605 results about "Data normalisation" patented technology

The invention relates to a multi-data standard definition conflict resolution method based on a large model and a knowledge graph, and belongs to the field of public data governance and data standardization. The method comprises the following steps: extracting and preprocessing a multi-data standard definition; defining semantic representation and large model analysis: performing semantic analysis on the definition of each data item by using a large model, and generating a semantic embedding vector and a key feature; knowledge graph construction and entity alignment: constructing a knowledge graph containing all data items, and connecting data item nodes with similar semantics in different standards by adopting an entity alignment algorithm to form a candidate alignment relationship; conflict detection and type identification: aiming at the aligned data item definition, comparing attributes and values, identifying definition conflict points, and classifying and marking conflict types; and carrying out conflict resolution and unified definition generation by using a globally optimized conflict resolution algorithm. According to the method, the problems of data islands and semantic conflicts caused by inconsistent data standard definitions in the prior art are solved.

The invention belongs to the field of bioinformatics, and relates to a molecular property prediction method based on multi-modal gating and comparative learning, which comprises the technologies of comparative learning, graph neural network, cross-modal alignment, gating attention and the like. Firstly, data standardization and graph construction are carried out, and molecular fingerprint embedding is extracted; secondly, a heterogeneous dual-channel graph coding architecture is adopted, one path captures atom short-range interaction through an attention mechanism, the other path integrates a molecular global structure and long-range dependence, and complementary molecular representation is generated; then, a cross-modal attention mechanism is introduced, bidirectional association of graph and fingerprint features is achieved, and modal weights are adaptively and dynamically distributed through a gating fusion module; and finally, a comparison pre-training strategy is adopted, a molecular graph and fingerprints are utilized to construct a sample pair, and discriminative molecular representation is learned on unlabeled data. According to the method, the accuracy of molecular property prediction is remarkably improved, and an efficient and reliable calculation tool is provided for virtual drug screening and lead compound optimization.

The invention relates to the technical field of atmospheric environment monitoring, in particular to an atmospheric pollution source tracking and early warning system based on deep learning, which comprises a multi-source data acquisition layer for acquiring multi-dimensional data of atmospheric pollutant concentration, weather, geography and the like through multi-element equipment such as satellite remote sensing and ground sensors; the data preprocessing layer completes data cleaning by using a statistical method and a machine learning algorithm, and realizes heterogeneous data standardization processing through feature extraction, multi-source integration and space-time alignment, and the deep learning model layer realizes heterogeneous data standardization processing by means of a space-time convolutional neural network, a graph neural network and a long-short term memory network in combination with a space-time attention mechanism. The traceability analysis layer is combined with a back diffusion algorithm and a geographic information system to position a pollution source and generate a thermodynamic diagram. And the early warning decision-making layer sets threshold early warning through transfer learning of the adaptive area, and generates an optimal pollution control scheme based on reinforcement learning.

The invention discloses an enterprise data link management and value management method and system, and the method comprises the steps: carrying out the real-time capturing of multi-source heterogeneous data of all business systems in an enterprise through a distributed data collection engine, and recognizing the types of original data in different formats through a preset data source adapter; if structured data is detected, a relational database connector is adopted for extraction, and if the structured data is recognized as unstructured data, a document analysis module is started for content extraction, and an initial data set containing metadata tags is obtained; performing format conversion and field mapping on the initial data set according to a pre-established data standardization rule base, eliminating duplicate records and abnormal values through a data cleaning algorithm, performing automatic evaluation on a data quality grade by adopting a naive Bayes classifier, if a data quality score is lower than a preset threshold value, triggering a data recovery process, and if the data quality score is lower than the preset threshold value, performing data recovery. And standardized data meeting a unified standard is obtained. The normativity and value utilization efficiency of data management are effectively improved.

The invention provides a water conservancy industry electronic dark bidding document enterprise internal examination method and system based on artificial intelligence, and belongs to the field of water conservancy industry bidding. Performing automatic pre-auditing on the bidding file: performing compliance inspection and integrity inspection, identifying problems existing in the bidding file, and providing improvement suggestions to ensure that the problems conform to the basic requirements of electronic dark label review; carrying out data standardization and cleaning on the bidding file: carrying out semantic extension and ambiguity elimination, identifying images, tables and handwritten contents in the bidding file, identifying a main body structure of the water conservancy design drawing, extracting engineering quantity list data, and carrying out compliance verification; identifying an abnormal behavior in the bidding file through a machine learning model; and an internal examination decision tree is constructed according to preset key indexes and score weights of the water conservancy project, an interpretable artificial intelligence algorithm is utilized to carry out internal examination decision making on the bidding document, an internal examination score result is fed back, and specific score deduction reasons are explained. And the standardization and the accuracy of internal examination of the bidding document are improved.

The invention discloses a dynamic task distribution system based on multi-source data fusion, belongs to the technical field of intelligent task scheduling, and aims to solve the problems of response delay and execution failure caused by undifferentiated rule verification, fuzzy resource matching logic and inaccurate real-time state evaluation in a traditional task distribution system. According to the system, a task request is obtained through a task receiving module, multiple indexes are converted through a data standardization processing module, a rule matching engine carries out multi-rule verification and outputs a matching degree score, a real-time capability evaluation module calculates a current capability value of an executor, and a dynamic decision module dynamically adjusts double weights according to a task emergency degree and generates a comprehensive score. And time, resource and skill conflicts are eliminated through the conflict detection unit, and finally the optimal executor is selected by the task allocation unit to issue the task. The system is suitable for various fields requiring efficient and accurate task allocation, such as grid command center order distribution, emergency response, logistics distribution, maintenance service and the like.

The invention discloses an intelligent control method and system for an iron wire rust-proof treatment process, and relates to the technical field of intelligent iron wire rust prevention. The intelligent control method and system for the iron wire rust-proof treatment process comprise the steps that S1, a detection terminal is deployed to collect batch characteristics, process environment and treatment process data, standardized preprocessing is conducted, and a database is constructed; s2, performing comparative analysis on the personalized antirust process parameters based on a database, and dynamically adjusting parameter binding weights and fine tuning priorities; s3, analyzing the deviation degree of the technological parameter execution value and the reference value, evaluating the matching degree, and updating the adjustment amplitude and the correction strategy; and S4, integrating parameter comparison and deviation analysis results, combining the characteristic matching degree of the previous batch, and optimizing rapid identification and self-adaptive adjustment of antirust process parameters. The problems that in the existing iron wire manufacturing and anti-rust treatment process, the capacity of rapidly recognizing and adaptively regulating and controlling technological parameters based on batch characteristics is lacked, and personalized matching and quality consistency improvement of the anti-rust technology are difficult to achieve are solved.

The invention relates to a cargo transportation track real-time tracking method based on the Internet of Things, and the method comprises the steps: carrying out the node collection and multi-source fusion of sensor data (including GPS, RFID, timestamps and the like) of all links of logistics, and employing data standardization and time sequence verification, thereby achieving the consistency processing of different devices and node data. The method is characterized in that standardized trajectory data and breakpoint detection data are stored in a distributed manner by using a block chain non-tampering and multi-party consensus mechanism, third-party multi-source data and a fuzzy reasoning model are fused, and confidence completion is performed on trajectory breakpoints. The system can output a complete and traceable trajectory path, anomaly recognition and responsibility attribution result, and provides a visual and third-party notarization interface. According to the method, the authenticity, the integrity, the space-time consistency and the responsibility traceability of the logistics track data flow are remarkably improved, and the logistics full-link monitoring and risk management capabilities are enhanced.

The invention discloses a metabonomics data batch correction method based on multi-kernel learning, and belongs to the cross technical field of bioinformatics and analytical chemistry. According to the method, the multi-kernel learning technology is utilized, the advantages of different kernel functions are fused in a self-adaptive mode, a model conforming to data reality is constructed, complex drift characteristics of metabolite signals are accurately captured, and efficient and accurate normalization processing of metabonomics data is achieved. Compared with traditional data standardization methods such as SVR and LOESS, the method has the advantages that the performance is excellent in the aspect of reducing the metabolite peak intensity variability, and the data stability is remarkably improved. In the subsequent multivariate statistical analysis, the classification accuracy is greatly improved, the comparability among different batches of data is also remarkably enhanced, reliable data support can be provided for discovery of disease biomarkers, and the method plays a key role in large-scale metabonomics research.

The invention relates to the technical field of anti-terrorism early warning, in particular to an intelligent anti-terrorism early warning system based on image recognition and big data analysis, and the system comprises a multi-source data collection module which is used for collecting video streams, image data and environment parameters through a monitoring camera, a sensor and an Internet of Things device in a deployment region, executing target detection and desensitization operation at the edge computing node, and caching original data to a distributed message queue; and the data standardization processing module is connected with the message queue and is used for carrying out space-time alignment and semantic mapping on the multi-modal heterogeneous data. According to the invention, monitoring videos, sensor data, Internet of Things information and the like are preprocessed and desensitized at edge nodes, space-time alignment and semantic unification are completed through a data standardization processing module, and cross-modal feature fusion is realized through a multi-modal fusion analysis module, so that barriers among different types of data are broken through, and the accuracy of data fusion is improved. Scattered information forms an organic whole, and a comprehensive and consistent data basis is provided for abnormal behavior recognition.

The invention relates to the technical field of geothermal exploitation, and discloses a geothermal well group intelligent cooperative regulation and control method for geothermal exploitation, which comprises the following steps: collecting multi-source heterogeneous data in real time through multiple types of sensors deployed in a geothermal well group and a surrounding environment, data standardization, time sequence alignment and noise filtering are carried out through a uniform interface and a communication protocol, and a multi-dimensional monitoring database of the whole geothermal exploitation process is constructed; on the basis of multi-source heterogeneous data, historical mining data in a database is monitored in combination with a geologic structure of a geothermal reservoir, a seepage-heat conduction coupling mechanism and multiple dimensions. According to the invention, by deploying multiple types of sensors and constructing a multi-dimensional monitoring database, real-time acquisition and standardized processing of high-precision and multi-source heterogeneous data in the whole geothermal exploitation process are realized, a reliable data basis is provided for subsequent intelligent decision making, and the sensing ability of the system to complex geology and exploitation environments is significantly improved.

The invention relates to an intelligent continuous rigid frame bridge construction period deformation prediction system. The system comprises a construction data acquisition module, a data primary processing module, a feature extraction model construction module, a mode special model construction module and a deformation prediction module. According to the invention, original data is obtained through data acquisition; a data primary processing method of data standardization, weighted time sequence alignment, effect decoupling and data set segmentation is adopted; a multi-branch deep learning model is adopted as a feature extraction model, the time dynamics, the spatial topological relation and the physical mechanics priori of bridge structure response are integrated, and the completeness and the discrimination ability of feature expression are remarkably improved; a progressive strategy of firstly extracting and clustering features and then grouping and independently modeling is adopted, so that not only is the specificity of different construction stages fully considered, but also the prediction precision is improved through targeted model optimization, and the problem of mode diversity in a complex construction system is solved.

The invention relates to the technical field of liquid caustic soda concentration regulation and control, and discloses a liquid caustic soda concentration monitoring and automatic regulating system based on Internet of Things and data fusion. A liquid caustic soda concentration data acquisition module of the system is connected with a plurality of sensors through the Internet of Things to acquire spatio-temporal information such as liquid caustic soda concentration, temperature, flow velocity and the like; the edge node operation and maintenance analysis module is used for monitoring operation and maintenance information such as memory, bandwidth and CPU utilization rate of the edge computing node; the data fusion preprocessing module performs standardization processing on the sensor data to generate a data matrix; the liquid caustic soda concentration anomaly detection module is used for extracting fusion features based on the data matrix and identifying abnormal nodes; the concentration adjustment optimization module is used for generating an optimization adjustment parameter set according to the abnormal nodes; the automatic adjusting control module is used for adjusting the valve opening and the pump speed according to the parameter set; and the distributed storage management module is used for storing sensor data and operation and maintenance information. The system realizes comprehensive monitoring and accurate adjustment of the concentration of the liquid caustic soda, and improves the operation stability and reliability of the system.

The invention relates to the technical field of intelligent regulation and control, and discloses a data-driven workshop production equipment flow intelligent regulation and control method. Comprising the steps of S1, equipment state data acquisition in a data acquisition stage, S2, data cleaning abnormal value processing in a data preprocessing stage, S3, equipment health degree analysis model in a data analysis and modeling stage, S4, equipment scheduling decision in an intelligent regulation and control decision stage, and S5, regulation and control effect feedback and effect evaluation index production efficiency in an iteration stage. According to the data-driven workshop production equipment flow intelligent regulation and control method, the data acquisition and processing efficiency is improved, the integrity of equipment state data is improved to 98% through multi-dimensional sensor deployment (vibration 100Hz sampling and temperature 30s / time), the time consumed for automatic correction of an abnormal value is shortened from 30min to 1min, and the efficiency of automatic correction of the abnormal value is improved. And after data standardization, the multi-dimensional fusion analysis efficiency is improved by 4 times, and a foundation is laid for accurate regulation and control.

The invention relates to the technical field of computers, and discloses a livelihood appeal trend pre-judgment method and system based on quantitative analysis, and the method comprises the steps: obtaining multi-source heterogeneous livelihood appeal data, carrying out the standardization processing, generating an integrated data set, extracting trend features and fluctuation features, and determining an evolution mode of livelihood appeals. Constructing a saturation model based on the dynamic variation amplitude, identifying a distribution interval exceeding a risk judgment threshold, and generating a critical point trigger signal when the dynamic variation amplitude exceeds a risk fluctuation judgment threshold; calculating a correlation strength index variable quantity, when the correlation strength index variable quantity exceeds a correlation deviation judgment threshold value, triggering a parameter optimization mechanism of a saturation model, generating prediction distribution of a time window and a risk level, and updating extraction parameters of volatility characteristics based on the prediction distribution and historical time sequence data; and generating a final livelihood appeal trend prediction report according to the updated extraction parameters. According to the method, accurate resource allocation driven by data can be realized, and the immediate response capability of emergencies is enhanced.

System and methods are provided for achieving data standardization and normalization through an Agnostic Data Format (ADF) architecture. ADFs systems and processes provide a transformative bridge, enabling disparate data sources to converge into a unified and standardized format within the Real-Time Data Mesh (RTDM) framework. This dynamic process utilizes Artificial Intelligence (AI) and Machine Learning (ML) algorithms to interpret and align diverse data attributes. The ADF management system, integrated into a dynamic event-driven architecture, allows vendors to interact with RTDM by translating and standardizing their data. The synchronized data integrates canonically, incorporating real-time updates and collaborative decision-making across the distribution platform. This innovative approach enhances operational efficiency, enables data-driven decision-making, and provides users improved ability to use data within the distribution ecosystem.

A computing system is disclosed for generating fulfillment-ready coordination sessions based on tokenized item data and user-submitted participation parameters. The system ingests structured, semi-structured, or unstructured item data from merchant sources and applies schema-aligned transformation logic to normalize the data into structured item representations. The normalized records are tokenized into machine-readable item tokens that encode fulfillment constraints and canonical attributes. The system receives user item selections and associated participation parameters, encodes the item tokens and participation data into structured vector embeddings, and applies compatibility scoring logic using vector comparison and rule-based threshold evaluation. Compatibility scores are evaluated against session eligibility constraints derived from the item tokens. When eligibility conditions are met, the system generates a coordination session payload comprising match outcomes, proportional pricing, and fulfillment metadata, and issues orchestration instructions to external fulfillment systems for group-based delivery or preparation execution.

The invention belongs to the technical field of data visualization, and particularly relates to a dynamic visualization generation method, system and device based on user behaviors and context awareness and a medium, and the method comprises the steps: generating a structured operation sequence after standardizing original input data; performing time sequence modeling on the operation sequence to generate a user behavior semantic vector, and generating a joint feature vector by adopting an attention mechanism; pre-loading an input data set, and generating a candidate view set in combination with the user intention preference in the joint feature vector; calculating view scores through a layout optimization function, and screening an optimal view scheme with the highest score; dynamically simplifying or enhancing the chart component according to the equipment performance and context parameters in the joint feature vector; calling a rendering engine to output a view, and monitoring a user interaction event; and updating the strategy network through a PPO algorithm, and optimizing a subsequent view generation path. The problem of unsmooth interaction caused by a static template is avoided, and the user experience is remarkably improved.

Techniques for generating recommendations of model domain entities from a model domain for mapping to comparison domain entities from a comparison domain are provided. A model domain includes a code set of standard references codes. A comparison domain includes a code set of reference codes that include non-standard reference codes. The reference codes represent clinical and non-clinical health concepts and are represented by one or more attributes. The system generates vector embeddings for entities of the comparison and model domains by applying a vector embedding function to the attributes fields of the comparison and model domain entities. The system compares the vector embeddings of the comparison domain entity to the vector embeddings of the model domain entity to compute similarity metrics for the entity pairs. The entity pairs are presented to a user based on the similarity metrics. A selected model domain entity is mapped to the comparison domain entity.

The invention relates to the technical field of equipment health management, and provides a new energy station equipment state evaluation and early warning method. Comprising the steps of S1, collecting operation, environment and inspection image data in real time through multi-source sensing equipment, and generating a data set after standardization processing; s2, selecting an AI large model supporting multi-modal input, injecting a fault knowledge graph and an industrial standard, and generating an adaptive model through general power data pre-training and station exclusive data fine tuning; s3, time domain / frequency domain features and image damage information are extracted, and a unified health index is constructed through dynamic weighting; s4, predicting an HI value in the next 24 hours based on LSTM, dynamically adjusting a threshold value in combination with a working condition, and executing early warning in three stages; and S5, updating the model every quarter, verifying the index requirements, and analyzing and optimizing the rule through misinformation. According to the invention, intelligent evaluation and accurate early warning of multi-source data fusion are realized, the operation and maintenance efficiency is improved, non-planned shutdown is reduced by more than or equal to 100 hours per year, and unattended transformation of a new energy station is promoted.

The invention discloses an industrial production machinery fault early warning system based on Internet of Things sensing, and relates to the technical field of industrial equipment fault early warning, and the system comprises a working condition sensing module which collects an operation state signal of industrial production machinery, carries out the time synchronization and data standardization processing of the operation state signal, and generates a structured operation state data set; the state index extraction module is used for calculating an operation state characteristic index based on the structured operation state data set and generating a multi-source operation condition change characteristic vector according to a unified timestamp; and the trend modeling module is used for averaging the multi-source operation condition change feature vectors in the sliding time window, calculating the state mean value change rate between adjacent windows, constructing an operation stability scoring function and generating an operation stability scoring value. According to the method, by constructing the operation stability scoring function, quantitative expression of the fluctuation degree of the operation state of the industrial production machine is achieved, and continuity and sensitivity of operation state evaluation are improved.

The invention discloses a heat pump system state anomaly detection method based on a depth auto-encoder, and the method comprises the steps: collecting compressor data, and carrying out the standardization processing to construct a multi-dimensional time sequence; a spatial-temporal feature extraction depth auto-encoder with a thermodynamic coupling attention mechanism is constructed, coupling attention is utilized to calculate physical parameter coupling strength weights to extract spatial features, time features are extracted in combination with a long and short-term memory network, and normal state data are reconstructed and predicted through a decoder after fusion; residual vectors of predicted normal state data and original data are calculated, and a weighted mahalanobis distance is calculated by using a covariance matrix to generate an abnormal score; and constructing a sliding probability distribution model based on historical normal data, calculating a current score occurrence probability, and comparing the current score occurrence probability with a preset threshold to output an anomaly detection result. According to the method, a multi-physical parameter space coupling relationship and a time evolution rule are captured through a thermodynamic coupling attention mechanism, and the anomaly detection accuracy and robustness are improved.

The invention discloses a method and a device for analyzing and processing dynamic data of self-adaptive and active adaptive sensing signals. According to the method, through feature recognition, protocol dynamic matching and data standardization conversion, the problem that multi-source heterogeneous sensor signals cannot be processed in a centralized mode due to format difference is solved. The device comprises a signal interface module, a feature recognition module, a protocol adaptation module and the like, and supports multi-protocol communication and machine learning driven rule generation. The compatibility and the processing efficiency of the data acquisition system are remarkably improved, and the system is suitable for the fields of industrial automation and the Internet of Things.

The invention relates to DICOM image processing, in particular to a DICOM image preprocessing and quality control system based on Spark, and the system comprises a data collection module which collects a DICOM medical image from a data source, and automatically recognizes and extracts a key metadata field in the DICOM medical image; the index construction module is used for constructing a comprehensive and accurate index system according to key metadata fields of the DICOM medical images; the data standardization module is used for carrying out standardization processing on key metadata fields of the DICOM medical images, supporting version control and audit tracking on the key metadata fields and carrying out optimization processing on the DICOM medical images; the scoring module is used for carrying out objective quality evaluation on the DICOM medical image based on a multi-dimensional image quality evaluation model and calculating a corresponding comprehensive quality score; according to the invention, the defect that the DICOM medical images from different equipment manufacturers are difficult to efficiently preprocess can be overcome.

The invention discloses a digital twin-driven foundation settlement multi-physics field coupling simulation platform and a use method thereof, relates to the technical field of foundation settlement analysis, and solves the technical problem of settlement prediction deviation accumulation caused by incapability of synchronously updating seepage field and stress field coupling boundary conditions. According to the invention, the twinborn construction unit and the multi-physics coupling solving unit are installed, so that the rapid construction of the digital twinborn of the stratified geologic structure and the multi-physics coupling effect calculation of a stress field, a seepage field and a temperature field of a soil body are realized, and the problem of insufficient precision of traditional single-field simulation is solved; by installing a noise filtering unit and a data standardization unit, elimination of high-frequency interference components of sensor signals and time-space alignment of multi-source data are achieved, the problem that noise interference of geological exploration data is incompatible with heterogeneous formats is solved, and the accuracy and accuracy of foundation settlement analysis are improved. And the reliability of input data and the stability of a simulation result are improved.

The invention relates to the field of water environment pollution detection and analysis, in particular to a water environment pollution detection and analysis system and method based on the Internet of Things, and solves the problems of sampling redundancy, missing detection, high-dimensional data over-fitting, difficulty in traceability and early warning lag in traditional detection. The system comprises a monitoring acquisition module, a water quality anomaly detection module, a pollution tracing module, a pollution early warning module and a database. The monitoring acquisition module adopts chaotic adaptive sampling to adjust sensor frequency, and entropy optimization water quality data is obtained by combining permutation entropy and collaborative filtering denoising; the water quality anomaly detection comprises the following steps: standardizing data into high-dimensional point clouds, calculating a Betti number and a non-equilibrium state entropy, and fusing to generate a comprehensive pollution topological entropy index; according to pollution traceability, a dynamic graph and a diffusion kernel matrix are constructed by using GNN, and the optimal source intensity is solved through quantum annealing; the range is predicted through a diffusion equation for early warning, and information is integrated to generate a report to be pushed to users. The method corresponds to a module flow and provides support for pollution prevention and control.

The invention relates to a construction method of a coefficient prediction model, a coefficient prediction method and a storage medium, and the construction method comprises the steps: carrying out the modeling of a bridge prestressed beam through finite element numerical software, simulating a tensioning process, constructing a bridge parameter coefficient array, dividing the bridge parameter coefficient array into a training data set and a verification data set, performing data standardization and tensor data conversion, and constructing a data loader; an AND-based full-connection multi-layer multi-task neural network is constructed, and a standardizing device, a forward propagation function, a loss function, a learning rate scheduler and an optimizer are arranged; and carrying out model training, packaging a prediction function, and integrating a standardizing device and the trained prediction model. The prediction method comprises the step of predicting the friction resistance loss coefficient and the pipeline deviation coefficient according to the prediction model. According to the method and the device, coefficient prediction can be quickly, efficiently and accurately realized by only needing several on-site easy-to-measure parameters.

The invention relates to the technical field of financial data analysis and artificial intelligence, in particular to a multi-source heterogeneous financial data fusion and intelligent analysis system which comprises a data standardization processing module, a time sequence event fusion module, a knowledge graph construction module, a relation reasoning module and a self-adaptive anomaly detection module. The data standardization processing module is used for converting heterogeneous financial data from different sources into unified tensor representation; the time sequence event fusion module adopts a double-clue cooperation mechanism to establish a mapping relation between continuous time sequence data and discrete events; the knowledge graph construction module extracts financial entities and relationships thereof, and constructs a multi-level knowledge graph; the relation reasoning module performs deep reasoning based on a graph attention mechanism; and the adaptive anomaly detection module dynamically adjusts the detection threshold according to the market environment. According to the system, implicit association in heterogeneous financial data can be deeply mined, market anomalies are recognized in advance, and comprehensive support is provided for financial decision making.

The invention provides a dam safety monitoring system lightweight construction method and device, and the method comprises the steps: deploying a protocol conversion gateway, carrying out the protocol analysis and data standardization processing of an existing heterogeneous sensor, generating data in a unified format, and supporting the network disconnection caching and automatic supplementary transmission; deploying a data processing module on a local server or an industrial personal computer based on an edge computing architecture, performing feature extraction and multi-scale fusion analysis on acquired data, and performing data compression by adopting an improved revolving door algorithm; constructing a lightweight anomaly detection model, training by using historical data to generate a normal mode template library, calculating a dynamic time warping distance between new data and a template in real time, and triggering early warning when the distance of a plurality of continuous cycles exceeds a preset threshold value; the sampling frequency of the sensor is dynamically adjusted according to the real-time data analysis result, key parameters are collected in a high-frequency mode, non-key parameters are collected in a low-frequency or intermittent mode according to the change rate prediction result, and therefore the system resource use efficiency is optimized.

The embodiment of the invention provides a knowledge graph fusion method and system based on a large model, and the method comprises the steps: carrying out the data standardization, entity feature enhancement and relation semantic annotation of heterogeneous knowledge graphs from different sources; through semantic similarity calculation, context reasoning and alignment confidence evaluation, a multi-stage and multi-mode entity alignment mechanism is constructed in combination with a large language model, and cross-source entity matching is performed on entities in heterogeneous knowledge maps of different sources; based on conflict detection, dynamic weight distribution and a conflict resolution strategy, generating a data fusion result, and unifying multi-source data; and generating a high-quality unified knowledge graph through missing relationship prediction, logic consistency verification and an incremental updating mechanism. According to the knowledge graph fusion method and device, full-process automation, precision and dynamics of knowledge graph fusion are realized, the problems of high manual dependence, weak semantic processing capability, poor cross-domain adaptability and the like in the prior art are effectively solved, and the efficiency and quality of knowledge graph fusion are remarkably improved.