29results about How to "Improve clustering efficiency" patented technology

The invention discloses a power prediction method considering photovoltaic power clustering, which comprises the following steps of: firstly, acquiring historical data of a photovoltaic power station, decomposing a photovoltaic power time sequence by using an STL time sequence decomposition method, performing DBSCAN clustering on the decomposed photovoltaic power data, identifying a low-power cluster and a high-power cluster, and predicting the power of the photovoltaic power station according to the low-power cluster and the high-power cluster; establishing a photovoltaic power prediction model based on a time convolutional network and Times Net for low power and high power respectively; secondly, a badger algorithm is improved, Chebyshev chaotic mapping is adopted to improve initialization of a badger population, and a Gaussian mutation strategy and a lens imaging reverse learning strategy are introduced to obtain MHBA; and optimizing hyper-parameters of the TCN photovoltaic low-power prediction model and the TimesNet photovoltaic high-power prediction model by using an improved badger algorithm, and predicting photovoltaic power by using the optimized models to obtain a final prediction value. Compared with the prior art, the precision and effectiveness of the photovoltaic power prediction model can be improved.

The invention relates to a clustering-based industry subdivision electricity sale quantity prediction method and device and a storage medium, which are applied to the technical field of electricity market transactions, and comprise the steps of obtaining representation vectors in a historical preset period of time of an electricity user, so that the electricity consumption behavior of the user can be represented more accurately, the accuracy of a prediction model is improved, and the user experience is improved. Meanwhile, vectorization representation is carried out on the attributes of the users, and the attributes are spliced with power consumption behavior representation vectors, so that more comprehensive user features can be provided through the integration, and the generalization ability of the model is enhanced; according to the method, high-dimensional original time sequence data is converted into low-dimensional feature vectors, so that the calculation burden of a clustering algorithm is reduced, the clustering efficiency is also improved, users are divided into different class clusters, modeling prediction is carried out for the electrical load of each group of users, clearer model interpretation can be provided, and the user experience is improved. And the electricity utilization characteristics of different user groups can be understood conveniently.

The invention discloses a fast multi-view clustering method and system for anchor point diagram decomposition based on logarithm sparse constraint, a storage medium and computer equipment, and belongs to the field of machine learning and data analysis, and the method mainly comprises the following steps: reading a vectorized multi-view data set, and generating anchor points in all views; constructing an anchor point diagram between the original data and an anchor point set formed by the anchor points; performing anchor point diagram decomposition on the anchor point diagram to obtain a basis matrix and a coefficient matrix, performing log norm constraint on the basis matrix, and removing redundant information; and performing K-means on the coefficient matrix to obtain a clustering label, and generating a clustering result. According to the method, the clustering precision and efficiency can be remarkably improved when a large-scale multi-view clustering task is processed, and the method can be widely applied to the field of data analysis.

The invention provides an image clustering method and system based on a gravitational model, and the method comprises the steps: obtaining a self-adaptive neighbor set of each sample in a to-be-clustered image data set D, and carrying out the denoising of the data set D through combining the distribution characteristics of the data set D; combining samples with the same initial cluster label in the data set D by using a gravitation model to form an initial cluster set; constructing a new data set Dc by taking all convergence points in the current initial cluster set as samples; combining samples with the same local micro-cluster labels in the data set Dc by using a gravitation model to form a local micro-cluster set; and iteratively combining all local micro-clusters in the local micro-cluster set to obtain a final cluster set, and outputting the final cluster set as an image data clustering result. The problems that in the prior art, some clustering algorithms are prone to noise interference in the clustering process, the clustering result is inaccurate, and the clustering performance on a data set with the complex shape and the large density difference is poor are solved.

The invention discloses a retired battery screening method, system and equipment based on capacity increment curve prediction and a medium, and relates to the technical field of battery application. The method comprises the following steps: firstly, acquiring local charging data, including voltage and capacity, of a target battery, and performing discretization processing to obtain preprocessed data; then, a voltage-capacity curve prediction model based on a convolutional neural network is utilized to predict a complete charging curve of the preprocessed data, and a capacity increment curve is generated; and then, extracting characteristic data of the capacity increment curve, including a left peak height, a right peak height and corresponding voltage, as clustering indexes to screen out-of-service batteries. And finally, determining a judgment result of the target battery according to the feature data, and realizing accurate screening and evaluation of the battery. According to the method, the clustering feature acquisition time can be greatly shortened, the clustering efficiency is improved, and rapid screening of the retired batteries is realized.

The invention discloses a light-load combined typical scene generation method and device, and relates to the technical field of power distribution network planning, and the method comprises the steps: determining a target meteorological photovoltaic data set and a target meteorological load data set through correlation coefficient analysis based on a meteorological photovoltaic data set and a meteorological load data set, an improved time sequence generative adversarial network model is input for processing to obtain an enhanced meteorological photovoltaic data set and an enhanced meteorological load data set; dimension reduction and interactive clustering are carried out on enhanced meteorological data of the enhanced meteorological photovoltaic data set and the enhanced meteorological load data set to obtain a photovoltaic side meteorological scene and a load side meteorological scene; and after clustering analysis is carried out on the enhanced meteorological photovoltaic data set and the enhanced meteorological load data set, global-local time sequence matching of a meteorological day scene is carried out on the obtained photovoltaic cluster of each photovoltaic side meteorological scene and the obtained load cluster of each load side meteorological scene to generate a light-load combined typical scene set. According to the scheme, the reliability of the generated light-load combined typical scene is improved.

The invention provides a user intention mining processing method and device and related equipment, and aims to solve the problem of low user intention mining efficiency when self-service voice service intelligent equipment constructs a dialogue system in the traditional technology. The user intention mining processing method comprises the following steps: obtaining an initial to-be-mined text of a to-be-mined user intention, and according to a TF-IDF value, obtaining an initial to-be-mined text of the to-be-mined user intention; the method comprises the steps of obtaining word weights of corresponding lexical units, filtering lexical unit sentence texts corresponding to the lexical units according to the word weights to obtain target lexical unit sentence texts, vectorizing the target lexical unit sentence texts, determining target lexical unit sentence text vectors, clustering all the target lexical unit sentence text vectors, and determining target user intentions according to clusters. According to the user intention mining method and device, repeated corpora and corpora low in importance degree can be removed by filtering the lexical text corresponding to the lexical, the data scale is reduced, the user intention mining efficiency and quality are improved, the user intention mining effect is improved, and the user intention mining method and device can be applied to the field of medical health.

The invention discloses a text clustering method and device, a storage medium and a product, and relates to the technical field of natural language processing, and the text clustering method comprises the following steps: obtaining a to-be-clustered text; performing text clustering on the to-be-clustered text according to a plurality of preset clustering parameters to obtain text clustering results corresponding to the plurality of preset clustering parameters; inputting the text clustering results corresponding to the plurality of preset clustering parameters into a pre-trained text clustering quality evaluation model to obtain quality evaluation results corresponding to the plurality of preset clustering parameters; and determining a target text clustering result according to the quality evaluation index values corresponding to the plurality of preset clustering parameters. According to the scheme, iterative optimization of the text clustering result can be realized, so that the quality of the text clustering result is improved.

The present invention proposes a clustering method and system based on long short-term memory and attention, which relates to the technical field of wireless communication networks. The method includes: a user device measures the channel state information of a radio unit it serves and several radio units adjacent to the radio unit it serves, and feeds back the channel state information to each radio unit; calculates the current load factor of each radio unit, and uses a cloud computing platform to pre-process the load factor and the channel state information of several radio units to obtain the channel state information of M radio units with the strongest received signals; uses the channel state information of the M radio units as the input of a spectrum efficiency prediction model based on long short-term memory and attention, and outputs the spectrum efficiency of the user device; clusters the radio units communicating with the user device based on the spectrum efficiency of the user device. The present invention effectively reduces the computational complexity, improves the clustering efficiency, and can be expanded to large-scale networks.

The invention discloses a lithium battery health state estimation method and system based on equivalent granularity efficient fuzzy clustering integration, relates to the field of battery health state prediction, and aims to solve the problem that an existing method regards each sample as an independent individual, neglects an equivalence relationship among samples and cannot predict the health state of a battery. And learning a core main body cluster structure of the data set by using all sample points. The method comprises the following steps: constructing an equivalent point set of a data set, constructing a potential equivalent granularity set based on potential equivalent granularities of equivalent subset elements, dividing the potential equivalent granularity set into a core equivalent granularity set and a fuzzy equivalent granularity set, measuring a fuzzy relationship between any two core equivalent granularities, and constructing a core equivalent granularity relationship matrix. The main body cluster structure is identified, the fuzzy equivalent granularity is allocated to the obtained main body cluster structure, meanwhile, the label of the hidden sample point is restored to the label of the potential equivalent granularity equivalent to the hidden sample point, and a consensus result is obtained; and predicting the health state of the battery based on a consensus result.

The invention provides an electric vehicle charging user clustering method and system based on knowledge graph representation learning, and the method comprises the steps: carrying out the processing of each user and each order for the charging of an electric vehicle through the knowledge graph representation learning, and obtaining the initial representation of the user and the order; inputting the user and order initial representation into a trained BERT model for representation learning, and obtaining a plurality of user relationship vectors; and clustering the plurality of user relationship vectors by adopting a hierarchical navigable small world algorithm to obtain a clustering result of the charging users. As the trained BERT model and the navigable small-world network algorithm are combined with the users and the orders for clustering, the users with similar charging behaviors can be effectively distinguished when complex electric vehicle charging data are processed, and the clustering efficiency and accuracy are improved.

This invention belongs to the field of computer technology and discloses a method, apparatus, device, and storage medium for generating webpage structural fingerprints. The method includes: parsing the current webpage into a DOM tree and obtaining the attribute features of each node in the DOM tree and the node relationship chain formed by each node; calculating the hash weight of each node based on the node relationship chain; generating the hash value of each node according to its attribute features; and generating the webpage structural fingerprint of the current webpage based on its hash weight and hash value. By parsing the webpage structure and generating fingerprints through the above method, differentiated webpage structures can be achieved, facilitating the aggregation of pages with similar structures and a high risk of cheating, improving the clustering efficiency of webpage structures, shortening the perception time of webpage generation groups, and providing data support for subsequent rapid detection of cheating website groups and prevention of mass piracy.

The present application provides a method, system, device and computer-readable medium for clustering defects of wafers. The method includes: obtaining multiple defect data points corresponding to each defect of the wafer; the defect data points are used to characterize the position and size of the defect; according to the R-tree, the index information of the defect data points is determined; according to the R-tree and the DBSCAN algorithm, a scanning operation is performed to determine the bounding rectangle of each defect according to the index information and the defect data points, and the bounding rectangle is cross-processed to obtain a cluster list; the cluster lists corresponding to each defect are summarized to obtain the clustering results of the defects of the wafer. It can at least be used to solve the technical problem that the clustering efficiency is low and cannot meet the rapidly developing business needs in the solutions of the related technology.

The invention relates to the technical field of multi-face tracking, in particular to a multi-face tracking data set construction method and system based on Retinaface and DeepSort algorithms, and the method comprises the steps: constructing a multi-face tracking framework based on a Retinaface face detection algorithm and a DeepSort multi-target tracking algorithm, and carrying out the automatic marking of multi-face tracking data; a face data set cleaning method based on a DBSCAN clustering algorithm is adopted to automatically clean the multi-face tracking annotation data; on the basis of automatic cleaning of the multi-face tracking annotation data, the multi-face tracking annotation data are cleaned manually with manual proofreading as a main component; and logic detection and format detection are carried out on the cleaned multi-face tracking annotation data, and the conditions of logic errors and inconformity with the face tracking annotation format are eliminated. According to the method, the high-quality face tracking data set can be efficiently generated.

The invention discloses a window-based time sequence data clustering method using modeling dimension reduction. According to the time sequence data clustering method, the theoretical basis of time sequence modeling is fully exerted, the advantages of time sequence modeling on time sequence data feature description and prediction are utilized, the related technical problem that a time sequence modeling method is applied to dimension reduction in time sequence data clustering is solved, and the accuracy and efficiency of time sequence data clustering are improved. The technical scheme of the invention can be directly applied to the fields of financial and economic analysis, biomedicine and health monitoring, environmental science and climate change, information and signal processing and the like needing time sequence data clustering.

This application discloses a method, apparatus, device, and medium for event aggregation based on feature association, relating to the field of text classification and analysis. The method includes: acquiring multiple event texts to be aggregated and multiple historical event clusters; wherein each event text includes a title and a summary; based on single-pass clustering, clustering is performed on the title and summary respectively, using multiple historical event clusters, to determine the title identifier and summary identifier of each event text; traversing all summary identifiers, processing each event text to obtain multiple aggregated event clusters; wherein in each round of traversal, event texts are selected based on the current summary identifier to construct the current event set, and the current event set is updated according to the title identifiers of all event texts in the current event set to obtain the aggregated event clusters; and the historical event clusters and aggregated event clusters are merged and updated according to the title identifier and summary identifier to complete the event aggregation. Implementation of this application can improve the accuracy of event aggregation.

This application discloses a target object detection method, device, and storage medium. The method includes: acquiring a target point cloud, which is obtained by using a detection device to collect data from a detection area; performing dimensionality reduction mapping on the target point cloud to obtain two-dimensional point data, wherein the two-dimensional points in the two-dimensional point data are distributed in rows and columns; clustering the two-dimensional points in the two-dimensional point data to obtain clustering results; and determining the point cloud belonging to the target object based on the clustering results. Through the above methods, this application can improve the detection efficiency of target objects.

The present application relates to a clustering method, device, computer equipment, storage medium and computer program product. The method comprises: obtaining multiple samples included in the data to be clustered and the target weight of each sample; clustering the multiple samples by using the distance clustering algorithm and the target weight of each sample to obtain a first clustering result; determining the distinguishing parameter corresponding to the first clustering result, and determining the linear discriminant parameter corresponding to each cluster; updating the target weight of each sample based on the linear discriminant parameter corresponding to each cluster, and obtaining the target clustering result based on the updated target weight. By adopting this method, data compression can be avoided, the complete information of the data is retained, data clustering is achieved by weighted distance and real-time updated weights, the reliability of clustering is improved, and the weight of the sample is updated in real time by dynamic iteration, which can better adapt to the dynamically changing clustering process and improve the clustering efficiency.

The application provides a tumor point cloud optimization method and system in tumor ablation planning, which optimizes a tumor point cloud representing a set of three-dimensional voxels of a tumor to obtain an optimized tumor point cloud for tumor ablation planning. The tumor point cloud optimization method comprises the following steps: an acquisition step of acquiring the tumor point cloud and dividing the tumor point cloud into internal points representing a set of three-dimensional voxels inside the tumor and surface points representing a set of three-dimensional voxels on the surface of the tumor; an internal sampling step of down-sampling the internal points to obtain internal sampling points; a surface sampling step of sampling the surface points differently from the internal sampling step to obtain surface sampling points; and an output step of outputting the internal sampling points and the surface sampling points as the optimized tumor point cloud.

The application discloses an indoor positioning method and system fusing WiFi fingerprints and space information, the method realizes online positioning through offline construction of a fingerprint map. Wherein, WISP features fusing WiFi features and space features are proposed, the space features are classified and coded according to whether reference points are in straight corridors or corners. In addition, the application also constructs a bag-of-words tree, that is, the bag-of-words tree is used to represent the correlation between reference points, so that in the online positioning stage, firstly, the WISP features of the current position and the bag-of-words tree are used to calculate the similarity between the WISP features of the current position and the WISP features under each cluster; then the product of the similarity and the corresponding TF-IDF weight value is calculated, finally, the cluster with the maximum product value is selected, and the position corresponding to the WISP features under the cluster is used to deduce the final positioning result, effectively reducing the influence degree of the perception confusion of WiFi signals.

The present invention discloses a method and device for judging and correcting the tilt of a table image based on k-means clustering. The method comprises the following steps: randomly cropping an input image, performing text detection in the cropped small image, counting the heights of the N text areas detected, and calculating the average height H; performing Hough line detection on the entire image with the average height H as a threshold, filtering out the lines with a length less than H; calculating the slopes of the remaining lines and converting them into angle values; clustering all angles into two categories using the k-means clustering method, and always keeping the difference between cluster centers at 90° during the clustering process; finally obtaining the tilt angle according to the clustering result, and performing reverse rotation correction on the original image. The method and device can achieve accurate rotation correction of the image, thereby improving the accuracy and efficiency of data extraction and analysis.

The invention provides a graphic automatic encoder fault case clustering method based on multi-feature fusion, and relates to the field of fault diagnosis, and the method comprises the steps: obtaining a plurality of fault cases; establishing a fault case graph structure based on the plurality of fault cases; a plurality of case clusters and the cluster center of each case cluster are determined based on the fault case graph structure through a case clustering model, and the case clustering model at least comprises an encoder, a decoder and a self-training clustering unit; obtaining a current fault description text; determining an embedded representation of the current fault description text; determining a target case cluster based on the embedded representation of the current fault description text and the cluster center of each case cluster; and searching the target fault case from the target case cluster based on the embedding representation of the current fault description text, so that the method has the advantages that the graph embedding and clustering processes are jointly optimized, the nodes are efficiently and accurately divided in the feature space, and the node division accuracy and the clustering efficiency are improved.

The embodiment of the invention discloses a data mining method and device for a running log, equipment and a storage medium, and the method comprises the steps: obtaining a first data set corresponding to the running log of a server, the first data set comprising a plurality of to-be-mined sample data; determining each second data set for reflecting adjacent sample data corresponding to the sample data by utilizing a first distance between the sample data, a first average distance of the first data set and a preset adjacent sample selection rule; according to the data density of the second data set and the second average distance, target parameters used for reflecting density distribution characteristics of the second data set are determined; performing clustering initial center point selection processing by using each target parameter and a preset center selection rule, and determining an initial center point; and performing clustering processing based on the initial center point, a preset clustering algorithm and the first data set, and determining a target clustering result. The initial center point can be determined without enumeration, and the clustering efficiency is improved.

The present disclosure provides a node clustering method and device, electronic equipment and storage medium, the method comprising: determining a plurality of routing paths according to the calling relationship between a plurality of network nodes; determining a starting node and its belonging node hierarchy from the plurality of network nodes; traversing each routing path starting from the starting node; when traversing the current routing path, determining the hierarchy of each node according to the distance between each network node and the starting node and the hierarchy of the starting node; if the hierarchy of the next node of the current node has been determined, ending the traversal and recording the path traversal result; when the traversal of the plurality of routing paths is completed, clustering the network nodes at the same hierarchy into the same cluster node group according to all the results. The method clusters the network nodes according to the data flow direction in the network, and sets the traversal end condition, which can solve the problem that node clustering cannot be achieved in the presence of a loop.

The present disclosure provides a virus clustering method, a virus clustering device, a storage medium and an electronic device, and relates to the field of information security technology. The method includes: obtaining index information and feature information of files to be clustered; dividing the files to be clustered into multiple sample sets according to the index information of the files to be clustered; determining a target sample set associated with the seed virus file in the multiple sample sets according to the index information of the seed virus file; matching the feature information of the seed virus file with the feature information of the files to be clustered in the target sample set, and clustering the files to be clustered in the target sample set according to the matching results. The present disclosure can achieve highly subdivided virus clustering, which is conducive to quickly locking the category to which the virus file belongs during virus detection, improving detection efficiency, and can reduce the amount of calculation in the clustering process and reduce clustering time.

The invention discloses an industrial waste gas emission supervision system and method. Waste gas emission source data in a supervision range are acquired and stored through an emission source information base module; internet public information is captured and analyzed through a public opinion monitoring module, so that public opinion event data is obtained; waste gas diffusion simulation is carried out through a waste gas emission source screening module in combination with waste gas emission source data, public opinion event data, meteorological data and geographic data, and influence evaluation of a waste gas emission source matched with a public opinion event is obtained.

The invention discloses an ammeter test method and device, and a storage medium. The method comprises the following steps: collecting user information and an original electricity utilization sequence signal for an electricity user; splicing the original electricity utilization sequence signals into reference electricity utilization sequence signals, and extracting original electricity utilization characteristics from the original electricity utilization sequence signals; reducing the dimension of the reference power utilization sequence signal into a first target power utilization sequence signal and a second target power utilization sequence signal; clustering electricity users according to the first target electricity consumption sequence signal and the reference electricity consumption characteristic to obtain a first user cluster; in the first user cluster, clustering the electricity users according to the second target electricity utilization sequence signal and the user information to obtain a second user cluster; in the second user cluster, constructing a test power utilization sequence signal according to the second target power utilization sequence signal; and generating a test case matched with the second user cluster according to the test electricity utilization sequence signal, and calling the test case to test the ammeter to obtain a test report. And the performance consistency of the electric meter is ensured.

The invention relates to a power distribution network energy storage bilevel planning method considering demand response under different photovoltaic permeability. The method comprises the following steps: step 1, power distribution network flexibility resource modeling: flexible supply of the power distribution network mainly comes from flexible resources such as an energy storage device of each node, an interruptible load of a demand side and a superior main network; 2, constructing a demand response model, wherein demand response means that a user adjusts a power utilization mode through price information or an incentive mechanism, and the demand response comprises an interruptible load in a price type demand response and an incentive demand response; step 3, power distribution network energy storage double-layer planning; 4, example analysis is carried out; the method has the advantages that upper and lower layer correlation modeling is adopted, the bilayer planning model is converted into a single layer, the solving efficiency is improved, and the economical efficiency and flexibility of the power distribution network are improved.

The invention relates to a stress curve clustering method for a building fiber Bragg grating stress sensor, comprising the following steps: obtaining daily load data of a plurality of building stress sensors; preprocessing the daily load data of each building stress sensor to obtain initial cluster data; performing dimensionality reduction processing on the initial cluster data to obtain dimensionality reduction cluster data, clustering the dimensionality reduction cluster data based on an inverse nearest neighbor density estimation clustering algorithm to obtain a sensor group with similar features, wherein a method for calculating sample distance in the inverse nearest neighbor density estimation clustering algorithm is a cosine similarity calculation method, establishing a daily load clustering feature set of the sensor group, establishing a full-year model analysis chain, and constructing a building health analysis model; the invention clusters stress data of a fiber Bragg grating building stress sensor with a large amount of data into a sensor group with similar features, can better predict stress change trends of key structures of different types of buildings, and provides a more reliable method for smart building safety monitoring.