161 results about "Occurrence probability" patented technology

The invention relates to a renal transplantation post-operation rejection risk monitoring and early warning method and a renal transplantation post-operation rejection risk monitoring and early warning system. The method comprises the steps of collecting recipient nursing monitoring data, laboratory indexes and transplanted kidney ultrasonic blood flow parameters in a follow-up visit period, performing timestamp alignment, deletion processing and standardization on multi-source data, extracting features to construct a time sequence feature sequence, inputting the time sequence feature sequence into a pre-training risk prediction model, outputting the rejection reaction occurrence probability of the next period, and forming a risk trend. Calculating a nursing sensitive index contribution weight based on the model contribution information, and screening a target nursing monitoring index; and establishing an individualized baseline model to obtain a baseline value and an allowable fluctuation interval, extracting characteristics such as deviation amplitude, direction, rate, fluctuation and continuous deviation duration and the like, and performing individualized calibration on the occurrence probability to obtain a calibration risk score. When the threshold value is not reached and the trend is not triggered, generating a nursing monitoring suggestion of the next period; and pushing early warning and generating grading intervention suggestions when a threshold value is reached or a trend is triggered.

The invention relates to the technical field of resource scheduling, in particular to a digital-intelligent non-accompanying service management scheduling system, which comprises a service baseline construction module for instantiating a service item into a standard plan event flow; the state portrait generation module is used for collecting service object data flow, establishing a dynamic time sequence signal by applying a recurrent neural network model, and quantifying the occurrence probability of a future abnormal event through multi-step prediction; when the triggering is abnormal, executing causal two-way collision positioning reasons by applying the knowledge graph; the task load calculation module is used for integrating the plan event flow into a plan task component, and generating a worker resource list in combination with the predictive risk score and the worker real-time load and space reachability analysis containing the fatigue index; the system further comprises a task distribution module, the optimal staff is determined and a closed-loop scheduling instruction is generated by minimizing a composite cost function containing predictive load cost, and digital intelligent unattended service management from prediction to scheduling is realized.

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

The invention discloses a risk assessment method for a supercritical carbon dioxide conveying pipeline and related equipment, and the method comprises the steps: constructing a fault tree model for a failure event of the pipeline; obtaining a consequence event corresponding to the failure event, and constructing a consequence model according to the consequence event; based on the fault tree model and the consequence model, obtaining a bow-tie model of the supercritical carbon dioxide conveying pipeline; obtaining a plurality of groups of evaluation data of the plurality of evaluation policies for the basic event in the bow-tie model, and obtaining a failure probability corresponding to the basic event based on the plurality of groups of evaluation data; and obtaining an occurrence probability of a leakage consequence corresponding to the basic event based on the failure probability, and performing hazard assessment on the leakage consequence based on the occurrence probability to obtain an assessment result. According to the method, the occurrence frequency of consequences in various risk scenes is accurately calculated, the problem that the risk in the actual conveying process cannot be accurately reflected is avoided, and the design and implementation of subsequent risk management decisions and optimization measures can be effectively supported.

The invention provides an opencast coal mine VR safety training dynamic difficulty regulation and control method, which comprises the steps of collecting multi-dimensional interaction behavior data of a target student in a VR training scene in real time, and encoding the multi-dimensional interaction behavior data into a behavior vector sequence; inputting the behavior vector sequence into a pre-trained prediction model, and outputting a potential risk behavior and a risk occurrence probability; when the risk occurrence probability is higher than a preset threshold value, generating a risk event continuously caused by the potential risk behavior through a risk deduction model; dynamically generating a negative guide plot based on the risk event, and implanting the negative guide plot into the VR training scene; and dynamically adjusting a subsequent generation strategy of the negative guide plot according to a response result of the target student to the negative guide plot. The method has the technical effects of deeply understanding the behavior intention of the student, early predicting the potential risk and performing dynamic intervention.

The invention relates to the technical field of power system operation and control, in particular to a power system recovery capability evaluation method, device and equipment considering unconventional risks and a medium, and the method comprises the steps: determining parameters for calculating the occurrence probability of earthquake disasters of different earthquake magnitudes; calculating intensity distribution by using an earthquake intensity diffusion model; calculating transmission tower and transmission line fault probabilities to obtain a fault line set; according to the operation power flow and the maximum allowable power flow, the cascading failure situation is divided into high risk and low risk; aiming at the two conditions, respectively enumerating a first-order fault state set and a second-order fault state set to obtain a system recovery capability initial value; the value serves as input, a convergence threshold value is set, a ULBI-IISE algorithm is adopted for iterative calculation, when the difference value of the upper cut set and the lower complementary set is smaller than the threshold value, the recovery capacity and the interval are output, and the method reduces high-order fault complete enumeration and the calculation amount while guaranteeing the precision, and is suitable for rapid evaluation of emergency scenes such as earthquakes.

The invention discloses a port bulk cargo intelligent collaborative transport full-process safety control method and platform, and the method comprises the steps: building a digital twin model and an associated database of a port and equipment, and collecting multi-dimensional monitoring data; the risk identification deep neural network identifies suspected risks, and through verification of a preset rule, risk types and occurrence probabilities are determined; outputting the structured risk information; dynamically optimizing the original operation plan; mapping and driving the parameter change of the digital twinborn model, and inputting the preliminary scheduling instruction sequence for simulation verification and optimization to obtain a final scheduling instruction; uploading a storage certificate; according to the management and control method and platform, multi-dimensional monitoring data are fused and subjected to risk identification through cooperation of a deep neural network and a rule engine, the identification precision, reliability and accuracy are improved, a whole-process safe closed loop is achieved, a scheduling instruction is verified through a digital twin model, the accuracy and safety of decision making are guaranteed, and the management and control efficiency is improved. And the global job cooperation efficiency and the resource utilization rate are improved through multi-target dynamic optimization.

The invention belongs to the field of landslide early warning and risk management and control research, and particularly discloses a rainfall threshold value dynamic updating method for landslide early warning, which comprises the following steps: according to a regional landslide record and rainfall data, counting the occurrence probability of a landslide on a region; useful information in the real-time early warning record is extracted, the useful information comprises a plurality of rainfall parameters and whether the landslide is triggered or not, then sample marking is conducted on the early warning record according to whether the landslide is triggered or not, if the landslide occurs, the occurrence probability is marked as 100%, and if not, the occurrence probability is marked as 0%; taking the occurrence probability of the landslide on the region as pre-training data, fitting the relationship between rainfall parameters and the occurrence probability of the landslide through a machine learning model according to the occurrence probability of the landslide under a certain rainfall event in the slope, and dynamically updating a rainfall threshold value of the risk slope; according to the updated rainfall threshold value, landslide early warning is issued to the risk slope, and a new early warning record is generated. The method is high in early warning accuracy, and can meet the requirements of disaster prevention and reduction under the conditions of changeable climate and frequent earthquakes at present.

The invention discloses an industrial park micro-grid toughness planning method and system based on opportunity constraint, and relates to the technical field of power grid planning, and the method comprises the steps: building a combined scene pool containing scene weight according to the extreme strength probability of risk factors in a historical scene based on the coupling and association failure of multiple risk factors; constructing a pre-disaster protection planning layer according to opportunity constraints and protection dimensions; constructing a post-disaster recovery planning layer by using a staged recovery mechanism and an emergency operation mode; constructing an optimization objective function by minimizing the protection cost and the recovery cost; constructing a dual-stage planning model by using the pre-disaster protection planning layer, the post-disaster recovery planning layer and the optimization objective function; and matching the current triggering scene and the occurrence probability according to the real-time industrial park micro-grid operation data and the combined scene pool, inputting the current triggering scene and the occurrence probability into the double-stage planning model, and generating a tough protection planning strategy. The method has the beneficial effects that the protection planning strategy gives consideration to the toughness requirement and disaster recovery requirement of the micro-grid under the extreme event.

This application discloses a method for predicting the probability of myopia occurrence in adolescents and related products. When implementing the method provided in the embodiments of this application, firstly, multidimensional prediction parameters such as race, gender, age, equivalent spherical power, and genetic characteristics are collected, and the validity of the parameters is verified. Then, a hash matching algorithm is used to retrieve a pre-built myopia risk prediction dictionary, matching corresponding data entries, thereby outputting the probability of myopia occurrence, risk level, risk interpretation, and prevention and control guidance for one and two years, supporting bilingual display, completing the entire process of quantitative prediction of myopia risk in adolescents. This application avoids human judgment bias through automated prediction, quantifies the probability of myopia occurrence and risk level in two cycles of one and two years, dynamically predicts the onset window period, and improves the limitations of traditional static prediction. Furthermore, the prediction results support bilingual presentation and have both prevention and control guidance and popular science functions.

This application provides a multi-intent prediction model training method and a multi-intent recommendation method, relating to the field of artificial intelligence technology. The multi-intent prediction model training method locates multiple target candidate intents of users to the dimension of target scene, constructs a unified sample for multiple target candidate intents in the target scene, and trains a model using the unified sample. The resulting model can predict the probability of occurrence of multiple target candidate intents in this target scene. It eliminates the need to construct samples separately for each target candidate intent and train the model separately using the constructed samples, thereby avoiding repetitive sampling operations for different intents at the same sampling time, and avoiding multiple model trainings, which can save manpower and resources and reduce costs.

The application discloses a kind of stable control system strategy adaptability risk assessment method, it is related to power system safety and stability control technical field.The method includes: processing new energy historical output data and establishing time sequence correlation model, generating partition scene set;Accordingly generate multiple risk working condition sample, determine key feature vector set by transient simulation, feature extraction and dimension reduction;Scene clustering reduction is obtained to strategy scene set containing probability weight;Enumerate fault chain sequence, execute time sequence simulation to three-layer stable control strategy;Calculate multiple risk indexes to construct multidimensional matrix;Combined with new energy power time-varying quantile fluctuation band, the risk value and occurrence probability are identified and classified using fuzzy comprehensive judgment, and the comprehensive evaluation conclusion is output.The application can accurately depict the time sequence fluctuation characteristics of new energy, realize stable control strategy full-link assessment and risk form differentiation control, and provide support for power grid safety decision-making.

The invention discloses an event prediction method and system based on a time sequence hypergraph, and belongs to the technical field of event prediction. The method comprises the following steps: acquiring multi-source heterogeneous data of a target region, defining a unified time index, and generating a time sequence feature sequence of each variable of the region through preprocessing; then, identifying a variable causal relationship in the region based on a frequency domain anti-fact condition mutual information algorithm, and fusing the variable causal relationship with a time sequence evolution relationship to construct a time sequence hypergraph structure representing the interior of the region; a dynamic filter is used for filtering the graph, and deep features of the graph are learned by means of a multi-band spectrum gating mechanism, so that internal complex causal and time sequence modes are effectively captured; and finally, performing dichotomy prediction based on the learned graph representation, and outputting the occurrence probability of future events in the region. According to the method, accurate and explainable event prediction is realized, training and prediction do not need to cross regions, data privacy and calculation efficiency are guaranteed, and stronger robustness is shown for specific data distribution change of the regions.

An object of the present disclosure is to predict an occurrence probability of a violation with high accuracy.Therefore, content of the present disclosure is a violation prediction apparatus that predicts an occurrence probability of a violation, and is configured to: evaluate conversation data that includes conversation partner information for identifying a partner of a conversation and indicates a conversation content and a conversation situation, thereby obtaining a conversation content evaluation value and a conversation situation evaluation value; evaluate a relationship with the partner of the conversation based on relationship data that indicates a human relationship with a target user and on the conversation partner information, thereby obtaining a relationship evaluation value; calculate a social interaction effect based on the conversation content evaluation value, the conversation situation evaluation value, and the relationship evaluation value; calculate a time attenuation value of the social interaction effect based on a time attenuation function; and calculate an occurrence probability of a violation.

This disclosure provides a method and apparatus for predicting human-machine conflict, capable of proactively predicting human-machine conflict from multiple dimensions. By acquiring and analyzing various physiological and behavioral data of operators in historical human-machine interaction scenarios, significant characterization factors corresponding to fatigue states are screened, enabling a more accurate quantitative representation of operator status. Simultaneously, the significant characterization factors of operators are combined with environmental and machine characteristic dimensions (including the complexity of interface interaction) to establish a human-machine conflict prediction model suitable for the target scenario. This method can dynamically reflect changes in multiple factors during system operation, proactively predicting the probability of human-machine conflict occurrence, thereby improving the comprehensiveness, timeliness, and reliability of identification, avoiding lag and bias caused by single data or rules, and ultimately contributing to improving the safety and stability of complex human-machine systems.

The application relates to the technical field of artificial intelligence, in particular to a label recommendation method and device, a label recommendation model training method and a medium, wherein the method comprises the following steps: obtaining a reference label and at least two candidate labels; determining semantic similarity between the reference label and the candidate labels; determining co-occurrence probability between the reference label and the candidate labels, the co-occurrence probability being used for describing the probability that the reference label and the candidate label belong to the same label of multimedia data; and selecting a target label from the at least two candidate labels according to the semantic similarity and the co-occurrence probability. Since the semantic similarity represents the semantic similarity of the labels and the co-occurrence probability represents the probability that the labels appear in the same multimedia data, the target label obtained based on the semantic similarity and the co-occurrence probability is more consistent with the distribution assumption of the multimedia data, so that the obtained target label is more accurate.

The invention belongs to the technical field of industrial safety monitoring, and particularly relates to a risk situation monitoring model, method and system. The risk situation monitoring method comprises the steps that the occurrence state of each initial event and the operation states of preventive protection measures and remission protection measures are collected; determining the access probability of a single event evolution link according to the occurrence state of the single initial event and the running state of the preventive protection measure, and determining the access probability of a single accident evolution link according to the access probability of the single event evolution link and the running state of the remission protection measure; determining the occurrence probability of the top event according to the access probability of the plurality of event evolution links; and determining the occurrence probability of a single accident consequence according to the occurrence probability of the top event and the operation state of the remission protection measure. According to the method, the occurrence probability of a certain accident consequence under the condition is calculated by considering the condition that a plurality of initial events exist, so that the method is closer to the actual industrial operation condition.

Embodiments of the present application disclose an article topic extraction method, device, equipment, storage medium and processor. The article topic extraction method comprises two stages: 1) full amount calculation: extracting keywords from multiple articles, each article comprising multiple keywords; for each article, determining at least one associated combination according to the multiple keywords corresponding to the article, the associated combination comprising at least two keywords; determining the occurrence probability of each associated combination according to the number of each associated combination; 2) target article mapping: determining the topic of a target article according to the occurrence probability of each associated combination and the associated combination corresponding to the target article, wherein the target article is one of the multiple articles. Through the present application, the technical problem of poor accuracy of article topic determination in the process of article topic extraction in the related art is solved.

The application discloses a kind of nuclear power plant operation event trend analysis and prediction method and device, for the accuracy of existing statistical analysis method is insufficient in complex nuclear power environment, lack of multivariate nonlinear consideration and real-time analysis capability is short of etc., the application fuses deep learning and big data analysis technology, realizes event trend identification and high-risk area prediction.It includes: collecting operation log, sensor data and other multi-source event data, is stored after cleaning, standardization preprocessing;Extract the key features of event occurrence time, type, severity, etc., and construct a feature set;Through the analysis of time series data based on standardized event data extraction multi-LSTM based on standardized event data extraction multi-neural network model, identify long-term trends and periodic changes;Combined with deep learning and regression analysis, predict the probability of event occurrence and severity, locate high-risk period and area;Generate real-time warning information and provide prevention suggestions.

Based on an initial probability of occurrence of a random defect within a layout of a workpiece, a subset of locations on the workpiece at which the initial probability is above a threshold is selected. The subset of locations is grouped in a pattern shape. An expected defect count is determined for each of the pattern shapes. A subset of the pattern shapes is then selected for repair.

The invention belongs to the technical field of oil and gas exploration and development, and relates to an accident early warning method and system for an FPSO mooring system under an extreme weather condition, and the method comprises the steps: building an accident scene library according to extreme weather data; grading accidents in the accident scene library according to expert opinions; fusing the expert opinions through a fuzzy mathematical method to obtain the weight of each expert opinion; combining expert opinions with the weights to obtain an accident prediction result of the key nodes of the FPSO mooring system; and inputting the time-varying extreme weather condition data and the key node accident prediction result into a dynamic Bayesian network model to obtain an accident early warning result of the FPSO mooring system. Accident occurrence probability calculation and accident early warning of the whole mooring system, subsystems and equipment units under the extreme weather condition are achieved, and data support is provided for field emergency protection.

The application discloses a data compression method, system, device and computer readable storage medium, obtains target data to be compressed; statistics the total number of bytes in the target data and the occurrence probability of each type of character; determine the target linear function of the function x*log2(x) under the preset approximation condition; determine the information entropy operation formula without logarithm operation based on the target linear function; calculate the target information entropy of the target data based on the total number of bytes and the occurrence probability through the information entropy operation formula; judge whether the target information entropy is less than the preset value, if the target information entropy is less than the preset value, compress the target data, if the target information entropy is greater than or equal to the preset value, do not compress the target data. In the application, the function x*log2(x) is converted into the target linear function without logarithm operation, so that the information entropy operation formula without logarithm operation can be determined based on the target linear function, the calculation efficiency of the target information entropy is improved, and the data compression efficiency can be improved.

The invention relates to a safety management system and method for a bridge construction site, and the system achieves the real-time collection of multi-dimensional data, such as a structure state, an environment state, a personnel position, and a mechanical equipment state, breaks through the limitation of the conventional single-dimensional monitoring, achieves the comprehensive and real-time sensing of related safety factors of the construction site, and improves the safety of the construction site. The defects that manual inspection coverage is incomplete, and hidden risks are prone to being missed are effectively overcome. The multi-source data is subjected to fusion analysis by means of the processing module, potential correlation among factors such as structures, environments, personnel and equipment can be deeply mined, composite risks which are difficult to find by traditional isolated data can be accurately recognized, the comprehensiveness of risk recognition and the perspectiveness of pre-judgment are improved, and the problem of risk lag caused by subjective judgment depending on experience is avoided. The real-time performance and accuracy of safety management and control of the bridge construction site are effectively improved, the accident occurrence probability is reduced, and the safety of constructors and orderly proceeding of engineering construction are guaranteed.

Proposed is a method and device for analyzing battlefield threat based on a dynamic graph neural network. The method may include classifying a behavior at a specific time point for a plurality of objects in a battlefield based on battlefield information received from the outside. The method may also include predicting a threat occurrence probability between the plurality of objects according to the classified behavior. The method may further include generating and outputting a battlefield threat analysis result including the classified behavior and the threat occurrence probability.

The application discloses a kind of multi-stage system task reliability modeling evaluation methods considering complex dynamic characteristics, belong to system reliability modeling and evaluation technical field, including: according to the structure of system component unit, function principle and task flow, establish system function model and stage model;Based on the finite state machine with constraint, the state-transition model of each structure component unit is established respectively;According to the task activity of each stage and the success and failure criterion of task, the task flow model of system in the corresponding stage is constructed;Integrate the above steps, obtain the reliability model of multi-stage task, carry out task reliability simulation, calculate the occurrence probability of the structure component unit state or structure component unit state combination concerned.This application guarantees the efficient and stable operation of complex dynamic multi-stage system.

The invention belongs to the technical field of low-altitude flight control, and discloses a low-altitude task allocation method and device and a medium, and the method comprises the steps: obtaining and storing a historical operation characteristic parameter set of an airspace operation unit containing a task interruption occurrence frequency, a post-interruption associated abnormality occurrence probability and a system influence degree index; obtaining association relationship information of tasks to be distributed, and calculating failure propagation sensitivity parameters of the tasks to be distributed; screening candidate airspace operation units according to basic operation requirements of tasks and acquiring characteristic parameter sets of the candidate airspace operation units; then calculating a combined risk value of the task and the candidate airspace, and determining that the unit with the combined risk value lower than a preset threshold value is a suitable allocation unit; and finally, determining a final execution airspace based on the combined risk value of the suitable allocation unit. According to the method, accurate matching of the task and the airspace is realized, the low-altitude operation cascade failure risk is effectively reduced, and the system operation stability and the airspace resource utilization rate are improved.

The invention discloses a ground disaster early warning method, system and device, a storage medium and a program product, and belongs to the technical field of geological disaster early warning, the method comprises the steps that multi-modal time sequence data of a target monitoring area is acquired in real time and preprocessed, and the multi-modal time sequence data comprises ground disaster environment data, image data and meteorological data; the preprocessed multi-modal time series data are input into a pre-trained ground disaster prediction model, the ground disaster prediction model carries out multi-modal feature fusion on the multi-modal time series data and dynamically adjusts the space-time weight, and the disaster risk probability in the target monitoring area is output; and triggering a corresponding disaster early warning or checking action according to the disaster risk probability. According to the invention, the occurrence probability of the geological disaster can be accurately predicted, and accurate prediction of the geological disaster is realized.

The present application relates to the technical field of resource scheduling, in particular to a digital intelligent unaccompanied service management scheduling system, comprising: a service baseline construction module, which instantiates service items into standard plan event streams; a state portrait generation module, which collects service object data streams, applies a recurrent neural network model to establish dynamic time series signals, and quantifies the occurrence probability of future abnormal events through multi-step prediction; when an abnormality is triggered, a knowledge graph is applied to perform bidirectional collision positioning of causes; a task load calculation module integrates the plan event streams into plan task components, combines the predictive risk score, and further combines the real-time load of staff containing a fatigue index and spatial accessibility analysis to generate a staff resource list; the system further comprises a task allocation module, which determines the optimal staff and generates closed-loop scheduling instructions by minimizing a composite cost function containing a predictive load cost, thereby realizing digital intelligent unaccompanied service management from prediction to scheduling.

This invention discloses a method and system for calculating spare parts demand in subway operation and maintenance based on health status prediction, belonging to the field of intelligent operation and maintenance technology. The method includes: generating a failure probability distribution based on component health prediction; simulating concurrent failure scenarios and their probabilities of occurrence through sampling; constructing a virtual spare parts space; calculating train operation value entropy based on real-time operation data to determine resource allocation priorities; simulating high-value priority resource allocation within the virtual space; calculating competition penalty factors to derive collaborative spare parts demand under a single scenario; constructing a macroscopic time-varying demand field by combining scenario occurrence probabilities and single-scenario demands; performing time-domain rolling optimization under dynamic window constraints; and finally outputting an adaptive dynamic spare parts demand list. This achieves an intelligent scheduling closed loop from underlying probability prediction to global dynamic optimization.

The invention discloses an elevator intelligent maintenance method and device based on DGConv and an improved CBAM attention mechanism, and the method comprises the steps: firstly obtaining fault-related continuous data and discrete data based on an elevator mainboard, carrying out the data length alignment of the continuous data through dynamic time warping, and combining with the discrete data to construct an elevator fault prediction data set; then, constructing a CNN-Transform hybrid neural network of cavity global convolution and an improved CBAM attention mechanism for predicting the occurrence probability of various faults at the next moment, and performing training based on an elevator fault prediction data set; and finally, fault maintenance priorities are allocated to different faults according to the fault probabilities, and a targeted intelligent maintenance strategy is generated. The method provided by the invention has a remarkable effect in intelligent maintenance of the elevator, can greatly reduce the manpower and material resource overhead of a traditional maintenance method, saves the maintenance time, and optimizes the maintenance strategy.