533results about How to "Improve classification efficiency" patented technology

According to the goaf detection method based on transient electromagnetic and seismic wave field joint inversion, data acquisition and joint inversion are carried out on the goaf through the combination of the transient electromagnetic detection system and the reflection seismic detection system, the complementary advantages of the two detection methods are played, the bottlenecks of a single method in the aspects of resolution and signal-to-noise ratio are broken through, and the goaf detection method based on transient electromagnetic and seismic wave field joint inversion is realized. Fine characterization of the structure, the physical property and the stability of the goaf is realized; a machine learning classification algorithm is introduced to analyze a goaf multi-attribute feature data set, and intelligent discrimination of the type, scale and stability of the goaf under complex geological conditions is realized; establishing a quantitative response relationship between goaf physical property parameters and goaf electrical and elastic difference characteristic parameters, constructing a goaf transient electromagnetic and seismic wave field joint forward modeling numerical model, and constructing an electromagnetic-seismic joint inversion objective function; and calculating and solving to obtain goaf resistivity, seismic wave velocity three-dimensional distribution and uncertainty quantitative evaluation results, and reducing blind areas of goaf judgment.

The invention belongs to the technical field of remote sensing monitoring, and particularly relates to a sequential SAR crop classification method based on lightweight linear attention. The method comprises the following steps of: firstly, efficiently extracting spatial characteristics of an image of each time step in a time sequence image by utilizing a weight-shared U-Net encoder by utilizing spatial and temporal characteristics of the time sequence SAR image; lLTAEBlock is used for extracting spatiotemporal features from time sequence advanced spatial features, FAVOR + is used for achieving linear calculation complexity, a shared query matrix serves as a learnable parameter, the calculation amount and the parameter amount are reduced, global information interaction in the time dimension is achieved, and modeling is conducted on the complex phenological relation of crops; and the decoder retains the deep spatial-temporal features and fuses the time sequence shallow spatial features to finally obtain a prediction result with the same spatial scale as the input data. And under the constraint of the loss function, adjusting through an optimizer to obtain a crop classification model with the best fitting. The method is especially suitable for crop classification of long-time-sequence SAR images, reduces the need of a memory, and improves the crop classification efficiency.

The invention provides a network node classification method based on a multilayer graph neural network model, and the method comprises the steps: constructing a graph according to network nodes, carrying out the preprocessing of initial node features in the graph, and obtaining an initial embedded vector; according to the initial embedding vectors of the node and the neighbor node thereof, updating the node representation by adopting a layered message passing mechanism; according to the initial embedded vectors of the nodes and the neighbor nodes thereof, the graph attention network uses an attention mechanism to calculate weights for the neighbor nodes of each node and then dynamically updates feature vectors of the nodes; a multi-head attention mechanism is adopted to splice and merge the feature vectors of the nodes output by the graph attention network and the updated node representation, and the comprehensive feature vector of each node is obtained; the comprehensive feature vectors are further optimized through graph contrast learning and a node embedding module, and optimized features are obtained; and obtaining predicted node classification according to the optimization features. According to the method, complex features of heterogeneous graph data can be effectively captured, the method has good robustness for an over-smoothing problem, more accurate heterogeneous network representation learning is realized, and the method has advanced performance and robustness in a node classification task.

The invention provides a semantic similarity analysis method for science and technology project management, and belongs to the technical field of information, the semantic similarity analysis method for science and technology project management comprises the following steps: preprocessing collected project documents, including text cleaning, word segmentation and stop word removal; extracting vocabulary features in the document, and converting the vocabulary features into numerical vector representation; calculating the semantic similarity between the documents or terms; and applying a similarity analysis result to document management and information retrieval: performing automatic preprocessing on the document, including text cleaning, word segmentation, stop word removal and standardization processing, so that a system can quickly prepare document data, prepare for subsequent analysis, automatically extract vocabulary features in the document by using an advanced word embedding model (such as Word2Vec, GloVe or BERT), and perform data processing on the document. And the information is converted into a numerical vector for representation, so that the requirement of manual intervention is greatly reduced.

The invention relates to the technical field of data management, in particular to an artificial intelligence-based automatic data grading management method, which comprises the following steps of: acquiring to-be-graded data through a multi-source data acquisition channel, and performing data preprocessing on the to-be-graded data to generate a training data set; constructing a feature extraction network based on an improved Transform architecture, extracting data features in the training data set in combination with a cross-modal mechanism, and generating a dynamic feature mapping matrix; and constructing a time-space domain fusion model based on a graph neural network by using the dynamic feature mapping matrix, calculating a data sensitivity index, and performing adaptive classification. According to the method, complex cross-modal data can be processed, time-space domain features are fused, and efficient hierarchical management is realized through an improved deep learning model, so that the problems of data diversity, real-time performance and accuracy of an existing data hierarchical method are effectively solved.

The invention discloses a data set classification method and system based on unbalanced incremental learning, and the method comprises the steps: obtaining an original data set, and carrying out the preprocessing of the original data set, and obtaining a training set and a test set; determining an unbalanced incremental learning model, and performing model training and model optimization on the unbalanced incremental learning model according to the training set and the test set to obtain a data set classification model; and obtaining a current to-be-processed data set, inputting the current to-be-processed data set into the data set classification model, and outputting a data set classification result. According to the method, the non-equilibrium incremental learning model is trained and optimized to obtain the data set classification model, and the classification efficiency and accuracy of the data set can be effectively improved through the data set classification model.

The invention provides a text classification method based on quantum transfer learning, and belongs to the field of fusion of quantum computing and artificial intelligence. In consideration of complex feature space and nonlinear characteristics in text classification, quantum circuit design, a self-attention mechanism and a quantum transfer learning process are optimized, so that the learning efficiency and classification accuracy of the model are improved. The high-dimensional feature representation and a complex nonlinear decision process are converted into a quantum self-attention network structure, an optimal strategy of text classification is obtained by utilizing a complex quantum kernel self-attention network (CQKSAN) model, and a quantum superposition and entanglement mechanism is introduced to enhance the expression ability of the model. A simulation result shows that compared with a traditional deep learning algorithm and other mixed quantum-classical algorithms, the algorithm provided by the invention has higher classification precision and learning efficiency. The method not only shows the potential of a mixed quantum-classical method, but also provides a basis for further research of a future full-quantum learning system.

The invention discloses an unmanned aerial vehicle traffic jam and personnel gathering detection method based on AI identification, and the method comprises the following steps: S1, obtaining a real-time video and three-dimensional space data of a target region, and constructing a data set; s2, preliminarily processing the data set, and extracting key features; s3, the extracted key features are transmitted to a cloud server in real time through a 5G network, and an AI model is constructed and optimized; s4, performing multi-target detection and classification on the received key features to generate a multi-target detection result; s5, performing global scheduling optimization by adopting an intelligent scheduling algorithm of fuzzy logic control and particle swarm optimization; s6, identifying possible equipment faults in advance by using a graph neural network and an adaptive lifting algorithm; s7, monitoring the flight state and the recognition result of the unmanned aerial vehicle in real time; and S8, displaying the identification result and the analysis report through a visual interface. According to the invention, AI identification and intelligent scheduling are combined, unmanned aerial vehicle path planning and maintenance are optimized, and the method has the advantages of high efficiency, safety and high adaptability.

The invention relates to the technical field of quality evaluation, and discloses a lightweight beef quality evaluation method based on unsupervised feature learning, and the method comprises the steps: obtaining original hyperspectral data of beef as real data, and generating high-quality sample data based on a generative adversarial network model; preprocessing the high-quality sample data, mapping, reconstructing and fusing the preprocessed sample data, extracting spectral and spatial features of different levels, and fusing or splicing the spectral and spatial features with feature values of other auxiliary data; the fusion sample features are mapped and fused, sample data of specific tiny disturbance similar to real data are generated, the sample data and the real data are alternately input into a Transform model, and parameters of the Transform model are updated; the beef quality is evaluated on the basis of the Transform model with the updated parameters; according to the method, the accuracy, objectivity, rapidness, non-destructive property and comprehensiveness of beef quality evaluation are improved.

The invention discloses a cultivated land interplanting forest identification method combining mixed pixel decomposition and deep learning. The method comprises the following steps: generating basic classification data by processing remote sensing image data; on the basis of historical monitoring data and classification standards, cultivated land interplanting forest sample labels are established, and a standardized sample set is constructed; calculating end member abundance and a cross end member contribution ratio by using a mixed pixel decomposition technology, and completing preliminary classification in combination with a region area; designing a deep learning network architecture, and performing model training and optimization by using a multi-scale and direction feature extraction technology; automatically extracting spectrum, texture and spatial features through the model, and fusing to generate a classification result; and performing performance evaluation on the model by adopting a verification set and a test set, and optimizing classification parameters. According to the invention, accurate classification and identification of cultivated land interplanting forest ground feature targets are realized.

The embodiment of the invention discloses a dangerous chemical identification method, and the method comprises the steps: obtaining chemical information data, and constructing a dangerous chemical semantic database according to the chemical information data through employing a deep learning multi-modal data fusion algorithm; according to naming rules and attributes of chemicals, defining text variables and numerical variables, extracting hazardous chemical judgment conditions from the chemical information data, and establishing a hazardous chemical rule base according to the text variables, the numerical variables and the hazardous chemical judgment conditions; according to the chemical information data, establishing a hazardous chemical data model based on a graph neural network technology; constructing a hazardous chemical substance identification system by using the hazardous chemical substance semantic library, the hazardous chemical substance rule library and the hazardous chemical substance data model; and obtaining to-be-classified chemical information, and classifying to-be-classified chemicals in the to-be-classified chemical information by using a hazardous chemical identification system to obtain a hazardous chemical judgment result. According to the invention, more intelligent and accurate dangerous chemical identification is realized.

The invention provides a meta-learning-based continuous casting blank defect classification method, system and equipment. The meta-learning-based continuous casting blank defect classification method comprises the steps of 1, preprocessing an obtained public image classification data set and an obtained continuous casting blank image containing defects; 2, randomly forming a meta-task through meta-learning task allocation on the preprocessed public image classification data set, and inputting the meta-task to a preset image meta-learning classification model to obtain a trained image meta-learning classification model; step 3, performing meta-learning task allocation on the preprocessed continuous casting blank image containing defects to form a meta-task, and performing fine adjustment on the trained image meta-learning classification model by using the obtained meta-task; 4, classifying the defects of the continuous casting blank to be processed by utilizing the final image element learning classification model; according to the method, the problem of dependence on a large amount of labeled data in a traditional defect detection method can be effectively solved, and the classification capability of the model under the condition of few samples can be improved.

The invention provides a network security attack classification detection method and system based on a random forest, and relates to the technical field of network security. The method comprises the following steps: collecting network flow data; determining target network traffic data through a time-based sliding window algorithm; extracting a plurality of network traffic characteristics in the target network traffic data; calculating an average entropy value of the network flow characteristics; judging whether the average entropy value of the network flow characteristics is within a preset entropy value range or not; if yes, preliminarily determining the target network traffic data as normal traffic data; otherwise, preliminarily determining the target network traffic data as abnormal traffic data, and entering the next step; performing data processing on the abnormal traffic data; and carrying out classification detection on the processed abnormal flow data through an improved random forest algorithm to obtain an accurate detection result. The feature importance can be deeply analyzed, the classification efficiency is high, and the time consumed in the classification process is short.

The invention relates to the technical field of land coverage remote sensing monitoring, in particular to a time sequence SAR crop classification method based on multi-scale cross attention. According to the method, the complex phenological relationship of crops is considered, the features of time and space dimensions of a time sequence SAR image are fully utilized, an input array is mapped to a high-dimensional feature space through an encoder, and multi-scale local space features are extracted; constructing a multi-scale cross attention module MCMSABlock to extract multi-scale time features of the time sequence SAR image block, taking a weighted result of an original scale as a query matrix of other scales, indexing and weighting, and extracting remote dependency information at different time scales; the decoder adopts a plurality of up-sampling modules to gradually recover the spatial scale, and multi-scale time features are fused while multi-scale local spatial features are reserved by utilizing jump connection. The method is suitable for crop diversity and complex time sequence SAR scenes, the requirement for a memory is reduced while an accurate crop classification result is obtained, and the classification efficiency is improved.

The utility model discloses a high-precision airflow classifier, and relates to the technical field of sorting. The high-precision airflow classifier comprises an airflow classifier shell and a classification device, the classification device comprises a feeding port, the feeding port is fixedly connected to the upper end of the airflow classifier shell and extends into the airflow classifier shell, the upper end of the feeding port is fixedly connected with a driving motor, and the output end of the driving motor is fixedly connected with a rotating shaft; the lower end of the rotating shaft is fixedly connected with a dispersing disc, the surface of the dispersing disc is fixedly connected with baffles, the surface of the dispersing disc is rotationally connected with blades, and resin raw material particles collide with the baffles and the blades through the centrifugal effect of rotation of the dispersing disc, so that the resin raw materials are scattered, and the resin raw materials are evenly distributed in the airflow classifier shell; the uniform distribution ensures that the resin raw materials can be subjected to uniform airflow and centrifugal force, so that the stability and precision of the grading process are improved, and the grading efficiency of the device is improved.

The invention relates to the technical field of intelligent garbage cans, in particular to an intelligent classification garbage can based on screw drive, which comprises a main body frame, the top of the main body frame is provided with a top cover, the top cover is provided with a garbage throwing port, and the front side surface of the main body frame is provided with a liquid crystal display controller; a spiral conveying mechanism is arranged below the garbage throwing opening and used for achieving garbage separation. A synchronous belt and a roller mechanism are arranged below the spiral conveying mechanism and are used for realizing garbage conveying; a storage mechanism for receiving garbage is arranged below the synchronous belt and the roller mechanism, and a rotary chassis mechanism is arranged below the storage mechanism; a battery is arranged on one side of the synchronous belt and the roller mechanism, and a compression mechanism is arranged on the other side of the synchronous belt and the roller mechanism and used for compressing the recyclable garbage. The garbage classification efficiency can be effectively improved, the intelligent degree of the garbage can is improved, and the difficulty of later garbage centralized classification treatment work is reduced.

The invention belongs to the technical field of information logistics, and particularly relates to an intelligent logistics control system and method based on machine vision and a storage medium, and the intelligent logistics control method based on machine vision comprises the steps: obtaining discharging information; controlling a visual identification module to run to a photographing position according to the discharging information so as to identify material grabbing position information and identification code information of an identification code; matching a discharging drawer of the storage cabinet module according to the identification code information, and generating matching information; and a robot carrying module is controlled to be matched with a transfer module according to the matching information and the material grabbing position information, so that the robot carrying module places the grabbed packaging parts on the transfer module, and the packaging parts are stored in a storage cabinet module through the transfer module. According to the invention, the classification, storage and taking efficiency of the packaging parts is improved, and the complexity and errors of manual operation are reduced.

The present invention belongs to the technical field of data classification and grading. The present invention discloses a method for grading and categorizing public data based on multiple dimensions, including: setting multiple classification dimensions and specific categories, formulating levels and rating processes; establishing a mapping relationship between public data metadata and categories, marking direct and indirect dimensions; setting keyword groups for indirect dimensions, and determining classification vectors of various categories based on historical classification data; obtaining target data and its metadata, and determining direct dimension categories according to the mapping relationship; extracting features from the target data to obtain feature vectors, and comparing them with indirect dimension classification vectors to determine categories; integrating the category results of direct and indirect dimensions to form classification data of the target data; determining the initial rating level according to the classification data; determining the final level according to the rating process, and storing the classification data and levels. Classification vectors are established through historical data, and classification is automatically performed according to the calculated similarity, thereby improving the efficiency of classification work.

The invention discloses an igneous rock lithology identification method based on an engineering optimization cascade forest, and relates to the field of lithology identification, and the igneous rock lithology identification method based on the engineering optimization cascade forest comprises the following steps: 1, randomly selecting logging curves of different igneous rocks from a to-be-identified region, and carrying out the preprocessing of the logging curves; the CXDF method provided by the invention only depends on conventional logging data, can not depend on expensive data such as stratum element logging, and is low in cost, high in accuracy and higher in universality; the CXDF method combines a depth forest and an extreme gradient lifting method, so that the problem of overfitting is avoided, and excellent classification efficiency can be ensured when a back-to-undersampling data set is faced; in addition, the CXDF method also performs engineering optimization on the combined depth forest and extreme gradient lifting method, and column block parallel learning is adopted for extreme gradient lifting, so that the calculation amount is remarkably reduced, and the calculation cost is also greatly reduced.

The invention discloses a client information management method and system based on real estate transaction, relates to the technical field of client information management, and solves the technical problem that client information management cannot be evaluated according to a real-time product demand trend, so that client types cannot be distinguished according to different demand trend stages in the prior art. Specifically, a demand trend evaluation unit evaluates the demand trend of a real-time sales product, collects demand trend information, substitutes the demand trend information into a formula to obtain a demand trend evaluation coefficient in a real-time circulation stage, and deduces that the current circulation stage is in a purchaser market or a supplier market according to coefficient comparison; a customer stage analysis unit performs customer stage analysis according to the real-time circulation stage, obtains the speed-to-time ratio information of a supplier and the speed-to-time ratio information of a purchaser, deduces whether a current customer is a customer in a knowing stage or a customer in an intention stage according to information comparison, and correspondingly sends the customer to a customer information management platform; the label classification setting unit performs label classification setting on clients.

The invention aims to provide a hyperspectral image classification method based on a Transform parallel GRU algorithm, and the method comprises the following steps: A, constructing a deep neural network model which comprises an improved Spectral Former framework and a GRU extraction time sequence feature network; b, training the improved deep neural network model to obtain a trained deep neural network model; c, combining the basic wave band data in the hyperspectral remote sensing image data to be measured with the SWIR wave band data, and then sequentially nesting the basic wave band data and the SWIR wave band data in pairs to obtain a two-dimensional data set; d, the two-dimensional data set is processed through an improved SpectraFormer frame, a time sequence feature network is extracted through GRU, and two branch processing results are processed through tensor flattening; and E, adding and fusing the processing results of the two branches, and performing 1 * 1 convolution to obtain a final output result. According to the method, the problem of sample imbalance can be better solved, and high-performance pixel-level hyperspectral image classification can be better realized.

The invention relates to a DBSCAN classification method, device and equipment based on secret sharing privacy protection and a medium, and relates to a service party, a requesting party and three independent and non-collusion proxy computing parties, and the service party and the requesting party respectively have different characteristics of the same sample. The method comprises the following steps: a service party and a requesting party carry out secret sharing encryption on own sample characteristics and then send the sample characteristics to an agent calculation party; the agent calculation party calculates a reachable matrix and sends the calculated reachable matrix to the requester; and the requester executes a DBSCAN algorithm based on the reachable matrix to realize data classification. Compared with the prior art, the method has the advantages of good data security, high calculation efficiency and the like.

The invention belongs to the technical field of hydrocyclones, and discloses a two-stage series integrated nested classification hydrocyclone which comprises a first-stage cylinder, the top end of the first-stage cylinder is connected with a top cover, and the top cover of the first-stage cylinder is connected with an overflow pipe; the bottom end of the first-stage cylinder is connected with an inverted outer circular truncated cone cylinder, an upright inner circular truncated cone cylinder is arranged in the outer circular truncated cone cylinder in a sleeved mode, and the bottom end of the outer circular truncated cone cylinder and the bottom end of the inner circular truncated cone cylinder are connected in a sealed mode through an annular groove. A second-stage cylinder is arranged in the first-stage cylinder in a sleeving manner, one end of the second-stage cylinder is connected with the top cover, the other end of the second-stage cylinder is connected with a second-stage circular truncated cone cylinder, the second-stage circular truncated cone cylinder is arranged in the inner circular truncated cone cylinder in a penetrating manner, and the second-stage cylinder is connected with the inner circular truncated cone cylinder; a spiral guide plate is connected in the second-stage cylinder, and a plurality of spiral inlets are formed in the side wall of the second-stage cylinder; the invention solves the problems that the underflow is fine during the grading operation of the cyclone, the grading precision of the single cyclone is insufficient, and the energy loss of the intermediate pipeline of the series cyclone is too much.

The invention discloses a watermelon quality grading method based on multi-source information fusion, and belongs to the technical field of agricultural information.The method comprises the steps that firstly, a data set is obtained, and the data set comprises images of watermelons, sound and vibration signals during knocking, skin temperature data, weight data, varieties, sweetness, moisture content, hardness and quality scores; performing data preprocessing on the data set; constructing a watermelon variety identification model, a quality index prediction model and a comprehensive evaluation model, and training the three models by using the preprocessed data set; and obtaining a trained watermelon variety identification model, a quality index prediction model and a comprehensive evaluation model, and performing watermelon quality grading by using the obtained watermelon image, the sound and vibration signals during knocking, the skin temperature data and the weight data.

The invention provides a chip performance grade prediction method, and relates to the technical field of chip detection.The chip performance grade prediction method comprises the steps that firstly, attribute parameters of a to-be-tested chip are obtained; thirdly, performing feature extraction on the attribute parameters of the to-be-tested chip by adopting a feature extraction model to obtain feature parameters; and finally, classifying the characteristic parameters by adopting an extreme learning machine to obtain a performance grade predicted value of the chip. Wherein the feature extraction model is a neural network model, the feature extraction model performs parameter optimization by adopting a preset parameter optimization method in advance, and the extreme learning machine performs training by adopting a restart strategy in advance. According to the embodiment of the invention, the feature extraction model is adopted to perform feature extraction on the collected attribute parameters of the chip, and then the extreme learning machine is adopted to classify the extracted feature parameters, so that the performance grade of the chip can be quickly and accurately obtained.

The invention discloses an object classification method and device, equipment and a storage medium, and the method comprises the steps: obtaining object features of a plurality of objects, and obtaining an object network constructed based on the plurality of objects; graph segmentation processing is carried out on the object network to obtain a plurality of object sub-graphs, and each object sub-graph comprises at least one node; calling a graph neural network model to perform unsupervised graph representation learning on each object sub-graph according to the object features of the plurality of objects to obtain node features of each node; and according to the node features of each node, the objects represented by the corresponding nodes are classified, so that the accuracy of object classification results (namely category information obtained by classification) is improved.

The invention provides an electrical equipment fault diagnosis method and device based on artificial intelligence, and relates to the technical field of fault recognition, and the method comprises the steps: obtaining historical operation data collected by a sensor installed in a power system, and enabling the historical operation data to serve as an original data set; expanding the original data set; inputting the expanded original data set into a feature extraction model to train the feature extraction model; training a feature dimension reduction model, and training a classifier model; and inputting real-time operation data collected by a sensor installed in the power system into the trained feature extraction model, the feature dimension reduction model and the classifier model in sequence, and outputting corresponding fault categories. The diversity of a data set is enhanced through a data expansion technology, the generalization ability of a model is improved, feature extraction, feature dimension reduction and classification processing are carried out, deep analysis and processing of data are achieved, and therefore the operation state and the possible fault type of the electrical equipment can be judged more accurately.

The invention discloses a medical image classification method and system based on comparative learning, and a storage medium, and relates to the technical field of long-tail medical image classification. A long-tail medical image data set is divided into a training set and a test set, and weak data enhancement and strong data enhancement are respectively performed on images of the training set in a batch processing form according to a preset scheme; performing a comparative learning task on the obtained weak data enhanced image and the strong data enhanced image through a deep convolutional neural network, learning network parameters, and obtaining the deep convolutional neural network after parameter optimization; the long-tail medical images in the test set are classified; through the prototype enhancement contrast learning strategy, the learnable prototype is generated for data enhancement, the balance implicit enhancement contrast learning loss is obtained, and the method has the advantages of high precision, high efficiency, low cost, wide applicability and the like.

The invention discloses an HSI classification method of LDA based on quaternion rayleigh entropy and an e-commerce application device, is applied to a hyperspectral image (HSI) classification method and an e-commerce device, and relates to the technical field of hyperspectral image classification. According to the method, a target projection vector matrix corresponding to a to-be-classified hyperspectral image is determined from a decomposition result of a global quaternion divergence matrix and a decomposition result of an inter-class quaternion divergence matrix, and the inter-class quaternion divergence matrix facilitates effective data classification in a quaternion space. And the quaternion projection vector matrix expresses the characteristics of the quaternion in a specific direction. Therefore, the calculation complexity and the calculation amount when the quaternion discrimination method is used for processing HSI classification are reduced, and the HSI classification efficiency is improved.

The invention relates to an efficient beneficiation process for recycling iron from iron tailings, which comprises the following steps of: feeding magnetite tailing pulp into a tailing recycling machine, feeding concentrate of the recycling machine into a first-section magnetic separator, and feeding concentrate of the first-section magnetic separator into a concentration magnetic separator; directly feeding concentrate of the concentration magnetic separator into a tower mill, feeding discharged ore of the tower mill into a swirler, and returning settled sand of the swirler to the tower mill to form closed-circuit ore grinding; overflow of the cyclone is fed into a second-stage magnetic separator, second-stage magnetic separator concentrate with the grade being 38% or above is obtained, and the second-stage magnetic separator concentrate is fed into a moxa sand mill; ore discharged by the moxa sand mill is fed into a third-section magnetic separator, concentrate of the third-section magnetic separator is fed into a fourth-section magnetic separator, concentrate of the fourth-section magnetic separator is fed into an elutriator, the concentrate of the elutriator is final concentrate, and the grade reaches 66% or above; the elutriator returns to the first section, the second section, the second section, the third section and the fourth section, and tailings of the magnetic separators are converged into comprehensive tailings. By optimizing the technological process, the concentrate grade is improved by more than 2%, and meanwhile, the tailing grade is reduced by 0.3%.