110 results about "Cosine Distance" patented technology

The invention discloses an electric power equipment safety long text knowledge retrieval method based on sparse and dense joint enhancement, which comprises the following steps of: encoding an electric power equipment safety long text and retrieval query by utilizing a pre-training language model for performing supervision and fine tuning on an electric power equipment safety field label data set, and generating a semantic word vector; a weighted sparse vector fusing semantic information and a dense semantic vector enhanced through nonlinear transformation are generated through fine-grained semantic enhancement branches; respectively calculating sparse similarity based on a common item weight product and dense similarity adopting a double-distance weighted fusion strategy combining a cosine distance and an Euclidean distance; and carrying out weighted summation on the two similarity scores through the learnable weight to obtain a final similarity, and realizing accurate sorting retrieval of the long text knowledge. The method gets rid of dependence on global features of sentence vectors, can accurately capture local key information in a long text, and has high retrieval precision and semantic robustness.

A method for calculating domain relevance scores for responses generated by LLMs is disclosed. The method includes receiving a response generated by LLM corresponding to user query. The user query is associated with a domain. The method further includes splitting the response into a plurality of response chunks using a splitting technique. The method further includes generating a plurality of response vector embeddings based on the plurality of response chunks using at least one sentence transformer. The method further includes computing a plurality of cosine distances between the plurality of response vector embeddings and a corresponding plurality of training data vector embeddings, wherein the plurality of training data vector embeddings corresponds to domain-specific training data of the LLM. The method further includes calculating a domain relevance score corresponding to the response, based on a sum of the plurality of cosine distances and a number of the plurality of chunks.

The invention provides an unmanned aerial vehicle tea tree disease detection method based on morphological perception, and belongs to the technical field of agricultural information and computer vision. The method comprises the steps of firstly collecting tea garden images and constructing a data set; then, a target detection network embedded with a differentiable morphological sensor module is constructed, and the differentiable morphological sensor module extracts multi-scale shape features by using differentiable morphological operation; an adversarial learning mechanism is introduced in training, and the distinguishing ability of the model on disease and health areas is enhanced through a discriminator; after the training is completed, mining a difficult case sample based on the cosine distance between the morphological characteristics and the disease prototype vector, and carrying out supplementary training; and finally, integrating a plurality of models with optimal performance, and generating a final detection result through weighted reasoning. The method effectively strengthens the perception capability of the model for the subtle morphological characteristics of the diseases, solves the problems of low disease detection precision and insufficient difficult sample learning in a complex tea garden background, and remarkably improves the detection accuracy and robustness.

The invention discloses a high-voltage circuit breaker state monitoring and risk prediction method, and the method comprises the steps: carrying out the dynamic calibration of a health degree model based on an electromechanical-thermoelectric-material coupling differential equation set and unscented Kalman filtering through synchronous collection of mechanical, electrical, environmental and insulation characteristic quantities; and adaptive dynamic threshold optimization is realized by combining kernel density clustering and a deep Q network, identity verification is completed by using operation fingerprint cosine distance comparison, and finally a precise risk early warning instruction is generated. According to the method, the problems of poor multi-parameter synchronism, threshold staticization, identity verification deficiency and the like in traditional monitoring are solved, the fault recognition accuracy and the early warning coverage rate are remarkably improved, and the operation and maintenance cost and the power grid power failure risk are reduced.

The invention discloses a daily load curve clustering method based on a mixed distance improved FCM algorithm, and belongs to the technical field of data processing, and the method comprises the steps: collecting daily load data of a user at a sampling frequency of 5 minutes, carrying out the corresponding data preprocessing, analyzing the fluctuation characteristics of a daily load curve, and carrying out the clustering of the daily load curve; euclidean distance representing load curve power amplitude information and cosine distance representing load curve power fluctuation direction information are constructed respectively, and then an entropy weight method is adopted to construct a hybrid similarity distance (HSD) fusing the Euclidean distance and the cosine distance as a similarity criterion between daily power load curves; replacing the Euclidean distance in the FCM algorithm with the constructed HSD, then calculating a corresponding membership degree and a clustering center, iteratively updating the membership degree and the clustering center by using a target function based on an intra-class error weighted quadratic sum, and completing daily load curve clustering according to a preset maximum iteration number; and finally, determining the optimal clustering number and the corresponding optimal daily power load curve clustering result by using the sum of intra-class errors (SAE), thereby effectively solving the prominent problems of poor effect, low efficiency and the like of the traditional power load curve clustering method.

The invention discloses a spatial data management method and system based on artificial intelligence, and relates to the technical field of spatial data management, and the method comprises the steps: defining the number of wavelet decomposition layers, calculating a self-adaptive threshold value, screening edges of an incidence matrix, generating a sparse incidence matrix, constructing a projection matrix, and projecting a feature matrix to a feature vector space through employing a matrix multiplication method. Generating a comprehensive feature matrix; and using a logistic function to define a nonlinear stream function, forming state vectors, calculating a mean value of the state vectors, fusing the mean value with the node feature matrix to form a dynamic feature matrix, and constructing a graph convolutional network model to predict the fault probability of the nodes. According to the method, fine-grained dynamic features of spatial data are accurately mined through combination of multi-scale wavelet decomposition and adaptive threshold screening, feature energy screening and a cosine distance matrix are introduced, the discrimination ability of feature selection and dimension reduction is improved, and the spatial data are extracted by using the graph convolutional network and combining a sparse embedding mechanism. And the generalization ability of the model in node fault prediction is obviously enhanced.

The invention relates to a gearbox fault diagnosis model construction method based on metric guide graph comparative learning, and belongs to the field of gearbox fault diagnosis model construction. The method comprises the following four core stages: firstly, carrying out frequency domain conversion and normalization on vibration signals of the gearbox to generate a node characteristic matrix; secondly, a cosine distance and an Euclidean distance are fused to construct a mixed distance matrix, and a fault diagnosis graph is generated based on a K-nearest neighbor algorithm; then unsupervised graph comparison pre-training is realized through graph data enhancement and a dynamic graph attention network (DGAT); and finally, weak supervision fine tuning is carried out by using a small number of marked samples to complete construction of the gearbox fault diagnosis model. According to the method, the construction of the high-precision gearbox fault diagnosis model can be realized in a scene with extremely few marked samples (1-10 samples per class), and the method is suitable for planetary gearbox health monitoring in the fields of wind turbines, helicopters, hybrid electric vehicles and the like.

The disclosed technology relates to methods, accent conversion systems, and non-transitory computer readable media for real-time accent conversion. In some examples, a set of phonetic embedding vectors is obtained for phonetic content representing a source accent and obtained from input audio data. A trained machine learning model is applied to the set of phonetic embedding vectors to generate a set of transformed phonetic embedding vectors corresponding to phonetic characteristics of speech data in a target accent. An alignment is determined by maximizing a cosine distance between the set of phonetic embedding vectors and the set of transformed phonetic embedding vectors. The speech data is then aligned to the phonetic content based on the determined alignment to generate output audio data representing the target accent. The disclosed technology transforms phonetic characteristics of a source accent to match the target accent more closely for efficient and seamless accent conversion in real-time applications.

The application discloses an intelligent substation virtual terminal automatic connection method and system based on an SCHO-GO algorithm, and the method comprises the following steps: obtaining a comprehensive distance according to an edit distance and a cosine distance of a virtual connection vector representation, and constructing a virtual terminal matching model according to the comprehensive distance; optimizing a distance weight vector in the virtual terminal matching model according to a preset SCHO-GO algorithm, obtaining an optimal target distance weight vector, updating the virtual terminal matching model according to the target distance weight vector, and obtaining a target virtual terminal matching model; inputting IED data to be matched into the target virtual terminal matching model, obtaining a comprehensive similarity of an input virtual terminal and an output virtual terminal by the target virtual terminal matching model, and matching and connecting the input virtual terminal and the output virtual terminal according to the comprehensive similarity and a preset matching rule. The efficiency and accuracy of the virtual terminal automatic connection are significantly improved, and the method is suitable for intelligent substation secondary design in a complex equipment naming scene.

The invention belongs to the technical field of artificial intelligence and computer vision, relates to an environmental sanitation video garbage detection method based on uncertainty guide hierarchical retrieval, and aims to solve the problem that an existing environmental sanitation video garbage detection method is high in labeling cost and weak in generalization ability or lacks historical context support, so that complex scenes are missed and missed. The method comprises the following steps: firstly, acquiring an environmental sanitation video frame sequence and dividing the sequence into fragments, extracting visual and garbage category language features through a pre-training encoder, and calculating a negative cosine distance to obtain category probability distribution; secondly, estimating the uncertainty of frames and fragments by using normalized Renyi entropy, retrieving high-confidence reference fragments from short-time, scene and global levels of a clean and junk double-memory library when the uncertainty is high, and directly inputting the high-confidence reference fragments into a pre-trained VLM model when the uncertainty is low; and finally, obtaining a final result through evidence perception time sequence attention fusion, and dynamically updating the memory bank. According to the scheme, additional training is not needed, the detection robustness and accuracy in complex scenes such as low illumination and shielding are effectively improved, and reliable technical support is provided for intelligent environmental sanitation operation.

The invention discloses a wind power industry task matching method and system which are applied to the technical field of intelligent employment, and the method comprises the steps: carrying out the splitting and marking of a task exclusive demand, calculating the multi-dimensional similarity based on a deployed task matching model, combining a cosine distance, a Manhattan distance and a Jaccard distance, and dynamically adjusting the weight, and outputting the optimal technical talents corresponding to each subtask, matching the confidence, replacing talent sorting and subtask parallel execution suggestions, and realizing accurate matching of task requirements and the technical talents. Compared with the prior art, specific wind power scene attributes are given to sub-task splitting for the problem of matching of intelligent employment and task talents of a wind power enterprise, a method for accurately matching the sub-tasks and technical talents is established, intelligent employment is modeled as the problem of matching of a demand pool and a talent pool, simple system design is achieved, and the intelligent employment and task talent matching efficiency is improved. System expansion and function updating are facilitated, and flexible application of the intelligent employment method in wind power enterprises is greatly promoted.

The application discloses a kind of based on composite distance's weighted rough membership clustering RGB-D image segmentation method.For extracting the image feature of RGB-D image, the image feature includes color feature, point cloud feature and normal feature;Initial class center is selected based on density method;Based on adaptive weighting and composite distance measurement method, clustering algorithm is optimized, and weighted rough membership clustering algorithm is obtained;Adaptive weighting includes by local feature weighting method to each feature dimension adaptive weighting;Composite distance measurement method includes by the method of fusing Euclidean distance and cosine distance to calculate the similarity between sample and clustering center;Based on weighted rough membership clustering algorithm, RGB-D image is clustered and region merging is carried out, and segmentation image is generated.The application can better adapt to the characteristics of different types of features by introducing feature weighting and improving similarity measurement method, and ultimately realize higher quality segmentation effect.

The invention belongs to a pattern recognition technology, and particularly relates to a WiFi open set gesture recognition method based on symbiotic metric learning and uncertainty perception, which comprises the following steps: constructing a feature memory library according to original feature vectors of known gesture image samples, acquiring K neighbor view sample sets closest to the cosine distance of the original feature vector of the to-be-identified image from the feature memory library, determining candidate prediction tags of a to-be-detected sample by adopting a majority voting mechanism, and calculating a neighbor distance score value of the to-be-detected sample; and if the neighbor distance score value is greater than a set threshold value, taking the candidate tag as the tag of the to-be-detected sample, otherwise, judging that the to-be-detected sample is an unknown gesture. Aiming at the problems that Wi-Fi signal environment noise interference is strong and feature distribution is loose in an open set scene, the generalization ability of the model in a cross-domain scene is effectively improved through a double-view consistency constraint and symbiotic fusion mechanism, and the rejection rate of unknown gestures and the recognition precision of known gestures are remarkably improved.

This application provides a method, apparatus, and system for detecting printing defects. The method includes: establishing an autoencoder model, which includes an encoder and a decoder; iteratively training the autoencoder model using multiple character images until the loss function value of the current iteration is less than the loss function value of the previous iteration, and determining the encoder of the current iteration as a first-order optimized encoder; performing comparative learning on the first-order optimized encoder to obtain a second-order optimized encoder, such that the feature vector output by the second-order optimized encoder contains information about printing defects in the character images; inputting the image to be tested and a template image into the second-order optimized encoder respectively to obtain a first feature vector and a second feature vector; determining that the image to be tested has printing defects if the cosine distance between the first feature vector and the second feature vector is less than a second predetermined threshold, thus solving the problem of time-consuming and labor-intensive printing defect detection methods in the prior art.

The application discloses a speaker verification method based on a SASFV aggregation model, and relates to the field of speech recognition.The method extracts a log Mel spectrogram through short-time Fourier transform and Mel filtering, generates frame-level features by using an ERes2Net network, introduces a SASFV aggregation model to generate fixed-length speaker-level features in combination with a Fisher Vector variable, a self-attention mechanism and a statistical method, and finally determines the identity of a speaker by using a cosine distance.The application solves the problem that the prior art cannot effectively represent and aggregate features in a short speech task, and significantly improves the accuracy, robustness and performance of a speaker recognition system.

The application provides an event causal relationship mining method and system based on atlas constraint and time sequence optimal transmission, which comprises the following steps: cutting a burst event description text into text blocks; performing atomic event extraction on each text block, and formalizing each atomic event into a binary feature group; mapping any two atomic events and into event nodes and in a preset knowledge atlas, calculating the shortest path topological distance of the event nodes and in the atlas, and constructing a teacher model probability distribution according to the shortest path topological distance; calculating the cosine distance between the vectors and as a basic semantic transmission cost, and performing time sequence constraint on the basic semantic transmission cost to construct a time sequence transmission cost matrix, searching for an optimal transmission matrix that minimizes the total transmission cost; and obtaining an event causal relationship that meets the time sequence optimal transmission under the constraint of a field knowledge atlas by minimizing a joint loss function of the teacher probability distribution and the optimal transmission matrix.

The present application belongs to the technical field of tobacco quality evaluation, and discloses a tobacco quality similarity evaluation method and system based on near-infrared spectroscopy, which comprises the following steps: scanning tobacco samples by using a near-infrared spectrometer to obtain spectral data, reducing the dimension of the spectral data by using principal component analysis to obtain the first D principal components and their scores whose cumulative variance contribution rate is greater than 0.99, calculating the cosine distance and Euclidean distance between samples based on the principal component scores corresponding to the target sample set, converting the two-dimensional vector composed of the above two parameters into a one-dimensional scalar by introducing a kernel function and L2 regularization, and finally obtaining the similarity value, so as to realize the digital evaluation of the quality similarity between target samples. The present application provides a new technical idea for tobacco raw material substitution, leaf group formula auxiliary design, and cigarette product quality stability evaluation.

The invention relates to the field of artificial intelligence and edge computing, and particularly discloses a real-time target detection tracking and prediction system based on edge equipment, which comprises an input acquisition module, a reasoning processing module, a tracking prediction module, an asynchronous pipeline scheduling module, a video rendering and plug flow module and a data interface service module. According to the method, FP16 semi-precision optimization and layer fusion are carried out on a YOLOv5 detection model and a ReID feature network through a TensorRT framework, so that the calculation delay is remarkably reduced; meanwhile, a dynamic frame skipping strategy and a multi-thread asynchronous assembly line are designed, load-aware resource scheduling is achieved, and high-frame-rate stable processing on edge equipment is guaranteed. In the aspect of tracking prediction, a DeepSort algorithm is improved by the system, cosine distance matching of IoU and appearance features is fused, track prediction and index moving average smoothing are performed by using a Kalman filter, and ID consistency and track prediction stability in a complex scene are effectively improved.

Disclosed is a computer-implemented method of clustering a plurality of vectors. The method starts by sorting the plurality of vectors by cosine distance from an origin vector to generate an ordered

The invention relates to a binary function clone detection method for graph disturbance and temperature parameter adjustment, and belongs to the field of artificial intelligence safety. The method comprises the following steps: firstly, constructing a function control flow diagram, and generating an attribute control flow diagram for node additional semantic features; secondly, applying structure and instruction disturbance to the attribute control flow diagram to generate diversified positive samples; then calculating function information amount by using structure and grammar features to adjust a temperature parameter of a loss function, and training a graph encoder by using comparative learning; and finally, generating a graph embedding vector of the function pair to be detected by using a graph encoder, and judging whether the function is a cloned function or not through a cosine distance threshold between the vectors. Aiming at the problem that an existing method is difficult to detect functions with few control branches and high grammar repeatability, the method utilizes function information amount to regulate and control contrast learning temperature parameters to increase function functional area indexing, and detection false alarms are reduced; for the problem that overfitting is easily caused by a fixed training data compiling mode, the sample diversity is increased by applying disturbance, and the detection accuracy is improved.

This invention relates to the field of image processing and discloses a method for tracking multiple moving targets with resistance to occlusion interference. The method includes: identifying target pixel clusters in a video frame sequence and determining their occlusion state; extracting residual visible pixel clusters for target pixel clusters in the occluded state, and constructing a local topological map using the geometric relationships between feature pixels to generate a topological feature vector; extracting optical flow vectors from the occlusion edges and converting them into size adjustment parameters for the spatiotemporal trajectory constraint envelope to determine the search area for subsequent video frames; calculating the cosine distance between candidate pixel clusters and the topological feature vector within the search area to complete trajectory association. This invention utilizes local topological invariants to maintain target identity, eliminating the system's dependence on global feature smoothness; and sensing blind zone movement trends through edge optical flow to narrow the search range, suppress identity switching, and ensure continuous and stable trajectory under complex conditions.

This application discloses a method and system for multimodal content source tracing analysis of social media propagation chains, including: collecting and preprocessing multimodal propagation data; encoding visual and semantic modal data through a deep feature extraction network and projecting it into a cross-modal alignment space to generate a fused semantic representation vector; calculating the weighted cosine distance through a modality adaptive attention mechanism to obtain the semantic fidelity attenuation, and combining it with platform encoding degradation estimation to obtain the net semantic attenuation; constructing a propagation dynamic graph based on propagation metadata with the net semantic attenuation as edge weights; aggregating propagation features through an edge-weight-aware graph convolutional network; tracing and locating the source node by performing reverse semantic gradient tracing through a source likelihood scoring network; and achieving specialized source tracing of adversarial mutation propagation through semantically invariant region detection and deep semantic structure correlation mining. This invention achieves deep coupling source tracing of content-level semantic information and propagation topology information.

A face image clustering method and apparatus, an electronic device, and a storage medium are provided. The method includes: performing feature extraction on samples in a face data set by using a face recognition model to obtain a feature; calculating a cosine distance between each two features, and constructing a connected graph covering all the samples; on the basis of a connected component, searching the connected graph to obtain low-level subgraphs, and aggregating the low-level subgraphs, to obtain first candidate clusters; calculating quality scores and intersection scores, and screening the first candidate clusters to obtain second candidate clusters; outputting probability values of vertexes in the second candidate clusters by using a graph convolutional neural network, and removing noise points to obtain third candidate clusters; and searching for a shared vertex between each of the other third candidate clusters and a reference cluster, and removing the shared vertex.

This invention discloses a privacy-preserving robust federated learning aggregation method to resist backdoor attacks. Based on a dual-server architecture, clustering algorithm, and threshold filtering algorithm, it filters out malicious clients while ensuring the privacy of local updates by federated learning clients. First, this invention uses a dual-server architecture and, through arithmetic sharing and quadratic association pairs, enables the two servers to calculate the cosine distance between local updates of each client without knowing the plaintext of the client's local updates, thus achieving privacy protection for client data. Furthermore, this invention combines clustering operations and threshold filtering, allowing the servers to filter out updates from malicious clients based on both the direction and magnitude of the client's local updates, thereby improving the robustness of federated learning.

The application provides a kind of intelligent image search method based on SAM, it is related to image processing technical field.The method comprises: inputting the image to be searched into SAM segmentation model, obtains the segmentation mask of all objects in the image to be searched;According to the object, select the object to be searched, obtain the segmentation mask corresponding to the search object image;According to the image to be searched and the segmentation mask corresponding to the search object image, determine the target object image;Obtain the feature vector of the target object image;Create image vector warehouse, obtain the feature vector of each image of the image vector warehouse;Determine the cosine distance between each image of the image vector warehouse and the target object image;According to the cosine distance, determine the most similar image of the target object image in the image vector warehouse.According to the application, the detail features of the search object can be highlighted, and part of the features of the surrounding object can be retained, and the search accuracy can be improved.

The application provides a kmeans log classification method based on adaptive radius center selection, and relates to the technical field of big data. The method comprises the following steps: fusing log samples until the number of log samples in a target sample set meets a first preset number condition, and constructing a first distance matrix according to the cosine distance of each log sample; storing a first center point obtained according to the first distance matrix into a center set, if a preset condition is triggered, continuing to fuse and update the target sample set until the number of log samples meets a second preset number condition, constructing a second distance matrix according to the fused and updated target sample set, continuing to obtain a second center point from the fused and updated target sample set according to the second distance matrix, and storing the second center point into the center set until the center point in the center set is K for Kmeans clustering. The scheme improves the quality of initial centroid selection, thereby improving the Kmeans clustering effect.

The invention discloses a voiceprint recognition-based hydropower station leakage and leakage recognition method and system. The method comprises the following steps: acquiring a voiceprint signal on a to-be-monitored pipeline; segmenting the voiceprint signal, generating a plurality of audio clips, and forming a data set; wiener filtering processing is carried out on the voiceprint signal; the filtered voiceprint signals are preprocessed; fbank features are extracted from the pre-processed voiceprint signals; performing sequence modeling on the Fbank features by using an ECAPA-TDNN model, and enhancing the feature expression ability through an SE-Res2Block module; replacing an Euclidean distance in the comparison loss with a cosine distance, introducing A-Softmax loss to optimize an intra-class distance, and constructing a voiceprint recognition model; and training the constructed voiceprint recognition model by using the divided data set to obtain a trained voiceprint recognition model for voiceprint recognition. The method has the advantages of accurate prediction and the like.

The invention provides a dynamic adaptive multilevel federated learning backdoor attack defense method, which comprises the following steps of: 1, feature extraction and clustering: extracting client model update features from cosine distance and normalized update energy dimensions, and clustering by using a DBSCAN algorithm; 2, model output classification: marking clients as possible malicious or benign clients according to model output; 3, dynamic weight aggregation: scoring the screened client model according to the classification statistics and the client aggregation result, and determining the weight of the client model in the global model according to the score; 4, directional rollback detoxification: after the global model is aggregated, analyzing the parameter update quantity of the client to identify abnormal update, and adaptively adjusting towards the direction of the initial model to eliminate the back door influence; and 5, self-adaption blacklist: quantifying historical malicious behaviors of the client through the scoring dictionary, and pre-filtering model parameters transmitted by the client in an aggregation preparation stage. According to the method, a multi-level defense system is constructed, and the confrontation adaptability and the security defense capability of the federal learning framework are remarkably improved.

The invention relates to the technical field of intelligent matching, and discloses a scientific and technological achievement intelligent matching method and system based on multi-dimensional semantic analysis and a knowledge graph. The method comprises the following steps: extracting a technical parameter dictionary, a demand keyword and a demand industry label in a demand text, and constructing demand structured data; performing word segmentation and coding on the demand structured data to obtain a demand semantic vector, constructing an achievement semantic vector of each achievement in an achievement database, and calculating a cosine distance, an industry association distance and an IPC classification distance; the cosine distance, the industry association distance and the IPC classification distance are subjected to weighted calculation, a comprehensive matching score corresponding to each achievement is obtained, a target achievement list is screened based on the comprehensive matching scores, and a recommendation result is returned. And an accurate and efficient intelligent matching service is provided for transformation of scientific and technological achievements.

A digital human voice and lip synchronization detection method, system, medium and product, in the method, an image frame group and a corresponding audio segment are extracted from a video; visual features are extracted using a visual coding model, context, content and tone features of the audio are extracted through a self-supervised speech model and a language model respectively; a distance matrix is calculated after fusing the audio features; a mapping relationship between the visual and audio features is established based on the minimum cumulative distance path; finally, the correlation weight is calculated through the cross-modal attention mechanism, and whether it is synchronized is judged by the cosine distance. When the cosine distance is less than the threshold value, it is determined to be in a synchronous state. The present application is used to improve the accuracy of digital human voice and lip synchronization detection in complex contexts.