64 results about "Confidence assessment" patented technology

This invention discloses a rural geological disaster prediction method and system based on edge computing, which relates to the field of geological disaster prediction technology. By comprehensively calculating the disaster prediction probability coefficient and the dynamic confidence coefficient obtained by dynamic confidence assessment based on the disaster prediction probability coefficient, the probability prediction magnitude is determined and the reliability of the prediction is assessed. This achieves second-level accurate early warning of rural geological disasters and improves the reliability of the early warning.

This invention relates to the field of fire protection data integration technology, and discloses a fire protection data integration method and system based on distributed heterogeneous protocol adaptation. This method achieves the acquisition and standardized conversion of multi-source fire protection data through a dual-library collaborative mechanism of a protocol template library and a plugin library. Enhanced fire event feature data is obtained by using sensor spatial topology modeling and multi-scale temporal feature collaborative extraction. This enhanced feature data is then subjected to temporal and spatial dual-path feature extraction and fusion analysis through a multi-scale temporal convolutional network and a spatiotemporal graph attention network. Combined with physical law verification and confidence assessment, intelligent judgment results of fire events are obtained. Hierarchical linkage control and multi-platform message push are executed through an event-driven rule-based process engine. This invention can solve the problems of difficulty in integrating heterogeneous fire protection equipment data, high false alarm rate of traditional fixed threshold methods, and insufficient early warning capabilities.

This invention relates to the field of intelligent document processing technology, specifically to a method and system for document processing in power transmission and transformation scenarios based on a brain-like memory mechanism. The method includes the following steps: generating a query plan based on query intent; recalling relevant documents from a hierarchically modeled power transmission and transformation document knowledge base; and extracting and reasoning information from the recalled documents using a dual-path parallel processing mechanism and a hierarchical abstraction processing mechanism; filling in a structured form according to a predefined template to generate preliminary structured output; simultaneously transforming the extracted and reasoned information into interpretable reasoning chain records; generating memory cases based on the reasoning chain records and confidence assessment results; and storing and optimizing the memory cases using a brain-like memory mechanism. This method possesses the ability to handle complex multi-step reasoning tasks, significantly improves reasoning accuracy, automates document information extraction, and greatly reduces manual processing time.

This invention relates to the field of smart station technology, and more particularly to a smart station emergency decision-making method based on a multimodal large model and knowledge graph. The method includes: acquiring multi-source heterogeneous data from the smart station; using a semantic segmentation strategy and a text generation model to transform the multi-source heterogeneous data into semantic descriptive text; inputting the semantic descriptive text into a trained large language model to extract local keywords; performing fusion-based graph node matching using the local keywords based on a semantic-topological dual-path index established by a pre-constructed event knowledge graph to obtain matching results; performing hierarchical confidence assessment and status labeling based on the matching results to obtain final abnormal nodes; and generating and outputting an emergency response plan for the abnormal event based on the final abnormal node and the pre-constructed event knowledge graph. This invention improves the intelligence, collaboration, and efficiency of emergency response.

This invention relates to the field of power cable testing technology, and discloses a method and system for detecting cable dimensional parameters based on point cloud feature registration. The method includes: acquiring multispectral image signals; obtaining the light trace energy matrix through physical simulation; constructing an error fingerprint database by combining topological mapping; performing semantic segmentation on the image signals to obtain a probability segmentation mask; calling the fingerprint database to obtain a correction matrix and extracting the original sub-pixel point cloud; performing confidence assessment based on environmental stress parameters to obtain a weighted confidence feature set; performing geometric center alignment to output the cable geometric center set, and then extracting the dimensions to obtain the cable cross-section measurement results. This invention achieves digital decoupling of stress-induced optomechanical coupling pseudo-drift, solves the technical problems of numerical jumps in insulation thickness and deviations in eccentricity calculation, and improves the confidence and measurement accuracy of cable cross-section configuration reconstruction under complex mechanical stress conditions.

This invention discloses a train control and management system based on multi-bus fusion in rail transit, relating to the field of onboard network control technology. Specifically, it includes: a multi-path acquisition module, a confidence assessment module, a cross-validation module, and a simulation prediction module; deploying three independent sensing paths, which are uploaded in parallel to the fusion processor via different onboard multi-buses at 100ms intervals; calculating confidence scores for the estimated data output by each sensing path based on Bayesian methods to determine the path's reliability and mapping it to discrete quality levels; performing three-way voting through weighted K-fold cross-validation to calculate a consistency index and compare threshold judgment instructions; constructing a digital twin model, and in case of conflict, performing Monte Carlo simulation for the next cycle, outputting the probability of the result to switch the bus fusion management strategy, effectively avoiding system blind spots caused by single sensor or bus failures, and improving the energy utilization efficiency of trains under high-speed sudden changes, severe load fluctuations, or strong interference scenarios.

The application relates to the technical field of vehicle part maintenance, in particular to a vehicle part matching method and system based on VIN code analysis, which comprises the following steps: a VIN code analysis module is used for segmentally analyzing the VIN code of a vehicle to be matched, and vehicle configuration information with ambiguity eliminated is generated; a part matching module is used for matching candidate part configuration information sets in an engineering database according to a candidate part matching strategy; an assembly constraint checking module is used for screening out unusable parts that do not satisfy preset reference conditions according to an assembly constraint checking strategy, and obtaining available configuration information sets; a part assessment module is used for analyzing historical maintenance, engineering change frequency and vehicle consistency data of the vehicle according to a confidence assessment strategy, and determining the confidence weight of the available configuration information sets; and a part matching output module is used for analyzing the confidence weight value according to a matching result output strategy, and generating part matching information. The application has the effects of reducing VIN code configuration ambiguity caused by engineering changes and improving part matching accuracy.

This invention discloses a high-trophic-level food chain biomagnification prediction model for organic chemicals. The model comprises the following steps: S1. Dividing the sample into six training samples and three validation samples; S2. Retaining a 1169-dimensional molecular descriptor matrix after screening; S3. Generating an extended pollutant parameter database by combining laboratory biomagnification factors; S4. Forming a position-time normalized sample dataset; S5. Obtaining a fused amplification probability result set; S6. Identifying a candidate set of pollutant amplification paths on the coupled directed graph of amplification probability-flux-stability; S7. Performing uncertainty propagation and confidence assessment on the candidate set of pollutant amplification paths, outputting a priority control list of pollutant amplification paths and their confidence information. This invention addresses the problems of insufficient model coverage and weak extrapolation ability caused by traditional methods relying solely on single molecular descriptors or experimental values.

This invention discloses an infrared anomaly region detection and segmentation method based on a cascaded architecture, belonging to the fields of infrared image processing and computer vision technology. Addressing the problems of high false detection rate and low segmentation accuracy in existing infrared anomaly region detection methods, this method employs a three-stage cascaded detection-filtering-segmentation architecture: After preprocessing the infrared image, it is input into a target detection model to generate candidate bounding boxes; multi-bounding box fusion technology is used to calculate spatial cue confidence; a secondary confidence assessment and false positive filtering are performed based on the channel attention mechanism and inverse residual structure of a lightweight feature extraction network, generating a filtering score; high-confidence detection boxes are converted into effective spatial codes and used as spatial cue words input into the segmentation model to complete pixel-level fine segmentation. This invention improves positioning accuracy through a multi-bounding box fusion confidence mechanism, reduces the false detection rate through secondary filtering, and achieves high-precision pixel-level segmentation without manual annotation through effective spatial code conversion.

This invention discloses a physically constrained, enhanced intelligent identification method and system for fiber optic monitoring intrusion events. The method includes: collecting and preprocessing multimodal data from the site to obtain a fiber optic vibration waterfall plot; performing target detection and category probability calculation on the fiber optic vibration waterfall plot, initially marking targets with a category probability consistently greater than a certain threshold as initial high-threat targets; calculating the vibration center of the initial high-threat targets and the maximum distance difference among all vibration centers; when the maximum distance difference reaches a certain threshold, the initial high-threat target is determined as a non-threatening signal and filtered out; and performing threat distance discrimination on the remaining initial high-threat targets to obtain the final high-threat targets and triggering an alarm. This invention performs multiple rounds of judgment and screening of high-threat targets, filtering out interference from non-threatening and long-distance low-threat signals, and performs multi-dimensional confidence assessment on the screened high-threat targets, thereby improving the accuracy of identifying and judging high-threat target intrusion events.

This invention discloses a method and system for interaction between intelligent agents in power grid dispatching that supports dynamic negotiation and result fusion, belonging to the field of power grid dispatching technology. The method includes establishing a contract network protocol and a verifiable dynamic negotiation framework among agents. Agents obtain dynamic negotiation process data through multiple rounds of bidding for resources and allocating tasks. Confidence assessment results for local decision schemes are obtained based on multi-level, multi-dimensional evidence. A multi-level evidence aggregation algorithm is used to dynamically weight all local decision schemes, perform preference attribution alignment, and conflict resolution reasoning, fusing them into a globally optimal decision scheme. A full-process decision tracing graph is constructed based on the globally optimal decision scheme and the dynamic negotiation process data. This invention solves the problems of existing power grid dispatching technologies lacking a dynamic negotiation and result fusion mechanism, leading to the inability to collaboratively optimize under multi-objective conflicts, the difficulty in scientifically fusing multi-source decision results to form a globally optimal solution, and the lack of traceability in the decision-making process.

This application provides a satellite terminal satellite acquisition method, electronic device, storage medium, and program product, relating to the field of satellite communication technology. This method, by introducing position confidence assessment, enables the satellite terminal to adaptively select the satellite acquisition path based on its own positioning quality. When positioning is reliable, it directly utilizes local ephemeris to quickly acquire low-Earth orbit (LEO) satellites. When positioning is unreliable or ephemeris is outdated, it switches to using high-Earth orbit (HEO) satellites to obtain differential correction and auxiliary position information. This effectively compensates for ephemeris and position errors without relying on real-time precise positioning, reduces the searching pointing deviation of LEO satellites, and narrows the search range. It avoids long waiting times and wasted power due to blind scanning, while improving the acquisition success rate. This allows the terminal to quickly join the network even under harsh network conditions, ensuring the timeliness of user service establishment and the terminal's survivability in extreme environments.

The present application relates to the technical field of intelligent packaging detection, and more particularly to a carton sealing abnormality detection method and system based on reflection sensing, which comprises constructing an adjustable physical detection channel, using a reflection type photoelectric sensing array to collect carton contour signals, and identifying sealing abnormality through adaptive threshold segmentation and an improved DTW algorithm; a confidence assessment model is constructed in combination with multi-modal data, and weighted exponential smoothing filtering is used to confirm effective abnormality; a PLC controller accurately separates abnormal cartons based on a predictive trajectory mapping algorithm, and device fault early warning is realized through edge computing cluster analysis. The present application can improve detection accuracy, reduce false positive rate and support intelligent maintenance.

This invention relates to the field of power consumption management technology, specifically to a real-time energy consumption analysis system for pump station units. The system includes a load feature extraction module, a frequency stability identification module, a start / stop window identification module, a voltage response control module, and a signal filtering module. In this invention, a sliding trend sequence is constructed using load state data and current increment information. Abrupt slope changes are identified and trend directions are classified. Combined with frequency variation amplitude, accurate identification of frequency operation stability segments is achieved. A control time window is constructed by judging the trend consistency of energy consumption and flow in the same time domain. A voltage input strategy is set based on the trend change rate and a mapping table is formed. In the confidence assessment of energy consumption labels, trend continuity judgment is used to achieve signal filtering and recovery, effectively enhancing the accuracy of behavior segmentation, the adaptability of power input control, and the continuity and controllability of overall operating status identification during energy consumption monitoring.

This invention discloses a deep learning-based InSAR geological hazard deformation identification method, belonging to the field of geological hazard monitoring and prevention technology. The method includes the following steps: S1, multi-source data acquisition; S2, establishing a multi-source data spatiotemporal registration and pixel-level fusion model; S3, constructing a joint extraction network for multi-scale three-dimensional deformation features; S4, introducing elastic mechanical constraints to optimize the three-dimensional deformation field inversion; S5, fusing the physical model and deep learning output uncertainty quantification results, finally outputting the three-dimensional deformation of each pixel and its corresponding confidence assessment, forming a quantitative deformation result map for geological hazard risk assessment. This deep learning-based InSAR geological hazard deformation identification method employs surface deformation monitoring via synthetic aperture radar interferometry, multi-source remote sensing data fusion, and intelligent deformation inversion and risk assessment combining deep learning and physical constraints. It can be applied to the identification, monitoring, and risk assessment of geological hazards.

The application provides a kind of evaluation of residual disease regression data trend visualization analysis method and system, it is related to data processing technical field, method includes: acquisition evaluation of residual disease regression quantification data and external environment quantification data;Perform time alignment, abnormality rejection, denoising smoothing, missing compensation and numerical standardization processing, obtain standardized evaluation of residual disease regression quantification data and standardized external environment quantification data;By periodically evaluating the overall fluctuation degree of residual disease regression trend, mark trend mutation point, and cluster to form abnormal change interval;Quantify the environmental disturbance driving effect of each trend mutation point in the abnormal change interval, identify and reject environmental false positive anomaly;Abnormal confidence assessment is carried out to the retained trend mutation point, and the key suspected interval is identified;According to the key suspected interval, the authenticity and risk level of abnormal fluctuation are quantified by combining group, behavior and structure characteristics;Perform hierarchical response strategy, and trigger visual warning.

This invention discloses an adaptive dynamic optimization method and system for knowledge bases, relating to the field of knowledge base optimization technology. The invention uses a confidence assessment module to denoise and map user interaction behavior to generate feedback confidence scores, and dynamically adjusts the feedback admission threshold using knowledge structure association values, recognizing only high-confidence feedback as valid signals. It then updates the consolidation weights of knowledge items through a moving average calculation, and finally transfers low-frequency, low-value knowledge to archiving units based on these consolidation weights. This achieves effective retention of historical core knowledge while continuously absorbing new knowledge, avoiding noisy feedback from misleading the optimization direction, and solving the problems in existing technologies where dynamic knowledge base updates cannot effectively retain historical knowledge and user feedback noise interferes with optimization.

This invention discloses an intelligent code defect detection method integrating static analysis and AI reasoning, belonging to the field of artificial intelligence technology. It includes the following steps: S1: Performing static analysis on the code to be detected to construct verifiable static evidence containing defect candidates, evidence paths, variables and constraints, sources and sinks, and environment and configuration; S2: Organizing the static evidence and project context information into a structured evidence package according to the Evidence Constraint Architecture (ECS); S3: Under the evidence constraints, performing defect judgment and attribution on the evidence package through AI reasoning, outputting judgment conclusions, reasoning chains, and remediation suggestions, with each judgment conclusion establishing a traceable binding relationship with its referenced Must-Cite field; S4: Performing consistency verification and confidence assessment on the AI ​​reasoning conclusions, and calculating defect priority. This invention significantly reduces false positives in static analysis and suppresses AI illusionary conclusions through a closed-loop mechanism of "strong evidence constraints + formal consistency verification + conflict rollback."

This invention provides a method for medical device location tracking and idle status identification that integrates spatiotemporal information. This method acquires real-time positioning and status data of medical devices through a multi-source sensor network, performs data quality assessment, cleaning, and fusion, and constructs a spatiotemporal trajectory sequence. A trajectory prediction model is built based on a long short-term memory network and attention mechanism, and trajectory prediction is performed in conjunction with a hospital semantic map. Furthermore, clinical scheduling data is integrated, and a multi-layer status identification model is used to achieve refined identification and confidence assessment of the idle status of medical devices. This invention can effectively improve the positioning accuracy and status judgment reliability of medical devices, providing intelligent support for hospital equipment scheduling and management.

This invention belongs to the field of artificial intelligence and software engineering technology, specifically a method and system for cross-system dynamic workflow orchestration based on user intent recognition. The method includes: introducing confidence assessment and a multi-round clarification mechanism; performing zero-sample API semantic alignment through a shared embedding space and combining it with reliability weights for retrieval; dynamically generating a directed acyclic graph workflow; employing the Saga pattern during execution to ensure cross-system transaction consistency; performing local replanning through influence domain analysis when a node fails, replacing only the affected subgraph; and finally aggregating the results and updating the API reliability weights based on an exponential moving average. This invention solves the problems of error-prone intent understanding, static and inflexible workflows, lack of cross-system transaction guarantees, and inability to self-optimize in existing technologies, achieving highly robust, adaptive, and strongly consistent intelligent workflow orchestration.

This invention discloses an iterative optimization method and related apparatus for single-tree crown segmentation based on confidence decoupling and prior-driven principles. The method includes: inputting remote sensing image data into a single-tree crown segmentation model to output a coarse segmentation result; performing confidence assessment on the coarse segmentation result to generate a confidence assessment result; generating prior information from the confidence assessment result using a prior encoder, and fusing the prior information with the original high-dimensional features to generate fused features; inputting the fused features into a neural network decoder for the next optimization segmentation process, outputting the next optimized single-tree crown segmentation result, and returning to the confidence assessment step, until the number of optimization iterations reaches a preset number, at which point the final optimized single-tree crown segmentation result is output. In this embodiment, the boundary precision and regional consistency of remote sensing image segmentation in complex forestry scenarios are significantly improved.

This invention proposes an automated data governance method that integrates multidimensional matching and LLM Agent collaborative reasoning. This method is fully automated and executed by a unified LLM Agent architecture, requiring no manual intervention. It can quickly sort and govern messy and disordered data, automatically identifying Chinese definitions of fields, relationships between fields, and relationships between tables. Specifically, it includes the following steps: (1) multi-source metadata collection and knowledge graph construction; (2) multi-agent intelligent reasoning control based on LangChain; (3) multi-dimensional lineage matching engine; (4) graph neural network relationship prediction; (5) reinforcement learning-driven matching strategy optimization; (6) temporal evolution analysis of data structures; (7) multi-strategy fusion and confidence assessment; and (8) incremental update and continuous learning mechanism. This invention utilizes multi-dimensional fusion analysis: comprehensively employing multiple techniques such as data value matching, name similarity, semantic vectors, LLM reasoning, graph neural networks, reinforcement learning, and temporal analysis to significantly improve matching accuracy.

This invention provides a method, apparatus, and server for evaluating the confidence of a reused model, relating to the technical field of model evaluation. The method includes: comparing a reused model with an instance library to determine the similarity of conditional parameters, and constructing a similarity matrix using the conditional parameter similarity; performing conditional parameter sensitivity analysis on the reused model to determine sensitivity weights; using a preset similarity calculation model, based on the sensitivity weights and the similarity matrix, determining the model similarity between the reused model and each model in the instance library; and using an error expectation calculation model, based on the model similarity, determining the expected error between the simulated value of the reused model and the experimental value of the actual model, and determining the confidence of the reused model and the confidence evaluation result based on the expected error value. This invention can significantly improve computational accuracy and efficiency.

This invention relates to the field of educational informatization and intelligent teaching technology, specifically to a generative AI-enabled method for dynamically generating computer science classroom teaching resources. This method acquires teaching objectives and content to construct a knowledge graph; collects classroom data, generates learning gains and emotional representations within a time window, forms a sequence through confidence assessment and denoising, calculates the emotional core coupling index, and gates the core weights; updates the core and emotional weights based on the learning gains and emotional sequence, and applies stability constraints; generates teaching resources and adjusts their order according to emotional weights; combines learning and resource usage to generate evaluations, updates objectives or parameters, and achieves iterative optimization; updates the graph weights through a dual-channel approach of learning gains / emotions, coupling gating, and stability constraints, suppressing the "emotional injection" pollution of core edge weights by interaction heat; and generates resources based on the graph and adjusts their order according to emotional weights, achieving immediate response without deviating from the main course line.

This invention discloses a distributed control method and system for glass processing production based on the Internet of Things (IoT), belonging to the field of industrial automation technology. The method includes: cross-node correlation and fusion, condition feature extraction, and threshold parsing of structured raw process data; extraction of state parameters and control thresholds to generate multi-source fused control data; using rule-based control methods to perform condition matching, logical judgment, and decision processing on the multi-source fused control data to generate preliminary control commands; after the collaborative control commands are issued, edge intelligence methods are used to coordinate control points to execute control actions, real-time collection of operating status and control response data, and the use of anomaly detection and confidence assessment to filter invalid data and generate a high-quality control response dataset. This invention improves the adaptability of control commands to actual operating conditions, enhances the timeliness and stability of multi-node collaborative control, and ensures the continuous operation of the glass processing production process.

This invention discloses a non-intrusive AI-based automated monitoring system for new energy production, relating to the fields of industrial automation and intelligent monitoring technology. It includes a screen capture module, an action execution module, a multimodal information extraction module, a state fusion and confidence assessment module, an SC3 closed-loop monitoring control module, a process orchestration module, and a log auditing module. In each monitoring cycle, the system locks an interface snapshot and generates a set of interface anchor points and a set of readings. Through view positioning and region constraints, it performs structured extraction of readings to form a state candidate set. Combining recognition confidence, cross-frame stability, and cross-view consistency, it calculates state confidence and generates a state vector, constructs a conflict set, and performs gating decisions. Based on the afterimage verification results, it performs rollback or locking processing. The log auditing module records the entire process as a chain of evidence, achieving reliable closed-loop control of the monitoring process.

This invention relates to the field of vehicle driving safety monitoring technology, and more particularly to a driver behavior monitoring device and electronic equipment based on multimodal visual recognition. The device includes a physical device and a control device. The control device is integrated into an embedded computing platform and includes a data acquisition module that acquires vehicle dynamic parameters through a vehicle bus interface and controls a multispectral imaging unit to acquire video streams; a feature extraction module that fuses spatial features and temporal motion features from the video stream to generate a spatiotemporal feature tensor; a behavior analysis module that generates standard behavioral features through a generative adversarial network and calculates statistical deviations; a risk decision module that uses a dynamic weighted algorithm to output a comprehensive risk level and confidence assessment; and a control output module that executes early warning operations and sends feedback data to the behavior analysis module for model optimization. This invention reduces the false positive rate and improves the timeliness of early warnings through multimodal data fusion and closed-loop optimization mechanisms.

This invention relates to the field of industrial equipment fault diagnosis technology, and discloses a method and system for industrial equipment fault diagnosis based on federated learning and digital twins. The method includes: collecting multimodal operational data through edge nodes and training a local model to generate model update volume and integrity proof; performing update reliability control at aggregation nodes and weighted aggregation based on digital twin consistency scores to obtain a global fault diagnosis model; and using digital twin counterfactual simulation to achieve fault root cause analysis, confidence assessment, and maintenance recommendations. This invention improves the reliability of collaborative training and the interpretability of diagnosis while ensuring data privacy, solving the black-box problem of industrial equipment fault diagnosis.

This invention discloses an adaptive early-stopping generation method and system for language models based on dynamic confidence and domain reinforcement, applied to the inference process of large-scale language models based on autoregressive generation. During model generation, this method performs real-time confidence assessment on the generated text and constructs a multi-factor coupled dynamic confidence threshold function by combining task domain features, generated content structure, and quality constraints. When the generated text meets the pre-set confidence conditions and passes the final quality check, the generation process is terminated early, thereby reducing redundant generation. This invention does not require modification of the original model parameters or structure, is applicable to various inference service frameworks, and can effectively reduce generation latency and computational resource consumption while ensuring generation accuracy and completeness, thus improving the overall efficiency of large-scale model inference systems.

This invention discloses an automated SD-WAN zero-contact deployment system based on an edge AI model, belonging to the field of information networks. To address the problems in existing technologies, such as single-mode system authentication, susceptibility to forgery and replay attacks, insufficient AI decision reliability, lack of a safety net, coarse configuration verification, coarse rollback granularity, and susceptibility to model training contamination, lack of gradient anomaly detection, this invention effectively resists device forgery and replay attacks by using multimodal fusion verification of hardware fingerprints, visual recognition, and digital certificates, combined with timestamps, random number anti-replay, and certificate chain verification. Furthermore, it introduces a comprehensive confidence assessment; when the confidence level falls below a threshold, it automatically switches to a safety net rule generation mode, ensuring that devices can still obtain the minimum operational configuration in unknown scenarios and preventing network paralysis due to AI misjudgment.