17 results about "Agglomerative hierarchical clustering" patented technology

The application discloses a kind of methods for automatically analyzing and evaluating report, it is related to computer software and information processing technical field, including: based on graph neural network and visual-textual dual modal feature extractor, realize the adaptive analysis of complex non-standard structure report version, and the document is parsed into two-dimensional data table containing different classification dimensions;Based on BERT vectorization, etc. Adaptive clustering identifies the cluster structure of uneven semantic distribution, adopts the agglomerative hierarchical clustering to construct tree-shaped multi-granularity semantic hierarchy, realizes semantic aggregation;The application realizes the text content of non-standard form, the identification and processing of complex semantics;Overcome the defects of low efficiency, easy to make mistakes, subjective influence and only read specific format or specific location of text content, lack of flexibility and unable to handle complex semantics in prior art manual input.

The invention discloses a differentiated regulation and control method for irregularity of a large-span bridge track of a high-speed railway. The method comprises the following steps: integrating track irregularity historical detection data at different environment temperatures into multi-stage track irregularity historical detection data with environment temperature labels; establishing a multivariate empirical wavelet transform method, and obtaining a plurality of intrinsic mode components; defining the intrinsic mode component as an intrinsic mode, extracting multi-dimensional physical feature vectors of all the intrinsic modes to construct feature vectors, and performing unsupervised classification on all the intrinsic modes by using an agglomerated hierarchical clustering algorithm; component category division is carried out according to a classification result, and different differentiation regulation and control strategies are made according to different component categories; and when the orbit adjustment amount required by the classification exceeds the limit, establishing an optimization model containing the adjustment amount physical constraint and the smoothness expectation target, and solving the optimal orbit adjustment amount considering the current state and the future temperature adaptability.

The present application relates to a kind of table area distributed photovoltaic power ultra-short term prediction method and system, belong to distributed photovoltaic power prediction technical field.Based on the condensed hierarchical clustering algorithm, the table area photovoltaic in region is clustered into the homogeneous sub-region set of output characteristics, combined with GraphSAGE graph neural network and Transformer encoder model, the decoupling representation of space-time characteristics in sub-region is realized, based on composite space-time characteristics, finally synchronously output the photovoltaic power prediction result of each table area in sub-region, further based on the shared feature between sub-region, construct suitable migration modeling strategy, realize the fast lightweight modeling of each sub-region prediction model, finally, the spatial aggregation of sub-region prediction power obtains regional total power prediction result.

The application provides a key event identification method and system based on a hierarchical processing architecture. The method according to the application comprises: acquiring reported events from different channels, performing data preprocessing on the reported events to obtain processed event texts, and classifying the event texts; adopting a semantic regularization condensed hierarchical clustering method to cluster the classified texts; identifying repeated events in the texts according to the clustering results by using a cluster-in-entity keyword extraction and comparison mechanism to obtain key event identification results. That is, the key event identification method proposed in the application constructs a hierarchical processing architecture of "classification-clustering-identification", effectively solves the technical problems existing in the screening of one event reported by multiple persons, and finally screens out repeated reported events as key events that need to be marked, so that relevant management personnel can give priority to the disposal or sufficient attention to these key events.

The application discloses a shortest path divide-and-conquer search method based on a condensation level, improves the operation efficiency of an algorithm by introducing network layering, limiting a search level, divide-and-conquer search and the like, wherein the network layering is adopted to divide network nodes according to a condensation level clustering method, a plurality of level subgraphs are obtained, and the complexity of the search is reduced; the search range is limited within a certain level by limiting the search level, and invalid calculation in the search process is avoided; meanwhile, in order to further improve the search efficiency, the divide-and-conquer search is adopted to divide the whole search process into a plurality of subtasks and perform simultaneously, and the whole search method can accurately and efficiently perform the shortest path search in an edge computing network.

The application discloses a label flipping attack method for a machine learning model and a defense method thereof. In the label flipping attack method, firstly, training data to be attacked is selected by performing condensed hierarchical clustering on the training data, label flipping attack is performed on the selected training data, and then a classification model is trained by using a obtained contaminated data set to implement the attack; in view of the above attack, a small pure set and the contaminated training data are used, the TrAdaBoost method is used to update the weight of the contaminated data, the attacked data is identified according to the updated weight, the data without a label or with a wrong label is re-labeled, a new training set including the contaminated training set and the small pure set is obtained, and the classification model is re-trained by using the new training set to improve the model performance; the label flipping attack can be quickly and accurately performed on the training data vulnerable to contamination, and the suspicious contaminated data can be found, and the label flipping attack can be prevented by disinfecting the contaminated data.

The invention discloses a patient multi-dimensional data similarity measurement and queue discovery method based on artificial intelligence, relates to the technical field of smart medical treatment, and solves the technical problems that an intermediate state that a patient possibly crosses multiple clusters is ignored, the queue division dimension is single, and dynamic adaptability is lacked. By extracting dynamic characteristics, such as vital signs and symptom scores, of the patient, which change along with time, the limitation of only depending on static characteristics is avoided. And patients with short-term fluctuation but long-term stability and continuous deterioration can be distinguished conveniently. And subtype typing of chronic diseases is more accurate, and a time sequence mode is a key typing basis. And the time sequence track vector and the static feature are used for similarity calculation after being spliced or subjected to dimension reduction. And the single feature noise influence is reduced. Disease generality and individual heterogeneity are considered. Aggregate hierarchical clustering is adopted, similarity among samples is calculated, similar clusters are gradually combined, a tree diagram is generated, and patient grouping logic and correlation and causality distinguishing are visually displayed through a clustering tree.

The high-speed railway large-span bridge track irregularity differential regulation method comprises the following steps: integrating track irregularity historical detection data under different environmental temperatures into multi-period track irregularity historical detection data with an environmental temperature label; a multivariate empirical wavelet transform method is established to obtain a plurality of intrinsic modal components; the intrinsic modal components are defined as an intrinsic mode, a multi-dimensional physical characteristic vector of all intrinsic modes is extracted to construct a characteristic vector, and an unsupervised classification is performed on all intrinsic modes by using a condensed hierarchical clustering algorithm; according to the classification result, a classified division is performed, and different differential regulation strategies are formulated for different classified categories; when the track adjustment amount required by the classified category exceeds the limit, an optimization model containing a physical constraint of the adjustment amount and a smoothness expectation target is established, and the optimal track adjustment amount considering the current state and future temperature adaptability is solved.

The application relates to an indoor visible light positioning method based on improved condensed hierarchical clustering, which comprises the following steps: dividing a grid in a positioning area and selecting a plurality of reference points; installing LED light sources capable of being used for optical communication on a roof and laying photoelectric sensors and wireless nodes for data acquisition and transmission indoors; measuring the average power of the LED light sources and establishing a fingerprint library; adopting condensed hierarchical clustering to combine all data points into one cluster; selecting a required cluster number to construct a new sub-database; performing secondary classification on the new cluster according to the power of the light sources, and dividing the new cluster into a high-power area and a low-power area; in the positioning stage, comparing the Euclidean distance between the light power of a mobile terminal and a new clustering center, and putting the mobile terminal into the cluster closest to the mobile terminal; putting the power of the mobile terminal into the corresponding power area, and adopting a KNN matching algorithm to traverse the fingerprints to lock the target coordinate position.

The invention provides a principal component agglomeration hierarchical clustering method suitable for flight takeoff and landing type identification, and belongs to the field of flight data processing, and the method comprises the steps: obtaining original flight takeoff and landing data, and carrying out the preprocessing of the data, and obtaining a flight parameter data set; calculating correlation coefficients between the flight parameters in the flight parameter data set to obtain a correlation coefficient matrix, screening the correlation coefficient matrix according to a correlation coefficient threshold to obtain required flight parameters, and forming a principal component analysis flight parameter data matrix by the required flight parameters and the discrimination parameters; calculating a correlation coefficient matrix of the principal component analysis flight parameter data matrix and performing eigendecomposition to obtain principal component eigenvalues and eigenvectors, sorting the principal component eigenvalues, obtaining principal component contribution rates according to the principal component eigenvalues, and determining principal components by accumulating the principal component contribution rates; and carrying out agglomeration hierarchical clustering on the principal components to obtain two-dimensional space distribution of flight takeoff and landing in any two principal components, and carrying out flight takeoff and landing type identification according to the two-dimensional space distribution and discrimination parameters.

The application discloses a kind of sand earthquake liquefaction discrimination method and system based on SSA-CNN-SVM model coupling, and the present application relates to the technical field of seismic safety evaluation, comprising the following steps: obtaining historical sand liquefaction sample data set, including key influence index and liquefaction state label, while collecting geographic location information, extract statistical characteristic parameters to calculate anti-liquefaction intensity index and vibration intensity index, and according to the weighted similarity measurement of geographic characteristic parameter, the sample area is divided into multiple geological regions by condensation hierarchical clustering algorithm;In each region, the Mahalanobis distance between sample regions is calculated, and a secondary clustering is carried out using a density-based clustering algorithm to identify similar liquefaction mechanism sample clusters, and a prediction model coupled with a deep learning model and an optimization algorithm is established for each cluster to assess liquefaction risk, significantly improving the accuracy and robustness of sand earthquake liquefaction discrimination.

The invention relates to the technical field of data processing, in particular to a food production data monitoring method and system. The method comprises the following steps: determining a target moment from a plurality of moments in a current food drying process, and determining a distortion degree value of the target moment; determining a true degree value of the target moment, and taking a ratio of the true degree value of the target moment to the distortion degree value as an evaluation value of the target moment; performing agglomeration hierarchical clustering on a plurality of temperature data points in the current food drying process to obtain a plurality of clusters, and for a cluster group formed by two clusters in the plurality of clusters, obtaining a merging distance of the cluster group according to an evaluation value of a moment corresponding to the temperature data points in the cluster group; and determining an abnormal detection result of the temperature in the current food drying process according to the merging distance of the plurality of cluster groups, so as to monitor the drying temperature of the food drying equipment according to the abnormal detection result. According to the technical scheme, temperature monitoring in the food drying process can be better achieved.

This invention discloses a method and system for identifying seismic liquefaction of sandy soil based on a coupled SSA-CNN-SVM model. This invention relates to the field of seismic safety assessment technology and includes the following steps: acquiring a historical sandy soil liquefaction sample dataset, including key influencing indicators and liquefaction state labels; simultaneously collecting geographical location information; extracting statistical feature parameters to calculate the liquefaction resistance index and seismic intensity index; performing weighted similarity measurement based on geographical feature parameters; dividing the sample area into multiple geological regions using a hierarchical clustering algorithm; within each region, calculating the Mahalanobis distance between sample areas; performing secondary clustering using a density-based clustering algorithm to identify clusters of samples with similar liquefaction mechanisms; and establishing a prediction model coupled with a deep learning model and optimization algorithm for each cluster to achieve liquefaction hazard assessment, significantly improving the accuracy and robustness of sandy soil seismic liquefaction identification.

The invention provides a mass balance rapid calculation method based on a hierarchical clustering algorithm, and belongs to the field of mathematical geology in earth science, and the method comprises the steps: carrying out the standardization processing of data through the calculation of content ratios R, arranging the ratios R of all elements according to a sequence from small to large, and constructing an ordered array [R]; performing systematic difference quantitative analysis on ratio elements in the ordered array R by using an agglomerated hierarchical clustering machine learning algorithm; and averaging the Rvalues corresponding to all the identified inactive elements, taking the obtained average value K as a balance constant, and carrying out quantitative calculation on the element migration quantity by taking the average value K as a reference. According to the method, various complex geological environments such as a complex water-rock reaction system, multi-element coupling migration and a multi-stage geological process can be effectively treated, and a solution with higher calculation precision and higher analysis efficiency is provided for quantitative evaluation of rock element migration in multiple fields such as mineralogy, petrology, environmental geoscience and resource exploration.

This application belongs to the technical field of spectral analysis and discloses a method, device, electronic device, and storage medium for identifying spectral transition times. The method includes: periodically acquiring real-time spectral data of the sample to be tested; employing an agglomerative hierarchical clustering method, combined with Mahalanobis distance and minimum variance method, merging the real-time spectral data into corresponding cluster tree structure data according to the time series; determining the transition point data that meets preset clustering distance abrupt change conditions and preset frequency domain feature jump conditions based on the merging distance in the cluster tree structure data using a sliding window algorithm and a Fourier transform algorithm; verifying the transition point data according to the isolated forest algorithm to determine the time point corresponding to the transition point data of non-abnormal data as the transition time point; the above method improves the identification efficiency of spectral transition times.

This invention discloses a method for topology identification of low-voltage distribution network areas based on a dual-modal liquid graph neural network, comprising the following steps: macroscopic topology localization of user nodes in the low-voltage distribution network area; construction of a dynamic nearest neighbor spatial topology adjacency matrix; construction of a discrete liquid graph neural network to calculate the Euclidean distance matrix of depth spatial features; calculation of the explicit waveform trend distance matrix; execution of dual-modal weighted fusion to generate the final fused distance matrix; application of an agglomerative hierarchical clustering algorithm, combined with intelligent search for optimal cluster numbers using contour coefficients, to output the final topology structure of micrometer boxes. This invention, through a discrete truncation mechanism and a dual-modal weighted fusion model, can effectively improve the accuracy of micro-topology identification of low-voltage distribution network areas while avoiding complex continuous differential solutions; combined with embedded space optimization training and intelligent optimization of contour coefficients, it can obtain better meter box clustering results within the candidate cluster number search interval, improving the accuracy and stability of topology identification.

This invention relates to a knowledge-based multi-stroke casting and rolling collaborative scheduling method and system, belonging to the field of metallurgical automation technology. The method includes data preparation; pre-sorting / slab clustering, utilizing the slab insertion constraint knowledge set in the knowledge base as a constraint condition during merging, performing agglomerative hierarchical clustering algorithm to cluster slabs and output slab groups; subsequent steps include main material group division, hot-roll material selection, merging main material groups, merging hot-roll materials and main materials, selection of finishing materials, and KPI calculation. The overall scheduling time is reduced from 20+ minutes to 7 seconds, achieving one-click intelligent multi-stroke automatic scheduling, effectively improving KPI indicators such as rolling hot charging rate and rolling mileage, significantly reducing the workload of planners while providing more stable scheduling quality, and improving the automation level of steel plants.