114 results about "Algorithm complexity" patented technology

A method for estimating typhoon structural parameters by fusing spaceborne GNSS reflectometer data and radiometer data, which relates to the technical fields of data fusion and typhoon monitoring. The method comprises: acquiring GNSS-R reflectometer data and radiometer data; filtering typhoon data from the GNSS-R reflectometer data and the radiometer data to obtain filtered GNSS-R reflectometer data and radiometer data; performing data spatio-temporal matching on the filtered GNSS-R reflectometer data and radiometer data to obtain a spatio-temporally matched region; performing data fusion processing on the spatio-temporally matched region to obtain fused data; and performing typhoon structural parameter estimation on the obtained fused data to obtain structural parameters of a typhoon at each development stage. Fused data of spaceborne GNSS-R reflectometer data and radiometer data is used for typhoon structural parameter estimation, such that the temporal resolution and accuracy of parameter estimation can be improved, and the algorithm complexity is low.

The invention discloses a feature recognition and path planning method for point cloud three-dimensional-two-dimensional-three-dimensional conversion of a curved-surface workpiece, and the method comprises the steps: obtaining three-dimensional point cloud data of the curved-surface workpiece, and carrying out the preprocessing of the three-dimensional point cloud data; projecting and converting the preprocessed three-dimensional point cloud data into two-dimensional point cloud data by adopting a slice projection method, and forming a fitting curve based on the two-dimensional point cloud data; identifying and obtaining a two-dimensional inflection point set meeting the requirement by a curve inflection point detection method based on an angle integral window; converting the two-dimensional inflection point set back to a three-dimensional coordinate space; adopting a two-stage fitting strategy to identify and obtain an optimal fitting plane from the three-dimensional inflection point set; and a plane cutting method is adopted to obtain a planned path for actual machining. According to the method, a complicated point cloud feature extraction problem is converted into a two-dimensional analysis problem with higher calculation efficiency, so that the algorithm complexity is reduced; the problem of low feature extraction accuracy in a noise environment is effectively solved; the robustness under the condition that the outliers exist is enhanced; an intermediate link of CAD modeling in a traditional method is avoided, and accumulative errors are reduced.

The invention relates to the technical field of cable manufacturing, in particular to a full-line automatic linkage cable production method and system, and the method comprises the steps: carrying out the data collection of the operation data of a plurality of process nodes on a cable automatic production line; performing extreme value feature extraction on the operation data to construct a minimum value feature array and a maximum value feature array; whether synchronization abnormity occurs or not is judged in real time according to the minimum value feature array and the maximum value feature array, and if the synchronization abnormity occurs, dispatching control is conducted on the cable automatic production line to eliminate the synchronization abnormity; according to the method, whether synchronization abnormity exists or not can be rapidly judged with the minimum computing power, linear speed deviation caused by process slowdown can be rapidly recognized, the algorithm complexity is low, the duration of the synchronization abnormity can be accurately recognized, the recognition precision of the synchronization abnormity under the condition that the duration of the ascending time period and the descending time period is short is improved, and the recognition efficiency of the synchronization abnormity is improved. And the problem of cable product quality caused by rapid accumulation of linear velocity deviation is avoided.

The invention discloses a high-resolution tomographic SAR four-dimensional imaging method for space-time baseline decoupling processing, and the method comprises the following steps: 1, reconstructing original satellite data into uniform baseline observation data, and solving the noise-free estimation of the uniform baseline observation data through the low-rank characteristic of a Hankel matrix; step 2, inverting elevation information based on noise-free estimation, taking the elevation information as priori, constructing a deformation spectrum estimation dictionary through space-time decoupling, and performing deformation information estimation; and step 3, matching the estimated elevation and deformation quantity by using a maximum likelihood method so as to realize four-dimensional imaging. According to the method, the algorithm complexity of four-dimensional imaging is reduced exponentially while high-precision imaging is realized, and differential tomography SAR four-dimensional imaging result verification is carried out based on domestic land exploration No.1 satellite data.

The application discloses a kind of high-resolution tomography SAR four-dimensional imaging methods of space-time baseline decoupling processing, which comprises the following steps: step 1, reconstruct original satellite data into uniform baseline observation data, and utilize the low rank characteristic of Hankel matrix, solve its noiseless estimation;Step 2, elevation information is inverted based on noiseless estimation, and elevation information is used as priori, deformation spectrum estimation dictionary is constructed by space-time decoupling, and deformation information estimation is carried out;Step 3, the elevation and deformation variable estimated are matched using maximum likelihood method to realize four-dimensional imaging.The method realizes high-precision imaging while exponentially reducing the algorithm complexity of four-dimensional imaging, and the differential tomography SAR four-dimensional imaging result verification is carried out based on domestic land exploration No.1 satellite data.

The invention is suitable for the field of computer vision and artificial intelligence, and provides an automatic target detection and tracking method and system based on deep learning, and the method comprises the steps: obtaining a video stream and a scene structure diagram, extracting a target position bounding box, a category label and an appearance feature vector frame by frame, and calculating a behavior parameter and a priority score; generating a detection frame interval and a tracking algorithm complexity parameter according to the priority score, and initializing a special tracker to realize automatic tracking; when the target is lost, generating a space-time probability graph based on historical data and the scene structure graph; determining retrieval parameters according to the priority scores, and performing directional detection on the screened space-time regions; and after the target is retrieved, the identity is associated and parameters are redistributed to recover tracking. According to the method, through differentiated resource allocation, accurate loss prediction and directional retrieval, tracking precision, efficiency and robustness are considered, and the problems of target tracking interruption, resource waste and the like in a complex scene are effectively solved.

The invention discloses a channel estimation method of a time-varying channel in a time delay-Doppler domain pilot mode, which comprises the following steps of: superimposing a hybrid superimposed pilot and a data symbol in a time delay-Doppler domain, the pilot comprising a high-power center pilot and a low-power edge pilot; the signal is converted to a time domain through inverse symplectic Fourier transform and Hisenberg transform; a receiving end obtains a receiving signal through Wigner transform and Sextile Fourier transform; estimating integer time delay and Doppler taps by using a center pilot frequency, and constructing a sparse channel matrix; estimating fractional Doppler and channel gain through a sparse Bayesian learning algorithm; and detecting a data symbol based on a minimum root-mean-square error algorithm, and realizing accurate estimation of channel parameters through iterative interference elimination. According to the method, the peak-to-average power ratio and the algorithm complexity can be effectively reduced, and non-correlation channel components and cross interference are inhibited.

The invention discloses a self-adaptive task priority management method based on a dynamic entropy weight and a time decay factor, and relates to the technical field of computer task scheduling and resource allocation. The method comprises the following steps: acquiring a to-be-processed task set and constructing a multi-dimensional feature matrix, dividing features into benefit type indexes and cost type indexes, and respectively carrying out same-direction standardization processing on data by adopting forward and reverse normalization formulas; calculating entropy values and difference coefficients of the characteristic indexes in real time based on an information entropy theory, determining dynamic weights reflecting current task flow characteristic distribution, and calculating static basic scores of the tasks; introducing an exponential time decay model containing a natural constant and a time sensitive coefficient, performing nonlinear acceleration compensation on the static basic score according to the queue residence time of the task, and generating a final dynamic priority index; and screening the task corresponding to the maximum value according to the index to preferentially allocate computing resources. According to the method, the blindness of manual weighting can be eliminated, the hunger and deadlock problems of low-priority tasks are effectively solved through an exponential-level time compensation mechanism, and the method has the advantages of low algorithm complexity, high environment adaptability, high scheduling fairness and the like.

The demodulation method based on the ultra-weak fiber grating OFDR includes: performing fast Fourier transform on the time domain reflection signal collected by the OFDR system to obtain a frequency domain spectrum; setting an amplitude threshold, identifying the UW-FBG array reflection peak in the frequency domain spectrum, calibrating the spatial position of the sensing unit, and intercepting the window segment spectrum signal corresponding to each UW-FBG; performing inverse Fourier transform on the intercepted window segment spectrum signal to restore the spectrum signal of a single UW-FBG; for the reconstructed spectrum signal, selecting a fitting region containing the Bragg reflection peak, iteratively optimizing the Gaussian function fitting parameters by the least square method, and demodulating the peak Bragg wavelength; traversing the window segment spectrum signals of all UW-FBGs and repeating the above steps to obtain the Bragg wavelength shift distribution of the whole sensing region. The demodulation method based on the ultra-weak fiber grating OFDR improves the high-precision detection characteristics of the OFDR, realizes dynamic demodulation, significantly improves the sensing demodulation rate, and simplifies the algorithm complexity.

The invention relates to the technical field of wireless communication and signal processing, particularly discloses an efficient implementation method related to a frequency domain of a micro-frequency-hopping symbol, and aims to solve the problem of high demodulation calculation complexity related to the frequency domain when the length of the micro-frequency-hopping symbol is a prime number P. The method comprises the following steps of: decomposing a time domain point multiplication signal of which the length is prime number P into a zero point signal and a P-1 point out-of-order time domain point multiplication signal of which the length is non-prime number length, converting the P-1 point out-of-order time domain point multiplication signal into a frequency domain, performing rotation compensation in the frequency domain, performing secondary Fourier transform, and performing compensation by using the zero point signal and performing re-order; and finally, combining with the direct-current component to obtain a final frequency domain related signal. By using the method, the algorithm complexity is reduced from O (P * P) related to a direct frequency domain to 2 * O ((P-1) * nFactor) (wherein nFactor is the number of prime factors of P-1), and the calculated amount is reduced by dozens of times to hundreds of times.

The invention discloses an aircraft model identification method based on point cloud data. The method comprises the following steps: acquiring a three-dimensional point cloud and a two-dimensional Obtaining an aircraft source point cloud only containing an aircraft; dividing the aircraft source point cloud into an aircraft head point cloud and an aircraft body point cloud; obtaining a main plane and a vertical plane; engine spacing, rear wheel spacing, front and rear wheel spacing and nose front wheel spacing of the aircraft are calculated; and judging the aircraft type of the to-be-tested aircraft in combination with the standard aircraft type parameter library. By processing and analyzing the point cloud data of the airplane, the key characteristic parameters of the airplane can be accurately extracted, the problem of non-uniform distribution of the point cloud data acquired by a laser radar in the prior art is solved, the accuracy and stability of airplane type identification are effectively improved, and the method is suitable for popularization and application. Especially, aircraft targets with complex outlines can be stably captured. The method is simple in structure and low in algorithm complexity, does not need a complex deep learning model, reduces the requirement for the computing power of equipment, improves the detection speed, and improves the practicability of the system.

The invention discloses a teaching quality evaluation model construction method and a teaching quality evaluation system. The evaluation model construction method comprises the following steps: constructing an index system including four dimensions of teaching objectives, contents, methods and evaluation; evaluation of peers, students and supervisors is integrated, and course teaching direct quality is calculated through fuzzy comprehensive evaluation. Calculating the course teaching quality of the teaching team by taking the course score as a weight; the course teaching direct quality and the teaching team course teaching quality are combined, the course influence degree is calculated through the weighted Euclidean distance, and a course teaching indirect quality evaluation model is constructed; and when the evaluation results are the same, an elastic close degree mechanism is introduced to carry out fine sorting. According to the method, course teaching indirect quality indexes are introduced, and individual evaluation and team evaluation are effectively fused; an elastic close degree mechanism is introduced, so that the distinguishing capability under the same grade is improved; a multi-source evaluation integration model is constructed, and evaluation objectivity and accuracy are improved; the method is low in algorithm complexity and suitable for large-scale course evaluation scenes.

The method comprises the following steps: S1, envelope extraction is performed on the received satellite ADS-B overlapping signal to obtain an envelope signal; S2, Hilbert transform is performed on the envelope signal to obtain overlapping IQ complex data; S3, the IQ complex data is input into a complex neural network for overlapping signal separation to obtain separated IQ signals; S4, the data bits of the separated IQ signals are subjected to PPM decoding and then CRC checking; and S5, the separated correct signals are stored according to the checking result. The envelope signal is extracted by using an empirical formula, the calculation amount is reduced, and the separation efficiency is improved; the overlapping signal is separated by using a complex neural network, the separation accuracy is high, the separated signal response time is fast, and the engineering realizability is strong, so that the problems of high algorithm complexity, long time consumption and low separation efficiency of the traditional separation method are solved.

The application discloses a kind of network intrusion detection identification deep learning method, device, storage medium and computer equipment, this method uses Concise-former neural network model based on the improvement of Transformer model, convolution gate self-attention layer is introduced in encoder module, to enhance the mining of local dependence in sequence data for encoder module, further strengthen the expression ability and generalization ability of network, improve the accuracy and stability of intrusion detection, by simplifying network, reduce the algorithm complexity of model, improve the calculation efficiency of model.In addition, the method of the application also uses joint learning to train neural network, so as to greatly improve the calculation speed of the model and reduce the memory consumption under the condition of ensuring accuracy, improve the practicability and flexibility of intrusion detection.Therefore, the present application can effectively detect various types of network intrusion.

The invention discloses an energy efficiency self-adaptive regulation and control device and method for frequency spectrum detection equipment, and relates to the technical field of radio frequency spectrum monitoring. The device comprises a dynamic sleep wake-up module, an energy efficiency self-adaptive adjustment module, a task priority management module and a feedback optimization module, during standby, environment radio frequency signals are sampled at a low rate, intensity, bandwidth and period characteristics are extracted, and a wake-up threshold is dynamically adjusted based on target characteristic judgment and noise and leak detection to trigger wake-up; during working, the gain, the sampling rate, the quantization precision and the algorithm complexity are jointly adjusted according to task requirements and energy efficiency constraints, and a performance accepting and rejecting instruction is generated according to task priorities when resources are limited; and collecting detection, power consumption and performance data in an idle state, and updating a wake-up threshold value and operation parameters for a next period through reinforcement learning or regression analysis. By means of the device and method, invalid wakeup can be restrained, the missing detection risk can be reduced, and self-adaptive balance of energy efficiency and task performance is achieved.

The invention discloses a small target detection method based on a time-space domain recursive network. The method comprises the following steps: step 1, preprocessing image data as input data; 2, constructing a spatial-temporal feature extraction backbone network, inputting the input data into the backbone network, and generating feature maps of four stages; 3, constructing a time domain recursion module, and generating a fused spatial-temporal feature based on the feature map of the third stage; and step 4, constructing a lightweight detection head, constructing multi-scale features based on the spatial-temporal features and the feature maps of the other three stages, and outputting a classification result and bounding box coordinates through the lightweight detection head. The method has high detection precision, and the spatial-temporal feature fusion effectively enhances a target signal and inhibits background interference. The method is suitable for a static platform and a motion platform, does not need complex inter-frame registration, and has no strict constraint on a target motion mode; and meanwhile, the algorithm complexity is low, a fixed weight convolution kernel or a lightweight network can be adopted, and hardware implementation is facilitated.

The application relates to the technical field of image processing, and particularly provides a dark and weak small target detection and centroid positioning method for large-size infrared images, which comprises the following steps: pre-processing a large-size and low signal-to-noise ratio infrared image, reducing the influence of noise in the picture by random cutting, obtaining image block 1, image block 2... and image block N which meet the requirements of a down-sampling rate and a size; improving a U-net network and designing a backbone feature extraction network to obtain a multi-branch feature extraction network, performing feature extraction on the cut image blocks, and obtaining a feature map with high semantic and detailed information; designing a centroid positioning network, inputting the feature map, determining centroid coordinates by using the centroid positioning network, and designing a loss function; and the method has the advantages of high centroid accuracy, high robustness, low calculation amount and low algorithm complexity.

The invention discloses a motor driving system open-circuit fault diagnosis method, which can eliminate the influence of load fluctuation and controller adjustment on a fault current track. According to the method, 1-norm of a three-phase current instantaneous value is taken as a reference value, a stator current is standardized, and a current contribution degree and a current deviation degree are further defined; and then, analyzing the change trend of three-phase current contribution degree and deviation degree characteristics in healthy and fault states, and on the basis, designing a power device open-circuit fault diagnosis algorithm based on the stator current contribution degree. According to the method, high robustness and high generalization ability are shown in the face of controller adjusting effect influence and load fluctuation, and the method has low algorithm complexity and high diagnosis speed; finally, the effectiveness of the method in the open-circuit fault diagnosis of the motor driving system is verified through experiments.

The invention provides an image definition evaluation method, device and equipment, and the method comprises the steps: dividing an image into different confidence regions according to the local features of different positions in the image, and enabling the local features to be used for evaluating the confidence of the definition of the corresponding position to the real resolution, the local features comprise local frequency domain features and local time domain features; respectively segmenting the different confidence regions obtained by division into a preset number of confidence sub-regions; respectively carrying out definition detection on each confidence coefficient sub-region to obtain the definition of each confidence coefficient sub-region; and calculating the definition of the image by using a fusion algorithm based on the definition of each confidence coefficient sub-region. By means of the image definition evaluation method and device, in the image definition evaluation process, the algorithm complexity can be reduced, and meanwhile high accuracy is achieved.

The application discloses a kind of processing method and device of 3D printing path.It includes: control 3D printer to start point as start point;Determine the printing point to be printed that 3D printer needs to execute printing action in the process of executing 3D printing job based on the region surrounded between start point and reference point;The start point and the printing point to be printed are sequentially connected by smooth straight line, and the printing path is generated;3D printer is controlled based on printing path to execute 3D printing job to obtain target object, so as to effectively reduce the number of line segments of slice profile line of three-dimensional model forming target object, avoid the pause frequency of 3D printer at the beginning and end of line segment in printing job, and simultaneously avoid the problem that long time energy radiation 3D printing model surface protrusion is caused due to pause.In reducing pause frequency, printing is more smooth, printing efficiency is improved, algorithm complexity is also reduced, which is helpful to algorithm simplification, and effectively simplifies the algorithm of 3D printer.

The application discloses a kind of processing method and device of 3D printing path.It includes: control 3D printer to start point as start point;Determine the printing point to be printed that 3D printer needs to execute printing action in the process of executing 3D printing job based on the region surrounded between start point and reference point;The start point and the printing point to be printed are sequentially connected by smooth straight line, and the printing path is generated;3D printer is controlled based on printing path to execute 3D printing job to obtain target object, so as to effectively reduce the number of line segments of slice profile line of three-dimensional model forming target object, avoid the pause frequency of 3D printer at the beginning and end of line segment in printing job, and simultaneously avoid the problem that long time energy radiation 3D printing model surface protrusion is caused due to pause.In reducing pause frequency, printing is more smooth, printing efficiency is improved, algorithm complexity is also reduced, which is helpful to algorithm simplification, and effectively simplifies the algorithm of 3D printer.

A method and apparatus for super-resolution localization of multiple targets using frequency-modulated continuous wave radar includes: determining the number K of targets based on the number of eigenvalues ​​satisfying a condition in the covariance matrix of the acquired radar array signal; finding the frequency values ​​corresponding to the K largest spectral peaks based on the acquired number of targets K, using these frequency values ​​as coarsely estimated intermediate frequency (IF) values, and determining the final IF value using the coarsely estimated IF values; calculating the distance of the corresponding target relative to the center O of the antenna array based on the final IF value; obtaining the noise subspace of the array signal and the steering vector related to the target distance and angle based on the eigenvalues ​​of the covariance matrix of the array signal, constructing a MUSIC spectral function, and determining the estimated value of the target echo signal direction; and then determining the position of the corresponding target. This invention has higher range and angle resolution and lower algorithm complexity, enabling super-resolution localization of multiple targets.

The application discloses an energy efficiency adaptive regulation device and method for a spectrum detection device, and relates to the technical field of radio spectrum monitoring. The device comprises a dynamic sleep-wake module, an energy efficiency adaptive regulation module, a task priority management module and a feedback optimization module. When on standby, low-rate sampling of environmental radio frequency signals is performed, and intensity, bandwidth and periodicity characteristics are extracted. Based on target characteristic determination, noise and missed detection are dynamically adjusted to trigger wake-up. When working, gain, sampling rate, quantization accuracy and algorithm complexity are jointly adjusted according to task requirements and energy efficiency constraints, and performance trade-off instructions are generated according to task priority when resources are limited. When idle, detection, power consumption and performance data are collected, and wake-up threshold and operating parameters are updated for the next period through reinforcement learning or regression analysis. Through the device and method, invalid wake-up can be inhibited, the risk of missed detection can be reduced, and adaptive balance of energy efficiency and task performance can be achieved.

The invention relates to the technical field of frequency measurement, and discloses a short-wave carrier center frequency measurement method, which comprises the following steps: collecting short-wave signal data, and carrying out parallel processing to generate multi-domain feature representation; constructing a multi-scale time-frequency analysis framework by applying fractional order wavelet transform; fractal dimensions and self-similarity indexes of the signals are calculated, and geometric features are extracted; combining fractal features and noise type recognition results to optimize fractional order parameters; feature fusion is executed in a multi-domain multi-scale space, and enhanced frequency representation is constructed; accurately positioning the carrier center frequency by applying a hierarchical peak detection algorithm; according to the method, the accuracy and the reliability in the short-wave carrier are remarkably improved while the complexity of the algorithm is kept controllable, and particularly, the method has obvious advantages in a low signal-to-noise ratio and complex interference environment, so that powerful support is provided for improving the performance of a short-wave communication system.

This invention discloses a maneuvering target tracking method based on trajectory Poisson-Dobernal filtering. By fusing interactive multi-model and trajectory Poisson-Dobernal filtering methods, it achieves accurate tracking of maneuvering target trajectories. This invention fills a technological gap in the current field of maneuvering target tracking, providing an effective solution for achieving more accurate and real-time target tracking. This invention employs the Poisson-Dobernal approximation (PMB) concept, using KL divergence to obtain the Poisson-Dobernal components from the Poisson-Dobernal mixture components after filtering updates. This overcomes the computational complexity problem caused by the large number of Poisson-Dobernal mixture components in existing technologies, thus reducing algorithm complexity, improving filtering efficiency, and enhancing real-time filtering performance.

The invention discloses a storage space allocation method and device and storage device.The method comprises the steps that a node list comprising node identifiers, occupation information and idle capacity values of storage nodes is searched according to a preset search direction, and when the idle capacity values of target nodes are matched with the data size of data to be stored in the node list, the target nodes are allocated to the storage nodes; inserting a new storage node after the target node, updating the idle capacity value of the target node, and storing the to-be-stored data according to the initial address of the to-be-stored data. Therefore, according to the embodiment, the storage nodes and the storage areas corresponding to the storage nodes are managed through the node list, data storage and storage space allocation are achieved, the state of storage resources can be grasped globally, time and algorithm complexity during data storage are reduced, fragments are reduced, an existing dynamic continuous space management method is improved, and the dynamic continuous space management efficiency is improved. And the dynamic continuous space management effect is optimized.

The application belongs to the field of optics, in order to solve the problems of high demand for computer resources in the ADL optimization design process, low energy utilization rate of the optimization result, mapping eccentricity in the design and the like, a monolithic full-visible light imaging diffractive lens and a design method are provided. By setting an input plane wave matrix, a plane wave neural network imaging model passing through the ADL is constructed, a loss function is used as an optimization standard of the ADL surface microstructure, and a monolithic full-visible light imaging diffractive lens is designed by taking the PSF and the OTF as imaging constraint conditions of the ADL. The lens can image full-visible light, and the algorithm complexity of the current ADL design is reduced, and the defects existing in the design are solved.

The invention discloses a three-dimensional tangent point-passing route planning method based on hierarchical projection and sliding window geometric analysis. The method comprises the following steps: S1, unifying and initializing a coordinate system; s2, a three-element sliding window geometric solution algorithm is adopted to generate a two-dimensional optimal smooth path composed of straight line segments and arc segments; s3, converting the two-dimensional optimal smooth path to a three-dimensional geographic space; and S4, outputting the three-dimensional coordinate information of all the path points to an external visualization module. The method has the beneficial effects that a complicated three-dimensional problem is decomposed into low-dimensional two-dimensional geometric solution and height mapping by adopting a layering strategy of two-dimensional first and three-dimensional second, and a three-element sliding window is utilized to carry out iterative analysis on local elements, so that global large-scale optimization solution is avoided, the algorithm complexity is remarkably reduced, and the algorithm efficiency is improved. The planning process has high calculation efficiency, and the real-time or quasi-real-time route planning requirement can be met.

The application is suitable for the field of computer vision and artificial intelligence, and provides an automatic target detection and tracking method and system based on deep learning, which comprises the following steps: acquiring a video stream and a scene structure graph, extracting a target position bounding box, a category label and an appearance feature vector frame by frame, calculating a behavior parameter and a priority score; generating a detection frame interval and a tracking algorithm complexity parameter according to the priority score, and initializing a special tracker to realize automatic tracking; when the target is lost, generating a space-time probability graph based on historical data and the scene structure graph; determining a search parameter according to the priority score, and performing directional detection on the screened space-time region; after the target is found back, associating the identity and reassigning the parameter to restore the tracking. Through differentiated resource allocation, accurate loss prediction and directional recovery, the application takes into account the tracking accuracy, efficiency and robustness, and effectively solves the problems of target tracking interruption and resource waste in a complex scene.

The application discloses a data arrangement method, device, product, equipment and medium, comprising: determining the storage space after the data allocation position in the storage space corresponding to the target volume as a first storage space, and determining the storage space before the data allocation position as a second storage space; traversing the file data in the target volume to obtain a target file data set; determining the space in the first storage space that does not belong to the data in the target file data set to obtain a target space; determining the data stored in the second storage space and belonging to the target file data set to obtain target data; constructing a first moving set based on the target data; moving the data in the first moving set to make the target data and the original data in the first storage space form continuous data; and describing the continuously used space in the first storage space in a VDL description mode. In this way, the data complexity and algorithm complexity can be reduced, and the storage access performance of the elastic file system can be improved.