597 results about "Relevance analysis" patented technology

The invention provides a prediction model construction method and system for personalized equipment operation and maintenance, and relates to the technical field of data processing, and the method comprises the steps: collecting equipment operation data and environment data, extracting the change characteristics of the equipment operation state, carrying out the correlation analysis of the environment data based on historical equipment fault records, and obtaining a prediction model. Performing normalization processing, performing time sequence analysis, generating a joint feature matrix, segmenting the joint feature matrix into time slices of a fixed window according to a time sequence, classifying the time slices into a normal state and an abnormal state, performing feature contribution degree analysis, generating a feature weight matrix, and performing feature extraction; re-combining the equipment features in the time slice feature data set with the environment factors according to feature weights, generating fusion feature data layer by layer, performing supervised learning training on the fusion feature data, constructing an equipment prediction model, and outputting the equipment prediction model as a prediction model of personalized equipment operation and maintenance; according to the invention, the operation and maintenance effect of personalized equipment is improved.

The invention discloses a light industry supply chain multi-modal data fusion analysis method based on deep learning, and the method comprises the following steps: carrying out the cleaning and standardization processing of text, image, audio and video data collected in a supply chain environment, and constructing a standardized multi-modal data set; then, a special feature extraction network is adopted to generate each modal feature vector, and a feature incidence matrix is constructed through cross-modal correlation analysis; feature weights are dynamically adjusted in combination with a domain knowledge rule base, multi-modal feature interaction is achieved through a cross-modal attention fusion network, and unified fusion features are generated through a self-attention mechanism; and finally, constructing a supply chain decision model, and mapping the fusion feature into a supply chain state evaluation result and an optimization parameter. According to the method, knowledge rule constraint and a deep attention mechanism are fused, supply chain situation awareness precision and decision reliability can be effectively improved, and technical support is provided for intelligent management of the light industry supply chain.

The invention relates to a water conservancy equipment service life prediction and fault monitoring method. The water conservancy equipment service life prediction and fault monitoring method comprises the steps of performing comprehensive digital modeling on water conservancy equipment, determining a fault sensitive area and a key monitoring point, generating a sensor deployment scheme, preprocessing analog and simulated sensor data, and ensuring that the data is comprehensive and targeted; performing multi-domain fusion feature extraction, deep feature learning and correlation analysis on the data, screening out important features to form a feature subset, and capturing equipment fault features in all directions; a mixed life prediction model is constructed, parameter initialization, pre-training and formal training are completed, a multivariate Gaussian mixture model and a deep belief network are constructed, and then a fault monitoring model is obtained; sensor data arranged according to a deployment scheme is obtained in real time, features are extracted after preprocessing, real-time feature vectors are input into a life prediction model and a fault monitoring model respectively, life prediction and fault monitoring of the water conservancy equipment are achieved, powerful decision support is provided for equipment maintenance, reliable operation of the water conservancy equipment is guaranteed, and fault loss is reduced.

The invention provides a construction site collision risk assessment method based on a digital twinborn scene, and relates to the technical field of building simulation and collision detection. According to the method, after collision risk evaluation factors are screened out by constructing a construction site digital twinborn scene, correlation analysis is carried out by using a weighted Heraonian average operator, and a determined weight is obtained; constructing a membership function of each collision risk evaluation factor, performing fuzzy reasoning, establishing a construction site collision risk evaluation mechanism, and outputting an evaluation result; dynamically generating and updating the working space of the digital twinborn scene according to the evaluation result, reconstructing the digital twinborn scene, and executing voxelization collision detection to obtain an accurate collision detection result; and according to an accurate collision detection result, in combination with the generated dynamic working space, calculating a collision time-space amount to obtain a final risk value. The method is high in collision detection speed and accurate, is applied to a dynamic complex environment of a construction site, and can achieve objective and accurate evaluation of space-time collision risks.

The invention provides a method and a system for identifying and cleaning abnormal data, which relate to the technical field of data processing, and are used for identifying and cleaning abnormal data by acquiring real-time data flow, determining a self-adaptive threshold value by using a trained Gaussian mixture model and detecting abnormal data points. A deep belief network and long and short term memory network composite model is adopted to carry out deep feature learning and anomaly verification, and high-level feature representation and anomaly degree quantitative evaluation results are obtained; and evaluating a conditional dependency relationship among the abnormal data points by using the probability graph model, constructing a target probability dependency graph, and generating an abnormal data point recognition result. Based on an identification result, a reward mechanism excitation algorithm is applied to optimize a cleaning strategy; according to the method, the to-be-determined abnormal region is identified, the multi-modal fusion technology is introduced to perform correlation analysis, and the data in the to-be-determined abnormal region is judged and cleaned based on the analysis result to obtain the target cleaning strategy, so that the abnormal data identification and cleaning efficiency and accuracy are improved, and the method has relatively high adaptive capability and expansibility.

The invention belongs to the field of data analysis, and discloses a data analysis method for engineering consultation digital intelligent management, which comprises the following steps: mapping multi-project heterogeneous data to a unified three-dimensional space-time grid through space-time grid division to form a grid mapping data set; detecting data format and attribute conflicts based on neighborhood correlation analysis, and distributing calibration data through dynamic weight; missing values and abnormal fluctuations are processed by using a time sequence autoregression model and a smoothing technology, and a complete data set with continuous time is constructed by combining linear interpolation and multi-dimensional data fusion; key indexes are extracted to construct a digital mirror image containing spatial positions, time sequences and attribute association, real-time data are synchronized, and outlier grid points are corrected; and multi-scene operation conditions are constructed based on the mirror image data, and a dynamic adjustment scheme is realized. According to the method, heterogeneous data are integrated through space-time grids, digital twinning and multi-scene simulation technologies are combined, and full-period management and risk intelligent decision-making of engineering data are achieved.

The invention relates to a cotton field carbon sink dynamic evaluation method and system based on multi-source data fusion. The method comprises the following steps: firstly, comprehensively collecting multi-source data of a cotton field area environment, and processing the multi-source data by using a time window alignment technology to generate a multi-source heterogeneous data set; based on the data set, key features are extracted through a data mining means, and a key influence factor weight table is generated; and then, inputting the key influence factor weight table and the multi-source heterogeneous data set into the trained optimization evaluation model together to obtain cotton field carbon sink space-time distribution characteristics. And finally, carrying out correlation analysis on the spatial-temporal distribution characteristics and meteorological continuity data, and generating a curve capable of visually displaying the dynamic change of the cotton field carbon sink along with time. The method overcomes the limitation of a single data source, greatly improves the accuracy and comprehensiveness of cotton field carbon sink evaluation, can accurately reflect the real state of cotton field carbon sink under different time-space conditions, and provides a key basis for agricultural managers to formulate scientific and reasonable cotton field planting management strategies.

The invention relates to the technical field of deep learning, in particular to an AI chip test parameter adaptive optimization method based on deep learning, which comprises the following steps: acquiring historical test data of an AI chip, and calculating correlation strength among different failure modes based on the historical test data; identifying a failure coupling matrix according to the edge weight, and converting a preset static detection parameter constraint boundary into a dynamic constraint space changing along with a failure detection state; a multi-level optimization framework is constructed, the upper layer executes failure type correlation analysis and generates constraint propagation information, the middle layer optimizes a parameter cluster based on the constraint propagation information, and the lower layer adjusts a single detection parameter and outputs a parameter optimization result; establishing a neural network mapping model, and obtaining a nonlinear mapping relationship between the detection parameters and the failure types; based on the physical state parameters, the nonlinear mapping relation is adjusted, the dynamic constraint space is updated, parameter optimization is executed again, a parameter optimization result is output, and an optimal test parameter combination is output.

The invention provides a supply chain prediction method based on a knowledge graph and an industrial model, and the method comprises the steps: collecting the features needed by supply chain prediction, and the needed features comprise historical order data and production plan data, industrial product purchasing data and collection information, logistics data and storage data; performing data cleaning, standardization and correlation analysis on the historical order data, the production plan data, the industrial product purchasing data, the collection information, the logistics data and the storage data to obtain target features; key entities and relationships in the target features are identified, and a knowledge graph is constructed based on the key entities and the relationships; the industrial model is used for identifying supply chain key nodes and node relations in the knowledge graph, the supply chain key nodes and the node relations are converted into numerical feature vectors used for supply chain prediction so as to carry out supply chain prediction, the relations among the nodes in the supply chain can be better captured by introducing the knowledge graph and the industrial model, and the supply chain prediction accuracy is improved. Therefore, the supply chain prediction precision is effectively improved.

The invention relates to a multi-factor fusion Internet of Things outlier data identification method, and belongs to the technical field of Internet of Things, and the method comprises the steps: determining an identified target factor, fusing a plurality of influence factors associated with the target factor, obtaining corresponding historical data, and carrying out the preprocessing; performing correlation analysis on the specific indexes, and selecting index data having significant influence on target factors to form a final effective index combination; constructing a prediction model combining the LSTM with a feature attention mechanism, performing prediction by using the data after correlation analysis screening, outputting a prediction value in a future period of time, and obtaining an actual prediction value through reverse normalization; a prediction model is adopted, an outlier data identification method fused with multi-factor comprehensive analysis is adopted, an isolated forest algorithm is used for modeling, prediction residual errors and influence factors serve as input features, and the abnormal score of each data point is calculated; and based on the distribution of the abnormal scores, dynamically setting a threshold value by adopting a sliding window technology, and judging the data points exceeding the threshold value as outlier data.

The invention relates to the technical field of power system measurement, and discloses a current transformer error dynamic monitoring method and system.The current transformer error dynamic monitoring method comprises the steps that current transformer time sequence data and a system event log are obtained; constructing a time sequence causal graph to represent the time correlation between the event and the error change; identifying potential causal links by applying a counter causal model; designing a multi-world simulation engine to generate an anti-fact scene; quantifying a causal effect by comparing actual observation with an anti-fact simulation result; establishing a monitoring mechanism to track key trigger events in real time; generating a dynamic causal interpretation report and adjusting a compensation strategy; according to the method, the limitation of traditional correlation analysis is broken through, the causal relationship and the correlation can be accurately distinguished, the real triggering factor of the error change of the current transformer can be accurately identified, the false alarm rate and the missing report rate are reduced, and the accurate dynamic monitoring of the error of the current transformer is realized.

The invention discloses a common concrete and ultra-high performance concrete performance prediction and mix proportion multi-objective optimization design method and system, and the method comprises the steps: obtaining a comprehensive data set which covers the mix proportion, performance data and cost data of common and ultra-high performance concrete; correlation analysis is carried out, and influence factors strongly correlated with the target variable are determined; constructing a concrete performance prediction model by using a machine learning algorithm, training and testing, then carrying out interpretability analysis, and selecting an optimal concrete performance prediction model; constructing a mix proportion optimization design objective function and an ultra-high performance concrete cost function; establishing a multi-objective optimization design mathematical model in combination with constraint conditions, a cost function and an optimization objective function; and solving by adopting a multi-objective evolutionary algorithm, generating an approximate Pareto frontier solution set, and determining an optimal mix proportion optimization design scheme. According to the method, the concrete performance can be predicted, the mix proportion with the optimal comprehensive performance and cost effectiveness is obtained, and multi-objective optimization design of the concrete mix proportion is achieved.

The invention relates to the technical field of legal text generation, in particular to an intelligent case generation method based on a judicial knowledge domain atlas, which comprises the following steps: S1, constructing the judicial knowledge domain atlas; s2, extracting case facts and judgment reason parts of the document; s3, classifying and splitting case facts of the document; s4, carrying out deep learning to generate an abstract; s5, correlation comparison of the content is carried out, and integrity and accuracy are verified; s6, optimizing a judgment key through a convolutional neural network model; s7, automatically generating correlation indexes with other historical cases according to correlation analysis in the judicial knowledge domain graph; s8, summarizing the results, and splicing the results into a complete case document; according to the method, by combining the judicial knowledge domain graph and the deep learning technology, the legal document is automatically generated, the integrity of document content and the accuracy of legal logic are ensured, historical cases are efficiently associated, and the efficiency and quality of judgment document generation are remarkably improved.

Provided in the present invention are a method and system for real-time update of a medical knowledge base, and a medium and a device. The method comprises: acquiring medical literature data in real time; analyzing the medical literature data, so as to obtain first structured data; performing correlation analysis on the first structured data and second structured data in a medical knowledge base, so as to obtain an analysis result; on the basis of the analysis result, determining whether to update the medical knowledge base; identifying the differences of the medical knowledge base before and after the update, so as to obtain a difference identification result; assigning a unique version number to each difference in the difference identification result, so as to obtain version update records; and on the basis of the version update records, using incremental hash table technology to perform data storage for each difference. The present application has a higher update efficiency without the risk of omission; and by means of difference analysis and by using incremental hash table technology to store difference data, the present application significantly reduces data storage space requirements, and also improves data access speed.

The invention discloses an intelligent question and answer method and system based on a mine safety large model. The method comprises the following steps: constructing a vector database based on a mine document data set; obtaining an input user question, and generating a corresponding similar question based on the user question; after the similar questions and the user questions are combined, vectorization processing is carried out, and user question vectors are generated; performing correlation retrieval of the text blocks in a vector database based on the user question vector to obtain a corresponding preliminarily screened text block set; reordering the preliminarily screened text block set to obtain a finely arranged text block set; and inputting the user question and the reordered finely-arranged text block set into a large model for correlation analysis, outputting the text blocks most relevant to the user question, and sorting the text blocks according to similarity to form a data set as a retrieval result. According to the method, related questions are generated on the basis of user questions to cover more possible query intentions and expression modes, so that the accuracy and efficiency of mine risk hidden danger question answering are improved.

The invention is suitable for the field of abnormal data monitoring, and provides an abnormal data monitoring method and system based on artificial intelligence, and the system comprises a real-time data flow collection module, a cross-level correlation analysis module, a dynamic baseline model building module, an abnormal behavior comparison module, and an abnormal traceability module. According to the method, through real-time data acquisition, cross-hierarchy analysis, dynamic modeling, anomaly detection and deep threat tracing, an efficient and intelligent anomaly monitoring closed loop is constructed, and remarkable beneficial effects are presented. According to the method, firstly, real-time data flow capture and cross-level correlation analysis are utilized to ensure that interaction behaviors of multiple protocol levels in a network are comprehensively covered, and a complex abnormal mode is recognized in combination with context information; according to the multi-dimensional analysis, the detection accuracy is remarkably improved, false alarm and missing alarm are effectively reduced, meanwhile, an abnormal mark data set with weights is generated, and high-quality data support is provided for follow-up processes.

The invention relates to an offshore wind power prediction method, and aims to improve the accuracy and reliability of prediction. The method comprises the following steps: (1) a data preprocessing stage: detecting an abnormal value in data by using a DBSCAN clustering algorithm, reconstructing the abnormal value by using a KNN interpolation method, detecting time sequence abnormity through an LSTM automatic encoder, and performing regression reconstruction by using LSTM to ensure the retention of time sequence features; (2) a feature engineering stage: screening out key features through correlation analysis, generating a label column through K-means clustering and wind direction classification, and extracting features such as wind direction change rate, time periodicity and wind speed interaction; and (3) a model construction stage: constructing a composite model in combination with multi-scale convolution (Inception), a bidirectional long short-term memory neural network (BiLSTM) and a multi-head self-attention mechanism, extracting local features through a convolution layer, capturing a time dependency relationship through a bidirectional LSTM layer, enhancing the attention of key features by using the multi-head self-attention mechanism, and finally realizing high-precision wind power prediction.

A photovoltaic power generation few-sample transferable prediction method based on a large language model comprises the following steps: carrying out extreme value normalization and block cutting on photovoltaic time sequence data to generate an embedded module adaptive to the input of the large language model; fusing high-order partial correlation analysis and a gating residual network to dynamically allocate feature weights, and extracting space-time dependence and nonlinear correlation features in the multi-dimensional data; mapping the structured time sequence features to a large language model semantic space, and realizing high-fidelity alignment with a pre-training corpus by using a mask multi-head attention mechanism; generating a cue word prefix containing a data background, a domain mode and statistical characteristics based on a preset template, and guiding a large language model to accurately analyze time sequence semantics; and generating a natural language prediction result through the pre-training large language model of the frozen parameters, and finally performing inverse analysis through linear projection to obtain a numerical power generation prediction value. The method can effectively solve the problems that a traditional model is insufficient in generalization ability and poor in cross-station migration prediction stability in a data scarcity scene.

The systems and methods described herein can identify meaningful relationships between variables, such as particular investments or general asset classes. Unlike conventional correlation analysis, these systems and methods provide an improved technique of co-movement analysis that implements a threshold to eliminate data “noise” and then discretizes the remaining observations to normalize any outliers. Such co-movement analysis has numerous advantages over known techniques for characterizing relationships between variables.

The invention relates to the field of data processing, in particular to a multi-source data quality improving method which is particularly suitable for processing and optimizing load data. Performing feature extraction on the multi-source load data to obtain load data containing a mode and a structure of the data; performing anomaly detection on the load data by applying a local anomaly factor LOF algorithm, and screening out abnormal data; correcting the detected abnormal data through a Pearson correlation analysis method; and based on the feature extraction and anomaly correction results, calculating the weight relationship between the load data features by applying an entropy weight method, and further optimizing the data correction and feature extraction process so as to improve the overall data quality and accuracy. According to the scheme, a reliable data basis is provided for big data analysis and operation state evaluation of the smart power grid, the efficiency and accuracy of data mining and analysis are effectively improved, and a solid guarantee is provided for optimal scheduling and decision support of the power grid.

The invention relates to the technical field of data transmission of the Internet of Things, in particular to a self-adaptive data compression and transmission method of a low-power-consumption wide-area Internet of Things. According to the method, a three-layer collaborative architecture comprising an equipment layer, a fog computing layer and a cloud computing layer is constructed, data preprocessing and feature analysis are performed on the equipment layer, and data types, entropy values and repeatability information are extracted; the fog calculation layer selects an optimal compression algorithm based on a multi-dimensional decision engine, and reduces redundancy through spatial-temporal correlation analysis and data aggregation; the cloud computing layer collects compression performance data, adopts reinforcement learning and federal learning to train a global optimization model, and dynamically issues strategy parameters; and the fog node adaptively adjusts a compression strategy in combination with the system state to realize the optimal balance between the compression ratio and the reconstruction precision. The method is suitable for field deployment environments with limited electric quantity and network, has the advantages of low power consumption, high efficiency, strong adaptability and the like, and can be widely applied to Internet of Things scenes such as remote monitoring, smart energy and the like.

The invention discloses a power transmission and transformation project cost intelligent review method based on cost fluctuation characteristics, and relates to the technical field of intelligent review, and the method comprises the following steps: collecting historical cost data, preprocessing the data based on NACEMD, and recognizing power transmission and transformation project cost influence factors; judging main influence factors influencing the cost by adopting correlation analysis, and carrying out clustering analysis on different project types to obtain different types of power transmission and transformation project sample sets; on the basis of the historical cost data and the transmission and transformation project sample set, cost intervals of different types of costs of the transmission and transformation project are calculated through a Cheff-Snow ratio inequality for different types of costs, and fluctuation intervals of different types of costs are judged; corresponding intelligent methods are set for different types of fees, and based on prediction analysis of the three types of fees, evaluation standard determination of the power transmission and transformation project cost is realized through input of related project parameters. And the scientificity and accuracy of the review process are ensured through model selection for different fluctuation types.

The invention discloses a judicial field class case retrieval method and system based on a large model. The method comprises the following steps: constructing a judicial document vector database by combining a vector model with an obtained judicial document; performing semantic recognition and question enhancement on judicial case or judicial question texts through the large model; generating vectors for the enhanced judicial case or judicial question text through a vector model, and performing similarity retrieval in a judicial document vector database to obtain a primarily screened judicial document set; reordering the primarily screened judicial document set through a Reranker model to generate a finely arranged judicial document set; and inputting the enhanced judicial case or judicial problem text and all judicial documents in the finely arranged judicial document set into a large model for correlation analysis, outputting the judicial documents most related to the judicial case or judicial problem text, and sorting the judicial documents according to similarity to form a data set as a retrieval result. According to the method, the accuracy and efficiency of class case retrieval can be improved.

The invention discloses a method for dynamically predicting the underground water level during excavation of an overtopping ground layer foundation pit, and relates to the technical field of dynamic prediction of the underground water level, which comprises the following steps of: acquiring multi-source data related to the underground water level in an engineering range; comprising information of soil moisture content, stratum permeability coefficient, rainfall capacity, foundation pit excavation depth, foundation pit dewatering scheme and foundation pit waterproof and drainage measures; historical underground water level, underground aquifer data and Yangtze River water level change information are obtained. According to the method, data quality is optimized through multi-source data acquisition, correlation analysis and z-score standardization, nonlinear modeling is realized in combination with a support vector machine (SVM) and Bayesian optimization, and model precision and generalization ability are improved. Model parameters are dynamically adjusted through a real-time monitoring and feedback optimization mechanism, the adaptability to sudden hydrological changes is enhanced, engineering risks are effectively reduced, and construction safety and economical efficiency are guaranteed.

The invention discloses a heavy duty gas turbine compressor scale deposition detection method based on a liquid neural network, and relates to the technical field of anomaly detection, and the method comprises the following steps: collecting operation data for correlation analysis; the selected feature data is preprocessed; extracting time characteristics of the operation parameters of the gas compressor; calculating weights of interaction among the parameters, and outputting spatial correlation; constructing a space-time fusion model, and inputting normal operation data to train the model; and a parameter prediction sequence is output, a multi-dimensional residual vector of a predicted value and an actual value is calculated, and by constructing a dynamic threshold function, when the model converges and residual distribution deviates from a normal working condition confidence interval, a gas compressor fouling anomaly detection result is output. According to the invention, through the dynamic topological structure of the liquid neural network and in combination with a spatial-temporal characteristic collaborative mining mechanism, quantitative evaluation of the scale deposition degree of the gas compressor is realized, and the precision and robustness of gas compressor scale deposition anomaly detection are improved.

The invention relates to the technical field of data processing, and particularly provides an address text correlation analysis method, system and device and a storage medium, and the method comprises the steps: receiving a target address text; based on the semantics of the target address text, retrieving a plurality of candidate standard address texts from a pre-constructed address knowledge base; on the basis of the target address text and the retrieved candidate standard address text, a cue word is constructed, and the cue word comprises an instruction used for guiding a large language model to conduct address relevance judgment and context information; and inputting the cue word into a large language model trained in an address field, and obtaining and analyzing the output of the large language model to determine a standard address text associated with the target address text and the association degree thereof. According to the method, the domain knowledge base and the large language model are fused, so that the accuracy and practicability of address correlation analysis are remarkably improved.

The invention discloses a multi-source data resource key information mining method and system, and the method comprises the steps: obtaining multi-source data of various forms and types, and carrying out the preprocessing; performing division according to data types; word frequency statistics and word correlation analysis are carried out on the character data, and numerical value meanings of the digital data are extracted through context semantic correlation; constructing a cross-modal key information data set based on the key information data set of each data type; designing a multi-branch long-short-term memory neural network model, inputting a cross-modal key information data set into the model for training, and generating key information mining models for different fields by dynamically adjusting network parameters; and selecting to carry out key information real-time extraction and updating on the optimal model, generating a knowledge graph, and carrying out visual operation. The method has the advantages that through multi-source data fusion and processing, the long-short term memory neural network model is combined, the knowledge graph is generated, and domain-specific key information mining and visualization operation are efficiently carried out.

The invention discloses a TC path and intensity prediction method and device based on AI and physical characteristics and a medium, and aims to improve the short time scale prediction precision of the TC path and intensity, and through integration of a plurality of factors with definite physical significance, such as guide airflow, ventilation flow, vorticity, ocean surface temperature and the like, the TC path and intensity can be predicted. The physical factors are subjected to correlation analysis, regression analysis and the like, and it is ensured that the input factors have significant influences on TC paths and intensity changes. A plurality of AI models such as a convolutional neural network (CNN), a recurrent neural network (RNN), a multi-layer perceptron (MLP), a random forest (RF), a limit gradient boost (XGBoost) and a long short-term memory network (LSTM) are adopted to capture a complex nonlinear relationship between meteorological factors. In addition, by adopting a real-time feedback mechanism, new observation data are allowed to be dynamically input, model parameters are optimized, and the real-time performance of a prediction result is improved. The method is particularly suitable for the northwest Pacific Ocean region, has wide application prospects, and provides scientific support in the fields of meteorology, aviation, marine transportation and the like.

The invention relates to a correlation analysis method and device for computing power resources of a data center and energy consumption of refrigeration equipment, and the method comprises the steps: obtaining related data of the computing power resources of the data center and the energy consumption of the refrigeration equipment, carrying out the correlation analysis of the preprocessed related data, and obtaining key parameters related to the computing power resources of the data center and the energy consumption of the refrigeration equipment; selecting a model according to the key parameters and the modeling target, training the selected model by using historical data to learn the correlation between the computing power resource and the energy consumption of the refrigeration equipment, and evaluating the performance index of the selected model; according to the modeling target and the constraint condition, an optimization algorithm is selected to carry out joint optimization logic of the data center computing power resources and the refrigeration equipment energy consumption, the optimization algorithm is operated, and distribution of the data center computing power resources and operation parameters of the refrigeration equipment are adjusted through iteration; and obtaining a performance index for evaluating the correlation between the computing power resource of the data center and the energy consumption of the refrigeration equipment. According to the method, the prediction accuracy, generalization ability and interpretability of the model are remarkably improved.

The invention belongs to the technical field of traffic pollution prediction, and particularly relates to a LightGBM-based multi-source data fusion pollutant concentration prediction method, which comprises the following steps of: 1, integrating and processing multi-source data, and constructing a plurality of feature sets; and 2, carrying out feature analysis on meteorological, pollutant and traffic index variables through correlation analysis and time sequence analysis, and providing support for modeling and model interpretation. And step 3, dividing a training test set according to a time sequence, and training and optimizing the LightGBM pollution prediction model through parameter tuning by taking minimization of RMSE as a target. And 4, verifying the performance of the model from prediction precision, spatial distribution and wind direction influence. And 5, analyzing and displaying the key driving factor and quantifying the contribution of the key driving factor. According to the invention, through feature engineering processing and model optimization of heterogeneous data such as weather and traffic, high-precision prediction and influence factor analysis of lane-level pollutant concentration are realized.