine the random mapping value of the hippopotamus individual according to random mapping.

[0104] Step S2221-2: Determine the chaotic mapping value of the hippopotamus individual according to the random mapping value and chaotic mapping.

[0105] In this embodiment, for any hippopotamus individual, first determine the random mapping value corresponding to the hippopotamus individual through random mapping. Further, through chaotic mapping, map out the chaotic mapping value corresponding to the random mapping value.

[0106] In an embodiment of the present application, the chaotic mapping can specifically be Cubic chaotic mapping or Tent chaotic mapping.

[0107] Taking the chaotic mapping in the above step S2221-2 as Tent mapping as an example, the chaotic mapping can be represented by the following formula one.

[0108]

[0109] Among them, represents the random mapping value of the i-th hippopotamus individual, represents the chaotic mapping value of the i-th hippopotamus individual, and μ represents the control parameter in the Tent mapping, where 0 < μ < 1. When μ = 1 / 2, the result of the Tent mapping is uniformly distributed.

[0110] Step S2221-3: Determine the initial position of the hippopotamus individual according to the chaotic mapping value of the hippopotamus individual and the initial position constraint condition of the hippopotamus individual.

[0111] Among them, the initial position constraint condition of the hippopotamus individual is used to represent the upper limit value and the lower limit value of the initial position of the hippopotamus individual.

[0112] Taking the data decomposition algorithm as the VMD algorithm and the initial position of the hippopotamus individual as the initial values of k and alpha in the VMD algorithm as an example, the initial position constraint condition of the hippopotamus individual is used to represent the upper limit value and the lower limit value of k, and the upper limit value and the lower limit value of alpha.

[0113] In the traditional hippopotamus optimization algorithm, the initial position of the hippopotamus individual is determined according to the following formula two.

[0114] X(:,i) = X min (i) + r1 × (X max (i) - X min (i)) (Formula Two)

[0115] Among them, X(:,i) represents the initial position of the i-th hippopotamus individual, r1 is the random mapping value of the i-th hippopotamus individual, X max (i) represents the upper limit value of the i-th hippopotamus individual, X min (i) represents the lower limit value of the i-th hippopotamus individual, X max (i) and X min (i) can be set according to experience.

[0116] In this embodiment, the specific implementation of the above step S2210-3 is to replace r1 in the above formula two with the chaotic mapping value of the i-th hippopotamus individual.

[0117] Taking the chaotic mapping as the Tent mapping as an example, as Figure 4 shown, the chaotic mapping value obtained based on the chaotic mapping is more uniformly distributed than the random mapping value obtained by the random mapping. On this basis, the initial position distribution of the hippopotamus individual obtained through the above steps S2210-1 to S2210-3 is more uniform, which can increase the exploration difficulty and reduce the convergence speed.

[0118] Step S2222: Determine k sub-modal components for the historical pose sequence according to the data decomposition algorithm.

[0119] In this embodiment, after obtaining the data decomposition algorithm based on the above step S2221, the historical pose sequence is input into the data decomposition algorithm, and the data decomposition algorithm outputs k sub-modal components.

[0120] Step S2223: Determine the current individual fitness value of the hippopotamus individual according to the k sub-modal components.

[0121] In this embodiment, the above step S2210 can be specifically implemented in one of the following two ways.

[0122] Way 1: The above step S2223 is specifically implemented through the following steps S2223-1 and S2223-2.

[0123] Step S2223-1: Determine the reconstructed data according to the k sub-modal components.

[0124] In this embodiment, by adding the k sub-modal components, the reconstructed data can be obtained. Taking the data to be decomposed as X = (x1, x2,... x M ) as an example, the reconstructed data can be expressed as

[0125] Step S2223-2: Determine the Euclidean distance between the reconstructed data and the historical pose sequence as the current individual fitness value of the hippopotamus individual.

[0126] In this embodiment, the above step S2223-2 can be specifically implemented through the following formula three.

[0127]

[0128] Among them, represents the Euclidean distance between the reconstructed data and the historical pose sequence.

[0129] Way 2: The above step S2223 is specifically implemented through the following step S2223-3.

[0130] Step S2223-3: According to the k sub-modal components, determine the sum of the fuzzy entropies corresponding to the k sub-modal components, and determine the sum of the fuzzy entropies as the current individual fitness value of the hippopotamus individual.

[0131] In this embodiment, before determining the sum of the fuzzy entropies corresponding to the decomposition result data, first calculate the fuzzy entropy of each sub-modal component in the k sub-modal components. Then, sum the fuzzy entropies of all sub-modal components to obtain the sum of the fuzzy entropies.

[0132] Among them, the steps of calculating the fuzzy entropy of each of the k sub-modal components successively include the steps of phase space reconstruction, distance calculation, probability calculation, and fuzzy entropy calculation, which are specifically as follows.

[0133] The phase space reconstruction of each of the k sub-modal components is carried out by the following formula four.

[0134]

[0135] Among them, I is the index value, I, j = 1, 2, …, N-(m-1)τ; N is the length of the corresponding sub-modal component u k (t); τ represents the delay time, the time interval used to construct the phase space vector; m identifies the embedding dimension, which is used to represent the dimension of the reconstructed phase space, and m generally takes the value of 2.

[0136] The above distance calculation can be carried out by calculating the Euclidean distance or Manhattan distance, etc. Taking the Euclidean distance as an example, the distance calculation is carried out by the following formula five.

[0137]

[0138] Among them, represents the phase space reconstruction result of other sub-modal components, which can also be expressed as which can also be expressed as

[0139] Combining the above content, after counting the number of the phase space reconstruction results of the sub-modal components of the distance the probability is calculated by the following formula six

[0140]

[0141] Among them, r represents the width of the boundary of the fuzzy function. When r is too large, a lot of statistical information will be lost. When r is too small, the effect of the estimated statistical characteristics is not ideal, and the sensitivity to the result noise will be increased. r usually takes a certain proportion of the standard deviation of the signal (such as 0.1 - 0.25 times).

[0142] The fuzzy entropy H of the sub-modal component is calculated by the following formula seven k Calculation.

[0143]

[0144] Of course, other methods can also be used to calculate the fuzzy entropy of each sub-modal component. This application does not make any limitations in this regard.

[0145] Step S2230: Determine the current relative speed change rate of the hippopotamus individual according to the current individual fitness value of the hippopotamus individual and the number of times of repeatedly executing the fitness value determination step.

[0146] In an embodiment of the present application, the above step S2230 is specifically implemented through the following steps S2231 to S2235.

[0147] Step S2231: When the number of times of repeatedly executing the fitness value determination step is 0, determine that the current relative speed change rate of the hippopotamus individual is infinite.

[0148] In this embodiment, when the above step S2200 is executed for the first time, the number of times of repeatedly executing the fitness value determination step is 0. When the above step S2200 is executed for the second time, the number of times of repeatedly executing the fitness value determination step is 1. And so on, the number of times of repeatedly executing the fitness value determination step can be determined.

[0149] When the number of times of repeatedly executing the fitness value determination step is 0, the current relative speed change rate of the hippopotamus individual is determined based on the above step S2231. When the number of times of repeatedly executing the fitness value determination step is greater than 0, the current relative change rate of the hippopotamus individual is determined based on the following steps S2232 to S2235.

[0150] Step S2232: When the number of times of repeatedly executing the fitness value determination step is greater than 0, determine the current optimal fitness value according to the current individual fitness value of each hippopotamus individual.

[0151] In this embodiment, the current optimal fitness value is selected from the current individual fitness values of all hippopotamus individuals obtained after the above step S2200 is currently executed for any hippopotamus individual.

[0152] In an example, when the Euclidean distance between the reconstructed data and the data to be decomposed is determined as the current individual fitness value of the hippopotamus individual in Method 1, the smallest current individual fitness value is the current optimal fitness value. And when the sum of fuzzy entropies is determined as the current individual fitness value of the hippopotamus individual in Method 2, the smallest current individual fitness value is the current optimal fitness value.

[0153] Step S2233: Determine the historical optimal fitness value according to the historical fitness value obtained by each hippopotamus individual in the previous execution of the fitness value determination step.

[0154] The historical optimal fitness value is selected from the current individual fitness values of all hippopotamus individuals obtained after the previous execution of the above step S2200 for any hippopotamus individual.

[0155] Step S2234: Obtain the historical individual fitness value of the hippopotamus individual obtained in the previous execution of the fitness value determination step.

[0156] For any hippopotamus individual, determine the current individual fitness value obtained after the previous execution of step S2200 for this hippopotamus individual as the historical individual fitness value of this hippopotamus individual.

[0157] Step S2235: Determine the current relative speed change rate of the hippopotamus individual according to the historical individual fitness value, the current individual fitness value, the historical optimal fitness value, and the current optimal fitness value.

[0158] Based on the above steps S2231 to S2235, in this embodiment, the above step S2230 can be specifically implemented by the following formula eight.

[0159]

[0160] Where t represents the current number of times of repeating the above step S2200, and the maximum value of t is the iteration times of the hippopotamus population; represents the current relative speed change rate of the i-th hippopotamus individual; f(·) represents a preset fitness function; B t represents the current optimal fitness value; B t-1 represents the historical optimal fitness value; represents the current individual fitness value of the i-th hippopotamus individual, represents the historical individual fitness value of the i-th hippopotamus individual.

[0161] Based on the above steps S2231 to S2235, the present application provides a method for determining the current relative speed change rate of a hippopotamus individual.

[0162] Step S2240: Update the initial position of the hippopotamus individual according to the current relative speed change rate of the hippopotamus individual to obtain the updated position of the hippopotamus individual.

[0163] In an embodiment of the present application, the initial position of the hippopotamus individual can be updated according to the specific value of the current relative speed change rate. For example, when the current relative speed change rate represents a large change amplitude, the initial position of the hippopotamus individual is updated by a large-scale position adjustment method. When the current relative speed change rate represents a small change amplitude, the initial position of the hippopotamus individual is updated by a small-scale position adjustment method.

[0164] Compared with the traditional hippopotamus optimization algorithm, in the pose prediction method provided by this application, instead of grouping and updating positions according to the order of hippopotamus individuals as in the traditional hippopotamus algorithm, the position is updated depending on the current relative speed change rate of each hippopotamus individual. On this basis, the problem of difficultly finding the optimal solution when using the traditional hippopotamus optimization algorithm for optimization can be avoided.

[0165] Therefore, this application improves the traditional hippopotamus optimization algorithm, and determines the optimal solution of the data decomposition algorithm based on the improved hippopotamus optimization algorithm, so as to avoid the problem of difficultly finding the optimal solution when using the traditional hippopotamus optimization algorithm for optimization.

[0166] Step S2250, update the initial position of the hippopotamus individual to the updated position of the hippopotamus individual, and repeat the fitness value determination step until the hippopotamus population iteration cut-off condition is reached.

[0167] In an embodiment of this application, the hippopotamus population iteration cut-off condition includes: repeating the fitness value determination step until the hippopotamus population iteration times are reached.

[0168] Alternatively, the hippopotamus population iteration cut-off condition includes: the error between the reconstructed data corresponding to the k sub-modal components and the historical pose sequence is less than a preset error.

[0169] In an embodiment of this application, the error between the reconstructed data corresponding to the k sub-modal components and the historical pose sequence can be represented according to the Euclidean distance between the two. Among them, the preset error can be set according to experience.

[0170] In this embodiment, after updating the initial position of the hippopotamus individual to the updated position of the hippopotamus individual, repeat the above step S2200 until repeating the above step S2200 reaches the hippopotamus population iteration cut-off condition.

[0171] After updating the initial position of the hippopotamus individual to the updated position of the hippopotamus individual, at this time, when repeating the above step S2220, after step S2220, the parameter value of the data decomposition algorithm is specifically the parameter value of the data decomposition algorithm represented by the updated position. That is, the specific value of k has changed.

[0172] Step S2260, output the k sub-modal components corresponding to the optimal current individual fitness value among the currently obtained current individual fitness values of the hippopotamus individuals as the k' sub-modal components corresponding to the historical pose sequence.

[0173] In this embodiment, among the current individual fitness values of the latest obtained hippopotamus individuals, the optimal current individual fitness value, and the position of the corresponding hippopotamus individual, which is also the parameter value of the data decomposition algorithm, is the optimal solution. When the data decomposition algorithm is the VMD algorithm and the position of the hippopotamus individual is the k value and the alpha value in the VMD algorithm, the aforementioned optimal solution is the optimal k value and alpha value in the VMD algorithm. That is to say, in this application, the k value and alpha value in the VMD algorithm are determined by the improved hippopotamus algorithm, which is different from the traditional technology of setting according to experience.

[0174] Therefore, among the current individual fitness values of the latest obtained hippopotamus individuals, the k sub-modal components corresponding to the optimal current individual fitness value are the optimal decomposition result k' sub-modal components corresponding to the historical pose sequence.

[0175] Based on the above, in this application, for the historical pose sequence, the improved hippopotamus optimization algorithm can be used to determine the k sub-modal components corresponding to the optimal current individual fitness value when the hippopotamus population iteration cutoff condition is reached. Since the position of the hippopotamus individual corresponding to the optimal current individual fitness value when the hippopotamus population iteration cutoff condition is reached is the optimal solution of the parameter value of the data decomposition algorithm, therefore, the k sub-modal components corresponding to the optimal current individual fitness value when the hippopotamus population iteration cutoff condition is reached are the accurate result k' sub-modal components of the historical pose sequence. That is to say, when the data decomposition algorithm is the VMD algorithm, the above steps S2210 to S2260 can determine the optimal k value and alpha value in the VMD algorithm through the improved hippopotamus algorithm, thereby realizing the accurate decomposition of the historical pose sequence.

[0176] In an embodiment of this application, the above step S2240 is specifically implemented through the following steps S2241 to S2243.

[0177] Step S2241, when the current relative speed change rate of the hippopotamus individual is greater than the preset change rate, update the initial position of the hippopotamus individual according to the position update method in the first exploration stage of the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual.

[0178] In this embodiment, the preset change rate Rate1 represents the critical value of the current relative speed change rate in the first exploration stage and the second exploration stage, and the preset change rate can be set according to experience. In one example, the value of the preset change rate can be 1.

[0179] And, the updated intermediate position of the hippopotamus individual is an intermediate quantity in a population iteration process and awaits further update through the following step S2430.

[0180] The traditional hippopotamus optimization algorithm includes two exploration phases, namely Exploration Phase 1 and Exploration Phase 2. In this embodiment, Exploration Phase 1 is denoted as the First Exploration Phase, and Exploration Phase 2 is denoted as the Second Exploration Phase.

[0181] In an embodiment of the present application, the position update method in the first exploration phase of the traditional hippopotamus optimization algorithm is specifically as shown in Formula Nine below. That is, when the current relative speed change rate Rate is greater than the preset change rate Rate1, the initial position of the hippopotamus individual is updated through Formula Nine below.

[0182] X_P1(i,:) = X(i,:) + r2 × (D hippo - I1X(i,:)) (Formula Nine)

[0183] Among them, X_P1(i,:) represents the updated intermediate position of the i-th hippopotamus individual when the current relative speed change rate of the hippopotamus individual is greater than the preset change rate; X(i,:) represents the current initial position to be updated of the i-th hippopotamus individual, r2 represents a random number in the interval [0, 1]; D hippo represents the initial position of the current optimal hippopotamus individual, that is, the initial position of the hippopotamus individual corresponding to the current optimal current individual fitness value; I1 represents a random number in the interval [1, 2].

[0184] In an embodiment of the present application, the above step S2241 can also be specifically implemented through the following steps S2241-1 to S2241-3.

[0185] Step S2241-1: Determine the adaptive weight of the hippopotamus individual according to the current individual fitness value of each hippopotamus individual.

[0186] In an embodiment of the present application, the adaptive weight of any hippopotamus individual can be specifically determined through the following Formula Ten.

[0187]

[0188] Among them, f represents the current individual fitness value of the hippopotamus individual; f avg represents the average value of the current individual fitness values of all hippopotamus individuals; f min represents the minimum value of the current individual fitness values of all hippopotamus individuals; f max represents the maximum value of the current individual fitness values of all hippopotamus individuals; ω min represents the minimum weight; ω max represents the maximum weight; a represents an adjustable parameter; ω represents the adaptive weight of the hippopotamus individual.

[0189] It should be noted that different values of a result in different value ranges of tanh. For example, in this embodiment, when a takes different values, the values of the tanh function are as Figure 5 shown. Based on Figure 5 it can be seen that the larger the value of a, the faster the change rate of tanh. Therefore, in this embodiment, the value rule of a is when taking the maximum value, tanh converges, that is, tanh approaches 1.

[0190] Based on the above formula ten, it can be realized that when the adaptive weight is relatively large, the global search ability of the algorithm is strong, and when the adaptive weight is relatively small, the algorithm can perform fine search around the optimal solution to accelerate the convergence rate. In this embodiment, when the current relative speed change rate of the hippopotamus individual is greater than the preset change rate, the adaptive weight is determined according to the current individual fitness value of the hippopotamus individual to adjust the global search and local exploration capabilities. If the current individual adaptive fitness value of the hippopotamus individual is lower than the average value of the current individual fitness values of all hippopotamus individuals, the adaptive fitness weight value increases to enhance the global exploration ability. If the current individual fitness value of the hippopotamus individual is higher than the average value of the current individual fitness values of all hippopotamus individuals, the adaptive fitness weight decreases to enhance the local exploration ability.

[0191] Step S2241-2: According to the adaptive weight, update the position update formula in the first exploration stage of the hippopotamus optimization algorithm to obtain the updated position update formula in the first exploration stage.

[0192] In this embodiment, the above step S2241-2 can be specifically implemented by the following formula eleven.

[0193] X_P1(i,:)=ω(t)×X(i,:)+r2×(D hippo -I1X(i,:)) (Formula eleven)

[0194] where, w(t) represents the adaptive weight when repeating the above step S2200 for the current number of times.

[0195] Step S2241-3: According to the updated position update formula in the first exploration stage, update the initial position of the hippopotamus individual and the updated intermediate position of the hippopotamus individual.

[0196] Step S2242: When the current relative speed change rate of the hippopotamus individual is less than or equal to the preset change rate, update the initial position of the hippopotamus individual according to the position update formula in the second exploration stage of the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual.

[0197] In this embodiment, the position update formula in the second exploration stage of the hippopotamus optimization algorithm is as shown in Formula XII below. That is, when the current relative speed change rate Rate is less than or equal to the preset change rate Rate1, the initial position of the hippopotamus individual is updated by Formula XII below.

[0198]

[0199] Among them, X_P2(i,:) represents the updated intermediate position of the i-th hippopotamus individual when the current relative speed change rate of the hippopotamus individual is less than or equal to the preset change rate; r3 represents a random number in the interval [-1, 1]; b, c, d, and g are all uniformly distributed random numbers, the value range of b is [2, 4], the value range of c is [1, 1.5], the value range of d is [2, 3], and the value range of g is [2, 4]; Predator j represents the position of the predator in the search space, which is a random position. The specific value-taking method can refer to the traditional hippopotamus optimization algorithm; represents the factor for the hippopotamus to take defensive behavior to protect itself from predator attacks. The specific value-taking method can refer to the traditional hippopotamus optimization algorithm; F i represents the objective function value. The specific value-taking method can refer to the traditional hippopotamus optimization algorithm; represents a random vector with Levy distribution, which is used to describe the position mutation of the predator when attacking the hippopotamus. The specific value-taking method can refer to the traditional hippopotamus optimization algorithm.

[0200] Step S2243: For any hippopotamus individual, update the updated intermediate position of the hippopotamus individual according to the position update formula in the exploitation stage of the hippopotamus optimization algorithm to obtain the updated position of the hippopotamus individual.

[0201] The position update formula in the exploitation stage of the hippopotamus optimization algorithm is as shown in Formula XIII below. That is, on the basis of the above steps S2241 and S2242, for the updated intermediate position of each hippopotamus individual, it is continuously updated by Formula XIII below.

[0202]

[0203] Among them, X_P3(i,:) represents the updated position of the i-th hippopotamus individual; r4 represents a random number in the interval [0, 1]; r5 represents a random number conforming to the normal distribution.

[0204] It should be noted that the above steps S2241 to S2243 belong to the complete update of the position of the hippopotamus individual, that is, it belongs to a complete iteration of the hippopotamus population.

[0205] For the position update method of the hippopotamus individuals shown in the above steps S2241 to S2243, compared with the traditional hippopotamus optimization algorithm, in this embodiment, instead of grouping and updating positions according to the order of hippopotamus individuals as in the traditional hippopotamus algorithm, the position is updated depending on the current relative speed change rate of each hippopotamus individual. On this basis, the problem that it is difficult to find the optimal k value and alpha value of the VMD algorithm using the traditional hippopotamus optimization algorithm can be avoided.

[0206] This application also provides a pose prediction device 600, as Figure 6 shown, the device 600 includes:

[0207] An acquisition module 610, configured to acquire a historical pose sequence, where the historical pose sequence includes a plurality of historical pose data arranged in time sequence;

[0208] A decomposition module 620, configured to decompose the historical pose sequence according to a data decomposition algorithm to obtain k' sub-modal components corresponding to the historical pose sequence;

[0209] A generation module 630, configured to generate a pose prediction subsequence for any sub-modal component according to the pose prediction model corresponding to the sub-modal component;

[0210] A fusion module 640, configured to fuse the pose prediction subsequences corresponding to the k' sub-modal components according to a fusion model to obtain a pose prediction sequence.

[0211] In an embodiment of the present application, the decomposition module 620 is specifically configured to: acquire the number of hippopotamus individuals in the hippopotamus population and the iteration cut-off condition of the hippopotamus population;

[0212] For any hippopotamus individual, execute a fitness value determination step to obtain the current individual fitness value of the hippopotamus individual. The fitness value determination step includes: determining a data decomposition algorithm according to the initial position of the hippopotamus individual, determining k sub-modal components for the historical pose sequence according to the data decomposition algorithm, and determining the current individual fitness value of the hippopotamus individual according to the k sub-modal components. The initial position of the hippopotamus individual is used to represent the parameter value of the data decomposition algorithm, and the parameter value includes at least k;

[0213] Determine the current relative speed change rate of the hippopotamus individual according to the current individual fitness value of the hippopotamus individual and the number of times of repeating the fitness value determination step;

[0214] Update the initial position of the hippopotamus individual according to the current relative speed change rate of the hippopotamus individual to obtain the updated position of the hippopotamus individual;

[0215] Update the initial position of the hippopotamus individual to the updated position of the hippopotamus individual, and repeat the step of determining the fitness value until the iteration cut-off condition of the hippopotamus population is reached;

[0216] Output the k sub-modal components corresponding to the optimal current individual fitness value among the current individual fitness values of the latest obtained hippopotamus individual as the k' sub-modal components corresponding to the historical pose sequence.

[0217] In an embodiment of the present application, the iteration cut-off condition of the hippopotamus population includes:

[0218] Repeat the step of determining the fitness value until the iteration number of the hippopotamus population is reached;

[0219] Or, the error between the reconstructed data corresponding to the k sub-modal components and the historical pose sequence is less than a preset error.

[0220] In an embodiment of the present application, the decomposition module 620 is specifically configured to: determine reconstructed data according to the k sub-modal components;

[0221] Determine the Euclidean distance between the reconstructed data and the historical pose sequence as the current individual fitness value of the hippopotamus individual;

[0222] Or, determine the sum of the fuzzy entropies corresponding to the k sub-modal components according to the k sub-modal components, and determine the sum of the fuzzy entropies as the current individual fitness value of the hippopotamus individual.

[0223] In an embodiment of the present application, the decomposition module 620 is further configured to: determine the random mapping value of the hippopotamus individual according to a random mapping;

[0224] Determine the chaotic mapping value of the hippopotamus individual according to the random mapping value and a chaotic mapping;

[0225] Determine the initial position of the hippopotamus individual according to the chaotic mapping value of the hippopotamus individual and the initial position constraint condition of the hippopotamus individual.

[0226] In an embodiment of the present application, the decomposition module 620 is specifically configured to: when the number of times of repeating the step of determining the fitness value is 0, determine that the current relative speed change rate of the hippopotamus individual is infinite;

[0227] When the number of times of repeating the step of determining the fitness value is greater than 0, determine the current optimal fitness value according to the current individual fitness value of each hippopotamus individual;

[0228] Determine the historical optimal fitness value according to the historical fitness values obtained for each of the hippopotamus individuals in the previous execution of the fitness value determination step;

[0229] Obtain the historical individual fitness value obtained for the hippopotamus individual in the previous execution of the fitness value determination step;

[0230] Determine the current relative speed change rate of the hippopotamus individual according to the historical individual fitness value, the current individual fitness value, the historical optimal fitness value, and the current optimal fitness value.

[0231] In an embodiment of the present application, the decomposition module 620 is specifically configured to: in the case where the current relative speed change rate of the hippopotamus individual is greater than the preset change rate, update the updated intermediate position of the hippopotamus individual according to the position update method in the first exploration stage of the hippopotamus optimization algorithm to obtain the updated position of the hippopotamus individual;

[0232] In the case where the current relative speed change rate of the hippopotamus individual is less than or equal to the preset change rate, update the initial position of the hippopotamus individual according to the position update method in the second exploration stage of the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual;

[0233] For any one of the hippopotamus individuals, update the updated intermediate position of the hippopotamus individual according to the position update method in the exploitation stage of the hippopotamus optimization algorithm to obtain the updated position of the hippopotamus individual.

[0234] In an embodiment of the present application, the decomposition module 620 is specifically configured to: determine the adaptive weight of the hippopotamus individual according to the current individual fitness value of each hippopotamus individual;

[0235] Update the position update formula in the first exploration stage of the hippopotamus optimization algorithm according to the adaptive weight to obtain the updated position update method in the first exploration stage;

[0236] Update the initial position and the updated intermediate position of the hippopotamus individual according to the updated position update method in the first exploration stage.

[0237] The present application also provides an electronic device, and the electronic device includes any one of the pose prediction devices 600 provided in the above device embodiment.

[0238] Or, as Figure 7 shown, the electronic device 700 includes a memory 710 and a processor 720. The memory 710 is used to store computer instructions, and the processor 720 is used to call the computer instructions from the memory 710 to execute any one of the pose prediction methods provided in the above method embodiment.

[0239] The present application also provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements any one of the pose prediction methods provided in the above method embodiments.

[0240] The present application may be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for causing a processor to implement various aspects of the present application.

[0241] A computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: 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), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or raised structures in a groove having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not construed as being a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0242] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to respective computing / processing devices, or may be downloaded to an external computer or an external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. A network adapter or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0243] The computer program instructions for performing the operations of the present application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may 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 may 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 may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present application.

[0244] Aspects of the present application are described herein with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer - readable program instructions.

[0245] These computer - readable program instructions can be provided to a processor of a general - purpose computer, a special - purpose computer, or other programmable data - processing device, thereby producing a machine such that when these instructions are executed by the processor of the computer or other programmable data - processing device, a device is produced that implements the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, and these instructions cause the computer, programmable data - processing device, and / or other devices to work in a particular manner. Thus, the computer - readable medium storing the instructions includes a manufacture, which includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0246] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process, such that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0247] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the boxes may occur in a different order than noted in the figures. For example, two consecutive boxes may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each box in the block diagrams and / or flowcharts, and combinations of boxes in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are equivalent.

[0248] The embodiments of the present application have been described above. The above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein. The scope of the present application is defined by the appended claims.

Claims

1. A posture prediction method, characterized in that: The method comprises: Acquire a historical posture sequence, wherein the historical posture sequence includes a plurality of historical posture data arranged in time sequence; Decomposing the historical posture sequence according to a data decomposition algorithm to obtain k' submodal components corresponding to the historical posture sequence; For any sub-modal component, generating a posture prediction sub-sequence according to the posture prediction model corresponding to the sub-modal component; The pose prediction subsequences corresponding to the k' sub-modal components are fused according to the fusion model to obtain a pose prediction sequence.

2. The method according to claim 1, characterized in that Decomposing the historical posture sequence according to the data decomposition algorithm to obtain k' submodal components corresponding to the historical posture sequence includes: Get the number of hippopotamus individuals in the hippopotamus population and the iteration cutoff condition of the hippopotamus population; For any hippopotamus individual, a fitness value determination step is performed to obtain a current individual fitness value of the hippopotamus individual, wherein the fitness value determination step comprises: determining a data decomposition algorithm according to an initial position of the hippopotamus individual, determining k submodal components for the historical posture sequence according to the data decomposition algorithm, and determining the current individual fitness value of the hippopotamus individual according to the k submodal components, wherein the initial position of the hippopotamus individual is used to characterize a parameter value of the data decomposition algorithm, and the parameter value at least includes k; Determine the current relative speed change rate of the hippopotamus individual according to the current individual fitness value of the hippopotamus individual and the number of times the fitness value determination step is repeated; According to the current relative speed change rate of the hippopotamus individual, the initial position of the hippopotamus individual is updated to obtain the updated position of the hippopotamus individual; Updating the initial position of the hippopotamus individual to the updated position of the hippopotamus individual, and repeating the fitness value determination step until the hippopotamus population iteration cutoff condition is reached; The k submodal components corresponding to the best current individual fitness value among the latest obtained current individual fitness values ​​of the hippopotamus individual are output as the k' submodal components corresponding to the historical posture sequence.

3. The method according to claim 2, characterized in that The hippo population iteration cutoff conditions include: Repeat the fitness value determination step until the number of hippo population iterations is reached; Alternatively, the error between the reconstructed data corresponding to the k sub-modal components and the historical posture sequence is less than a preset error.

4. The method according to claim 2, characterized in that: Determining the current individual fitness value of the hippopotamus individual according to the k sub-modal components includes: Determining reconstructed data according to the k sub-modal components; Determine the Euclidean distance between the reconstructed data and the historical posture sequence as the current individual fitness value of the hippopotamus individual; Alternatively, based on the k sub-modal components, the sum of the fuzzy entropies corresponding to the k sub-modal components is determined, and the sum of the fuzzy entropies is determined as the current individual fitness value of the hippopotamus individual.

5. The method according to claim 2, characterized in that: Before determining the data decomposition algorithm according to the initial position of the hippopotamus individual, the method further comprises: According to the random mapping, determining the random mapping value of the hippopotamus individual; Determining the chaotic mapping value of the hippopotamus individual according to the random mapping value and the chaotic mapping; The initial position of the hippopotamus individual is determined according to the chaotic mapping value of the hippopotamus individual and the initial position constraint condition of the hippopotamus individual.

6. The method according to claim 2, characterized in that Determining the current relative speed change rate of the hippopotamus individual according to the current individual fitness value of the hippopotamus individual and the number of times the fitness value determination step is repeated includes: When the number of times the fitness value determination step is repeated is 0, determining that the current relative speed change rate of the hippopotamus individual is infinite; When the number of times the fitness value determination step is repeated is greater than 0, determining the current optimal fitness value according to the current individual fitness value of each of the hippopotamus individuals; Determine the historical optimal fitness value according to the historical fitness value obtained by performing the fitness value determination step for each hippopotamus individual last time; Obtaining a historical individual fitness value obtained by performing the fitness value determination step for the hippopotamus individual last time; The current relative speed change rate of the hippopotamus individual is determined according to the historical individual fitness value, the current individual fitness value, the historical optimal fitness value and the current optimal fitness value.

7. The method according to claim 2, characterized in that The updating of the initial position of the hippopotamus individual according to the current relative speed change rate of the hippopotamus individual to obtain the updated position of the hippopotamus individual includes: When the current relative speed change rate of the hippopotamus individual is greater than the preset change rate, the initial position of the hippopotamus individual is updated according to the position update method of the first exploration phase in the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual; When the current relative speed change rate of the hippopotamus individual is less than or equal to the preset change rate, the initial position of the hippopotamus individual is updated according to the position update method of the second exploration phase in the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual; For any of the hippopotamus individuals, the updated intermediate position of the hippopotamus individual is updated according to the position update method in the development phase of the hippopotamus optimization algorithm to obtain the updated position of the hippopotamus individual.

8. The method according to claim 7, characterized in that The method of updating the initial position of the hippopotamus individual according to the position update formula of the first exploration phase in the hippopotamus optimization algorithm to obtain the updated intermediate position of the hippopotamus individual includes: Determine the adaptive weight of each hippopotamus individual according to the current individual fitness value of the hippopotamus individual; According to the adaptive weight, updating the position update formula of the first exploration phase in the Hippo optimization algorithm to obtain an updated position update method of the first exploration phase; According to the updated position updating method of the first exploration phase, the initial position of the hippopotamus individual and the updated intermediate position of the hippopotamus individual are updated.

9. A posture prediction device, characterized in that: The device comprises: An acquisition module, used for acquiring a historical posture sequence, wherein the historical posture sequence includes a plurality of historical posture data arranged in time sequence; A decomposition module, used for decomposing the historical posture sequence according to a data decomposition algorithm to obtain k' submodal components corresponding to the historical posture sequence; A generation module, for generating a posture prediction subsequence for any submodal component according to a posture prediction model corresponding to the submodal component; The fusion module is used to fuse the posture prediction subsequences corresponding to the k' sub-modal components according to the fusion model to obtain a posture prediction sequence.

10. An electronic device, characterized in that: The electronic device comprises the apparatus as claimed in claim 9; Alternatively, the electronic device includes a memory and a processor, the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method as described in any one of claims 1-8.

Images