480 results about "Transformation parameter" patented technology

The invention provides an industrial defect image generation system and method based on deep learning, and relates to the technical field of artificial intelligence. A defect form adaptive module, a physical attribute modulation module and a multi-mechanism fusion module are integrated in a defect image generation module; dynamically selecting a feature extraction unit according to the defect type label based on a pre-constructed generative network model, and generating a defect feature map; generating an affine transformation parameter based on the physical attribute vector, and performing channel-by-channel linear modulation on a defect feature map of a middle layer of the generative network model, so that a multi-scale defect feature map finally generated by the generative network model contains specified defect type features and physical attribute features; and fusing the multi-scale defect feature image and the defect-free background image to obtain a fused defect image. The problems that in the prior art, industrial defect image generation is insufficient in sense of reality, poor in controllability and poor in fusion effect are solved, the method can be used for data enhancement of industrial visual inspection, and downstream model performance is improved.

The invention discloses a remote sensing image classification model compression method based on incremental information guidance, and mainly solves the problems of evaluation deviation caused by insufficient representation of dynamic characteristics of a filter and poor coordination of pruning and quantization technologies in the existing model compression technology. Comprising the following steps: 1) acquiring a remote sensing image data set and preprocessing the remote sensing image data set; 2) pre-training the model by using the preprocessed data; 3) obtaining rank information and gradient information of the feature map, and calculating an importance score of a filter in the model according to the information; 4) optimizing affine transformation parameters, obtaining scores and generating a sorting result; and 5) performing compression and fine adjustment on the model in stages to obtain a lightweight model. According to the method, model compression is guided by gradient information, collaborative optimization is realized through integrated design of pruning and quantification in combination with rank information, the model scale and the calculation complexity can be remarkably reduced under the condition that the precision is not affected, and the compression effect is effectively improved.

The invention belongs to the field of data processing, particularly relates to a standardized processing method, system and equipment for original engineering parameters of a flight simulator, and aims to solve the problems of serious field limitation, low processing efficiency and poor adaptive capacity in the prior art. The method comprises the following steps: analyzing a predefined configuration file, and dynamically generating a database temporary table matched with an original data file structure according to field structure information and a parameter mapping rule defined in the configuration file; directly loading original engineering parameter files into the temporary table by adopting a batch loading mechanism based on a file system path, and executing multi-file parallel import based on a task queue; and converting calculation logic in the parameter mapping rule into an executable query expression, and directly exporting a standardized parameter file after calculation is executed through the temporary table. According to the method, field limitation is broken through, efficient processing of mass data is achieved, instant updating of service logic is achieved through configuration rules, and the maintenance cost is greatly reduced.

Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

The invention relates to the technical field of data processing and mode recognition, in particular to a bearing fault diagnosis method based on multi-scale feature fusion, which comprises the following steps: fusing multi-source data such as vibration, acoustic emission and rotating speed, performing angle domain resampling by using rotating speed data, generating a two-dimensional order spectrogram, and stacking to construct a three-dimensional working condition information tensor; a master-slave modulation heterogeneous neural network is adopted, high-dimensional spatial-temporal features are extracted through a main branch three-dimensional convolutional network, time sequence details are extracted from an original sequence through an auxiliary branch one-dimensional convolutional network, affine transformation parameters are generated, and dynamic modulation is achieved on the high-dimensional features; and the output state vector is mapped to a fault evolution knowledge graph, probability prediction is carried out through a graph attention network and by introducing a Monte Carlo discarding mechanism, a probability mean value is calculated as a fault classification result, and the diagnosis confidence is quantified by a probability variance. According to the invention, through multi-scale feature fusion and dynamic modulation, the problem of insufficient feature discrimination caused by scale mismatch under variable working conditions is solved.

The invention discloses a global registration algorithm for low-overlapping-rate point clouds, and relates to the technical field of point cloud registration, and the algorithm comprises the steps: constructing a multi-scale descriptor under a multi-radius neighborhood for key points in a source point cloud and a target point cloud, screening a rough matching set through employing an evolutionary stabilization strategy, and obtaining a first-order matching set; based on a corresponding propagation mechanism, aggregating each matching element in the first-order matching set into a global candidate set through a corresponding propagation operation; and according to the aggregated global candidate set, generating transformation parameters with the same number, screening an optimal transformation parameter through a quality function, performing coarse alignment on the point clouds, and performing fine optimization through a truncation-ICP (Inductively Coupled Plasma) algorithm. Therefore, the global registration algorithm for the low-overlapping-rate point clouds can effectively cope with the situation of missing part of the point clouds, has relatively high robustness, and improves the registration precision under the conditions of low resolution and low overlapping rate.

The invention discloses a multi-modal remote sensing image registration method based on domain self-adaption and an optimizer set algorithm, and relates to the field of image processing, and the method comprises the steps: respectively extracting the feature vectors of a reference image and an image to be registered, carrying out the feature matching of the feature vectors according to the class label containing conditions of the feature vectors, and obtaining a registration result; obtaining a feature matching vector based on a matching result; estimating transformation parameters corresponding to the affine transformation model by using a random sampling consistency algorithm, and optimizing the affine transformation model according to an estimation result and similarity measurement; and performing spatial transformation on a to-be-registered remote sensing image by using the optimized affine transformation model to realize spatial alignment between the reference image and the to-be-registered image. According to the method, firstly, the feature points of the multi-modal remote sensing image are extracted, the difference of feature vectors is reduced by using a domain adaptive method, the precision and robustness of feature matching are improved, transformation parameters are optimized through an optimizer set algorithm, and search is prevented from falling into local optimum.

The invention relates to the technical field of water quality prediction. The pollution risk prediction method and device based on multi-source water quality data fusion, the equipment and the medium are provided, and the method comprises the following steps: carrying out multi-source collaborative acquisition processing on hydrological data, meteorological data and real-time water quality monitoring data to generate a time-space association data set; carrying out pollution scene feature coupling analysis processing on the space-time correlation data set to generate a pollution type identification matrix and a dynamic driving parameter; collaborative activation processing of the process modules is carried out through a scheduling engine, and a target simulation module topology network is generated; performing adaptive parameter configuration processing on the topological network of the target simulation module to generate a migration and transformation parameter tensor; performing dynamic evolution processing on the migration and transformation parameter tensor to generate a risk early warning hologram spectrum; and carrying out multi-dimensional parallel rehearsal processing on prevention and control measures to generate a treatment efficiency quantitative report so as to improve the pollution characteristic analysis precision and optimize the accuracy of a prediction result.

The invention relates to the field of assembly automation and flexible manufacturing, and discloses an assembly method for a prefabricated firewall of a transformer substation, and the method comprises the following steps: setting a plurality of space positioning reference points at the edge of a wallboard; acquiring three-dimensional coordinate data to form a first point set and a second point set; calculating an initial rigid body transformation parameter between the wallboards according to the first point set and the second point set; establishing an energy functional for describing a total error; carrying out minimization solution on the energy functional by adopting a variational method to obtain an optimal disturbance vector field; according to the optimal disturbance vector field, a plurality of fine adjustment actuators of the wallboard are controlled, posture fine adjustment is conducted, and physical assembly connection of the wallboard and the target wallboard is completed. According to the invention, accurate attitude estimation and error correction in the wallboard assembly process are realized; the robustness and geometric fitting capability of the assembly process are improved; the assembly precision and efficiency are remarkably improved, and the problem that traditional redundancy control distribution is unstable is solved.

The invention discloses a self-adaptive environment image processing method for industrial gas detection, which relates to the field of industrial gas detection and comprises the following steps: extracting feature points of a current frame by utilizing a feature point detection algorithm according to image frames of an industrial monitoring video stream, and acquiring coordinates of feature points between frames by combining an optical stream tracking technology; generating affine transformation parameters, performing transformation decomposition on the coordinates of the feature points by using the affine transformation parameters, and extracting pose change parameters to obtain an image motion track; predicting an image motion track by using an image track processing algorithm, and comparing the predicted image motion track with a real-time image motion track generated by the current frame; and optimizing the affine transformation parameters, and carrying out frame-by-frame processing on the video stream by using the optimized affine transformation parameters. Through feature point detection and an optical flow tracking algorithm, image motion information in an industrial monitoring video can be extracted, and industrial application requirements of high real-time performance and high stability are met.

The invention discloses a multi-modal image registration method and system based on deformation adaptation and computer equipment, and the method comprises the steps: collecting a plurality of groups of multi-modal images, carrying out the gray standardization, and constructing a diversified registration data set; building a registration network model comprising a pyramid coding module, a deformation adaptive module, a cross-modal interaction module and a registration parameter estimation module; inputting an image pair into the modules in sequence, respectively extracting basic feature mapping, deformation feature mapping and interaction enhancement feature mapping, and finally outputting an estimation conversion parameter matrix; a training process is supervised through a preset loss function, optimal network parameters are selected, and a trained registration model is obtained; in practical application, an image pair to be registered is input into the trained model, a conversion parameter matrix is obtained, and image registration is completed. The multi-modal image registration performance can be effectively improved, and the method still has good robustness and adaptability especially under the condition that serious geometric distortion and significant modal difference exist.

The invention relates to the technical field of multi-view angle analysis, in particular to a monitoring analysis method based on multi-view angle image area synthesis, which comprises the following steps: constructing a centralized dynamic anchor point set and generating multi-view angle coordinate transformation parameters and a multi-view angle observation position sequence based on target original position data collected by a multi-view angle sensor; and space-time constraint conditions of the centralized dynamic anchor point set are extracted. According to the method, through dynamic anchor point centralization processing and self-adaptive generation of multi-view coordinate transformation parameters, the coordinate system reference of multi-source heterogeneous data is effectively unified, and the cross-view positioning deviation is reduced; in combination with a space-time constraint mechanism of an elastic synthesis region, a target trajectory is dynamically predicted by using Kalman filtering and an elastic boundary is delimited, so that the stability and fault tolerance of trajectory prediction in a complex motion scene are improved.

The invention relates to the technical field of image processing, in particular to an injection molding part defect detection method and system based on machine vision, and the method comprises the steps: obtaining a to-be-detected image, constructing three-dimensional space points, calculating the direction difference between normal vectors of each space point and adjacent points in the same region to quantify the bending degree, and calculating the bending degree of the to-be-detected image; performing grid division on the to-be-detected image and the standard image, calculating the matching degree based on the average difference of the bending degrees of all the spatial points in the two grid areas, selecting the spatial points with the maximum matching degree in the two grid areas, and obtaining transformation parameters from the to-be-detected image to the standard image through singular value decomposition; and performing transformation alignment on the to-be-detected image based on the transformation parameter by using an ICP algorithm so as to identify the deformation defect of the to-be-detected image based on the two aligned images. According to the invention, the accuracy of image matching by using the ICP algorithm can be improved, so that the accurate recognition of the deformation defect area in the to-be-detected image is realized.

The invention provides a block adjustment method and device for a multi-source remote sensing image, and solves the problem that the splicing precision and efficiency of the multi-source remote sensing image in a large area are low. All panchromatic images and a multispectral image corresponding to each panchromatic image are distinguished from the image data set, and connection points of the panchromatic images are extracted; carrying out connection point matching among all panchromatic images; performing connection point matching between the panchromatic image and the corresponding multispectral image; performing control point matching on all panchromatic images and a satellite remote sensing orthographic reference image; obtaining object space coordinates of each matching point; based on the object space coordinates of the connection points and the RPC parameters of the images corresponding to the connection points, resection is carried out, and error points and error images are removed; joint adjustment is carried out on the connection points and the control points, and transformation parameters and object space coordinates of the connection points of each image are calculated; and according to the object space plane coordinates after the connection points are corrected, obtaining the elevation based on the DEM, comparing the obtained elevation with the original elevation, and if the obtained elevation value does not change, correcting the original RPC parameter file.

The invention provides a credible permission mutual recognition method, device and system for cross-domain agents, and relates to the technical field of artificial intelligence security, and the method comprises the steps: receiving a call request from a source domain agent for executing a corresponding operation on a target domain agent; obtaining an affine transformation parameter set through a permission conversion model according to the space relation characteristics of a source domain permission space and a target domain permission space involved in the calling request, and finally screening out affine transformation parameters suitable for permission voucher mapping by utilizing cone volume measurement evaluation and security verification, and mapping an original permission voucher of the source domain agent from a source domain permission space to a target domain permission space by using the affine transformation parameter, and generating a mapped permission voucher which can be identified and verified by the target domain. According to the method, the permission space is geometrized, and affine transformation, space division and geometric calculation are utilized, so that the permission credible mutual recognition problem in cross-domain agent collaboration is effectively solved.

The invention discloses a small sample crack recognition method and system based on transfer learning, and the method comprises the steps: constructing an innovative and deep-coupled neural network architecture, and enabling a self-adaptive crack perception attention module integrated with a parallel asymmetric convolution kernel to recognize the linear geometric features of a crack, and generating an attention graph; then, the attention map is adopted to carry out pixel-by-pixel signal pre-modulation on an original input image, the enhanced image is sent to a pre-training MobileNetV4 backbone network integrated with a feature-level linear modulation layer, and channel-level dynamic adaptation of feature flow in the network is realized by learning affine transformation parameters; and finally, the extracted depth features are sent to a Gaussian naive Bayes classifier for classification, and depth geometric analysis is carried out on the attention map so as to realize interpretable fracture severity evaluation. According to the method, the accuracy, robustness and interpretability of crack identification are remarkably improved, and the technical bottleneck in a small sample scene is effectively solved.

The invention provides an image target intelligent tracking and positioning method and system under Beidou position constraint, and relates to the technical field of Beidou positioning, and the method comprises the steps: obtaining a multi-source heterogeneous data flow, constructing a multi-modal representation model, and building a coordinate system dynamic projection transformation relation; generating a search mask to limit a tracking range by using the Beidou position information; bayesian correction is carried out on a tracking result through double-domain consistency measurement; and dynamically updating projection transformation parameters and feature weights based on residual distribution. According to the invention, deep fusion of vision and Beidou information is realized, and the precision and robustness of target tracking in a complex scene are improved.

The invention provides a medical image registration method and system based on a multi-dimensional loss function. The method comprises the following steps: preprocessing 3D-CT medical image data, wherein the 3D-CT medical image data comprises a fixed image and a floating image; the method comprises the following steps: constructing an initial model of a registration model by adopting a transformer-based deep learning architecture, and firstly, carrying out coarse registration on preprocessed 3D-CT medical image data to obtain coarse registration rigid body transformation parameters; further performing fine registration through an initial model of the registration model based on the rough registration rigid body transformation parameters; and further optimizing the initial model of the registration model by adopting a multi-dimensional adaptive loss function to obtain a final registration model capable of obtaining an optimal result. According to the method, a deep learning network technology is comprehensively adopted, a registration structure based on a transformer deep learning network framework from a coarse stage to a fine stage is adopted, a multi-dimensional self-adaptive loss function is introduced, and meanwhile, the registration adaptation range and the registration precision are improved.

The invention discloses a safety auditing method and device supporting data owner replacement, equipment, a medium and a product, and relates to the field of auditing, and the method comprises the steps that if the data ownership is changed, an original data owner calculates a trap door parameter value based on a random number j and a private key of the original data owner; the new data owner calculates a conversion parameter value according to the trap door parameter value and a private key of the new data owner; the cloud server calculates the label of each data block after the data ownership is changed according to the conversion parameter value, the reciprocal of the random number j and the label of each data block before the data owner changes; the cloud server generates auditing evidences according to the labels of the data blocks and the inquiry information; the third-party auditor carries out safety auditing according to the auditing evidence and the inquiry information, and after the data ownership is changed, it can be ensured that the changed data owner can still ensure the continuity of data integrity verification under the condition that all the data are not downloaded.

The embodiment of the invention provides a method and device for protecting model safety, equipment and a storage medium. The method comprises the steps of obtaining an input feature representation for a first model layer in a machine learning model; generating a first feature tensor for the first model layer at least by processing the input feature representation with the first weight tensor in the processing unit; transmitting the input feature representation and the first feature tensor to a trusted execution environment; in the trusted execution environment, processing the input feature representation with the direction transformation parameter to generate a direction correction tensor; and in the trusted execution environment, correcting the first feature tensor based on the direction correction tensor to determine an output feature representation corresponding to the first model layer.

The invention provides an image processing method and device, equipment, a medium and a program product, and relates to the technical field of image processing. The image processing method comprises the following steps: carrying out linear transformation on an original grayscale image to obtain an initial grayscale image; performing gamma transformation parameter calculation on the initial grayscale image to obtain a first gamma transformation parameter; performing equal region division on the initial grayscale image to obtain a plurality of image blocks; for each image block, under the condition that the contrast ratio of the image block is greater than or equal to a threshold value, determining that the first gamma transformation parameter is the gamma transformation parameter of the image block; under the condition that the contrast ratio of the image block is smaller than a threshold value, the gamma transformation parameter of the image block is adjusted based on the first gamma transformation parameter, and a second gamma transformation parameter is obtained; determining the second gamma transformation parameter as the gamma transformation parameter of the image block; and performing nonlinear transformation on the initial grayscale image based on the gamma transformation parameter of each image block to obtain a target grayscale image so as to adjust the brightness of the original grayscale image.

The invention provides a non-contact measurement-oriented three-dimensional point AI registration and tolerance analysis method and system, and relates to the field of three-dimensional point AI registration and tolerance analysis, and the method comprises the steps: synchronously collecting point cloud data through multiple sensors, and carrying out the adaptive preprocessing, and obtaining a preprocessed point cloud pair; constructing a multi-scale geometric descriptor by using a local curvature and a normal vector, and performing multi-scale hierarchical feature extraction to obtain an enhanced point feature set; calculating a bidirectional matching probability matrix by using an optimal transmission theory, screening high-confidence point pairs through spatial compatibility constraint to obtain a high-confidence matching point pair set and a matching score, performing transformation matrix estimation and quantification uncertainty, and outputting optimal rigid body transformation and a covariance matrix thereof; self-adaptive optimization is executed in a layered mode, the search range is dynamically adjusted, transformation parameters are verified in a cross-scale mode, and a convergent accurate registration result is output. The method is used for overcoming the defect that in the prior art, low-overlapping-rate registration precision is low.

The invention discloses a data processing method, device and equipment and a readable storage medium. The method comprises the following steps: acquiring sample data for model training; the sample data is determined based on the sample object and the historical resource data of the historical business operation executed by the sample object; calling a recommendation model to carry out probability prediction processing on the sample data to obtain a sample prediction probability; monotonic transformation processing is carried out on the sample prediction probability through the monotonic transformation parameter of each business index, and a sample transformation probability corresponding to each business index is obtained; performing training optimization on the recommendation model through the N sample transformation probabilities; the trained and optimized recommendation model is used for carrying out probability prediction processing on the service data in a resource data pushing scene. The resource data recommendation method and device can be applied to various scenes such as the map field, the traffic field, the automatic driving field, the vehicle-mounted scene, the cloud technology, artificial intelligence, intelligent traffic and auxiliary driving, and the resource data recommendation accuracy is improved.

The application discloses a similarity optimal on-board image registration method based on inertial navigation data fast convergence, and comprises the following steps: constructing a projection transformation model between an image transformation matrix, a to-be-registered image and a reference image; obtaining the projection transformation matrix according to the field of view optical axis position and three-angle offset of the satellite at the imaging moment and coarse registration; performing global coarse matching by using the projection transformation model and the projection transformation matrix to obtain a coarse matching image; decoupling the image transformation matrix according to a mathematical model to obtain a to-be-solved transformation parameter, substituting the to-be-solved transformation parameter into the image transformation matrix to obtain an optimal transformation matrix, and applying the optimal transformation matrix to the to-be-registered image to obtain a fine registration image; and calculating the similarity of the fine registration image and the reference image according to a local normalized image similarity measurement algorithm to obtain an optimal matching result. The application has the advantages of meeting the on-board calculation capacity requirement, meeting the image processing precision requirement and meeting the on-board storage resource requirement.

The invention provides a video fusion method and device based on a three-dimensional scene and a storage medium, and belongs to the technical field of video surveillance, and the method comprises the steps: obtaining video frame data, including a video frame image and a corresponding timestamp, collected by a camera installed on sports equipment, obtaining space-time information of the sports equipment, comprising geographic data and corresponding timestamps; extracting image feature points of each video frame image, and constructing a mapping relation between the image feature points and the geographic data; based on the mapping relation, the pose data of the camera is iteratively solved by minimizing a re-projection error, and an objective function corresponding to the re-projection error comprises strong constraint optimization of geographic data; and determining a conversion parameter between a first coordinate system of the video frame image and a second coordinate system of a pre-constructed three-dimensional scene model based on the pose data to obtain a video fusion parameter, so as to fuse the multi-frame video frame data with the three-dimensional scene model, thereby improving the fusion effect of the three-dimensional scene and the video.

The invention discloses a self-adaptive spatial transformation network for cross-medium optical distortion, and solves the problem that the existing spatial transformation network is difficult to consider both global transformation and local nonlinear optical distortion. The network is integrated in a target detection model, and the method comprises the steps that firstly, a parameter prediction network synchronously outputs affine transformation parameters and a water surface fluctuation physical parameter diagram; then, the local distortion grid generation network generates a distortion sampling grid based on the parameter diagram and a predefined water surface fluctuation physical model; meanwhile, the grid generator generates an affine sampling grid according to the affine transformation parameters; then, a grid fusion device fuses the two grids to generate a final sampling grid; and finally, the sampler samples the input image or the feature map according to the final sampling grid to obtain an output image or a feature map. Through a space transformation mechanism guided by physical prior, optical distortion caused by water surface fluctuation can be effectively relieved, and the accuracy and robustness of a target detection model in a cross-medium underwater scene are remarkably improved.

The invention discloses a high-fidelity splicing method and system for an unmanned aerial vehicle image, and the method employs a dual-stage processing strategy, achieves precise positioning through coarse-fine two-stage alignment, calculates an overall transformation parameter through global estimation to complete coarse alignment, refines non-rigid offset through local correction, and achieves high-fidelity splicing of the unmanned aerial vehicle image. The feature weight is dynamically adjusted in combination with self-adaptive enhancement, and geometric smooth constraint is used for limiting regional displacement; smooth weights with continuous boundaries and the weight sum being 1 are generated based on the shape of the overlapping region, images are decomposed to different frequency layers for layer-by-layer fusion, and the system comprises an image acquisition unit, a dual-stage processing unit and an output display unit and can be deployed on the end side of an unmanned aerial vehicle or a ground station. The method is high in alignment precision, can process large parallax and non-rigid deformation, is traceless in fusion, is high in structural fidelity, and meets the real-time processing requirements of airborne or edge equipment.

The invention relates to the technical field of image processing of financial and medical scenes, and discloses an image-to-video generation method and device, computer equipment and a storage medium, and the method comprises the steps: receiving an input image, and obtaining a corresponding multi-scale depth map; extracting spatial-temporal feature sequences of the input image and the corresponding multi-scale depth map, and performing coding and dynamic modeling to obtain six-degree-of-freedom motion transformation parameters; performing continuous frame transformation and synthesis on the input image by using the six-degree-of-freedom motion transformation parameter to generate an initial output video sequence; performing authenticity discrimination on a global time sequence level and a local space-time detail level by using the initial output video sequence to generate an authenticity score; and iteratively executing optimization processing on the input image until the authenticity score reaches a preset threshold value, and generating a final output video sequence with high space-time coherence. The method has the advantage that the space-time consistency and the reality sense of the generated video are remarkably improved.

The invention relates to the technical field of image processing, in particular to an X-ray image processing system for enteritis prognosis analysis, which comprises the following steps of: obtaining a gray level image according to multi-threshold segmentation; obtaining the gray level fluctuation degree of the gray level image according to the histogram of the gray level image; determining a pixel point aggregation degree through connected domain analysis; obtaining an initial lesion probability by combining the gray level fluctuation degree and the pixel point aggregation degree of the gray level image; according to the fitting result of each gray level image, obtaining the probability of existence of intestinal tract gas; adjusting the initial lesion probability according to the intestinal tract gas probability to obtain the lesion probability; obtaining transformation parameters of the gray level image according to the lesion probability; linear transformation is conducted on the X-ray image according to the transformation parameters, and an enhanced intestinal tract X-ray image is obtained and visualized. The contrast ratio between a lesion area and the surroundings is enhanced, the visual effect of shadow caused by gas is weakened, and prognosis analysis of doctors is facilitated.

The embodiment of the invention provides a program conversion method and a compiling device, and relates to the technical field of computers, in the method, an IR file of a GPU program is obtained to serve as a to-be-converted file, for a function parameter of any function in the to-be-converted file, the function parameter is converted into a function parameter matched with a CPU, and the converted parameter is obtained. And determining the IR statement having data dependence with the converted parameter as a statement to be adapted. And for any statement to be adapted, adjusting the statement to be adapted based on the parameter type of the converted parameter and the thread execution mask of the CPU. And compiling the adjusted to-be-converted file to obtain an executable file adaptive to the CPU. The GPU programs written by different high-level languages can be converted into the IR file, so that the conversion is carried out from the dimension of the IR file, and the support for different high-level languages can be realized. Therefore, the limitation is lower.