11737 results about "Big data" patented technology

The present invention discloses an artificial intelligence-based adaptive big data storage and retrieval optimization system and method designed to intelligently manage and optimize large-scale distributed data environments. The system integrates data acquisition, distributed storage, metadata processing, adaptive learning, and retrieval optimization units configured to work collaboratively for continuous self-optimization. The invention employs deep reinforcement learning and predictive neural network techniques to dynamically analyze system telemetry, workload behavior, and data access patterns in real time, enabling proactive adjustment of data placement, caching, replication, and compression parameters across distributed nodes. The metadata processing framework utilizes graph-based dependency modeling to maintain semantic and contextual relationships among datasets, facilitating intelligent and context-aware data retrieval. The retrieval optimization unit interprets user queries semantically and computes the optimal retrieval route using latency prediction models and dynamic routing techniques.

The invention provides a dynamic graph neural network modeling method for space-time big data, and relates to the technical field of data processing, and the method comprises the steps: mapping a network function entity into a topology vertex and mapping a topology correlation characteristic into a weighted transmission link, and triggering a sequence through a signaling event to drive topology reconstruction, and generating a communication network topology model; inputting the communication network topology model into a dynamic graph neural network, executing state feature space aggregation of a topological vertex neighborhood through a spatial-temporal feature extraction layer, and fusing time evolution dependency of a historical topological sequence to generate a network node spatial-temporal state tensor; and based on the network node space-time state tensor, a particle swarm optimization algorithm is adopted to calculate a whole network risk level quantitative topology feature, and network resource strategy optimization is dynamically executed to suppress end-to-end risk conduction. The adaptive capacity of the network to the dynamic scene is improved.

The invention relates to the technical field of agricultural information management, and particularly discloses an agricultural information management system and method based on a big data platform, and the method comprises the steps: firstly deploying a multi-source data collection module at an edge calculation node, and obtaining and standardizing the soil moisture content, meteorological environment and equipment operation data in real time; secondly, constructing a local dynamic irrigation strategy model, and realizing multi-objective optimization through a reinforcement learning algorithm; establishing a federated learning framework at the cloud, dynamically distributing node weights by adopting an attention mechanism, and realizing model aggregation of privacy protection in combination with secure multi-party computing; an optimal irrigation instruction is generated through a multi-source data fusion engine, and a three-level response exception handling mechanism is established; and finally, a closed-loop feedback system containing short-term incremental learning and long-term architecture optimization is formed. The corresponding management system comprises six functional modules, namely a data acquisition module, a local modeling module, a federated learning module, a real-time decision-making module, an abnormal monitoring module and a closed-loop optimization module.

A parallel processing unit comprises a plurality of processors each being coupled to a memory access hardware circuitry. Each memory access hardware circuitry is configured to receive, from the coupled processor, a memory access request specifying a coordinate of a multidimensional data structure, wherein the memory access hardware circuit is one of a plurality of memory access circuitry each coupled to a respective one of the processors; and, in response to the memory access request, translate the coordinate of the multidimensional data structure into plural memory addresses for the multidimensional data structure and using the plural memory addresses, asynchronously transfer at least a portion of the multidimensional data structure for processing by at least the coupled processor. The memory locations may be in the shared memory of the coupled processor and / or an external memory.

The invention provides a new energy automobile battery thermal management method and system based on big data. The method comprises the steps that real-time data flow and a historical temperature change curve in a battery pack are collected in real time through a distributed sensor array; inputting a pre-trained time sequence prediction model, outputting a predicted temperature change curve and calculating a real-time temperature rise slope; obtaining an environment comprehensive compensation amount according to the environment temperature and the battery health state, and subtracting the environment comprehensive compensation amount from the basic safety threshold value to obtain a dynamic safety threshold value; determining a dynamic temperature compensation amount through a preset slope grading mechanism, and subtracting the dynamic temperature compensation amount from the dynamic safety threshold to obtain an advanced intervention temperature point; and when the temperature of the battery pack reaches the advanced intervention temperature point, a graded cooling system is started, and cooling power grades are dynamically switched according to the growth interval where the real-time temperature rise slope is located. The battery temperature is accurately controlled, and the energy consumption is remarkably reduced.

The invention provides a resource scheduling control method and system for a big data server, and the method comprises the steps: constructing a multi-dimensional resource portrait module, collecting the CPU, memory, network, storage I / O load and task queue length of each node in real time, and predicting a resource demand trend through a time sequence algorithm; extracting characteristics such as calculation intensity, data dependence, memory requirements, network transmission quantity and the like; adjusting the weight coefficients of the resource utilization rate, the task completion time and the energy consumption efficiency according to the system load and the historical effect; establishing a bipartite graph model by taking a resource trend as a node feature and a task vector as an edge feature, and calculating a matching score through graph convolution and a multi-objective optimization function; the scheduling scheme is synchronized by adopting a consistency algorithm; automatic rollback and reallocation are carried out when resources are detected to be insufficient; and optimizing a weight coefficient and a network parameter through reinforcement learning. Through the method, the system resource utilization rate can be improved, the task execution efficiency is improved, the overall scheduling effect stability is improved, and the system fault recovery time is shortened.

The invention relates to the technical field of computer network security, and discloses a computer network security access control management method based on big data. The method comprises the following steps: constructing a network security situation knowledge graph, collecting a real-time access behavior sequence through a probe, and synchronizing the real-time access behavior sequence to the knowledge graph; simulating a network entity interaction state in the knowledge graph, and predicting a threat propagation path and a potential intrusion behavior; setting a dynamic access control strategy, constructing a multi-dimensional feature matrix in combination with a real-time access behavior sequence association influence degree and a strategy execution priority constraint condition, calculating a strategy conflict risk score by using a deep learning model, comparing with a preset threshold to judge whether a conflict exists or not, and if yes, reconstructing the strategy; and automatically executing access blocking, session termination and data encryption operations according to the reconstructed strategy, recording an execution log and security feedback data, and updating the knowledge graph in real time. According to the method, the dynamic property and the security of access control are improved, and security threats in a complex network environment can be effectively handled.

The invention discloses a computer big data information processing system, which comprises a data acquisition layer, a data processing layer and a data processing layer, wherein the data acquisition layer is used for accessing structured, unstructured and streaming data by using a multi-source adapter and Apache NiFi, executing format standardization, and extracting basic metadata and semantic tags through a rule engine and an NLP model; the metadata intelligent management layer integrates four modules, namely a federal learning framework for realizing cross-domain dynamic classification labels, an intelligent contract for real-time uplink storage evidence blood relationship change, a Neo4j combined graph neural network for constructing a knowledge graph for mining implicit association, and a reinforcement learning engine for optimizing a storage strategy based on frequency and risk indexes; the distributed storage calculation layer is used for processing batch and real-time metadata by adopting a Cassander + MinIO mixed framework and Spark / Flink, and dynamic partition balance performance is realized; and the application service layer is used for outputting functions of blood relationship query, classified browsing, compliance report and the like through a Vue.js portal and a Spring Cloud micro-service API (Application Program Interface) to form a full-link closed loop.

The invention discloses a big data privacy protection modeling method and system based on federated learning and a block chain, and relates to the technical field of privacy protection and joint modeling. According to the method, homomorphic encryption, differential privacy, federated learning, secure multi-party computing and block chain technologies are fused, big data privacy protection and joint modeling are realized, encryption and dimensionality reduction are performed on original data through homomorphic encryption and differential privacy, an encrypted training sample of secure privacy is generated, a local model is trained on an encrypted data set through federated learning, and a big data privacy protection result is obtained. The method comprises the following steps: calculating aggregation parameters by using security multiple parties, constructing a verification network in combination with a block chain, ensuring credibility and integrity of model training, and finally, adding noise optimization performance for a global model by using differential privacy, testing generalization ability through cross validation, and determining a deployable privacy protection joint learning model, thereby breaking traditional data islands, promoting cross-mechanism data cooperation, and improving the privacy protection performance. Big data values are released, and data protection regulations and privacy requirements are met.

The invention relates to the field of power data management, and discloses a power big data adaptive management method and system fused with spatial-temporal feature mapping, and the method comprises the steps: obtaining a real-time operation data flow from a multi-source power terminal, and constructing an original power data set with a time sequence label and a device identifier; the method comprises the following steps: dividing an original power data set into parallel processing units based on a storage-while-computing architecture, performing dynamic index updating by adopting an event-driven index mapping rule, and constructing a multi-dimensional data index cache system with real-time responsiveness; identifying a key abnormal trajectory through a time-varying feature nesting mechanism, and performing hierarchical measurement and entropy disturbance analysis on a data fluctuation degree in the key abnormal trajectory by using a streaming feature aggregation network; identifying potential security risk nodes in combination with the structure matching degree between the historical abnormal event evolution graph and the key abnormal trajectory; and generating a multi-level response instruction chain based on the risk assessment result. The method has the advantage of improving the operation safety of the power grid.

The invention discloses a big data platform asset intelligent sensing method based on LLM and a customizable MCP, and the method comprises the steps: defining a standard resource library of a model context protocol, constructing a model context protocol server, integrating a plurality of scanning tools, and carrying out the automatic adaption; receiving a natural language demand input by a user, and calling a pre-trained LLM model; the scene analysis module converts a natural language demand into a standardized scene description object; the intelligent scanning module is used for describing an object according to a standardized scene, generating an optimal tool execution chain, executing a complete scanning task, obtaining a task scanning result and unifying formats of heterogeneous data in the task scanning result, and the conflict resolution module is used for removing conflicts; the multi-source data association module fuses network topology resources and flow data captured by a probe to construct a dynamic asset atlas including asset attributes, service dependence and vulnerability information, and the report generation module generates a structured report. The method can provide a global risk perspective and decision support.

The invention discloses a big data risk control decision support system based on multi-modal data, and the system comprises a data access module which is used for accessing and analyzing multi-source entity information, building a grouping calibration rule base, and generating a compliance multi-modal data set; the preprocessing and characterization module is used for preprocessing the data, generating basic characterization of each modal and establishing a micro verifier library; the causal hypergraph module is used for constructing a causal hypergraph and outputting a stable causal structure and a gating mask; the fusion and anti-fact module is used for executing cross-modal fusion to generate a risk representation, generating and verifying a minimum change anti-fact sample, and outputting a reachable identifier and an adjustment representation; the evidence chain module is used for calculating a shortest evidence overpass, generating a structured evidence chain and outputting an evidence index; and the strategy module is used for generating and correcting scores, triggering strategy actions and recording execution information. Through multi-modal data fusion and causal reasoning, high-precision, low-delay and interpretable big data risk control decision support is realized.

The invention discloses a dynamic flow control method for a two-phase cold plate liquid cooling system based on multi-modal sensing, and relates to the technical field of equipment cooling. Comprising the following steps: S1, collecting liquid cooling monitoring data in real time, and performing data preprocessing; s2, judging the state risk of the cold plate, carrying out signal cross validation, and taking an abnormal regulation and control measure; s3, cooling liquid flow regulation and control are carried out, and the matching degree of flow regulation and control and chip thermal load is evaluated, so that flow regulation and control correction is carried out; and S4, constructing a big data modeling and simulation feedback platform, evaluating a flow regulation and control self-healing effect, optimizing each parameter and strategy, and carrying out self-learning evolution. The problems that an existing two-phase cold plate liquid cooling system generally only depends on a single temperature signal, lacks a multi-source redundancy check mechanism, has the problems of response lag, weak local reflection capacity, high risk during failure and the like, consequently, the cooling capacity distribution and adjustment precision is insufficient, and the actual requirement of a high-heat-density data center for heat dissipation is difficult to meet are solved.

The invention relates to a big data-based passenger-roll transport demand prediction and ship intelligent scheduling method and system. The method comprises the steps of obtaining multi-source shipping data for a target area; inputting the multi-source shipping data into the spatial-temporal feature mining model, and predicting passenger rolling transportation demand information of the target area; acquiring ship real-time position, passenger carrying capacity, energy consumption data and port real-time operation state in the target area, and dynamically generating an optimal scheduling scheme by adopting a shipping scheduling model in combination with the predicted passenger transport demand information; the shipping scheduling model is obtained by interacting a decision scheduling model with an intelligent agent corresponding to the passenger roller transportation system and performing iterative training by adopting a reinforcement learning algorithm; and converting the optimal scheduling scheme into visual information, pushing the visual information to operation terminals of the ship and port workers so as to start corresponding shipping scheduling operation, and monitoring the execution effect of the shipping scheduling operation in real time.

The invention discloses a multi-disaster disaster risk grade coupling evaluation method. The method comprises the following steps: establishing a multi-dimensional database covering multiple disaster types; key features related to the disaster risk are extracted from the multi-dimensional database; establishing a risk assessment model according to the key features, and determining a plurality of single-disaster risk levels; identifying association rules, causal relationships or space-time coupling modes among different disasters by using a big data mining algorithm; coupling weights among different disasters are determined, and a coupling model is constructed to convert a coupling relation into a quantitative risk superposition effect; based on the coupling model, a single-disaster risk and a coupling effect are integrated, a multi-disaster comprehensive risk level is generated, through multi-dimensional data integration, quantitative coupling modeling and a dynamic adjustment mechanism, advantages are formed in evaluation precision, social and economic adaptability and model adaptability, and the method is more suitable for scenes needing accurate risk grading and decision support.

A coal mine risk early warning system based on big data analytics, the coal mine risk early warning system comprising: a data collection module, used for collecting data in real time during coal mine operation; a data storage module, configured to store historical data records collected by the data collection module; a data processing module, which uses big data analytics technology to process the stored data and identify potential risk factors; a risk assessment module, which assesses the risk level of coal mine operation on the basis of analysis results of the data processing module, there being three risk levels: low, medium, and high; and an early warning module, which sends an early warning signal to relevant personnel when the risk level reaches a preset threshold.

The invention discloses a bank loan business risk control system and method based on big data analysis, and relates to the technical field of financial risk control, and the method comprises the steps: collecting and preprocessing real-time behavior data, and obtaining a user behavior feature set; based on the user behavior feature set, calling a behavior map modeling engine to carry out structured mapping, matching with a risk anchor point rule base, identifying a potential risk mode and labeling an initial anchor point risk label; correcting the deviation between the initial risk anchor point tag and the actual default record by adopting a value function optimization method, and predicting the risk grade score of the current behavior of each user in combination with the historical behavior sample data and loan feedback data of the user; predicting probability distribution of migrating to a default state in the future through user risk grade scores and historical state evolution data; and in combination with the potential loss under each behavior path, evaluating the current loan business risk, and generating a risk control strategy through a risk level mapping rule and a strategy decision engine.

The invention discloses a nondestructive testing method for internal defects of a concrete structure fusing big data feature extraction and deep learning. According to the method, through multi-source data collaboration and dynamic feature fusion, the accuracy and robustness of concrete structure defect detection are remarkably improved. In a data processing link, ultrasonic electromagnetic induction infrared thermal imaging data and the like acquired by a multi-source nondestructive testing technology are subjected to collaborative preprocessing, so that the influence of noise interference and environmental fluctuation is eliminated, and standardized input is provided for feature extraction. The dynamic weight distribution network further combines the relevance of each modal feature in a historical defect sample, adjusts fusion weights of different modals in real time, reinforces ultrasonic features with great contribution to cavity recognition or infrared features sensitive to cracks, effectively compresses redundant information, and improves the accuracy of cavity recognition. According to the method, features and data-driven deep features of the fused feature vectors are manually designed at the same time, so that the limitation of single-modal data is avoided, and a model can more accurately capture multi-dimensional features of defects.

The invention discloses a bridge construction abnormity monitoring data identification method and system based on big data, and relates to the technical field of bridge construction monitoring, the system comprises a collection module, an analysis module, a process matching module and an execution module, the collection module collects construction data, transmits the construction data to the analysis module, carries out linkage verification on the construction data through an analysis unit, and carries out process matching on the construction data; identifying and outputting abnormal data, transmitting the abnormal data to a process matching module, constructing a judgment standard for dynamic matching through a construction process, comparing the abnormal data with the judgment standard, outputting a preliminary judgment result, transmitting the preliminary judgment result to an execution module, executing multi-stage cross validation on the preliminary judgment result, and outputting a final abnormal judgment result. By responding to multi-source data, missed judgment is prevented, a space-time linkage verification mechanism is constructed to improve anomaly recognition accuracy, a dynamic judgment standard adapts to risks of all stages, false anomalies are filtered through three-stage verification, the efficiency is improved through full-process automation, hidden danger early warning is assisted, accidents are avoided, and bridge construction quality and safety are guaranteed.

The invention relates to the technical field of big data analysis and mining, in particular to a construction progress deviation early warning method and system based on data mining, and the method comprises the following steps: integrating a construction task list, the spatial position of a component in a BIM, the number of operators in a construction log, and the operation state of a tower crane, and generating a multi-dimensional constraint construction map node set; according to the method, a multi-dimensional node set with time, space and resource attributes is constructed by integrating a construction task list, the spatial position of a BIM component, the number of operators in a construction log and the operation state of a tower crane, and structural expression of a construction site is achieved; on the basis, a causal association relationship among construction logic, resource occupation and space proximity is identified, and a time sequence causal conduction map with a deviation conduction coefficient value is further established, so that a risk conduction path between construction events has quantitative calculation capability.

The invention relates to the technical field of cultivated land supervision, in particular to a big data-based cultivated land utilization supervision system, which comprises a pattern spot remote sensing interpretation module, a pixel state aggregation module, a boundary mutation recognition module, a time sequence cultivation fluctuation analysis module and a response priority pattern output module. According to the method, a time sequence label grid set is established through spatial boundary analysis and pixel index extraction of remote sensing image spots, state labels are introduced to classify pixel tillage evolution, an image spot state evolution chain and path structure is constructed on the basis of spatial aggregation, and a continuous fluctuation area is extracted through sliding window analysis of planting behavior factors in the image spots. A co-occurrence block of boundary disturbance and behavior fluctuation is positioned in combination with a space overlapping relation, a response urgency index is constructed after multiple indexes such as state density, disturbance range and duration period are quantified, multi-dimensional judgment and intervention priority ranking of the farmland utilization abnormal area are achieved, and the identification precision and response efficiency of farmland utilization changes are effectively improved.

The invention is suitable for the technical field of data asset management, and provides a data asset management system based on a block chain and big data analysis, and the system comprises a first terminal which carries out the storage of the ownership information of data assets through a block chain network, and generates a storage data package; generating an evaluation result based on a preset technical index analysis model; writing the hash value of the evaluation result into transaction data of the main chain of the block chain, and generating an evidence storage voucher matched with the block chain transaction; an interaction data sequence is packaged for identity signature, encryption and compression to generate a target code stream, and the target code stream is sent to the second terminal; the second terminal decrypts the encrypted data in the target code stream by using a private key, decompresses the data by using a compression algorithm matched with the first terminal, and restores the data into an interactive data sequence; verifying the access authority and the transaction condition of the evidence storage data packet; checking the anchoring state of the evidence storage voucher on the main chain of the block chain; and the data transaction is completed, the data asset state report is generated, and the data element marketization configuration efficiency is improved.

The invention relates to the technical field of data twinning, in particular to a saline-alkali soil water-salt motion simulation method based on big data analysis. The method comprises the following steps: collecting saline-alkali soil multi-source monitoring data; based on the saline-alkali soil multi-source monitoring data, salt soil layer correlation feature analysis and water-salt driving factor coupling feature analysis are carried out, and salt soil layer correlation feature data and water-salt driving factor coupling feature data are obtained; simulation relation model design of saline-alkali soil water-salt movement is carried out through the saline-alkali soil level correlation feature data and the water-salt driving factor coupling feature data, and a saline-alkali soil water-salt movement simulation model is generated; based on the saline-alkali soil water-salt motion simulation model, designing saline-alkali soil farmland irrigation simulation parameters; and carrying out water-salt motion simulation prediction and feedback of the saline-alkali soil farmland irrigation on the saline-alkali soil farmland irrigation simulation parameters. According to the saline-alkali soil water-salt motion simulation analysis method, multi-driving-factor fusion and accurate spatial heterogeneity description are achieved.

The invention provides a production energy efficiency optimization method and system based on industrial big data, and the method comprises the steps: generating an industrial production data set and creating an industrial knowledge graph according to multi-dimensional operation parameters, energy consumption state data and production line constraint information generated by a target factory, mining a causal association relationship among the multi-dimensional operation parameters through ontology reasoning analysis to generate a causal association path; executing a sequential association rule mining operation on the energy consumption state data to obtain association rule mining information of energy consumption fluctuation and operation parameter change, and matching and fusing the association rule mining information and a causal association path to generate a candidate root cause set of energy efficiency abnormality; inputting the candidate root cause set into a bidirectional long short-term memory network, positioning root cause information of energy efficiency abnormity through time dimension relevance modeling and spatial dimension feature reinforcement, and finally generating energy efficiency optimization guidance containing parameter adjustment priority and process optimization suggestions. The accuracy of energy efficiency anomaly root cause positioning and the pertinence of optimization measures are improved.

The invention provides a landslide prediction method and system based on big data analysis, and relates to the technical field of big data analysis, and the method comprises the following steps: obtaining multi-source geological data of a target region, constructing a three-dimensional geological model, and dividing slope units; calculating an initial safety coefficient of each slope unit by adopting a limit equilibrium method and Monte Carlo simulation; acquiring real-time monitoring data, establishing an inverse analysis optimization model, and inverting and calibrating physical and mechanical parameters; updating calibration parameters to the model, coupling rainfall infiltration and underground water seepage simulation, dynamically updating a pore water pressure field, and calculating a real-time dynamic safety coefficient; and according to a comparison result of the dynamic safety coefficient and a preset threshold value, determining the stable state of the slope and sending out corresponding early warning. According to the method, through multi-source data fusion, parameter dynamic inversion calibration and real-time hydrological and mechanical coupling simulation, accurate and dynamic evaluation and graded early warning of slope stability are realized, and the accuracy and timeliness of landslide prediction are remarkably improved.

The invention relates to the technical field of health management systems, and discloses a health management scheme recommendation system based on big data analysis. The system comprises a health data acquisition module, a health characteristic quantification module, a health state identification module, a health scheme prediction module and a health parameter coupling module. The health data acquisition module synchronously acquires three types of time sequence data of physiological indexes, health behaviors and environmental exposure of a user and performs timestamp alignment; a health feature quantification module extracts features from the aligned data and generates corresponding feature matrixes and vectors; the health state recognition module classifies the feature data according to a preset rule and generates a health state label set; the health scheme prediction module is combined with a health intervention measure knowledge base to generate an initial scheme set through an association rule mining algorithm; and the health parameter coupling module corrects the intervention intensity parameter of the initial scheme based on the mapping relationship between the human physiological response and the behavior intervention parameter. According to the system, multi-dimensional health data can be integrated, and an accurate personalized health management scheme is generated.

The present application relates to the technical field of financial risk management, and in particular to a big data-based financial risk assessment and control system. By means of acquiring and preprocessing multi-source financial data of an enterprise, comprising data cleaning, data fusion, and data dimensionality reduction, the system generates standardized financial data. On the basis of the standardized financial data, constructing a multi-dimensional risk assessment model, comprising a market risk assessment model, a credit risk assessment model, an operation risk assessment model and a compliance risk assessment model. Using the multi-dimensional risk assessment model to perform risk assessment, generating a risk assessment report, and according to the report, generating a financial risk management suggestion, thereby implementing real-time alert and dynamic adjustment. The present invention improves the comprehensiveness and accuracy of financial risk assessment, achieves real-time monitoring and dynamic adjustment of financial risks, and improves the integration and reliability of the system.

The invention discloses a multi-dimensional natural resource intelligent monitoring method and system based on big data analysis, and relates to the technical field of resource monitoring, and the method comprises the steps: calculating the information sharing degree between different data streams, constructing an abnormal feature credibility distribution map, and carrying out the calculation of the abnormal feature credibility distribution map; and inputting the abnormal feature credibility distribution graph and the multi-source auxiliary information into an integrated classifier, carrying out joint analysis and comprehensive research and judgment on multi-dimensional information to output a target list, constructing an event response relation graph reflecting a monitoring task priority and an execution logic relation according to the attribute features of each element in the target list, and carrying out event response analysis on the monitoring task priority and the execution logic relation. Wherein each node represents a to-be-monitored target, an edge represents a dependency relationship between tasks, and an optimal monitoring execution path is planned for various intelligent monitoring carriers by using an improved A algorithm integrated with a multi-factor cost function. Through natural resource monitoring of multi-modal data interference correction, intelligent classification and path optimization and dynamic response, the monitoring quality and the execution efficiency are effectively improved.

The invention belongs to the technical field of electric power system information processing, and particularly relates to an electric power information analysis method based on big data, through semantic fusion of multi-source heterogeneous data and dynamic feature mining of a time sequence attention mechanism, in a load prediction scene, compared with a traditional single data source model, the electric power information analysis efficiency is improved. After the meteorological data, the user power consumption behavior data and the power grid operation data are fused, the prediction average error rate is reduced; in an equipment fault early warning scene, through multi-dimensional correlation analysis of vibration signals, oil temperature data and environmental factors, transformer latent faults can be early warned in advance, and the fault identification accuracy is improved; meanwhile, a self-adaptive modeling engine and a closed-loop feedback mechanism enable the system to have a self-evolution capability: when the power grid topology is adjusted or the new energy grid-connected proportion is changed, the model does not need to be manually retrained, and self-adaptive adaptation can be completed in two scheduling cycles through dynamic feature weight adjustment and meta-learner parameter optimization, so that the analysis performance is maintained to be stable.

The invention relates to the technical field of data processing, in particular to an abnormal mode data processing system driven by power marketing big data, which comprises a distributed collaborative acquisition module for constructing a space-time alignment three-dimensional data stream, a multi-modal feature reconstruction module for separating periodic noise and quantizing environmental interference, and a data processing module for processing abnormal mode data. The resistance feature decoupling module generates a purification feature vector set and a noise confidence index through orthogonal projection, and the dynamic algorithm adaptation module dynamically schedules an isolated forest algorithm, a weighted distance measurement algorithm and a sparse self-encoding clustering algorithm according to the noise confidence index. The behavior chain verification module establishes a combined physical rule verification mechanism of an environment temperature threshold value, a load deviation degree and an equipment state, and the closed-loop strategy engine module adaptively adjusts a feature decoupling loss function weight according to a decision boundary offset, so that the accuracy and the environmental adaptability of real electricity consumption abnormity identification in a complex noise environment are effectively improved.