240 results about "Pattern detection" patented technology

The invention discloses an intelligent low-code development method and system based on deep learning model optimization, and relates to the technical field of deep learning. A multi-dimensional domain knowledge graph is constructed, a three-dimensional space-time fusion training sample set is constructed based on the domain knowledge graph, and cross-modal feature alignment is performed on the training sample set, so that the multi-dimensional domain knowledge graph is constructed; the method comprises the following steps: generating an executable logic flow template, encoding the executable logic flow template into a Markov decision process, and performing joint strategy optimization on an optimization target of logic flow by integrating a feature importance index generated by a gradient back propagation path and a multi-target reinforcement learning framework of a Pareto leading edge analysis module. Extracting a strategy parameterization sequence after joint strategy optimization, injecting the strategy parameterization sequence into a dynamic verification sandbox environment, and performing abnormal mode detection and feedback type parameter distillation iteration on an execution track through an online variational auto-encoder to complete dynamic adjustment of the strategy; and the elasticity, the stability and the expandability of the low-code platform are improved.

The invention belongs to the technical field of fault prediction and management, and discloses a production line abnormity real-time diagnosis system based on industrial Internet of Things, which comprises a data acquisition and processing module, a distributed sensor network covering key equipment of a production line is constructed, multi-dimensional production line data is acquired, and the data acquisition and processing module is used for acquiring data of the production line; a self-adaptive sampling technology is adopted to dynamically adjust the multi-dimensional production line data acquisition frequency according to the equipment state, and preliminary multi-dimensional production line data processing is executed at the edge end; and the multi-scale time sequence management module adopts a hot, warm and cold three-level hierarchical storage architecture, compulsively switches sampling frequencies of key equipment parameters in combination with a multi-level safety threshold mechanism, performs resource allocation through a hierarchical calculation architecture, and introduces an abnormal sensitive new mode detection and double-track system template updating mechanism to identify a novel abnormal mode. The state change of the equipment is continuously monitored; it is ensured that resources can be efficiently scheduled in normal, early warning and abnormal states, and the anti-risk capacity of the system is improved.

A federated distributed computational system enables secure drug discovery and resistance tracking through hybrid simulation capabilities. The system implements a hybrid simulation orchestrator that coordinates molecular dynamics simulations with machine learning models for drug discovery analysis, while maintaining secure cross-institutional data exchange. The architecture coordinates multi-scale spatiotemporal synchronization across computational nodes, with each node containing local processing capabilities for molecular dynamics simulation and resistance pattern detection. Through a distributed graph architecture, the system enables real-world clinical data integration, resistance evolution tracking, and multi-scale tensor-based analysis with adaptive dimensionality control. The system implements real-time drug response prediction through multi-modal data analysis, enabling pharmaceutical companies and research institutions to collaborate on complex drug discovery projects while maintaining strict data privacy controls.

The invention relates to the technical field of intelligent risk analysis, in particular to an intelligent risk analysis system of a financial system. The system comprises a data flow analysis module, a relational graph construction module, an abnormal mode detection module, a security boundary monitoring module, a staged strategy planning module, a scene simulation evaluation module, a decision support module and a comprehensive risk management module. A graph database and a graph convolutional network are utilized to deeply analyze a financial entity relationship, reveal a risk association network, improve abnormal behavior recognition through a K-mean value and an isolated forest algorithm, enhance security boundary monitoring through a random forest algorithm, enable risk threshold adjustment to be more dynamic, combine a decision tree with a genetic algorithm, optimize a risk management strategy, and improve risk management efficiency. The system dynamics and proxy model technology in scene simulation evaluation strengthens risk prediction and increases foresight, principal component analysis and risk matrix evaluation are applied in a comprehensive risk management module, a quantitative analysis tool is provided, and more systematic and comprehensive risk management is realized.

A system (100) for automating financial consolidation and reporting in a cloud-based ERP environment, comprising: a data aggregation and integration module configured to collect and integrate financial data from multiple sources, including ERP, accounting software, and third-party applications; an AI-driven cross-company reconciliation module configured to use machine learning algorithms to identify and eliminate cross-company transactions, detect duplicate entries, missing records, and transaction discrepancies; a currency conversion and standardization module configured to enable real-time currency conversions and ensure compliance with international accounting standards such as IFRS and GAAP; a compliance and audit module configured to monitor compliance with financial regulations and tax laws, automate audit trails, and generate compliance reports; a financial analysis and anomaly detection module configured to analyze financial patterns, detect anomalies, and prevent fraudulent activities using artificial intelligence; a report creation and customization module configured to automate the creation of financial reports, balance sheets, and cash flow reports with customizable templates; a scalability and cloud deployment module configured to deploy the system (100) in a cloud-based ERP environment and enable real-time access to financial reports and dashboards; an automation and workflow optimization module configured to minimize manual intervention by automating data reconciliation, reporting, and compliance checks; a security and access control module configured to implement role-based access control, encryption, and authentication mechanisms to ensure data security; and an integration and API management module configured to enable seamless connectivity with external financial applications and enterprises via APIs.

Computer systems and processes are described herein for using code-derived message patterns to determine whether or not to trigger an anomaly notification. A system manager trains a pattern matching model and an anomaly detection model based on historical log messages, feedback about historical log messages, and message-generating portions of source code that generated the log messages. The message-generating portions of code may be processed to determine code-derived message patterns for a type of log messages. A log processor receives a message and determines the message is of the type for which code-derived message patterns are available. The message is matched to one of the available code-derived message patterns, and the log processor determines whether or not to trigger an anomaly notification based at least in part on which code-derived message pattern is matched to the message.

The invention relates to the technical field of user experience optimization, and discloses a concentration improvement method and system based on keyboard lighting effect guidance, and the method comprises the steps: carrying out the information preprocessing of manual use information, obtaining the preprocessing information, and recognizing a manual behavior mode of a user through the preprocessing information; detecting whether a computer scene connected with the keyboard is a new scene or not; when the computer scene is a new scene, inquiring the current use habit of the user about the lighting effect of the keyboard, establishing a basic keyboard lighting effect of the computer scene by utilizing a manual behavior mode, and guiding the lighting effect of the keyboard on the basis of the basic keyboard lighting effect by utilizing the current use habit; when the computer scene is not the new scene, keyboard lighting effect guiding is carried out on the user in a manual behavior mode, a second lighting effect guiding result is obtained, concentration improvement is carried out on the user through the second lighting effect guiding result, and a second concentration improvement result is obtained. The method and the device can meet individual requirements of users.

The invention relates to the technical field of image recognition technologies, and discloses an intelligent turnover cabinet safety management method and system based on an image recognition technology. The method comprises the following steps: acquiring a user interaction image sequence through an intelligent turnover cabinet, and carrying out illumination standardization and target area cutting processing to obtain a standardized image sequence; performing user behavior and environmental factor separation processing through a two-stage Transform encoder to obtain user behavior feature data; performing multi-scale time feature extraction through a time sequence analysis network to obtain user operation behavior features; and constructing a turnover cabinet use mode map, and generating a cabinet body use prediction result and an abnormal mode detection result. The intelligent turnover cabinet can accurately recognize abnormal behaviors deviating from a normal mode, visual safety prompts can be provided through different colors and flicker modes of the storage position indicator lamps according to abnormal mode detection results, meanwhile, the results are reported to a management system in real time through the RESTful interface, and a multi-level safety early warning mechanism is achieved.

The invention relates to the technical field of data analysis, in particular to a hazardous chemical substance transportation risk prediction method and system based on the Internet of Things, and the method comprises the steps: obtaining hazardous chemical substance type information of each cargo unit in a cargo compartment of a transportation vehicle, recognizing a coupling risk pair, and extracting a taboo reaction type and a coupling triggering condition parameter set; configuring a gas cross detection mode according to the partition position information of the related goods by the coupling risk, and detecting the characteristic gas of the hazardous chemical substance in the adjacent area; dynamically adjusting a sampling frequency and an alarm threshold value of a related partition sensor in combination with a threshold value parameter; coupling risk precursor triggering is judged, dynamic characteristics of a taboo reaction corresponding to the coupling risk precursor triggering are extracted, a time window needed by the taboo reaction to evolve from the current state to the danger degree is estimated according to the relation between the temperature and the reaction rate, and the time window serves as a safety intervention time limit to be output; and when the safety intervention time limit is lower than a preset threshold value, retrieving a corresponding blocking measure according to the coupling risk type, and issuing a control instruction to execute a blocking operation.

Systems and methods are provided for fault detection, diagnosis, and recovery in an electromechanical actuator. The system can include a data processing system having one or more processors and a memory. The data processing system can receive first electrical data from a first sensor positioned at a first terminal of a power source, in addition to second electrical data from a second sensor positioned at a second terminal of the power source. The data processing system can determine a first average value from the first electrical data and a second average from the second electrical data. The data processing system can determine a difference between the first average value and the second average value. The data processing system can detect a fault impedance according to a pattern of the difference over a measured time interval. The data processing system can provide an indication of the fault impedance.

A system for a compliance-based data ecosystem that includes: a) a compliance management engine configured to enforce compliance rules and dynamically update policies based on industry regulations; b) a data governance module to classify, track and manage data lineage while enforcing retention and access policies; (c) a secure data processing unit that encrypts, anonymises and processes sensitive data while maintaining data protection and security; (d) an access control mechanism that implements role-based access control (RBAC), multi-factor authentication (MFA), and dynamic access assessments; (e) an audit and monitoring module that continuously and tamper-proof logs data transactions, access attempts and compliance-related actions; f) an AI-driven analytics engine that analyses data access patterns, detects anomalies and predicts potential compliance risks; and g) a blockchain-based validation system configured to record compliance actions and enforce compliance with smart contract-based policies, h) the system ensures secure, automated and compliant data management across multiple entities while complying with regulatory requirements.

The invention discloses an elevator steel belt damage detection and quantitative analysis system based on eddy current and magnetic flux leakage dual-mode detection, and aims to solve the problems of single-mode information loss and serious industrial field strong noise interference in the existing steel belt detection. The system synchronously integrates an eddy current sensor, a magnetic flux leakage sensor and an encoder through a multi-probe array adapter; and multi-dimensional damage physical information in the steel strip is obtained. An improved wavelet packet transform-empirical mode decomposition (WPT-EMD) collaborative noise reduction algorithm is adopted, and in combination with a sub-band energy entropy and a self-attention mechanism, non-stationary mechanical noise is effectively filtered out. A multi-rule feature extraction engine is used for extracting smooth residual errors, derivative mutation and other features, a support vector machine (DE-SVM) model introducing physical priori knowledge weights is constructed, and the small sample recognition problem is solved in combination with a virtual sample generation technology. The method can realize high-precision positioning and quantitative evaluation of steel strip damage under complex working conditions, and has the characteristics of strong anti-interference capability, high identification accuracy and good generalization performance.

Systems and methods detect and prevent vishing attacks through an integrated framework combining SIP header customization, STIR / SHAKEN frameworks, AI / ML analysis, and real-time speech analysis using the Viterbi algorithm. The system begins with call initiation, embedding authentication information in the SIP header. The SIP data is transmitted and verified using STIR / SHAKEN frameworks, ensuring the authenticity of the caller's identity. Verified data is cross-referenced with third-party databases and analyzed by an AI / ML engine to detect anomalies. If potential fraud is detected, the call is blocked, and the customer is notified. Calls that pass initial checks are further analyzed using the Viterbi algorithm, which converts speech to text and identifies suspicious patterns. An anomaly pattern detector processes the converted text to detect vishing indicators, terminating the call if a match is found. This multi-layered approach ensures robust protection against vishing, enhancing the security and reliability of voice communications while safeguarding users from fraud.

A system and method for detecting anomalies in a data stream is described. The system receives the data stream that comprises values of metrics derived from observations of operation of a computing entity over a time window. A model comprising variances of the data over the time window is formed. The model identifies operating thresholds for each metric based on the variances of the data for each metric in the data stream. The system computes a steady state distance matrix of the data stream. The system determines that the steady state distance matrix exceeds a steady state threshold. In response to determining that the steady state distance matrix exceeds the steady state threshold, the system computes a pattern distance matrix based on the steady state distance matrix. The anomaly in the data stream is detected based on the pattern distance matrix. The system generates an alert indicating the anomaly.

The application discloses and realizes a dual-mode multi-load loop arc fault detection system, and aims at the problems of insufficient precision of existing real-time arc fault detection devices and high-load continuous operation of equipment, etc., divides the fault arc into two kinds of starting arc and process arc, and uses different modes of detection methods according to different conditions of starting fault and process fault, adopts a characteristic value partition detection method in the process mode, and makes the method tend to be simple under the condition of ensuring accuracy and real-time performance. The method takes an stm32H7 as a core microprocessor, is matched with a conditioning circuit, a power supply circuit, a data acquisition circuit and a wireless communication circuit to form a dual-mode fault diagnosis system. The application has the characteristics of high monitoring precision and high speed, and has strong popularization value and use value.

The invention discloses engraved line detection equipment and a detection method, and relates to the technical field of detection equipment. The engraved line detection equipment is used for detecting engraved lines on the surface of a to-be-detected piece and comprises a detection table, a mobile platform, a three-dimensional laser scanner, an auxiliary positioning device and a host. The detection table is used for placing a to-be-detected piece; the mobile platform is mounted on the detection table and is used for driving the three-dimensional laser scanner and the auxiliary positioning device to move; the three-dimensional laser scanner is used for scanning the engraved lines and forming three-dimensional contour data; the auxiliary positioning device is used for acquiring position information of the to-be-tested piece; the mobile platform, the three-dimensional laser scanner, the driving motor and the laser sensor are all in communication connection with the host, and the host can process position information and three-dimensional contour data. The to-be-detected piece is calibrated through the auxiliary positioning device, and the three-dimensional contour information of the engraved lines is automatically acquired by using the three-dimensional laser scanner, so that the detection efficiency is improved, and the defect of inaccurate manual detection value is overcome.

The invention provides a cache management method and system of a work meeting welfare platform in a high-concurrency scene, and belongs to the field of electric digital data processing.The cache management method comprises the steps that work meeting member request metadata is collected, burst mode detection is carried out based on a spectral clustering algorithm, potential high-demand welfare is marked, and dynamic fragmentation is carried out on inventory Key of the potential high-demand welfare; constructing a three-level collaborative cache based on the inventory Key after dynamic fragmentation, and realizing distributed inventory deduction through cooperation of a lease lock and atomic operation; establishing a multi-level asynchronous buffer queue including an edge queue, a region queue and a global queue, performing aggregation batch processing on the inventory change request, and combining incremental synchronization and block chain operation Hash uplink to guarantee final consistency; routing and fusing threshold values are dynamically adjusted based on potential high-demand welfare, different routes are allocated to high-concurrency requests, millisecond-level flow switching is achieved when regional nodes fail, and the stability of worker welfare issuing activities and the member right priority are guaranteed.

The invention discloses an intelligent diagnosis method and system for circuit breaker fault identification, and relates to the related technical field of circuit breaker fault diagnosis, and the method comprises the steps: synchronously collecting the multi-source heterogeneous operation data of a target circuit breaker through a high-precision sensor network; a multi-scale spatio-temporal feature extraction network is used for processing, and circuit breaker joint features are obtained; the combined characteristics of the circuit breaker are input into the bidirectional LSTM-GAN hybrid model; based on the fault sample, driving the target circuit breaker digital twin to obtain target circuit breaker fault data; and executing edge-cloud collaborative diagnosis of the fault data of the target circuit breaker, and generating a three-dimensional diagnosis report of the circuit breaker. The technical problems of low fault diagnosis efficiency and insufficient diagnosis result accuracy of the circuit breaker caused by single circuit breaker fault diagnosis means and low detection sensitivity to complex fault modes in the prior art are solved, and the technical effects of improving the accuracy of the diagnosis result and the fault diagnosis efficiency of the circuit breaker are achieved.

A system, method, and device for predicting a risk of wildfire are provided. The system includes a satellite imaging device for collecting data covering a target area and a processing server including an indices module for processing the data to generate key vegetation indices, a map generation module configured to generate weather and static maps, an analysis module configured to analyze historical wildfire data to identify past fire locations in the target area, an integration module configured to integrate the received, generated, and analyzed data to obtain a comprehensive dataset for the target area, and a risk prediction module configured to analyze the comprehensive dataset using a risk prediction model trained to predict the risk of wildfire for the targeted area, the risk prediction model including a machine-learning-based pattern detection model for receiving the comprehensive dataset as an input and generate prediction data describing a predicted risk as an output.

A system and method are described for detecting irregular network behavior, service quality or traffic patterns, subscriber behavior or deviation from typical operation of a 3GPP mobile data network. Convolutional techniques are applied to transform time series data of network events, network performance metrics, and traffic metrics into token sequences to enable pattern detection using a generative pre-trained transformer (GPT) Language Model (LM).

The invention relates to a power transmission and transformation equipment fault detection method and equipment based on photoelectric sensing, and relates to the related technical field of power transmission and transformation equipment detection, and the method comprises the steps: carrying out the topological correlation analysis based on the structure distribution data and attribute characteristic data of a power transmission and transformation equipment set; key node identification is carried out on the power transmission and transformation equipment topology network, and photoelectric sensing modules are deployed in sequence; building multiple equipment fault mode detection channels, carrying out fault switching detection based on an MOSFET switching circuit, and collecting N equipment mode detection feature sets at the same time; and performing global fault analysis on the N equipment mode detection feature sets, and outputting a power transmission and transformation equipment fault detection result. The technical problem that in the prior art, fault detection means are isolated, the real-time performance is poor, coverage is not comprehensive, and consequently a fault source is difficult to locate accurately is solved, and the technical effects that intelligent fault diagnosis of power transmission and transformation equipment relevance is achieved, and the fault detection efficiency and the fault locating precision are improved are achieved.

The invention relates to the technical field of automobiles, in particular to a vehicle child mode detection method, device and equipment, a storage medium and a computer program product. The method comprises the following steps: performing face detection on a back row passenger image based on a preset face detection deep learning model to obtain passenger face information and confidence information; determining a face posture angle according to face key point data in the passenger face information; judging whether a face corresponding to the passenger face information is a front face or not based on the face posture angle and the confidence degree information; if yes, age estimation is carried out on the front face image based on a preset age model, and the preset age model is constructed based on KL offline loss and average difference loss; if the age estimation results are all smaller than the preset child age threshold value, the vehicle is controlled to start the child mode, and the child riding safety is improved.

The invention relates to a multi-source partial discharge fault spectrogram detection and separation method and device and a medium. The method comprises the steps that a multi-source partial discharge fault spectrogram is collected and preprocessed; inputting the preprocessed multi-source partial discharge fault spectrogram into a pre-trained detection separation model to obtain a separated partial discharge fault spectrogram; wherein the detection separation model is pre-trained based on a multi-source partial discharge fault spectrogram data set, the multi-source partial discharge fault spectrogram data set is subjected to sample expansion through a Wasserstein generative adversarial network with gradient penalty, and the detection separation model uses a VoVNet network as a backbone feature extraction network. By generating a multi-scale feature map corresponding to different sizes of fault features in multi-source partial discharge, the detection and separation model effectively detects different types and sizes of fault features in multi-source partial discharge, and a multi-source partial discharge fault spectrogram is separated. Compared with the prior art, the characterization and detection capability of the model on the partial discharge characteristics of the small target is remarkably enhanced.

A real-time anti-pattern detection system integrating a framework into an online learning platform providing communication between the online learning platform and the real-time anti-pattern detection system. The real-time anti-pattern detection system displays the detected anti-patterns via a user interface on the online learning platform in real-time, thereby providing real-time feedback to the user for enhanced engagement and learning. The system is configured to collect session data using a session parser. The session data is parsed to extract one or more events relevant for identification of anti-patterns. The extracted events are shared with an anti-pattern detector. The anti-pattern detector is configured to compare the exact one or more events with a plurality of pre-stored rules The anti-pattern detector compares each event against the pre-stored rules. Upon matching, the anti-pattern detector generates an alert corresponding to the detected anti-patterns, which is displayed to the user via an online learning platform user interface.

Some embodiments relate to an overlapping electric loads operating mode detection method. The method includes measuring an aggregated power signal of an electrical outlet and determining an operating mode for the aggregated power signal. The operating mode is determined to be one of an active mode, a lower power mode, or switched off. On determining the operating mode is an active mode, the method includes determining a load category for the aggregated power signal; selecting a corresponding load category signature power signal from a load category database; evaluating spectral coherence between the aggregated power signal and the load category signature power signal; determining an overall probability of coherence between frequency components of the aggregated power signal and the load category signature power signal; determining if a low power mode is present within the active mode aggregated power signal; and determining the operating modes of each of the overlapping electric loads.

The invention provides a control method and device for the unloading working condition of an automatic bale breaker. A main controller obtains first sensing data of a weight sensor of a hooking device and second sensing data of a force sensor of a bag pushing device; detecting the in-place state of the ton bag according to the first sensing data and the second sensing data; switching an unloading mode according to the change condition of the first sensing data; and after it is detected that the first sensing data belongs to a first preset weight range, the flapping piece and the bag pushing device are controlled to stop working, the bag breaking device returns, and the first preset weight range is used for representing that unloading operation is stopped after the ton bags are in the empty bag state. It can be known that the different unloading modes are switched through the change of the weight data of the ton bags in the unloading process, and the different unloading modes are matched to solve the unloading operation of the unloading device under different stacking conditions, so that the operation efficiency and stability of the unloading working condition of the automatic bale breaker are improved, the refinement degree is improved, and material waste is reduced.

The invention discloses a new energy operation multi-temporal-spatial-scale situation awareness method. The method comprises the steps of multi-source heterogeneous data acquisition and preprocessing, multi-temporal-spatial-scale feature extraction and fusion, uncertainty quantification and probability prediction, edge cloud collaborative real-time situation assessment and multi-target collaborative optimization and feedback control. The invention belongs to the technical field of smart power grids, and particularly relates to a new energy operation multi-temporal-spatial-scale situation awareness method, which adopts multi-source heterogeneous data acquisition and preprocessing, clarifies data sources, preprocesses data through temporal-spatial alignment and anomaly detection, reconstructs an error to capture a complex anomaly mode by using a variational auto-encoder, and achieves the multi-temporal-spatial-scale situation awareness. Detecting a hidden equipment fault; edge cloud is adopted to cooperate with real-time situation assessment, a lightweight anomaly detection model is deployed on the edge side through a knowledge distillation technology, a local outlier factor algorithm is adopted to carry out millisecond anomaly detection, update parameters are issued through cloud digital twin modeling, and the communication efficiency is optimized.

Aspects of the present disclosure illustrate embodiments of systems and methods for deidentification of unstructured data using semi-structured elements. A system for deidentification of unstructured data using semi-structured elements includes at least a processor, and a memory communicatively connected to the at least a processor. The memory contains instructions configuring the processor to implement method for deidentification of unstructured data using semi-structured elements. The method includes receiving a plurality of case data, inputting the plurality of case data into a pattern detection machine-learning model, receiving, from the pattern detection machine-learning model, a template structure corresponding to a set of case data from the plurality of case data, inputting the template structure and case data into a data deidentification module, and receiving a deidentified set of case data.

An apparatus for data processing and related non-transitory computer-readable medium are provided. In the method, the apparatus computes a burst threshold for a data stream. The burst threshold is associated with a throughput of the data stream. The apparatus further identifies a set of bursts in the data stream based on the burst threshold, and detect a pattern in the data stream based on the set of bursts. The apparatus further estimates at least one subsequent burst in the data stream based on the pattern and the burst threshold, and outputs an indication of the at least one subsequent burst in the data stream. The method enables a device to predict one or more future data bursts based on characteristics of existing data. The predicted data bursts allow the transmission resource and power to be adaptively arranged to significantly reduce power consumption and improve transmission efficiency.

A data analysis computer system is provided that receives a timeseries dataset and generates implied data from the dataset. The dataset is further vectorized to reduce the dimensionality of the data. Users provide input to identify windows of data that either positively or negatively correlate to instances of a given type of occurrence within the data. The user defined windows are converted to fixed sized windows and a machine learning algorithm constructs a model from the data. The model is used to predict instances of the given type of occurrence in newly received data. Validation of the predications may be performed.