22results about How to "Fast classification" patented technology

The invention relates to the technical field of data security, in particular to an unstructured video data automatic classification method, which comprises the following steps: S1, video data preprocessing: standardizing video data to a uniform format and size, and carrying out noise processing; s2, video data feature extraction and multi-mode feature fusion: feature extraction is performed on the preprocessed video data from three modes of audio, video and text, time sequence processing is performed, and multi-mode feature fusion is performed; s3, video data same-category matching: classifying the fused multi-modal features to complete video classification; according to the invention, multi-modal information in a video can be captured more accurately, and automatic processing of video data is realized; high processing efficiency and classification accuracy are kept in large-scale data, meanwhile, the degree of automation is improved, the necessity of manual participation is reduced, and the overall process is optimized.

The invention provides a zero sample image classification system and method, and the system comprises a teacher model and a student model which are the same in architecture, and each of the teacher model and the student model comprises a visual encoder, a semantic encoder, a visual-semantic alignment module and a zero sample classification module; a visual encoder of the teacher model is constructed in a manner of cascading a CNN (Convolutional Neural Network) and a Transform; selecting a BERT network as a semantic encoder of the teacher model; the visual-semantic alignment module is used for constructing a teacher model and a student model based on a cross-modal attention mechanism; a full connection layer is adopted as a zero sample classification module of the teacher model and the student model; a visual encoder of the student model is constructed by adopting a lightweight EnviroNet network; and a semantic encoder of the student model is constructed by adopting a Core-BER network. The method has the advantages that under zero sample setting, the high unseen category classification performance can be kept, meanwhile, the model complexity is reduced, and deployment on actual equipment is better facilitated.

The invention provides a zero sample image classification system and method, and the system comprises a visual feature extraction module which is used for obtaining image visual feature data according to an input unseen category image; the semantic information extraction module is used for obtaining image semantic information data according to the input text information corresponding to the unseen category image; the cross-modal feature fusion module is used for obtaining aligned visual-semantic feature data according to the input image visual feature data and image semantic information data; and the classification module is used for obtaining a classification result of the image category according to the input aligned visual-semantic feature data. Compared with the prior art, the method has the advantages that image information, auxiliary information and shared information between the image information and the auxiliary information can be better utilized, and under the setting of zero samples, the classification precision of visible categories can be kept at a high level, and the classification performance of unvisible categories can be effectively improved.

The invention is suitable for the field of advertisement auditing, and discloses an advertisement content isolation auditing method, system and device and a medium, and the method comprises the steps: receiving advertisement content; the advertisement content is classified, and text advertisements, picture advertisements and video advertisements are identified and classified; the advertisement contents of different classifications are audited respectively; wherein when the picture advertisements are classified, digital watermarks are embedded in the picture advertisements, and the digital watermarks comprise category information of the picture advertisements. In the picture advertisement classification and auditing process, the digital watermarking technology is innovatively adopted in the picture advertisement classification and auditing method. By embedding the category information of the picture advertisement into the digital watermark and adding the watermark into the picture advertisement, quick classification and efficient management of the picture advertisement are realized, the accuracy and efficiency of picture advertisement classification are improved, convenience is provided for subsequent auditing work, and the user experience is improved. And the overall quality and efficiency of advertisement auditing are further improved.

The invention belongs to the technical field of archive management, and particularly relates to an intelligent archive management system based on multi-type analysis, which is characterized in that classification term priorities of various archives are determined on the basis of professional term distribution of classified documents in multi-type archives, and key terms in to-be-classified documents are extracted in actual classification operation, so that the classification efficiency is improved; according to the method and the system, document classification is carried out, and the document classification is matched with predefined classification term priorities to realize efficient classification, so that the classification speed can be improved, the occupancy rate of system resources can be effectively reduced, and high-performance operation of the archive management system is ensured; the classification accuracy is verified by carrying out similarity comparison on the newly classified documents and the classified documents in the classified archive types to which the documents belong, errors in initial classification can be found and corrected in time, rapid re-classification is facilitated, and it is ensured that subsequent document retrieval and access are not remarkably affected.

The invention discloses an intelligent line fault detection method for an active power distribution network, and belongs to the technical field of line fault detection, and the method comprises the steps: S1, taking the fault voltage and the voltage fundamental wave of each measurement point of an active power distribution network line as characteristic indexes for judging the operation state of the line; s2, extracting frequency band voltage peak values, inter-phase voltage differences and sixth harmonic components of line measurement points in normal and fault states as fault feature samples; s3, performing data preprocessing; s4, splitting the training set and the test set; s5, inputting the classified data set into a LightGBM (LightGBM) model for classification; s6, combining a plurality of independent decision tree classifiers in the LightGBM to generate a strong classifier; s7, inputting the output value of the strong classifier into the DNN for learning and training; s8, performing fault detection performance evaluation; and S9, outputting a fault detection result. The problems that after a large number of distributed power supplies are connected to the power distribution network, the system topological structure is complex, and line faults are difficult to locate are solved.

The invention provides a cereal classification method and device based on a pulse neural network, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. The grain classification method based on the pulse neural network comprises the steps of obtaining a first pulse sequence corresponding to an image of to-be-predicted grains; according to the first pulse sequence, utilizing a grain type prediction model to obtain the type of the to-be-predicted grain; wherein the grain type prediction model is a pulse neural network which is obtained through incremental learning and is used for predicting grain types. According to the invention, the cereals can be classified efficiently and accurately.

The invention relates to a target classification method and device, computer equipment and a storage medium. The method comprises the steps of performing dual-channel feature extraction on a plurality of targets in a to-be-processed image to obtain semantic feature information and spatial feature information corresponding to each target, performing fusion processing on the semantic feature information and the corresponding spatial feature information of each target, determining to-be-processed feature information of each target, and determining the to-be-processed feature information of each target based on the to-be-processed feature information of each target. The targets are correspondingly classified into different types of target sets to complete classification processing, and the difference value between the different types of targets in the multiple targets is smaller than a preset difference threshold value. By the adoption of the method, fine-grained classification can be achieved, the fine-grained classification difficulty is reduced, in the processing process, the multi-type feature information, namely semantic feature information and spatial feature information corresponding to all the targets, of all the targets can be obtained, then accurate classification is achieved based on the multi-scale feature information of all the targets, and the classification efficiency is improved. Therefore, the accuracy of fine-grained classification can be improved.

The invention discloses a semi-supervised image classification method based on anchor points and adaptive graph learning, belongs to the technical field of traditional machine learning, and provides various and reliable data for semi-supervised image classification by adopting data sets of different scales and types of digital images or color pictures; according to the constructed semi-supervised classification model, prediction sample labels can be converted into prediction anchor point labels through anchor points and a linear propagation mode, then the labels of the samples are obtained through linear combination, and the classification speed is effectively increased through the characteristic that the number of the anchor points is far smaller than the number of the samples; an adaptive graph learning method is adopted to take an adaptive graph as an object of iterative optimization, and the adaptive graph and a sample pseudo-label matrix are learned at the same time, so that the influence of an initial adjacent graph on the classification precision is reduced, and the classification precision is improved.

The present invention discloses a method and computer device for fall detection, the method comprising: obtaining a detection video of an object to be detected, wherein the detection video comprises a plurality of video frames; determining the detection tags corresponding to each of the video frames to obtain a detection tag group corresponding to the detection video, wherein the detection tags corresponding to the video frames reflect the position of the object to be detected corresponding to the video frames; and determining the fall detection result of the object to be detected according to the detection tag group. In the present invention, the detection tag group corresponding to the detection video is determined, each detection tag in the detection tag group reflects the position of the object to be detected in the video frame corresponding to the detection tag, and then determining whether the object to be detected falls according to each detection tag group. The amount of data obtained is small, no complex calculation is required, and the classification speed is fast. After each detection video is obtained, the fall detection result corresponding to the detection video can be quickly obtained, and real-time detection can be achieved.

The invention discloses a financial bill intelligent classification method and device based on artificial intelligence. The method comprises the following steps: receiving a financial bill image; inputting the financial bill image into a pre-trained convolutional neural network model, and outputting a financial bill category; the convolutional neural network model comprises a residual feature encoder and a classifier; the residual error feature encoder is used for extracting a layout topological structure and a landmark pattern of the financial bill image; the classifier is used for determining the type of the financial bill by using the layout topological structure and the landmark pattern; and the landmark pattern reflects the category and authenticity of the financial bill. According to the invention, the accuracy, robustness and efficiency of financial bill distinguishing can be improved.

The present invention provides a global learning device and method for hyperspectral image classification. The device includes: an encoder and a decoder; the encoder includes a spectral dimension adjustment layer, a first feature extraction layer and a second feature extraction layer in sequence according to the image processing order; the first feature extraction layer includes three MLBSA structure layers stacked together; the MLBSA structure layer includes three shuffled spectral attention SSA modules, two MLB layers and a downsampling layer; the input of the first SSA module is added and fused with the output of the downsampling layer after passing through the Zero‑padded convolution module, and the output is used as the output of the MLBSA structure layer; the decoder includes a first upsampling layer, a Concat layer and an output layer in sequence according to the image processing order; the output of the first MLBSA structure layer in the first feature extraction layer is used as the input of the first upsampling layer, the output of the second feature extraction layer and the output of the first upsampling layer are fused through the Concat layer, and the fusion result is processed by the output layer to complete the classification of the hyperspectral image.

The invention relates to a high-speed data packet classification method based on self-adaptive tuple replacement and application, and belongs to the technical field of data packet classification in the field of computer networks. By constructing the mixed data structure, the decision tree and the tuple are combined, and bottleneck branches are detected and replaced in the rule updating process, so that the data packet classification efficiency is improved. According to the method, a low-efficiency branch in a decision tree is replaced by a lightweight hash table tuple structure, so that the stability of the classification speed is kept under the condition that the rule is frequently updated. According to the method, the classification performance can be remarkably improved while memory use is optimized, and the method has good hardware deployment adaptability and is suitable for rapid packet classification in a large-scale network environment.

The invention relates to a time sequence and convolution combined computing power weblog anomaly detection method and system. According to the method, template classification of massive network calculation logs is accelerated by utilizing a hash optimized log template analysis algorithm based on an analysis tree. And meanwhile, the log variables can effectively construct spatial features by utilizing Hash-based spatial coordinate mapping. In addition, the log sequence features based on semantic information and the original sequence features of the logs are considered by combining the sequential network and the convolutional network, and the variable space features on the time sequence are also fully considered, so that the neural network model in the method has higher detection accuracy and robustness.

The invention relates to a crop classification method and system based on coded aperture snapshot calculation spectral imaging, and the method comprises the following steps: S1, capturing an agricultural scene through an optical encoder and an imaging element based on compressed sensing, and obtaining an output result of the optical encoder; s2, constructing a data set of an output result of the optical encoder and a real label of the crop variety, designing a deep learning decoder, constructing a deep learning framework, respectively carrying out training, testing and verification, and finally obtaining a weight file of the model through gradient descent; and S3, collecting compressed data through an optical encoder, and obtaining a crop classification result of an agricultural scene and a hyperspectral image of the corresponding scene in real time through network reasoning by using the obtained weight file. According to the crop classification method and system, an integrated method of optical hardware coding and decoding based on the deep learning network is used for crop classification, the classification speed is greatly improved, and the data storage cost is reduced.

This invention proposes a wafer surface defect classification method based on deep learning networks. This method can quickly and accurately identify wafer surface defect patterns and pinpoint their causes. The method aims to address the problems of high manual labor intensity and low detection efficiency in traditional wafer defect detection methods. The specific process includes: constructing and training a wafer defect detection and classification model based on the WM-811K dataset. The defect detection model is a binary classification model used to determine the presence of defects in the wafer image, while the classification model is a multi-class model used to determine the specific defect pattern category. The sample to be tested is input into the trained wafer defect detection and classification model to determine its defect pattern. Finally, by analyzing the causes of defect patterns in known samples, the causes of defect patterns in the sample to be tested are inferred, continuously optimizing the process flow and improving wafer product yield.

The invention discloses a text classification method and device, equipment and a medium. By introducing a classification-limited text prompt, a text classification process can be guided more accurately. The classification limited text prompt not only provides candidate category information to which the to-be-classified text possibly belongs, but also defines the output specification of the classification result. The restrictive information enables the large text classification model to more accurately judge the category of the text when processing a complex or fuzzy classification task, and meanwhile, the normalization and consistency of output results are ensured. Meanwhile, as the candidate range is reduced in the classification result generation process of the large text classification model, the decoding speed can be greatly improved, and the time consumption is reduced. By combining the coding feature data, the target hidden layer representation and the prefix tree corresponding to the classification limiting text prompt, the large text classification model can efficiently determine the target category from the candidate category information.

This invention relates to a computer-implemented method for automatically characterizing small bowel lesions in capsule endoscopy images, comprising detecting small bowel lesions in medical images by using a convolutional image feature extraction step, followed by an architecture that classifies pixels as lesions or non-lesions into one or more categories.

The invention provides a substation security equipment operation state monitoring method and system, and belongs to the technical field of electric power, and the method comprises the steps: collecting historical operation data of substation security equipment, and preprocessing the collected historical operation data; constructing a single-feature primary classifier, and performing primary pre-monitoring on each type of data; constructing a multi-feature integrated monitoring model; training a monitoring model by using the preprocessed historical data to obtain an optimal monitoring model; and obtaining the current operation data of the security and protection equipment of the transformer substation, and performing integrated monitoring on the preprocessed current operation data to obtain the operation state of the security and protection equipment. According to the invention, the robustness and speed of monitoring the operation state of the substation security equipment are improved through the integrated learning model.

The present invention discloses a pituitary neuroendocrine tumor classification system and method based on multimodal fusion of text and multiscale images, comprising the following steps: collecting and preprocessing the multimodal data of patients with pituitary neuroendocrine tumors before surgery, surgery, and follow-up; based on the prediction model of pathological classification, dividing the preprocessed multimodal data into text data and image data, and extracting the features of each modal data respectively, interacting the extracted features of each modal data, and obtaining fused multimodal features; using the fused multimodal features, training the prediction model of pathological classification; inputting the multimodal data of the patient before surgery, surgery, and follow-up to the prediction model of pathological classification trained by training, and obtaining the corresponding classification information of pituitary neuroendocrine tumors. The present invention uses the patient's medical text information and the prediction model of preoperative multiscale imaging examination for pathological classification to achieve accurate classification of pituitary neuroendocrine tumors.

The invention discloses an automatic classification method and system based on machine sound time characteristics, and the method comprises the steps: 1) carrying out the feature extraction of an original sound signal, and obtaining a logarithm Mel spectrum spectrogram (feature matrix); 2) calculating a similarity coefficient of each frame in the logarithm Mel spectrogram by using a method based on feature similarity measurement; 3) calculating the similarity coefficient variance of the spectrogram according to the similarity coefficient in the step 2); 4) processing all the sound signals of each machine ID according to the steps 1)-3) to obtain similarity coefficient variances of all the sound signals in the machine ID; 5) comparing each similarity coefficient variance in the step 4) with an experience variance, and deciding the stability of each sound signal; and 6) counting the specific gravity of the stationary signal and the non-stationary signal, and comparing the specific gravity with a set threshold so as to judge the overall stability of each machine ID. According to the method, the stationarity and non-stationarity classification task of the complex industrial sound signals can be quickly and efficiently completed, and accurate signal classification is realized.

The application provides an image classification model construction method and device. A training data set can include multiple training images, the training images have training labels, and each classification node of an image classification model can be constructed based on the training data set, and the classification node has a shunt rule. In the process of constructing each classification node, if a target node in each classification node corresponds to a defect image corresponding to multiple training labels, multiple child nodes of the target node are constructed, that is, the image classification model is a tree structure, the number of classification nodes is determined according to the training process, and the parameter amount is relatively low, so the classification speed is faster. The target node is used for classifying the defect image corresponding to the target node according to the shunt rule of the target node, obtaining multiple groups of defect images corresponding to the multiple child nodes one by one, so that the defect image can be classified by each classification node in turn, so that the defect category of the defect image can be accurately and quickly determined, and the classification accuracy and speed are improved.