1370 results about "Characteristic space" patented technology

The invention provides a new material production process parameter optimization method and system based on artificial intelligence, and relates to the technical field of parameter optimization, and the method comprises the steps: constructing a multi-dimensional process parameter feature space, collecting and preprocessing process parameters, extracting correlation features through a deep convolutional neural network, and building a parameter feature space model; generating a technological parameter collaborative optimization model, constructing a multi-objective optimization function, and performing iterative optimization by using reinforcement learning and an improved ant colony algorithm; and performing process parameter adaptive control, constructing a dynamic control interval, collecting parameters in real time and performing adaptive adjustment to realize closed-loop control and model dynamic update.

The invention discloses a semi-supervised identification method and system for a small target of a container, and belongs to the technical field of artificial intelligence and computer vision, and the method comprises the steps: carrying out the target detection of a container image through a pre-trained target detection model, intercepting a sub-image, and inputting the sub-image into an initial classification model, and obtaining a classification confidence coefficient; the uncertainty of the model on a sample classification result is quantified through a Monte Carlo Dropout method; a feature space distance filtering and dynamic threshold adjusting mechanism is combined, and samples with high confidence, low uncertainty and consistent feature space are screened out to serve as pseudo label data; pseudo label data and initial synthesis data are mixed, and the generalization ability of the model is gradually improved through semi-supervised iterative training. According to the method, the dependence on manual annotation can be remarkably reduced, meanwhile, the distribution difference between synthetic data and real scene data is gradually reduced, and finally, high-precision recognition and strong generalization ability of a classification model in a real scene are achieved.

The invention discloses a method for detecting disconnection of a control loop. The method comprises the following steps: acquiring an original signal data set, performing sampling frequency optimization on the original signal data set to obtain an optimized sampling frequency value, performing resampling and noise processing, and generating a quality evaluation index; performing enhancement processing on the preprocessed signal, extracting time-frequency domain features, performing correlation analysis and time sequence decomposition, and generating a reliable feature set and a reliability report; performing feature space mapping and hierarchical feature extraction based on the reliable feature set, executing fault recognition to obtain fault probability distribution, performing credibility evaluation, and generating an anomaly evaluation report and a final diagnosis result; and extracting time sequence characteristics according to the abnormal assessment report and the diagnosis result, performing trend prediction and risk assessment, and generating an optimization decision scheme. According to the invention, through multi-level signal processing and feature analysis and in combination with a credibility evaluation mechanism, accurate detection and predictive maintenance of the control loop broken line fault are realized.

The invention discloses an intelligent decision-making method for a large model in the field of industrial operation and maintenance, and the method comprises the steps: collecting and sorting industrial operation and maintenance text materials, and injecting industrial operation and maintenance knowledge into the large model based on prompt word engineering and construction of a large language model training text pair, thereby obtaining the large model in the industrial field; the method comprises the following steps: collecting sensor time series data, designing a cross-modal conversion module to convert the time series data into a feature space which is the same as a natural language text, and supervising training of the cross-modal conversion module by utilizing information learned by a text space through a cross-modal knowledge alignment strategy; on the basis, a task prompt text is constructed through prompt word engineering, and the large model is guided to output an industrial equipment state classification result. According to the method, the classification result of the industrial operation and maintenance task can be given based on the equipment state text and the time sequence modal data collected by the sensor and a large model, so that support is provided for intelligent decision-making of industrial operation and maintenance.

The invention relates to the technical field of aluminum alloy cold stamping quality control, in particular to a multi-source data fusion and real-time optimization-based cold stamping quality control method, which comprises the following steps of: inputting a fusion feature space into a pre-trained LSTM (Long Short Term Memory) model, and associating a real-time stamping speed with a dwell time parameter through an attention mechanism; combined prediction of springback value deviation and defect probability is realized for the first time, a process parameter correction value is dynamically generated based on a prediction result, and a thermal expansion compensation algorithm and micron-sized mold compensation are combined, so that the quality regulation response speed reaches a millisecond level, the compensation precision is improved to + / -2 [mu] m, and the error is reduced by more than 50% compared with that of traditional PID (Proportion Integration Differentiation) control.

The invention discloses a cloud platform auditing method based on multi-modal data processing, and relates to the technical field of cloud platform auditing. Independent features of text, image, audio, video and log data are extracted, each piece of modal information can be subjected to refined analysis in a corresponding feature space, and in a cross-modal feature fusion stage, a multi-modal feature fusion model is obtained. The correlation between different modal data is calculated by using a cross-modal consistency comparison network CMCN, and feature alignment is optimized through an attention mechanism, so that multi-modal information can be mutually verified, and misjudgment and missed judgment caused by independent auditing are reduced; in the auditing decision-making link, an auditing model based on deep learning is constructed, and end-to-end illegal content judgment is realized in combination with anomaly detection and a self-adaptive risk control threshold value, so that the intelligent level of an auditing system is improved; in addition, the suspicious areas of the image and the video are visually marked, and an auditing conclusion is generated by utilizing a natural language to generate an NLG model, so that the auditing result is more transparent.

The invention belongs to the field of artificial intelligence, particularly relates to a large model illusion suppression method, system and equipment based on a dynamic knowledge base and multi-modal consistency constraint, and aims at solving the problem that factual illusion is likely to occur when an existing large language model generates content. The method comprises the steps that a knowledge base of multi-source heterogeneous data is constructed and dynamically maintained, and a dynamic credibility weight fusing data source authority, knowledge timeliness and multi-modal consistency is calculated for each piece of knowledge in the knowledge base; when the content is generated by the model, high-credibility related knowledge is retrieved from the knowledge base according to the current context; in the decoding stage of the model, a constraint loss item is designed, and the generation probability is adjusted in real time by calculating the similarity between the currently generated content and the retrieval knowledge in the feature space. According to the method, the multi-modal knowledge base for dynamic credibility evaluation is introduced, and the real-time consistency constraint is applied in the generation and decoding link, so that the accuracy and the reliability of the generated content are remarkably improved.

The invention discloses a student sentiment analysis method and system based on a multi-modal dynamic memory large model, and belongs to the field of multi-modal sentiment analysis. The method comprises the following steps: firstly, acquiring facial expression images and corresponding real emotional state category labels when different students watch an online education course to form a training data set, training a multi-modal dynamic memory large model based on the data set, and in the training process, performing prompt fine tuning on an image encoder and a text encoder so as to obtain a multi-modal dynamic memory large model; visual aggregation representation generated in the historical training process is stored through a dynamic feature space, and model parameters are optimized through cross entropy loss; and finally, inputting a facial expression image to be classified into the trained multi-modal dynamic memory large model, and outputting an emotional state category prediction result of the facial expression image. The method can be effectively applied to the field of education, and is beneficial for teachers to know the emotional state of students, thereby improving the participation degree and learning effect of the students.

The invention provides a diffusion model LoRA fine tuning optimization method and system based on CLIP loss and perception loss, and the method comprises the steps: 1, dynamically adjusting the weights of the CLIP loss and the perception loss in combination with the CLIP loss and the perception loss in a LoRA fine tuning process; 2, calculating the semantic similarity between the denoised intermediate image and the target text by using a CLIP model, and optimizing the noise prediction capability of a diffusion model according to the similarity difference; step 3, calculating the difference between the intermediate image and the target image in the feature space by using perception loss, optimizing the noise prediction capability of the diffusion model, and improving the visual quality and detail fidelity of the generated image; and step 4, adjusting whether to start CLIP loss and perception loss or not according to the training progress. By introducing the CLIP loss, the model can better align the image and the text in the fine tuning training process, so that the generated image better conforms to the description of the text prompt.

The invention provides a financial document automatic analysis and question-answering system based on a large model, and relates to the field of data intelligent analysis, and the method comprises the steps: firstly carrying out the multi-granularity segmentation and semantic embedding coding of a financial document, so as to map the document data to a vector space; then dynamically matching user questions and candidate document fragments in a feature space by adopting a multi-layer retrieval mechanism so as to accurately position related contexts, and then carrying out cross-paragraph semantic association modeling on the candidate fragments by introducing dynamic propagation of feature space constraint so as to break through the information fragmentation limitation of traditional paragraph matching; and finally, a model is generated in combination with thinking chain reasoning, a traceable reasoning path is synchronously constructed when an answer is output, and the illusion risk of a large model is remarkably reduced. In this way, the analysis depth of the complex financial problem can be improved, and intelligent analysis services with both accuracy and credibility are provided for users.

The invention provides a man-machine cooperation method and system based on robot process automation, and relates to the technical field of automation, and the method comprises the steps: building a data perception processing network, collecting a user operation instruction, a system operation state and task environment data, obtaining a task feature vector through semantic analysis, and matching a business model to generate a task processing strategy. A man-machine cooperative processing framework is constructed based on the strategy, a robot unit processes a structured task, a manual operation unit processes an unstructured task and is connected through an information interaction channel, and transmission of a data analysis result and decision suggestions and updating of processing regulation information when deviation exceeds a threshold value are achieved. Besides, a knowledge migration processing network is constructed, business rules and expert experience data features are extracted, a scene migration model is trained, business feature vectors are mapped to a preset scene feature space, and after validity verification, parameters of the data perception processing network and the man-machine cooperative processing framework are updated.

The embodiment of the invention provides a dynamic point cloud compression method and device based on time sequence perception, and the method comprises the steps: carrying out the sparse convolution processing of two continuous frames of input point cloud data, and obtaining point cloud features in a feature space, carrying out local and global feature extraction on representations of two continuous frames in the feature space, splicing and fusing to obtain a motion vector, and carrying out motion compensation on point cloud features of the previous frame by utilizing the accurate motion vector to obtain a prediction frame of the current frame; calculating a residual error between a prediction frame and an actual frame, carrying out compression coding to obtain a residual error tensor, adding the prediction frame and the residual error tensor to obtain a coarse-grained prediction feature, and carrying out time alignment and feature fusion on the coarse-grained prediction feature and the three-frame point cloud features stored in the buffer region to obtain a fused prediction feature; performing up-sampling reconstruction on the fused prediction features to obtain a final point cloud frame; according to the invention, the accuracy and efficiency of point cloud data compression can be effectively improved.

The invention relates to the technical field of data processing, and discloses a multi-source heterogeneous big data processing system, which comprises the steps of dividing data into structural sub-data and non-structural sub-data, performing feature extraction on the non-structural sub-data to obtain multi-modal features, so that the data can be compared in a unified feature space, and then, performing feature extraction on the non-structural sub-data to obtain multi-modal features. The similarity and relevance between the data are identified through pattern matching, it is ensured that the data of the same entity are identified to be directly fused, redundancy is reduced, accuracy is improved, then the most similar data combination is selected through an optimization algorithm, and the actual relation type between the data is determined through relation deduction; and finally, the most suitable fusion mode is selected according to the relationships. According to the method, the accuracy and effectiveness of the data fusion process are ensured, and a reliable basis is provided for deeper analysis and decision making.

The invention provides a steel surface defect detection method and device, and belongs to the technical field of steel defect detection.The steel surface defect detection method comprises the steps that a defect detection network based on a YOLO architecture is constructed, and the defect detection network comprises a lightweight feature extraction network, a self-adaptive multi-scale feature fusion network and a head network; the lightweight feature extraction network comprises four layers of architectures, and each layer of architecture comprises a first convolutional layer and a space expansion feature module; the feature space expansion module comprises a second convolutional layer and an element multiplication operator module; the adaptive multi-scale feature fusion network comprises an adaptive fusion module and a feature space expansion module; training the constructed defect detection network based on the historical steel defect image, and performing channel pruning on the trained defect detection network by using LAMP (Loop-Mediated Isothermal Amplification); and acquiring a to-be-identified steel image, and inputting the to-be-identified steel image into the pruned defect detection network for defect detection. According to the method, the defect detection precision of the network can be improved while the network complexity is reduced.

The invention discloses a multi-class defect detection method and device based on a variational auto-encoder and a denoising network, and the method comprises the steps: obtaining an industrial product surface defect image, carrying out the preprocessing, and constructing a training set and a verification set; the training process of the method is divided into two stages: in the first stage, a preprocessed training image is input into a variational auto-encoder for training, feature distribution of the image is learned, and features of a normal image are captured by reconstructing the image; in the second stage, a denoising network and a feature guiding module are used for conducting secondary reconstruction on image features in the feature space of the variational auto-encoder, and therefore the reconstruction capacity and the multi-class reconstruction capacity of the model are enhanced; in the reasoning stage, multi-scale features of an original image and a reconstructed image are extracted through a feature extractor, feature comparison is carried out, and an abnormal scoring graph is generated. According to the method, normal information is reserved while the reconstruction capability of the variational auto-encoder is enhanced, and defect missing detection caused by reconstruction failure is effectively reduced.

The invention discloses a lifelong target re-identification method based on descriptive text prompt prototype compensation, relates to the field of computer vision, and aims to display and solve the problem of feature drift caused by model increment update by introducing a prompt prototype compensation module. The module generates a multi-modal vision and text prototype for each target category through a vision language pre-training model, and maps old task features to a new task feature space through a cross attention mechanism so as to realize fine-grained semantic drift compensation. In addition, a boundary perception prototype correction module is designed to solve the problem of boundary confusion caused by updating of old prototypes. The module dynamically samples false features in compensation distribution to correct old prototypes with fuzzy boundaries, focuses on categories easy to confuse to maintain clear decision boundaries, optimizes cross-task and intra-task correction loss to reduce category confusion, effectively alleviates the problem of disastrous forgetting, and improves the adaptability and generalization ability of the model.

The invention relates to a multi-modal sparse fusion three-dimensional target detection method in an unstructured environment, and the method is based on a complexity perception candidate region dynamic sampling strategy, and through the cross-domain self-compensation of point cloud geometric features and image spectral features, and the fusion of multi-view sparse features, the detection of a multi-modal sparse fusion three-dimensional target is realized. The perception capability and the recognition precision of the obstacle area, and the remote dynamic target detection performance and the real-time performance are improved; an anti-deformation convolution group and a terrain gradient perception attention module are introduced into a ParScaleNet image backbone network, so that the extraction of edge features of a complex scene is enhanced, and the cross-scale characterization capability of the features is improved; according to the method, a ContraSpaceOpt module with semantic maintenance capability is deployed behind a Transform, excessive smoothness of obstacle features is inhibited through class comparison loss functions and feature space anisotropy constraints, the space separability of obstacles is maintained, and the problems of point cloud fracture and texture misalignment caused by the obstacles are effectively solved.

The invention relates to the technical field of intelligent manufacturing equipment fault diagnosis, and particularly discloses a Meta-Transform driven multi-working-condition equipment bearing fault diagnosis method and system. The method aims at bearing fatigue damage risks caused by dynamic adjustment of technological parameters of a numerical control machine tool in the aerospace manufacturing process and challenges such as feature distribution offset and fault sample scarcity caused by variable working conditions. The diagnosis system is constructed through three core modules. The method comprises the following steps: firstly, reconstructing an original bearing signal into a multi-scale time-frequency feature space by adopting continuous wavelet transform; then designing a causal Transform architecture with a strict lower triangle attention mask, and realizing feature extraction and classification according to a physical causal law of fault propagation; and finally, integrating the mechanisms into a model-independent element learning framework, and realizing cross-working-condition rapid self-adaption through a self-adaption gradient pruning strategy. The bearing fault diagnosis accuracy under the condition of few samples is improved, the interpretability and generalization ability of the model are enhanced, and the industrial application practicability of bearing fault diagnosis is improved.

The invention discloses a surface defect detection method based on metric element learning, which belongs to the technical field of industrial visual monitoring, and comprises the following steps: acquiring defect images and non-defect images, and constructing a data set; a high-resolution image is generated based on a cascaded generative adversarial network fused with a multi-dimensional attention mechanism, and the local detail and global feature expression ability of the image is improved through the multi-dimensional attention mechanism; and constructing a defect detection model, and carrying out weak supervision detection on the surface defects based on metric learning and meta learning. According to the method, confidence coefficient screening and structural consistency constraint are performed on unlabeled samples through metric learning and feature space constraint, so that the representation capability and generalization performance of the model are effectively improved, and the problems of few defect samples, high labeling cost and difficult representation of small defects in an industrial scene are emphatically solved; and the defect detection accuracy and the fine-grained discrimination performance are improved.

The invention provides a dynamic game difficulty self-adaptive adjustment method and system based on user behavior feedback, and relates to the technical field of game design, the method comprises the following steps: carrying out dynamic weighting calculation based on a difficulty adaptation index, generating a dynamic difficulty correction coefficient in combination with user real-time physiological feedback data, and adjusting the dynamic game difficulty according to the dynamic difficulty correction coefficient; the dynamic difficulty correction coefficient comprises a scene complexity adjustment parameter and an interaction response threshold adjustment parameter; inputting the user feedback parameter set into an image feature weight distributor, dynamically adjusting weight distribution of image retrieval feature vectors according to user attention distribution data and operation delay parameters, and generating an optimized scene element retrieval strategy; and performing feature space mapping on the dynamic difficulty correction coefficient and the optimized scene element retrieval strategy, and generating a final game difficulty control instruction set through nonlinear superposition. Game design can be optimized, and game adaptability and flexibility are enhanced.

The invention discloses a small sample radar target identification method based on multi-feature fusion. According to the invention, the natural resonant frequency characteristics of radar echo signals are introduced into a small sample learning framework, and the advantages of certain stability and simple and rapid extraction under the condition of attitude and observation angle change are fully utilized; attention multi-feature weighted fusion based on energy guidance is carried out on natural resonant frequency features and time frequency features, scattering features are described from different feature mechanisms, and the completeness of the features under the small sample condition is improved; in addition, a loss function based on combination of feature similarity measurement and classification loss is also designed, so that the model can learn feature representation with higher distinction degree while the feature space discrimination is optimized, and the performance is improved in a feature fusion-classification network. According to the method, on the premise that the reasoning time and the calculation complexity are not remarkably increased, the recognition accuracy under the condition that the observation angle changes is effectively improved.

The invention discloses a noise text open intention classification method and system based on a large model, and belongs to the technical field of natural language processing and artificial intelligence, and the method mainly comprises the steps: extracting text features through a pre-trained large language model, carrying out the clustering of the text features through unsupervised granular ball clustering, and constructing intra-class structure representation in a feature space; dividing the training sample into a clean sample, an internal distribution noise sample, an external distribution noise sample and an uncertain sample based on a global particle-ball-level OOD tendency index and a sample-level consistency index; constructing a joint loss function guided by beneficial noise, and performing differentiation training on the model by using a sample division result; and constructing a multi-granularity decision boundary based on a granular ball structure, wherein the multi-granularity decision boundary is used for judging the category of the input sample. According to the method, multi-granularity structure information, a noise pattern recognition mechanism and a joint representation learning strategy are fused, and the recognition robustness and generalization ability of the model in a complex open environment are effectively improved.

The invention discloses a software project development method based on a low-code platform, which belongs to the technical field of software development, and specifically comprises the following steps: receiving original demand description through an embedded natural language parser, and establishing a semantic incidence matrix to extract demand elements; encoding the demand elements into three-dimensional structured demand vectors; mapping the demand vector to a three-dimensional orthogonal feature space, calculating the coordinates of a functional module, and generating an initial topological structure based on a Delou inner triangulation algorithm; rendering an interactive three-dimensional network map on a visual interface; monitoring user operation, and recalculating the adjacency relation of the affected module when the displacement of the module exceeds a threshold value or the connection edge is reconstructed; compared with a historical version, when a key service path is interrupted or a data flow ring is broken, a compensatory connection bridge is activated; a deployable architecture with a version traceability identifier is output, and a traceability code is built in the module to reversely map an original demand vector.

The invention discloses an incomplete multi-view comparative learning method based on cross-view coding and graph constraint, and belongs to the technical field of computer vision. According to the method, sample advanced representation is captured through a cross-view encoder, a relation graph is constructed by taking the sample advanced representation as a center, and due to the fact that different view features of the same instance are consistent in semantics, the same instance in different views can share similar relation graphs, and through the mode, the relation graph can be shared by the same instance in different views. The advanced feature representations of different views can be drawn close and aligned in the feature space; then, self-supervised high-confidence guidance is adopted to further enhance self representation learning; besides, in order to pay more attention to the neighborhood relation between the instances, reconstruction data are reversely pushed into the representation learning process by introducing graph constraints, and the reconstruction data are allowed to cooperate with one another to achieve better clustering.

The invention provides a few-sample fine-grained target detection method for an SAR (Synthetic Aperture Radar) image, and aims to solve the problems of insufficient detection precision and weak generalization ability caused by the problems of sparse texture, large fine-grained difference of target categories, limited labeled samples and the like in the SAR image. According to the method, ARS-DETR is used as a trunk detection model, d key point prediction branches are introduced on the basis of the trunk detection model, and the model is guided to pay attention to a target discriminative region through OKS loss; and meanwhile, a feature prototype set is constructed, class center representation is obtained through confidence screening and k-means clustering, and dynamic updating is performed in combination with an EMA mechanism. In the few-sample training stage, prototype regularization constraint is introduced to keep the feature space stable; in the test stage, through training test prototype distance and classification confidence coefficient weighted fusion, the final discrimination accuracy is improved. The method can effectively improve the structure modeling capability and the few-sample adaptive capability of the target detection task in the SAR image, and is suitable for fine recognition application in a complex remote sensing scene.

The invention provides a target identification method and device for a millimeter-wave radar and the millimeter-wave radar, and the method comprises the steps: carrying out the distance calculation of detection points of the millimeter-wave radar, obtaining a detection point graph, and determining a point cloud graph structure according to the detection point graph; performing multi-layer perceptron mapping on the point cloud image structure to obtain non-context coding features, and converting the non-context coding features into high-dimensional vector representation to obtain feature space data; performing graph convolution processing on the feature space data to obtain a context point code, and generating a target candidate frame according to the context point code; performing confidence evaluation on the target candidate box to obtain target confidence data, and calculating motion features and type probabilities of the candidate targets according to the target confidence data; and performing clustering and non-maximum suppression processing on the candidate targets according to the motion features and the type probability to obtain a target recognition result.

The invention relates to a PCB production line process parameter intelligent matching method based on feature space mapping, and the method comprises the steps: collecting and fusing the material attributes, structure parameters, sizes and historical process records of a plurality of batches of PCB products, carrying out the normalization preprocessing, removing abnormal data, and constructing a high-quality feature matrix; after multi-dimensional feature expression is realized by utilizing a multi-scale embedded network, a mapping relation between features and process parameters is dynamically learned on the basis of an adaptive space mapping network in combination with a soft constraint multi-objective loss function, and gradient cutting, step length adjustment and a disturbance elasticity pool mechanism are introduced in a parameter recommendation process to guarantee convergence and stability. After the parameters are implemented, feedback data are collected in real time, periodic iteration distillation optimization and loss function recalibration are carried out, and finally a fine-tuning parameter recommendation scheme marked with conflict indexes, confidence intervals and weight suggestions is output for an engineer. According to the scheme, the intelligence, the traceability and the field adaptation capability of parameter recommendation are improved.

The invention discloses a big data analysis-oriented edge artificial intelligence calculation method, which relates to the technical field of edge artificial intelligence, and comprises the following steps of: after a boundary aggregation condition is identified, calculating a data distribution compression ratio on the basis of a numerical mapping overlapping degree before and after truncation, a sample clustering overlapping rate of a boundary interval and an upper and lower adjacent section thereof, and a data distribution compression ratio; constructing a feature space overlapping ratio model for identifying whether a distribution folding trend exists or not; and on the basis of the boundary aggregation condition and the identification result of the distribution folding trend, constructing a credibility discrimination evaluation function, generating a credibility discrimination evaluation coefficient, and dividing the current input data into a high credibility area, a middle credibility area or a low credibility area. According to the method, the problems of data distribution folding and misjudgment caused by truncation processing in industrial edge calculation are solved, and dynamic evaluation of input credibility and adaptive regulation and control of a reasoning path are realized, so that the model discrimination accuracy and robustness are improved.

The invention relates to the technical field of mode recognition and data recognition, and discloses an intelligent visual detection method for non-standard precision part surface microdefects, which comprises the following steps: acquiring surface gray level image data of a to-be-detected part, physically abandoning low-frequency components through discrete wavelet transform, and reserving high-frequency detail components to construct a frequency domain input tensor; constructing a double-flow reconstruction model containing a space domain coding network and a frequency domain coding network, and minimizing the distribution difference of the same feature between double-domain characterization through potential feature space consistency constraint joint optimization; the method comprises the following steps of: calculating a spatial domain residual image and a frequency domain residual image, combining a texture topological residual image extracted by structural tensor characteristic decomposition, and generating a comprehensive abnormal response image through weighted fusion to judge the defect, and effectively inhibiting macroscopic geometric contour interference through frequency domain decoupling and a topological check mechanism on the premise of not needing a standard geometric template. And sensitive perception and accurate identification of weak texture defects on the surface of the non-standard part are realized.

The invention relates to the technical field of machine vision, in particular to a precision part size automatic detection method and system based on machine vision, precision part images are collected through a high-precision industrial camera, part positioning is carried out, sub-pixel-level topological feature mapping is carried out on interested area images, and precision part size automatic detection is carried out. Comprising the steps of gray histogram equalization, gray morphological processing, edge detection and edge chain code tracking, construction of an edge point topological feature space, execution of sub-pixel subdivision, obtaining of an edge line through contour analysis of a feature distance and a feature angle, and double-constraint geometric reconstruction based on the edge line. The characteristic distance and the characteristic angle are used for rotation matrix conversion and geometric dimension calculation, a relation model of the geometric dimension and the actual dimension of the part is established, precise part dimension measurement is achieved through dynamic error analysis and compensation, the measurement precision is remarkably improved, the risk caused by unreliability of a single characteristic is effectively reduced, and the measurement accuracy is improved. And the measurement stability is improved.