123 results about "Quantitative assessment" patented technology

The invention discloses a building outer wall falling risk detection method and system based on deep learning, and the method comprises the steps: obtaining an original surface image, extracting vertical face geometric features, constructing a homography matrix based on vanishing points, carrying out the geometric correction, and reconstructing an orthographic projection image; performing enhancement processing on the orthographic projection image, extracting an effective detection area and intercepting a detection image; inputting the detection image into a deep learning segmentation model into which edge weight constraint is introduced, and performing semantic segmentation, binaryzation and optimization to obtain a falling region; a mapping relation is established according to the actual physical size of the building outer wall, and pixel information of the falling area is converted into multi-dimensional parameters such as the actual physical area, the elevation, the width and the height; and combining the defect intensity input quantification risk assessment model to calculate a comprehensive risk index, determining a risk level and outputting a result. Automatic identification and quantitative evaluation can be realized, distortion and background interference are eliminated, accurate conversion from pixels to a multi-dimensional physical space is realized, and a scientific basis is provided for safety investigation.

The invention relates to the technical field of faults of the Internet of Things, in particular to a work order closed-loop management method and system for automatically handling faults of fire-fighting Internet of Things equipment. The method comprises the following steps: obtaining the equipment type, the located area code and the linkage fire-fighting equipment number, and calculating a fault risk index; the partial derivatives of the weight coefficients are solved according to the objective function, the gradient is formed according to the partial derivatives, and the weight coefficients are updated according to the partial derivatives in the reverse direction of the gradient through the principle of the gradient descent method. And the updated weight coefficient is combined with the maximum accommodation number of people corresponding to the region, the maximum linkage number of single equipment, the equipment type weight corresponding to the equipment type, the real-time number of people corresponding to the region and the linkage fire-fighting equipment number to recalculate the fault risk index, and after the weight is dynamically adjusted, influence factors are comprehensively considered, so that the fault risk index is obtained. More reasonable risk assessment is provided for each fault, risk misjudgment caused by unreasonable weight is avoided, and the accuracy of quantitative assessment of fault influence is improved.

The invention discloses an electronic equipment commissioning and testing quality problem management system and method based on an algorithm model, and the system comprises a quality basic data maintenance module which is used for building a quality problem classification algorithm model through historical quality problem data, classifying problems, and giving quality problem types; the quality problem maintenance module is used for automatically retrieving and recommending similar historical problems and solving paths thereof according to fault features corresponding to the current quality problem; the quality data analysis application module is used for carrying out quantitative evaluation and trend prediction on potential risks in batch production; the expert experience knowledge base module is used for recording and carding the extracted historical quality problems and solving measures thereof to form an expert experience knowledge base, and storing solutions of the quality problems subjected to cross-department processing in the expert experience knowledge base when new quality problems occur every time; the method has the advantage that the management efficiency and effect of the quality problem are improved.

The invention relates to a cable defect monitoring and risk grading method based on multi-modal depth fusion, and the method comprises the steps: obtaining visual modal data, carrying out the geometric correction and adaptive illumination enhancement processing, and obtaining the time sequence modal data of a sensor, and carrying out the standardization processing; image defects are extracted from the preprocessed visual modal data, the image defects are quantified into geometric parameters, and geometric feature vectors are formed by the geometric parameters; extracting a depth feature vector representing the deep state of the equipment from the modal data; splicing and fusing the depth feature vectors of different modes, and outputting a final fused feature vector; and splicing the final fusion feature vector and the geometric feature vector, and inputting into a multi-task decision network based on a multi-layer perceptron to obtain a cable health state and a quantitative evaluation result. Compared with the prior art, the method has the advantages that the early fault feature recognition degree is enhanced, associated information is extracted through multi-modal fusion, and health state assessment and risk grading are quantified.

The invention discloses a dynamic risk assessment method and system before network security insurance protection based on a PIPDR2 model, and the method comprises the steps: building and determining the PIPDR2 model, and enabling the PIPDR2 model to comprise a PIPDR2 risk assessment factor layer and a risk assessment index layer; a security policy factor module, a risk identification factor module, a security defense factor module, a security detection factor module, a security response factor module and a security recovery factor module are configured in the PIPDR2 risk assessment factor layer; in the risk evaluation index layer, corresponding risk evaluation indexes are configured for each evaluation factor module in the PIPDR2 risk evaluation factor layer based on network security level protection evaluation data; on the basis, an analytic hierarchy process (AHP) is adopted to carry out risk quantitative evaluation. According to the scheme, risk quantification, accurate premium pricing and continuous optimization are realized by integrating the equal insurance evaluation data and the AHP, and the collaborative efficiency of insurance products and safety protection is improved.

The invention discloses a pumped storage power station high-fall cable tunnel fire risk assessment method and system, relates to the technical field of fire science and safety, and aims to solve the problem that an existing cable tunnel fire risk assessment method is not suitable for a high-fall scene and lacks consequence quantification capability. Comprising the following steps: identifying a hazard source through multi-mode investigation and in combination with a high-fall cable tunnel structure and the like; a fire accident tree is constructed based on the method, and the occurrence possibility of a top event and the importance of various factors are determined through qualitative and quantitative analysis; a fire consequence severity grade standard is formulated, fire parameters are obtained through CFD simulation, and the fire consequence severity is determined from the two angles of transverse spreading and longitudinal spreading; adopting a risk matrix method to complete risk quantitative evaluation; and according to the accident tree index and the evaluation result, proposing prevention and control suggestions from multiple aspects. According to the invention, accurate quantitative evaluation of the cable tunnel fire risk in the high-fall scene is realized, and a scientific basis is provided for risk prevention and control.

This invention provides a method for calculating the risk level of online individuals based on multi-source data fusion and dynamic perception, relating to the fields of cyberspace security and social governance. By integrating online and offline behavioral data, this invention extracts behavioral frequency, violation records, trajectory features, and emotional characteristics to construct a basic risk level. This risk level is then dynamically corrected by incorporating time decay, event sensitivity, emotional polarization, and platform amplification effects, outputting the risk level of online individuals. This achieves a quantitative assessment of individual online individual risk, providing decision support for public opinion command and online risk early warning.

This application relates to a monitoring strategy adjustment method and apparatus based on quantitative risk assessment. The method involves detecting risks in a target scenario based on real-time monitoring data; obtaining quantitative parameters based on detected risk events; calculating the comprehensive risk value of a security event based on these quantitative parameters; the quantitative parameters include the prior probability of a security event occurring, the probability of the risk event occurring when the security event occurs, and the probability of historical risk events occurring; calculating monitoring strategy parameters based on the comprehensive risk value; and controlling monitoring equipment within the target scenario based on these monitoring strategy parameters. This approach solves the problems of single and inflexible monitoring strategies, enabling quantitative assessment of detected risk events, analysis of the comprehensive risk of security events, and dynamic strategy adjustment based on the quantitative assessment results, thereby improving the effectiveness of the monitoring system in preventing security problems.

This invention discloses a distributed situational awareness and safety decision-making method for manned and unmanned aerial vehicles (UAVs) in collaborative airspace. It dynamically aggregates the spatial topology and relative motion features of the local neighborhood of the aircraft using an EdgeConv graph neural network to generate a collaborative situational representation that incorporates the intentions of both manned and unmanned aircraft. A DRNN-LSTM hybrid model is used to learn temporal situational sequences, enabling a forward-looking quantitative assessment of future conflict risks. Manned aircraft commands are intrinsically embedded as conditional variables in the perception and prediction processes, making the safety-first principle an inherent constraint of the algorithm. Based on the risk assessment results and the constrained situational representation, a safety-first collaborative control command is generated through a distributed policy network, forming an autonomous closed loop of "perception-prediction-decision-execution" after execution. This invention achieves deep fusion of spatiotemporal situational awareness and risk foresight in complex airspace, internalizing manned aircraft safety as the core logic, and effectively improving the safety, adaptability, and mission efficiency of manned and unmanned aircraft collaborative operations.

This invention provides a method and system for predicting atrial fibrillation (AF) load based on intermittent PPG signals, belonging to the field of data processing technology. The method includes: training a first neural network using a first PPG signal with known AF results to obtain an AF probability prediction model; using the AF probability prediction model to predict the AF probability of a second PPG signal within a target time period and mapping it to an AF risk value; determining the AF probability at any given time based on the risk values ​​of two adjacent second PPG signals, integrating to obtain the total AF time, and thus obtaining the AF load; training a second neural network using historical AF loads from multiple time periods to obtain an AF load prediction model, used to predict the AF load for multiple future time periods. This invention achieves quantitative assessment and future trend prediction of AF load from discrete PPG signals to continuous AF load.

The invention relates to the technical field of unmanned aerial vehicle automatic inspection, provides an unmanned aerial vehicle take-off and landing platform rapid deployment and path planning method for a building curtain wall, constructs a gradient risk field model fusing geometric structures, environmental risks, visual perception and task regulations, and realizes unified quantitative evaluation of operation environmental risks. And based on the risk field, generating a global safe energy-saving path on the curved surface of the curtain wall through mixed search and path smoothing optimization guided by a risk navigation potential function. Through real-time updating of a local risk field and model prediction control, autonomous obstacle avoidance and smooth return flight of the unmanned aerial vehicle to sudden obstacles are realized. Meanwhile, a dynamic scheduling mechanism considering multi-target cost is introduced, and collaborative optimization of multiple unmanned aerial vehicles and take-off and landing platform resources is achieved. According to the method, full-link closed loop from environment modeling, global planning, real-time control to system scheduling is realized, and the safety, continuity and overall operation efficiency of automatic routing inspection of the super high-rise building curtain wall are improved.

This invention relates to the field of bid document management technology, and in particular to an automatic bid document review method and system based on natural language processing. The method includes: identifying target sections; determining historical performance and financial information; judging whether false performance exists; analyzing the complete sentences containing target keywords; calculating material scores; determining price deviation; and determining the review result. This invention achieves multi-dimensional and comprehensive review of bid documents by intelligently analyzing multiple sections such as qualifications, risks, materials, and pricing. This effectively improves the comprehensiveness and depth of the review. Utilizing natural language processing technology, it can accurately identify and extract key information from bid documents, overcoming the subjectivity and limitations of traditional manual review. Quantitative assessment based on risk level significantly improves the accuracy and relevance of risk identification. By comprehensively weighing material scores and price deviation, it significantly improves review efficiency.

This invention relates to the field of biomass pellet fuel transportation technology, and discloses a method and system for optimizing biomass pellet fuel transportation routes. By introducing mechanisms such as real-time data perception, quality risk quantitative assessment, dynamic task rescheduling, and multi-objective optimization, it can effectively cope with uncertainties in the transportation process, ensure the transportation quality and timeliness of biomass pellet fuel, significantly improve logistics efficiency, and reduce operational risks.

The invention discloses a large-scale low-altitude aircraft deviation early warning method and system, and the method comprises the steps: firstly integrating an aircraft airborne sensor and external environment data through a multi-source heterogeneous data fusion technology, and achieving the high-precision estimation of a flight state; the future three-dimensional trajectory of the aircraft is predicted based on deep learning; performing quantitative evaluation and grading by integrating multiple risk factors such as deviation distance, airspace density, meteorological conditions, airspace properties and the like; and finally, issuing a corresponding early warning or control instruction to the aircraft, a ground controller or a supervision department through an air-ground cooperative network according to the risk level. According to the invention, the dynamic deviation monitoring and early warning problem of a large-scale and high-density aircraft group in low-altitude traffic is solved, the conversion from passive lag response to active prediction and early warning is realized, and the safety, management and control precision and airspace operation efficiency of low-altitude flight are improved.

The invention relates to an AI-assisted lumbar intervertebral disc resection visual navigation device with a postoperative care monitoring function, and belongs to the technical field of medical equipment.The AI-assisted lumbar intervertebral disc resection visual navigation device comprises an AI assisting module, a visual navigation module, a postoperative care monitoring module and a data processing and transmission module, and the AI assisting module is internally provided with an image recognition model and a risk prediction model; the system is used for performing lesion recognition and positioning on image data of a patient before an operation, performing operation risk assessment in combination with multi-source information of the patient, and overlapping and displaying the operation risk in a three-dimensional model to realize real-time navigation in the operation, the AI auxiliary module realizes accurate lesion positioning and risk quantitative assessment, and the visual navigation module provides real-time guidance with the precision smaller than or equal to 0.5 mm. The postoperative nursing monitoring module achieves all-around real-time monitoring of physiological parameters, wound states and rehabilitation training, and the abnormity early warning subunit discovers the risks in time and treats suggestions in a grading mode to improve nursing pertinence.

This invention relates to the field of vehicle insurance claims management technology, and discloses a method, system, electronic device, and storage medium for constructing a life table for vehicle insurance claims. This invention integrates internal claims data with external industry data to construct a vehicle damage cost model and a personal injury cost model, and collects data and operational trajectories from the entire claims process. It combines cost deviation calculation and multi-dimensional personnel information to construct a claims personnel profile model, applies the evaluation results to personnel management, and iteratively optimizes based on feedback data. Simultaneously, it utilizes cost assessment and personnel profile correction to generate a graded evaluation of the institution's claims capabilities. This solves the problems in traditional vehicle insurance claims such as the lack of a unified quantitative cost standard leading to significant differences in loss estimation, the single dimension of personnel assessment making it difficult to accurately identify high-risk personnel, and the reliance on macro indicators in institutional evaluation failing to pinpoint micro-level shortcomings. It achieves improvements in the quantitative assessment of case cost, accurate identification of personnel risks, and scientific grading of institutional capabilities in vehicle insurance claims life table pricing.

The invention discloses a security risk assessment method and system based on attack chain deduction, relates to the technical field of network security, and solves the problem that security risks are difficult to comprehensively and accurately assess in the prior art. According to the embodiment of the invention, by establishing the asset-vulnerability-attack stage mapping relationship, the whole-process visual modeling of the attack chain from initial reconnaissance to target achievement is realized, the specific effect of the vulnerability in the attack chain is determined, and the problem that the vulnerability linkage effect is neglected in traditional assessment is solved, so that more comprehensive risk assessment is realized; in addition, the mapping relation can be updated in real time according to asset change and new vulnerability discovery, accurate basic data support is provided for attack path generation, and dynamic construction of an attack surface panoramic view is achieved. Besides, by introducing path selected probability parameters, subjective strategy preferences of the attacker are brought into quantitative evaluation of the risk, so that total risk evaluation better fits real attack decision logic, and a more accurate evaluation result is obtained.

This invention discloses a method for assessing and analyzing the impact of key source emissions on population health, including the following steps: (1) establishing a key source emission characteristic database and clarifying the list of key sources; (2) establishing an exposed population characteristic database and generating a spatial distribution map of exposure scenarios; (3) a health risk assessment method to quantify the health risks caused by pollutants to different population groups in different exposure scenarios; and (4) assessment, analysis, prediction, simulation, and decision-making to identify key prevention and control areas of "high pollution emissions + highly sensitive populations," conduct differentiated scenario prediction and simulation, and propose targeted action recommendations. This invention establishes a full-chain correlation analysis method of "key source emissions - environmental concentration - exposed populations - health effects," identifies key prevention and control areas of "high pollution emissions + highly sensitive populations," and realizes quantitative assessment, prediction, and precise prevention and control of health risks from key source emissions, providing a scientific basis for "targeted management" and "protection of sensitive populations" decisions.

The application provides an intelligent analysis platform for risk assessment of wild bird flu virus recombination, relates to the technical field of influenza virus monitoring and risk assessment, and comprises a multi-source monitoring data acquisition module, a data preprocessing module, a virus sequence intelligent analysis module, a recombination risk assessment module, a spatial situation analysis and visualization module and a report generation and early warning module connected in sequence through an API interface. The intelligent analysis platform for risk assessment of wild bird flu virus recombination can realize multi-source monitoring data acquisition, virus sequence intelligent analysis, recombination risk quantitative assessment and spatial visualization early warning, and provides whole-process technical support for influenza virus recombination prevention and control.

The invention provides a risk grading and evaluating method and system for a compressed air energy storage cavern, and the method comprises the steps: extracting key risk factors through principal component analysis, building a failure function for a typical failure mode, calculating a failure probability through a first-order second-moment method, and dividing a threshold value in combination with an overall comprehensive failure probability to determine the risk grade. Quantitative evaluation and intelligent grading of multi-mode failure risks are realized, accurate identification and dynamic management of full life cycle risks of the compressed air energy storage cavern can be realized, and the operation safety and decision-making efficiency of an energy storage system are improved.

The invention discloses a sensitivity-based heuristic critical path change probability detection method and system, and relates to the technical field of critical path change detection, and the method comprises the steps: constructing a directed acyclic graph based on a supply chain network of a target project, adopting a CPM critical path algorithm to obtain a reference critical path, a total project construction period and floating time of each activity under a normal condition; obtaining a heuristic sensitivity index based on the floating time; under an abnormal condition, determining an affected activity, and screening to obtain a to-be-evaluated condition based on the influence duration, the reference key path and the floating time; generating candidate key paths based on the total project construction period and the heuristic sensitivity index; corresponding random variables are determined based on the to-be-evaluated condition, and transition probabilities of all candidate key paths are obtained based on normal distribution of the random variables; and obtaining a key path change probability, a new key path and a corresponding total construction period based on all transition probabilities. Accurate quantitative evaluation of the dynamic risk of the supply chain network is realized.

The application discloses a risk assessment system for cross matching difficulty, and relates to the technical field of clinical medical examination and blood transfusion management. The system comprises a data input module, a risk calculation module, a risk stratification module and a result output and suggestion module. The data input module obtains key information of a patient, including irregular red blood cell antibody screening results, multiple myeloma diagnosis, hematology department medical history, age of 60 years or older, pregnancy-related disease state and blood type identification difficulty; the risk calculation module adopts a preset scoring algorithm to assign weights to each factor and calculate a total risk score; the risk stratification module divides the patient into three grades of low risk, medium risk and high risk; and the result output module provides a differentiated clinical management path corresponding to the risk grade. The application realizes early warning of cross matching difficulty through quantitative assessment, can optimize the efficiency of the blood transfusion process and reduce clinical risk, has good prediction performance (AUC=0.819) and a high negative predictive value (93.7%).

Disclosed in the present invention are a quantitative assessment method for the safety performance of a planning module of an autonomous driving system, an electronic device, a storage medium, and a computer program product. The quantitative assessment method for the safety performance of a planning module of an autonomous driving system comprises: decomposing hazard events of a planning module into events caused by planning uncertainties of different algorithm modules of the planning module; performing scenario modeling on the probability of the hazard events caused by the planning uncertainties of the planning module to obtain driver models under different hazard events; and at least on the basis of the driver models under different hazard events, obtaining quantization objectives corresponding to different algorithm modules of the planning module. The embodiments of the present application provide a theoretical basis-based complete quantitative assessment method for the safety performance of a planning module of an autonomous driving system.

This invention relates to the fields of software security and artificial intelligence, specifically a generative AI-based intelligent vulnerability discovery and risk assessment method for software security. The method includes: generating abnormal behavior patterns by collecting multi-source data from the target software, inputting this data into a pre-trained generative AI model for multi-level correlation reasoning, and automatically outputting a set of vulnerability descriptions containing location, path, and impact. Historical verification of the vulnerability descriptions enhances their accuracy, and a risk posture assessment is performed. The attack entry point exposure, exploitation path feasibility, and system impact scope of each vulnerability are quantitatively calculated to form a structured risk quantification matrix. Based on this matrix, risk level mapping is completed, and remediation suggestions and priority sequences are automatically generated. Finally, a risk assessment report is integrated and output. This method automates and intelligently discovers vulnerabilities and significantly improves the accuracy and operability of risk analysis through multi-dimensional quantitative assessment.

The invention provides a transformer substation surrounding environment sensitive point target identification method and system based on machine learning, and relates to the technical field of electric power engineering environment monitoring, and the method comprises the steps: obtaining a high-resolution satellite image, carrying out the preprocessing of the high-resolution satellite image, and obtaining the preprocessed data; inputting the preprocessed data into a sensitive target detection deep learning model for processing, and determining basic information of the target; performing coordinate conversion on the basic information of the target, and converting the position pixel coordinate of the target in the image into the geographic coordinate of the real world; calculating the Euclidean distance between the geographic coordinate of the converted target and the geographic coordinate of the core equipment of the transformer substation; performing risk assessment based on the Euclidean distance by using the risk quantitative assessment model, and determining the risk level of the identified target; and when the risk level exceeds a preset threshold value, early warning information is automatically generated. The method can improve the recognition precision of sensitive point targets in the surrounding environment of the transformer substation.

The invention relates to the field of violation monitoring, in particular to violation behavior monitoring equipment and method based on dual prevention. The technical problems that in the prior art, a violation behavior monitoring method lacks a prediction analysis and risk prevention and control mechanism, so that the early warning capability and the prevention and control effect of a monitoring system are limited, and a passive response mode is mostly adopted, that is, the violation behavior can be found and recorded only after the violation behavior occurs, and early warning and prevention cannot be performed in advance are solved; according to the technical scheme, the violation behavior monitoring equipment based on dual prevention comprises a high-definition camera, a mounting rack and a central processing unit; according to the invention, by introducing a risk assessment mechanism, quantitative assessment is carried out on the properties and consequences of the violation behaviors, the hazard level of the violation behaviors is determined, a scientific basis is provided for subsequent treatment measures, potential risk behaviors are predicted through a machine learning algorithm, early warning and prevention and control are realized, and occurrence of the violation behaviors and accumulation of potential risks are effectively reduced.

This invention provides a prospecting method for sulfide-type gold deposits in covered areas, comprising the following steps: obtaining the geological characteristics of typical gold deposits and delineating areas with similar geological conditions to known typical gold deposits; obtaining gas geochemical measurement results from each detection point; performing first-dimensional and second-dimensional classification based on the gas geochemical measurement results from each detection point; classifying prospecting target areas by combining the first and second-dimensional classifications; and delineating prospecting target areas and verification sequences based on the prospecting target classification results. This method achieves precise quantitative assessment of the distribution of sulfur-bearing gases and the enrichment degree of gold through a two-dimensional classification system, and further achieves precise classification of prospecting target areas through multi-dimensional combinations. This system effectively filters out the risk of misjudgment from single abnormal indicators, ensuring a high degree of matching between target area classification and the probability and scale of gold deposit existence, significantly improving the scientific nature of prospecting decisions and the success rate of target area verification.

This application discloses a safety credit evaluation method and related apparatus. First, it acquires behavioral data and a quantification model of multiple workers within a given period. In this quantification model, the difference between the occurrence time of a work behavior and the current time is negatively correlated with safety credit. Then, based on the quantification model, the behavioral data is quantified, considering the dynamic impact of work behavior at different times on the quantification score. This enables personalized and differentiated quantitative assessment of the safety credit level of different workers. Subsequently, the quantification score and the basic credit score are weighted and calculated to obtain the safety credit score for each worker. The weight corresponding to each worker's quantification score is positively correlated with their work period, effectively improving the reliability and confidence of each worker's safety credit score, and effectively enhancing the accuracy and intelligence of the safety credit evaluation.

The invention provides a primer composition for IgA nephropathy risk assessment, a detection kit, a polygene scoring model and a risk prediction method. According to the invention, 47 IgA nephropathy genetic susceptibility sites are systematically identified for the first time, 17 sites are new sites reported for the first time globally, and the 47 IgA nephropathy genetic susceptibility sites are utilized to construct a polygene scoring model for predicting the attack and progress risk of the IgA nephropathy. The model fully integrates the high-specificity SNP loci found in the invention, can be used for quantitatively evaluating the individual disease risk, predicting the disease progress trend and guiding clinical layered follow-up visit and individualized intervention, and has remarkable originality, scientificity and application value.

This invention relates to the fields of intelligent transportation and drone inspection technology, and provides a method and system for highway safety assessment based on drone inspection. The method includes the following steps: acquiring first-view data segments and second-view data segments of a preset road section; registering the first-view data segments with the second-view data segments to obtain a traffic flow map; extracting dynamic features of vehicle surface damage and static distribution features of road debris from the traffic flow map to obtain risk metadata including damage evolution trajectories and spatial coordinates of debris; predicting the structural stability attenuation coefficient of vehicles based on the damage evolution trajectory, and predicting the kinetic potential factor triggering secondary events based on the spatial coordinates of debris, to obtain a dynamic risk assessment result. This invention achieves a quantitative assessment of the dynamic deterioration trend of vehicle damage and the risk of road debris, significantly improving the intelligence level of highway inspection and the ability to prevent secondary accidents.