169 results about "Pattern detection" patented technology

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 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.

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.

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.

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 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.

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.

Pattern information and action information may be received from a customer of a monitoring service. The pattern information indicates a data pattern, and the action information indicates that a computer-executed action corresponds to the data pattern. A log may be analyzed, based on the pattern information, to detect one or more text strings within the log that match the data pattern. It may be detected that a first text string of the one or more text strings matches the data pattern. Based at least in part on the action information, the computer-executed action may be associated with the first text string. A selectable control, such as a drop-down menu or hyperlink, may be displayed, for example in the log, that is selectable to trigger the performing of the computer-executed action. The computer-executed action may be performed based on a user-selection provided via the selectable control.

Methods, systems, and devices supporting techniques for pre-fetching information using pattern detection are described. Some memory systems may support pre-fetching information, such as logical-to-physical (L2P) mapping tables, data, or both, if a sequential pattern of read commands is detected. In some examples, the memory system may store a list of logical addresses indicated by received read commands and may determine whether the list corresponds to a sequential pattern independent of intervening write-alike commands. The list may store previous logical addresses for read commands, allowing the memory system to determine whether subsequent read commands form a sequential pattern. Additionally or alternatively, the memory system may track a ratio of hibernate commands to other commands (e.g., sequential read commands) and may refrain from pre-fetching L2P mapping tables for a detected sequence if the tracked ratio satisfies (e.g., exceeds) a threshold ratio.

A system, method and computer program product to detect opportunistic mixed mode transportation virtual hubs are disclosed. The system may allow commuters to benefit from more relevant and contextual recommendations for “park and ride” commutes by algorithmically detecting opportunistic mixed mode transportation virtual hubs based on traffic conditions, parking capacity measures and mobility patterns of commuters.

A data structure and associated methods for analysis of a continuous 1,197,000-letter unvocalized Hebrew string referred to as the Word of God (WOG). The data structure contains only the twenty-two classical Hebrew letters and their five final forms, with no spacing, punctuation, vowelization, or editorial symbols. Intrinsic placement of the final letters enables deterministic segmentation of the string into 305,490 lexical units and 23,206 verses without external conventions. Fixed letter-number assignments provide a numeric architecture for evaluating substrings, detecting alterations, identifying encoded mathematical correspondences, and performing pattern analysis. The system preserves full semantic range by supporting multiple morphologically valid interpretations of unvocalized Hebrew strings. Methods for segmentation, numeric evaluation, reconstruction, integrity verification, semantic analysis, and mathematical pattern detection are provided thereby providing a reproducible foundation for computational and linguistic research.

The application relates to a classification detection device and method of down, and the classification detection device of down comprises a conveying assembly for conveying down, the conveying assembly comprises a connecting pipe and a detection pipe perpendicular to one end of the connecting pipe; a collecting assembly is arranged with multiple groups and is vertically communicated on the detection pipe; the down in the connecting pipe is blown to the detection pipe through airflow, and continuously rises in the detection pipe; when the down passes through the first collecting assembly from bottom to top, corresponding pattern detection assemblies judge the shape of the down; after judgment, if the down conforms to the shape characteristics collected by the first collecting assembly, a control assembly controls an airflow pushing member to spray airflow, so that the down is blown into the first collecting assembly; if the down does not conform to the shape characteristics collected by the first collecting assembly, the down continuously rises along the detection pipe until the corresponding shape characteristics collecting assembly is found.

An automated, analytics-driven invention that generates, validates, and orchestrates unified RBAC postures spanning cloud infrastructure, SaaS applications, and on-premise assets. The method ingests entitlement data, HRIS attributes, behavioral data, and security policy constraints to identify common access patterns, detect anomalies, and recommend consolidated roles that embody the principle of least privilege. A dual-perspective algorithm—bottom-up clustering of shared connections and top-down evaluation of organizational context—produces high-fidelity roles annotated with confidence scores. The system surfaces actionable insights such as over-entitlement, under-entitlement, segregation-of-duties conflicts, and duplicate connections, then prescribes remediation playbooks or just-in-time enforcement. By continuously comparing the current state to a dynamically computed ideal state, the invention guides enterprises toward an access model that minimizes risk, streamlines audits, and reduces administrative drag.

An attack detection device (120) includes an anomalous pattern detection unit (123) to detect whether an anomalous pattern is included in a time-series recognition score that is time-series data generated using a plurality of recognition scores that are calculated respectively using a plurality of pieces of image data captured of a range within an image-capture range at mutually different time points within an image-capture time range, and indicate results of detecting objects respectively in the plurality of pieces of image data. The anomalous pattern is a pattern that occurs when an adversarial sample patch attack has been conducted against at least one of the plurality of pieces of image data.

The invention relates to the technical field of power distribution network fault detection, in particular to a self-adaptive dual-mode detection method and system for a wire tree touch fault of a power distribution network. The method comprises the following steps: collecting zero-sequence current data of a distribution line in real time; the collected data are preprocessed; calculating a zero-sequence current baseline; judging whether the acquired data enters a large current mode or a small current mode; calculating a comprehensive trend score in a small current mode; calculating the fault credibility; in the large current mode, when the zero sequence current continuously exceeds the threshold value and reaches the preset confirmation time, the fault is directly judged; in the low-current mode, when the fault credibility reaches a high credibility threshold value and is maintained for a certain time, judging the fault; and outputting a fault state and corresponding diagnosis information. According to the invention, the large current mode can confirm faults in a short time, and the small current mode can effectively suppress false alarms through trend analysis and credibility accumulation, so that the system can quickly and accurately deal with various faults.

A system and method for learning a predictive function that can automatically learn different operating modes for a multi-modal system and predict the number of operating states for a multi-modal system and additionally the detailed structure for each state. Once learned, the predictive function (model) can be used to determine a mode of a new sample (an asset). Based on the determined components that maximize a log likelihood function, a mode of the new sample is detected into the model via dependency graphs. One aspect includes enforcing a lower bound for the number of sample points to form an operational mode for an asset. While a mode relates to sample points which maximizes like log-likelihood, an ability is provided to remove artifact modes due to noisy data by considering a sufficient sample data condition and maximizing log-likelihood. Domain knowledge can be incorporated into the model via dependency graphs.

The application discloses a Chinese continuous speech tone change automatic detection method and system, and belongs to the technical field of speech signal processing.The method comprises the following steps: a speech forced alignment step is used to acquire syllable time boundaries; a fundamental frequency transition trajectory extraction step is used to extract a fundamental frequency feature vector in an adjacent syllable connection area; a tone change rule matching step is used to acquire an expected mode from a knowledge base containing necessary and variable rules; a tone change mode detection step is used to calculate a matching score and determine whether the tone change is correct, missing or excessive; and a feedback generation step is used to generate a pitch curve labeling graph and rule explanation.The application realizes accurate tone change detection by focusing on the fundamental frequency transition features of the connection area, provides reasonable evaluation by using a hierarchical rule knowledge base, and helps learners to improve pronunciation by visual feedback.

The application discloses a multi-supply station repeated power grid pattern detection processing method based on multi-dimensional data analysis, and relates to the technical field of power grid pattern detection processing. The method comprises the following steps: obtaining historical power grid pattern data of multiple supply stations and performing multi-dimensional feature analysis to generate a pattern feature set containing line topology features, load distribution features and time sequence change features; constructing a pattern correlation graph based on the pattern feature set, taking a single power grid pattern as a node and taking feature similarity between patterns as an edge; performing a message passing aggregation operation of a graph neural network based on the pattern correlation graph, iteratively updating hidden state vectors of each node and calculating a repeated probability score between nodes; marking node pairs with a repeated probability score exceeding a preset threshold as a repeated pattern candidate pair, and outputting a repeated pattern detection result after time and space consistency verification. The application improves the detection accuracy and efficiency of repeated power grid patterns.

The application discloses a magnetic tape storage adaptive interleaving method and system based on dynamic error mode detection, relates to the technical field of magnetic tape interleaving, and comprises the following steps: continuously collecting error information in a magnetic tape reading and writing process and forming a structured report; judging the received structured report according to a preset rule, dynamically calculating new interleaving parameters, and outputting a decision package containing a new interleaving depth factor and a new available track list; checking whether the parameters in the received decision package are within a preset range, and if yes, sending an instruction to a magnetic tape drive through a bottom driver interface, setting new interleaving configuration for the magnetic tape, and obtaining a success status code returned by the magnetic tape drive; and the interleaving method significantly improves the reliability and error correction efficiency of the magnetic tape storage system in a complex error environment, reduces redundancy, and improves the effective utilization rate of storage space.

The invention relates to the technical field of computers, and particularly provides an intelligent compensation method and device for a distributed system interface, and the method comprises the following steps: S1, a business party carries out the persistent storage according to an interface configuration code after compensating a call interface configuration page, configuring call parameters and receiving the configuration parameters; s2, the service system initiates a request through the proxy interface, transmits an interface configuration code value, obtains interface configuration parameters according to a code after receiving a call request of the service system, and then calls a configured interface URL (Uniform Resource Locator); s3, receiving a result returned by the calling interface, and entering fault mode detection and compensation based on the returned result; s4, based on the fault modes classified in the step S3, corresponding compensation strategies are executed for different modes; and S5, if the compensation strategy is executed completely and the compensation calling still fails, carrying out manual intervention. Compared with the prior art, the system compatibility can be adaptively improved, the misjudgment rate is reduced through accurate fault recognition, and resource waste is reduced through a differentiation strategy.

A user learning pattern detection system and method to guide an Artificial Intelligence (AI) engine to identify and analyze user learning behaviors, specifically anti-patterns (negative patterns) and posi-patterns (positive patterns), within an online learning platform is disclosed. The user learning pattern detection method involves collecting diverse data, including media streams (e.g., webcam feed, microphone audio), user interaction (e.g., keystrokes, mouse clicks), and engagement metrics. This data is then analyzed to generate insights into the user's learning behavior. Using these insights, prompts are generated and provided to the AI engine, which employs machine learning algorithms and computer vision techniques to detect and classify learning behaviors. The detected patterns undergo a quality check using multimodal large language models (LLMs) to ensure accuracy. Finally, the method generates detailed reports, including video clips of key moments, verifying the patterns, and offering user recommendations to enhance the learning experience.

The application provides a station mark detection method and related equipment. First, the local part of the station mark is detected, and a candidate combination frame is determined according to a suspected frame pair in the result that meets a screening condition. The suspected frame pair includes a station mark pattern detection frame and a station mark character detection frame. The candidate combination frame is a circumscribed rectangle of the station mark pattern detection frame and the station mark character detection frame. The serialized features of the candidate combination frame are extracted and classified to determine whether the candidate combination frame is a station mark combination. Finally, the sub-frame and the parent frame in the station mark are output. The station mark pattern detection frame and the station mark character detection frame are the sub-frames, and the candidate combination frame is the parent frame. By using the topological relationship (correlation relationship) between the local structure of the station mark, the detection of the local part (sub-frame) and the whole (parent frame) of the station mark can be realized end to end, the situation of missing detection of the local part of the station mark is reduced, and the efficiency and accuracy of station mark detection and identification are improved.

The invention discloses a graph detection method and system, electronic equipment, a storage medium and a program product, and the method comprises the steps: obtaining a to-be-detected layout which comprises a to-be-detected graph; acquiring a simulation exposure pattern corresponding to the pattern to be detected; obtaining the area ratio of the simulation exposure pattern to the corresponding pattern to be detected, and taking the area ratio as a first area ratio; whether the first area ratio is larger than a first threshold value or not is judged, if yes, it is judged that the to-be-detected graph corresponding to the first area ratio meets the requirement, and if not, it is judged that the to-be-detected graph corresponding to the first area ratio does not meet the requirement. According to the embodiment of the invention, whether the to-be-detected graph meets the preset requirement or not is judged through the area ratio, the actual difference condition between the simulation exposure graph and the to-be-detected graph can be well reflected, and correspondingly, the difference degree between the simulation exposure graph and the to-be-detected graph can be more accurately reflected, so that the accuracy of a detection result is improved, and the detection efficiency is improved. The pattern detection method is correspondingly improved, and the performance of the semiconductor structure is improved.

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.