103 results about "Cluster labeling" patented technology

The invention relates to the technical field of communication production management, and discloses a communication equipment production intelligent management system based on machine learning. The system comprises a production data acquisition module, a feature engineering construction module, a dynamic clustering analysis module, an anomaly detection engine module and a production decision optimization module. The production data acquisition module acquires multi-source sensor data in real time and converts the multi-source sensor data into a standardized sequence with a unified timestamp; the feature engineering module extracts a time domain statistical feature, a frequency domain energy feature and an equipment state association feature to generate a high-dimensional feature vector set; the dynamic clustering module adopts an incremental algorithm to divide clusters online; the anomaly detection module establishes a multi-level Gaussian mixture model based on a clustering label, and quantifies an anomaly probability through a mahalanobis distance; and the production decision module integrates the results to generate an equipment maintenance priority sequence and a production takt adjustment instruction. According to the system, intelligent monitoring and dynamic optimization of the whole production process of the communication equipment are realized, and the real-time change requirement of a complex production environment is met.

The invention relates to a manufacturing system risk control knowledge matching method based on semantic embedding and clustering analysis, and the method comprises the following steps: collecting and preprocessing risk control text data: collecting unstructured text data of a manufacturing system history record, and obtaining preprocessed risk control text data, constructing a professional corpus for a discrete manufacturing scene; text semantic embedding generation; semantic clustering modeling: performing unsupervised clustering modeling on all semantic vectors, mining semantic association and potential structures between texts, obtaining semantic representations of risk control knowledge through a clustering algorithm, and assisting in generating clustering tags; and a risk knowledge matching mechanism.

The invention provides a public opinion video tag aggregation method and system based on artificial intelligence, and relates to the technical field of artificial intelligence. Comprising the following steps: acquiring pictures and text information in a short video, and performing semantic alignment; different large language models are adopted to generate preliminary labels for the pictures and the text information after semantic alignment; clustering the pictures and the texts after semantic alignment to obtain clusters; calculating the labeling probability of each primary label type in the current cluster by each large language model, and selecting the primary label with the highest probability sum as a clustering label of the current cluster; calculating the reliability weight of each large language model in the current cluster based on the clustering label of the current cluster; and based on the reliability weight, calculating the weighted support degree of all the large language models to different preliminary label types of each piece of data in the current cluster, calculating the weighted label of the current data, and further determining a final label. According to the method, the condition of few labels or no labels can be effectively processed, and the manual workload is greatly reduced.

The invention discloses a method for identifying traditional Chinese medicinal materials by combining infrared spectroscopy with clustering analysis, which comprises the following steps of: acquiring original infrared spectral data, averaging the original infrared spectral data to obtain single-sample original spectral data, constructing a sample graph and a wavelength graph based on standardized spectral characteristics, and fusing the sample graph and the wavelength graph to obtain the single-sample original spectral data. Obtaining fusion image data, inputting the fusion image data into a pre-trained image neural network model, extracting a low-dimensional feature vector of a target sample through forward propagation, and inputting the low-dimensional feature vector into a pre-trained dynamic cluster diffusion module to obtain a clustering label and distance data; and determining and outputting the quality grade of the rhizome traditional Chinese medicinal material sample based on the clustering label and the distance data. Therefore, interference can be effectively reduced, key features can be extracted, associated features of fused graph data are extracted in combination with a graph neural network, and the quality grade of traditional Chinese medicinal materials can be accurately determined in combination with clustering analysis of a dynamic cluster diffusion module.

The invention provides a multi-modal false news detection method based on unsupervised clustering and frequency domain information, and relates to the technical field of image text data. The method comprises the following steps: based on multi-modal sample data, respectively extracting text features, visual features and image text features, obtaining text feature clustering labels according to text feature global semantic correlation, inputting the text features with the labels into an unsupervised clustering learning network, and obtaining an unsupervised clustering learning result; semantic consistency is enhanced through a bidirectional gating loop unit and a multi-head attention mechanism, and enhanced text features are obtained; extracting frequency domain features based on the visual features, and fusing the frequency domain features with the spatial domain features to obtain visual joint features; and after image text features are also enhanced by the unsupervised clustering learning network, the image text features are fused with text and visual features through an attention fusion module by taking the image text features as a bridge to obtain multi-modal fusion features, and the multi-modal fusion features are input into a full connection layer to complete false news classification. According to the method, the accuracy of false news detection is effectively improved.

The invention provides a non-technical line loss state evaluation method based on multi-scale spatial-temporal feature fusion in a low-voltage distribution network environment, and relates to the technical field of electric power big data analysis and intelligent operation and maintenance of a distribution network. According to the invention, a fusion architecture based on a multi-scale time convolution network and a long short-term memory network is constructed; extracting multi-scale spatio-temporal characteristics of a user from instantaneous electricity utilization abrupt change to a periodic load rule through an MSTBlock unit; designing a cluster balance constraint mechanism to ensure that rare and key non-technical line loss abnormal early warning signals are not covered by mass normal power utilization data; according to the data scale, adaptively selecting a graph segmentation or spectral clustering integration strategy to output a clustering label, and mapping the clustering label into a user power consumption behavior evolution track; according to the method, the power utilization abnormal level can be identified from the original load signal with random fluctuation interference, and the troubleshooting priority is calculated in combination with the transformer area correlation analysis, so that the accuracy and interpretability of the non-technical line loss unsupervised evaluation decision of the power distribution network are remarkably improved.

The invention discloses a personalized teaching course recommendation method and system based on artificial intelligence, and relates to the technical field of artificial intelligence and education recommendation, and the method comprises the steps: collecting text data for preprocessing, and extracting a standard target set, a teaching target candidate set and a knowledge point candidate set; calculating cosine similarity and weight based on the standard target set and the teaching target candidate set, calculating knowledge point mastery degree and weight based on the knowledge point candidate set, and splicing the knowledge point mastery degree and weight to generate a learning feature vector; based on the learning feature vector, clustering is carried out by using a k-means + + algorithm, a clustering label and a clustering center set are output, after the clustering center is updated in combination with a Thompson Sampling algorithm and Monte Carlo, the posterior probability is recalculated, and a final recommendation result is output; the robustness and recommendation accuracy of personalized teaching course recommendation are effectively improved.

The invention provides an eye movement trajectory analysis method and system based on hybrid clustering and time constraint, and belongs to the technical field of computer vision. Calculating a time difference and a moving speed between continuous original eye movement data points; comparing the moving speed with a speed threshold value, and classifying the moving speed into candidate fixation points and glancing points; extracting spatial features and time features of the candidate fixation points, performing standardization processing, and performing weighted fusion to obtain spatial-temporal feature vectors; clustering the spatio-temporal feature vectors to obtain preliminary clustering labels of the candidate fixation points; performing time constraint processing on each cluster; calculating the duration of the clustering cluster after the time constraint processing, and generating a final clustering label of the candidate fixation point; and outputting a final classification label of each original eye movement data point in combination with the classification result of the glancing points.

The invention discloses an enterprise credit evaluation analysis method, and relates to the field of data processing, and the method comprises the steps: obtaining the credit data of a plurality of to-be-evaluated enterprises; performing feature extraction on the credit investigation data through an improved stack type self-encoding neural network model to obtain feature data; the improved stack type self-encoding neural network model comprises an encoder, a decoder, an attention layer and a prior rule layer; the attention layer adopts a Scaled Dot-Product Attention mechanism to learn a weight feature matrix Ha, and the priori rule layer sets feature constraints according to a priori rule; clustering the feature data to obtain a cluster to which the enterprise belongs; according to the feature value distribution of the enterprises in the clustering clusters, performing feature scoring by using a prior rule to obtain clustering labels of the clustering clusters; according to the clustering label and the weight feature matrix Ha, generating an enterprise credit investigation portrait, and according to the enterprise credit investigation portrait, carrying out credit investigation evaluation analysis; aiming at the low enterprise credit evaluation precision in the prior art, the reliability of the evaluation result is improved.

The invention discloses a large-scale unstructured data joint processing method and system. The method comprises the steps that S1, large-scale unstructured data is collected, and a metadata feature library containing dynamic updating and index retrieval optimization is constructed; s2, constructing a federated index based on the dynamic metadata feature library, constructing a cross-domain joint index on the basis of the federated index, and performing layered federated architecture optimization to obtain a cross-domain joint optimization index; s3, constructing a global correlation matrix based on the cross-domain joint optimization index to perform cross-domain correlation modeling, and obtaining a global correlation function through cross-domain correlation modeling; and S4, carrying out joint optimization solution based on the global correlation function to realize unstructured data joint processing, uniformly optimizing tasks such as clustering, label prediction and correlation rule mining by fusing a processing target function, and enabling the tasks to cooperate with each other, so that the whole data processing process is more intelligent and efficient, and the accuracy of a data processing result is improved.

This invention provides a method and device for short-term early warning of rock failure based on acoustic emission clustering analysis, relating to the fields of rock mechanics and geotechnical engineering. The method includes: acquiring acoustic emission characteristic parameters during rock deformation and failure; performing clustering analysis on the acoustic emission characteristic parameters using the K-means++ algorithm to obtain cluster labels corresponding to the acoustic emission characteristic parameters; calculating the importance scores of the acoustic emission characteristic parameters based on the cluster labels using the random forest algorithm; constructing an early warning index set based on the acoustic emission characteristic parameters; constructing an initial CNN-LSTM model; establishing a sample dataset of conventional and precursor signals of rock failure based on the early warning index set; training the initial CNN-LSTM model using the sample dataset to obtain a trained CNN-LSTM model; acquiring real-time acoustic emission signals; and inputting the real-time acoustic emission signals into the trained CNN-LSTM model to provide early warning by identifying the acoustic emission signal category. This invention can provide early warning for complex rock failure processes.

The embodiment of the application discloses a self-defined encryption protocol clustering method and device, the method comprises the following steps: obtaining a target encryption protocol to be identified, and extracting traffic data and metadata of the target encryption protocol; constructing a label matrix and a value matrix based on the traffic data; and fusing the label matrix and the value matrix by using a multi-mode matching algorithm to obtain a clustering label. In this way, the self-defined encryption protocol clustering method provided by the application combines double-matrix combination with a pattern matching algorithm to realize clustering of self-defined encryption protocols. The method solves the problem that mixed self-defined protocols cannot be quickly and accurately clustered, and provides support for subsequent protocol analysis by quickly and accurately realizing clustering of self-defined protocols.

The embodiment of the invention provides a multi-view clustering method and device, equipment, a storage medium and a program product, and relates to the field of financial science and technology. Obtaining a view data set corresponding to each view; based on the similarity between the feature elements in each view data set, constructing a similar matrix of each view data set; multiplying the similar matrixes of the plurality of view data sets to obtain a consistency matrix, and reconstructing the similar matrix of each view data set based on the consistency matrix to obtain a reconstructed similar matrix; and performing multi-view clustering based on the plurality of reconstructed similar matrixes to obtain a clustering result, the clustering result being used for indicating a clustering label corresponding to each sample. Through the above mode, the complementary information of the consistency matrix is utilized to maintain the stability of the clustering boundary, the misjudgment and missed judgment caused by the missing of the sample information in the view are reduced, and the accuracy of the multi-view clustering result is improved.

The invention discloses a new energy unit icing shutdown prediction method and system based on a multi-feature interaction threshold. The method comprises the steps of collecting and preprocessing multi-dimensional data of a new energy unit; based on meteorological and geographic features, generating a corresponding clustering label for each new energy unit by using a clustering algorithm; constructing a full-connection deep neural network shutdown prediction model, taking the preprocessed data and the clustering labels as input features, and training the icing shutdown probability of a model output unit; for a single feature, a feature fixing strategy is adopted, and a single feature threshold interval is determined; key features are selected for double-feature interaction analysis, a three-dimensional decision boundary is constructed, an interaction effect is quantified, and a multi-feature interaction rule is extracted based on a decision tree algorithm; and constructing a comprehensive discrimination rule, setting risk preference parameters, carrying out adaptive threshold updating, and finally outputting a shutdown prediction result. The method can significantly improve the shutdown prediction precision, and is suitable for different types of new energy equipment such as wind power and photovoltaic equipment.

The invention belongs to the technical field of calculus risk assessment, and provides a calculus risk prediction method based on machine learning and electronic equipment, and the method comprises the steps: to-be-detected original data collection and calculus risk prediction; the construction process of the stone risk prediction model comprises the steps of unmarked data collection, image feature extraction, index feature extraction, text semantic extraction, feature fusion, feature clustering analysis, iterative training, fine adjustment small sample data collection, meta-learning fine adjustment and cluster marking. According to the method, through a semi-supervised learning strategy of unmarked data clustering and small sample adjustment, the demand of marked data is greatly reduced; according to the method, clustering and unsupervised iteration are fused through DBSCAN and DPC double algorithms, so that pre-training under unmarked data is realized, and the reliability of unmarked training is improved; through combination of multi-modal data fusion, clustering iteration and meta-learning fine tuning, the robustness of the model is improved.

The invention relates to a micro-service architecture root cause positioning method based on heterogeneous graph modeling and active learning, and the method comprises the following steps: 1, carrying out the feature extraction and topological structure of indexes, logs, call chains and deployment information, and forming unified heterogeneous graph modeling; and step 2, clustering, label diffusion and boundary sample selection are carried out on the heterogeneous graph model constructed in the step 1, semi-supervised training driven by active learning is used to continuously optimize a root cause positioning model, and the model is deployed in a production environment online to realize real-time fault detection and positioning. According to the method, the structural characteristics of the micro-service system can be fully utilized, and the root cause positioning method with low labeling requirements is provided, so that the balance between the task performance and the labeling overhead is realized, and a better solution is provided for efficient root cause positioning of the micro-service system.

The invention discloses a customer consumption cost prediction method and device. The method comprises the following steps: acquiring first consumption data of a plurality of users in a first time period; performing statistical analysis on the first consumption data to obtain a multi-dimensional consumption data feature and a consumption data time sequence corresponding to each user; clustering the plurality of users based on the consumption data features to obtain a clustering label corresponding to each user, the clustering labels being used for reflecting consumption habits of the users; and for each user, determining an expense prediction model matched with the clustering tag of the user, and analyzing the consumption data time sequence of the user by using the expense prediction model to obtain second consumption data of the user in the second time period. The technical problem that a traditional consumption prediction scheme is difficult to accurately analyze and predict multi-dimensional consumption data of different users is solved.

The invention belongs to the technical field of medical data mining and rehabilitation evaluation, and provides a skeletal muscle spasm-to-contracture evolution rule quantitative analysis method and system and application, and the method comprises the steps: preprocessing spasm contracture time sequence data, and obtaining one-dimensional feature vector data; k-means clustering is carried out, state labeling of spasm and contracture is carried out, and clustering labels are obtained; determining the change rate of the torque characteristic and the adjacent angular velocity characteristic, and generating an eight-bit pseudo-sequential sequence representing the evolution rule from the spasm state to the contracture state in combination with a state transition threshold value determined by an ROC curve; constructing a Markov chain model to calculate a transition probability matrix from a spasm state to a contracture state, and identifying torque as a key driving feature of state evolution through grouping risk ratio; and constructing a dynamic correlation model based on the key driving features to complete quantitative analysis of the evolution rule from skeletal muscle spasm to contracture. According to the method, objective division from skeletal muscle spasm to contracture state can be realized, and the transition probability and key driving factors between the skeletal muscle spasm and the contracture state can be excavated.

The embodiment of the invention provides an incremental multi-view data clustering method and system based on a cross-time consensus graph, and belongs to the technical field of artificial intelligence. The method comprises the following steps: integrating historical knowledge with a consensus affinity matrix of current view information and learning time based on kernel induction expression, and constructing a dynamic consensus graph; spectrum embedding and discrete label learning are carried out; and alternately optimizing the consensus affinity matrix, the orthogonal rotation matrix, the consensus spectrum embedding matrix and the discrete clustering label matrix of the moments in the dynamic consensus graph by adopting staged updating variables. The method can efficiently adapt to incremental environment application, and is better in clustering precision, higher in calculation efficiency, higher in time sequence stability and better in robustness.

This invention relates to the field of data representation technology, and discloses a semi-supervised clustering method and its open-ended question answer text encoding method. The semi-supervised clustering method includes: acquiring a dataset to be clustered, its labeled dataset, and its unlabeled dataset; mapping the dataset to be clustered to a spatial density map and / or a topological density map; and using the labeled and unlabeled datasets to cluster the data in the dataset to be clustered into several clusters, wherein each data point in each cluster has a cluster label, which can be an existing label or a new label. This invention uses a semi-supervised clustering method to efficiently and accurately cluster open-ended question answer text data, and can discover new classes with limited prior knowledge. After clustering, keywords can be extracted and encoded from the open-ended question answer text of each class, facilitating a quick and accurate understanding of the situation of the interviewed group and improving the efficiency and quality of diagnosis and treatment.

The present application relates to the technical field of information security, in particular to a kind of unknown protocol clustering method and system based on frequent item extraction and double-layer self-encoder, through the preprocessing process, the original data is converted from bit form to byte form, and then the first 32 bytes are intercepted, then the frequency of frequent item and the number of frequent item of each byte are obtained by carrying out frequent item statistics to the preprocessed data byte by byte;Frequency self-encoder and quantity self-encoder are used to extract features from the byte with larger frequency of frequent item and larger number of frequent item respectively;The features extracted by frequency self-encoder are coarsely clustered to obtain coarse clustering label, and the coarse clustering label and the features extracted by quantity self-encoder are merged and clustered to obtain the final fine clustering label.The present application can not only retain protocol-level clustering, but also realize class-level clustering, with small amount of calculation, while ensuring the real-time of clustering, it can effectively solve the under-partition problem of unknown protocol clustering and improve the performance of clustering.

The invention relates to the technical field of clinical auxiliary diagnosis, and provides a drug recommendation method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the matching from a clustering result, obtaining a target class cluster to which detection data belongs, and taking a clustering tag of the dynamic change of the target class cluster as reconstructed detection data; based on the semantic similarity between the diagnosis description text and the standard diagnosis description text, performing text correction on the diagnosis description text to obtain a corrected diagnosis description; and performing drug recommendation based on the reconstructed detection data and the corrected diagnosis description. According to the method provided by the invention, the target class cluster to which the detection data belongs is obtained through matching from the clustering result, the detection data is abstracted based on the dynamically-changed clustering label, the reconstructed detection data which is high in interpretability, visual and accurate is obtained, and the diagnosis description text which is redundant and difficult to understand is subjected to text correction, so that the diagnosis accuracy is improved. Uniform expression of the standard diagnosis text is realized, the expression specification of the health record data is improved, and the accuracy of drug recommendation is further improved.

The invention relates to an intelligent wearable human body action recognition method based on multi-stage feature optimization clustering, and belongs to the technical field of human body action recognition of intelligent wearable equipment. The method comprises the following steps: segmenting a multivariate time sequence of the intelligent wearable equipment by adopting a sliding window; discrete cosine transform is executed, low-frequency components of a plurality of previous proportions are reserved, singular value decomposition is introduced to remove redundant information across variables, low-rank representation is obtained and input to a depth embedding modeling module, and unified embedding representation is obtained; inputting the unified embedded representation into an improved dynamic movement-splitting-merging distance measurement model to obtain a dynamic movement-splitting-merging distance; a clustering label is obtained through construction of a similarity matrix, graph Laplacian spectrum decomposition and clustering operation in sequence; and human body action recognition is realized based on the clustering labels. The objective of the invention is to solve the technical problems of feature redundancy, insufficient time sequence dependence modeling and inaccurate similarity measurement of an existing action recognition method.

The application relates to a power equipment management method and device based on a graph convolution network, and belongs to the technical field of power equipment management.The method comprises the following steps: obtaining operation data of power equipment, obtaining a causal feature vector based on the operation data, calculating a causal feature vector similarity to determine the causal strength between each device and constructing a causal strength matrix.The causal feature vector and the matrix are input into a graph convolution network, an output node embedding matrix is output, a clustering center vector is obtained to determine the clustering labels of each device, and a device clustering set is formed.A coordination index of each set is obtained, and a resource allocation amount is obtained accordingly, and the resource allocation amount of each power equipment is calculated by combining a device resource allocation weight.A dispatching plan is generated according to the resource allocation amount of each power equipment, and the application ensures that key areas and important equipment can obtain reasonable management resources.

The invention discloses a cultural relic comment platform based on a VR technology and a three-dimensional space hotspot extraction algorithm. The cultural relic comment platform comprises a 3D model outer surface approximate shortest circuit solving module, a comment hotspot clustering module, a comment weighted full-text construction module, a text simplification extraction module and a scene simulation module. The 3D model outer surface approximate shortest circuit solving module is used for extracting an approximate shortest circuit between any two points on the outer surface of the model; the comment hotspot clustering module is used for performing clustering labeling on the comments on the model and extracting hotspots in the comments; the comment weighted full-text construction module performs weighted construction on the comments of the same cluster label; the text simplification extraction module is used for carrying out simplification extraction on weighted full texts under the same clustering label comments; the scene simulation module constructs a model and a scene based on a VR technology. On the basis of cultural relic display, the functions of user comment, like giving and the like are provided, a cultural relic communication community is helped to be constructed, and the browsing experience of the user is improved by extracting hot comments on the cultural relics.

The invention belongs to the technical field of mass spectrum data analysis, and particularly relates to a mass spectrum gas source analysis method and system based on a K-means clustering algorithm. The method comprises the following steps: acquiring and preprocessing original mass spectrum time sequence data to obtain a standardized mass spectrum matrix; performing feature engineering optimization on the standardized mass spectrum matrix to obtain a low-dimensional feature space matrix; processing the low-dimensional feature space matrix through a clustering algorithm to obtain a clustering tag vector and a centroid feature vector; and based on a pollution source database, performing pollution source fingerprint matching and analysis through the clustering tag vector and the centroid feature vector. According to the invention, baseline correction is carried out through the asymmetric least square method, interference of baseline drift and background noise is eliminated, the accuracy of the signal is ensured, data is smoothed through the Savitzky-Golay filter, high-frequency noise is removed, key features of the mass spectrum signal are retained, peak alignment is carried out through the dynamic time warping algorithm, and the accuracy of the signal is ensured. The problem of time migration between different samples is solved, so that the characteristic peaks can be correctly aligned.

The application relates to the technical field of artificial intelligence, and discloses a model construction method, device, equipment and medium. The application obtains training corpus for constructing a model; based on a pre-trained clustering model, the training corpus is subjected to clustering processing to obtain a corresponding clustering result, wherein the clustering result comprises a clustering label and clustering corpus corresponding to the clustering label; based on the clustering label in the clustering result and the corresponding clustering corpus, model training and prediction are performed, and a target intent recognition model is determined according to a model training and prediction result. The above method of automatically generating the target intent recognition model reduces the time input in the process of familiarizing with business points and data labeling, accelerates the process of combing business points and labeling business corpus, improves the efficiency of constructing the target intent recognition model, and reduces the labor cost.

This invention belongs to the field of power system monitoring technology and discloses a method, system, equipment, and medium for analyzing the icing state of transmission lines based on point cloud modeling and deep learning, thereby overcoming the limitations of existing methods in time series processing. The method includes: dividing the time series point cloud of the transmission line into multiple time subsequences; generating a topological persistence graph for each subsequence through voxelization and persistent coherence analysis; calculating the dynamic topological distance between subsequences based on the persistence graph; extracting topological features to construct a feature matrix, and fusing topological distance, feature space, and feature distribution three views to construct a similarity matrix; using multi-view joint learning to obtain a consensus subspace and performing subsequence clustering within this space to obtain cluster labels; combining physical context information and predefined rules to assign physical pattern labels to the clustering results, generating an icing state classification report and visualizing it. This invention achieves temporal topological quantitative analysis and highly robust state identification of icing morphology.

The invention belongs to the technical field of network intrusion detection, and particularly relates to a defense method and system for a firewall persistent backdoor. The method comprises the steps of obtaining historical traffic data; performing feature extraction on the historical flow data to obtain structured feature vector data; performing dimension reduction on the structured feature vector data by using a diffusion diagram method to obtain dimension-reduced feature vector data; classifying and merging the dimension reduction feature vector data to obtain a clustering label; according to the clustering label, performing rule extraction on the current network flow data to obtain a classification rule; and combining the classification rules to obtain a rule set. The method can be used for monitoring the traffic of the Cisco ASA firewall backdoor program. The structure of data is learned in an unsupervised manner by using a diffusion diagram dimensionality reduction method, and tags are obtained by using clustering. And related abnormal traffic is extracted by using data classification, and possible backdoor communication traffic characteristics are distinguished.

The present disclosure relates to the technical field of mass spectrum data analysis, and particularly relates to a mass spectrum gas source analysis method and system based on a K-means clustering algorithm. The method comprises: obtaining original mass spectrum time series data and preprocessing to obtain a standardized mass spectrum matrix; performing feature engineering optimization on the standardized mass spectrum matrix to obtain a low-dimensional feature space matrix; processing the low-dimensional feature space matrix through a clustering algorithm to obtain a clustering label vector and a centroid feature vector; and performing pollution source fingerprint matching and analysis based on a pollution source database and the clustering label vector and the centroid feature vector. The present disclosure performs baseline correction through an asymmetric least squares method, eliminates the interference of baseline drift and background noise, ensures the accuracy of the signal, smoothes the data through a Savitzky-Golay filter, removes high-frequency noise, retains the key features of the mass spectrum signal, and performs peak alignment through a dynamic time warping algorithm, thereby solving the time offset problem between different samples and enabling the correct alignment of the characteristic peaks.