462 results about "Risk probability" patented technology

The present invention provides processes for determining accurate risk probabilities for fetal aneuploidies. Specifically, the invention provides non-invasive evaluation of genomic variations through chromosome-selective sequencing and non-host fraction data analysis of maternal samples.

The invention relates to the technical field of mobile robot autonomous navigation and discloses a service mobile robot navigation method in a dynamic environment. The service mobile robot navigation method in the dynamic environment includes the following steps that firstly, position tracking of people can be achieved by utilizing multiple global cameras and robot vehicle-mounted laser sensors in an indoor environment; secondly, the moving mode of people under a specific indoor environment site is trained according to collected samples, and the moving trend of people is predicated; thirdly, a current position and a predicated position of people are merged with an environment static obstacle raster map, and a navigation risk probability map is generated; fourthly, a robot navigation movement controller of a global route planning-local obstacle avoidance control gradational structure is adopted to control robot navigation behavior, and safe and efficient navigation behavior of a robot under a complex dynamic environment where the robot coexists with people is ensured through controlling.

The present invention provides processes for determining accurate risk probabilities for chromosome dosage abnormalities. Specifically, the invention provides non-invasive evaluation of genomic variations through chromosome-selective sequencing and non-host fraction data analysis of maternal samples.

The invention provides a rule engine-based method and a rule engine-based system for monitoring exceptional service of bank. The method mainly comprises the followings steps: defining and describing operational risk factors of bank service flows, products and service units; determining a lost data and risk data collecting frame to analyze important lost data to determine a cause-and-effect relationship between loss events and risk factors; determining a key risk indicator (KPI); measuring a possible loss amount and a risk probability; measuring the effectiveness of the current management and control method, and making a more effective management and control scheme; deciding and implementing an efficiency and phase equilibrium-based management and control system; and effectively monitoring risk early warning indexes, risk reports aiming at senior management and the risk management and control method. Operational risks of commercial banks are comprehensively monitored, and risks are ensured to be controlled. The system is divided according to logical levels and comprises a service data layer, a data acquisition layer, a data storage layer, a risk processing layer, a risk management layer and an information presentation layer.

The present invention provides processes for determining accurate risk probabilities for chromosome dosage abnormalities. Specifically, the invention provides non-invasive evaluation of genomic variations through chromosome-selective sequencing and non-host fraction data analysis of maternal samples.

The invention relates to an active-passive combined reactor core residual heat removal system for a nuclear power station. The active-passive combined reactor core residual heat removal system comprises a safety injection system, a containment spraying system, an auxiliary water supply system, a reactor cavity water injection system, a secondary side passive residual heat removal system, a passive containment heat leading-out system and related valves and pipelines. The active-passive combined reactor core residual heat removal system provided by the invention realizes three safety functions of controlling reactivity, discharging reactor core heat and containing radioactive substance when an accident occurs in an active-passive combined multi-redundancy diversity manner. The active-passive combined reactor core residual heat removal system provided by the invention can completely realize the safety functions of safety injection and safety spraying under the condition that the accident occurs in a nuclear power plant, reactor cavity water injection under the serious accident working condition and the like, effectively improve reliability of a safety system, enhance coping capability of the safety system under the working condition that the accident occurs in the nuclear power station, can effectively prevent and relieve the serious accident, reduce the reactor core melting probability and risk probability of large-scale radioactivity release and greatly improve safety performance of the nuclear power station.

The invention relates to a method for predicting dynamic risk and vulnerability at fine scale and belongs to the scientific field of global information. The method is mainly characterized in that an optimized Bayesian network is searched from multi-source heterogeneous spatiotemporal data on the basis of a grid format with certain resolution at fine scale; domain knowledge is combined to improve the network; therefore, the uncertain estimation of disaster risk and the vulnerability, namely probability estimation, is carried out. In the method, a nuclear density method is put forward to train a sample according to a sample derivative grid; an optimized discretization method is put forward to discretize continuous variables so as to provide discrete state space input for the network; a simulated annealing optimization algorithm is adopted to search an optimized network structure; and a method of accurate reasoning combined with approximate reasoning to predict the probabilities of risk and the vulnerability is adopted. The method provided by the invention can position the positions of the disaster risk and the vulnerability in real time at the fine spatial scale, estimate the spatial distribution of the risk probability and has important theoretical significance and practical value for improving the effects on the reduction and relief of disaster and building an intelligent public emergency pre-warning system by the state.

The invention belongs to a risk evaluation method for the operation of a large power grid. The method comprises the following steps of (1) statistics of fault and risk factors; (2) computation of risk probability; (3) risk quantitative evaluation based on the load loss; (4) classification and result evaluation on risk index. According to the risk evaluation method for the operation of the large power grid, the occurring probability of power system accidents and the number of load loss of the system are combined to form a new quantitative index, so a scheduling person can be helped to perform real-time risk evaluation and analysis, can further comprehensively master the safe operation condition of the power grid, and controls the risk level of the system within a reasonable range by adopting necessary measures, and the occurrence of the disaster fault is avoided. The real-time evaluation and management and control on the risk are realized by a power gird scheduling center and the method belongs to a load loss-based risk evaluation method for the operation of the large power grid.

A training method and apparatus for a fraud detection model and a fraud detection method and apparatus are provided. That method and apparatus include obtaining historical operation behavior information of a plurality of sample users in a first historical period and a second historical period, and labeling information of whether a fraud behavior of the sample user occurs in a second historical period; generating a behavior feature vector sequence corresponding to each service scenario for the sample user in a plurality of service scenarios; the behavioral eigenvector sequence is input into theloop neural network to generate the behavioral coding vector. After the behavior coding vectors corresponding to each service scenario are spliced, the classification neural network is inputted to obtain the fraud risk probability. Based on the fraud risk probability and labeling information, the circular neural network and classification neural network are trained to obtain the fraud detection model. The present application can improve the accuracy of judging whether or not the user operation behavior occurring when the user uses the electronic banking is a fraudulent behavior.

The invention discloses a credit score establishing method based on a machine learning and big data technology. The method is characterized by specifically including the following steps of establishing unified user ID of credit and loan subjects, extracting and preprocessing data of the credit and loan subjects with the unified user ID to obtain training sample data, establishing a credit risk model through a machine learning classification algorithm-integration tree model, obtaining the risk probability according to the credit risk model, automatically converting the risk probability into a credit risk score. The efficient and accacute integration and fusion of global multidimensional big data of the credit and loan subjects are realized through an ID-Mapping technology, the global data of the credit and loan subjects is provided for the establishment of the credit risk model, the quantitative credit risk analysis is conducted on the credit and loan subjects through the machine learning and big data technology on the basis, and therefore the financial risk management capacity is improved and the credit and loan risks are reduced.

The invention discloses a safety management method based on dynamic quantitative accident risk prediction, and the method comprises the following steps: an accident predicting platform is provided, and a basic event dynamic predicting model and an accident analyzing model are established; the accident predicting platform detects state information of production units in real time, and failure information is obtained; then the basic event dynamic predicting model predicts the failure information to obtain basic event dynamic probability; then the accident analyzing model calculates the basic event dynamic probability to obtain the current accident risk probability of the production unit; then the current accident risk probability and a preset risk probability control criterion are compared, if the accident risk probability is more than the risk probability control criterion, a preset emergency plan is started to assist an executor to tackle the accident; if not, a preset standard working flow is started, and a warning message is emitted so that the executor can correct a mistake. The method and the system can reflect the influence of dangerous factor change on probability dangers in real time, thus really realizing the safety management idea of prevention first.

The invention relates to a security risk assessment and early warning method for a high-speed railway tunnel during operation period. The method comprises the first step of constructing an evaluationbasis, including a risk rating assessment standard, an evaluation index system and an early warning mechanism establishment: the risk rating assessment standard includes a risk possibility assessmentstandard and a risk consequence severity rating assessment standard. The risk rating assessment is based on the risk probability rating as the ordinate, and the risk consequence severity rating as theabscissa to construct a risk assessment matrix. The evaluation index system is established by the hazard factors of the four aspects of "human- things-management-environment ", and constructs the risk probability membership function of the hazard factors. The early warning mechanism is established by four-color early warning. The second step of risk rating assessment is quantitatively calculatedbased on the membership function and the second-level fuzzy comprehensive evaluation model, and conducted combining the risk consequence severity rating assessment standard and the risk rating assessment matrix. The third step of determining the early warning rating: obtained by coupling the superposition analysis risk rating and the early warning indicator risk rating. The beneficial effects of the security risk assessment and early warning method for a high-speed railway tunnel during operation period are that the evaluation results are quantified, and the decision is based on science.

The invention relates to a risk-constrained oil and gas resource spatial distribution forecasting method which comprises the following steps of: (1) integrating seismic information and geologic information; (2) forecasting the exploration risk probability of a entire region; (3) establishing a resource abundance diagram of the discovered oil and gas accumulation; (4) establishing a resource abundance amplitude diagram and a resource abundance phase diagram; (5) establishing a modified resource abundance amplitude diagram; (6) establishing a risk probability amplitude diagram and a risk probability phase diagram; (7) establishing a forecast oil and gas resource abundance distribution diagram of the entire region; and (8) calculating the resource quantities of different risk regions: excluding the oil and gas accumulation with low abundance; excluding grid data points with high exploration risk; and verifying and modifying according to the data of the explored wells. The method can forecast the resource quantities in different risk regions and the spatial distribution positions of the remained oil and gas resources. A forecasting model and the method have strong operability. The invention can enhance the drilling decision level and the oil and gas exploration efficiency.

The invention relates to a security processor for fault-tolerant in a railway signal system. The security processor includes a hardware platform and a software architecture, wherein the hardware platform comprises an operation platform with double CPUs, and information is shared by the double CPUs through a double-port RAM; the security input implements the security collection of the same input signal by adopting independent and dissimilar design modes for two channels; the security output monitors the status of an output port of the system to ensure the security of the system output by adopting a retraced-collection mode; and the system security is guaranteed by generated check words, which are transmitted to a security monitor board by the CPUs, the security monitor board provides the electric power for an output board when the security monitor receives the correct security check words, otherwise the security monitor cuts off the power supply to the output board, thereby achieving fault-safety. Compared with the prior art, the invention can implement security protection for an onboard ATP during the calculating process, so that the risk probability of malfunction is lower than the design requirement of the system, and the operational security of the system is further ensured.

The invention discloses an analysis system and an evaluation method for power telecommunication business risks. The analysis system comprises a business impact analysis unit, a risk probability analysis unit and a communication risk evaluation unit. The business impact analysis unit is used for quantitatively assigning values for different types of power telecommunication network management businesses according to importance degrees and social impact effects of the businesses. The risk probability analysis unit is used for analyzing channel organization factor, route association factor, history data statistics factor and channel risk factor, and determining a probability value of each factor. The communication risk evaluation unit is connected with the business impact analysis unit and the risk probability analysis unit, and is used for obtaining a risk value of a power telecommunication business according to the quantitatively assigned value and the probability value. Various factors impacting the power telecommunication network communication business risks are comprehensively considered, so that the risk warning and evaluating index system of the power telecommunication network is more stable, more reliable, and applicable to making determination to achieve an effective warning result.

The present invention relates to accident probability evaluation, particularly provides a Bayesian network model based risk evaluation method for a road transportation accident, and aims to solve the problem that the influence of superposition and counteraction among root node factors on a final evaluation result is not considered in an existing method. For the purpose, the method comprises: acquiring factors related to the road transportation accident; constructing a Bayesian network model of the road transportation accident according to the factors; and estimating a risk probability of the road transportation accident according to the Bayesian network model. The method is characterized in that the Bayesian network model has a three-layer network structure, and the method evaluates the probability of an intermediate node according to the probability of a root node and evaluates the risk probability of the road transportation accident according to the probability of the intermediate node. According to the method, superposition and / or counteraction effects among the factors of the root node are considered when the Bayesian network model is constructed, so that the accuracy of final evaluation can be greatly improved.

The invention discloses a risk assessment based intelligent navigation method and device, equipment and a storage medium. The risk assessment based intelligent navigation method includes acquiring a route and navigation request sent from a client side, acquiring multiple original navigation routes according to starting location and target location of the route navigation, further acquiring to-be-assessed traffic data corresponding to each navigation route, performing rick assessment on the to-be-assessed traffic data corresponding to each navigation route through a road rick identification model trained in advance to acquire section risk probability of the corresponding road sections, acquiring the total risk probability corresponding to the original navigation routes according to the section risk probability of at least one corresponding navigation road section of each original navigation route, and finally determining the original navigation route with the lowest total risk probability as a recommended navigation route and sending the recommended navigation route to the client side. The risk assessment based intelligent navigation method can realize route planning based on safetyfactors, thereby guaranteeing safety in driving.

The embodiment of the invention provides a method and device for determining the risk probability of a service request event. The method comprises the steps that an event characteristic of the servicerequest event is acquired, and a user personal characteristic of a user related to the service request event is acquired; based on a crowd relation map of specific crowd containing the related user,a relation characteristic of the related user is determined; therefore, based on the event characteristic, the user personal characteristic and the user relation characteristic, the risk probability of the service request event is determined. In this way, the risk of the service request event can be comprehensively evaluated.

A vehicle driving behavior analysis big data public service platform used in the Internet+ age is used for analyzing vehicle driving behaviors and automobile running risk probability and comprises the steps that step one, automobile running data within a period of time is stored through the big data platform, and a MapReduce frame is adopted to process and analyze the data; step two, abnormal automobile driving times in a certain area and within a time period are counted after data processing based on the big data platform, including overspeed, overloading, rapid acceleration, fatigue driving and night driving; step three, a self-organizing mapping neural network algorithm is utilized to calculate the vehicle risk probability and predict the follow-up vehicle running risk after abnormal automobile driving behavior statistics. The vehicle driving behavior analysis big data public service platform preprocesses acquired data by acquiring Beidou / GPS navigation data of a vehicle, further mines the data and can analyze and judge driving behaviors of a driver.

The invention discloses a difference self-healing control method based on device failure probability and power grid operation risks. The difference self-healing control method includes the steps: 1 acquiring operation data and weather data, and calculating comprehensive failure probability corresponding to power distribution network devices; 2 determining risk threshold values; 3 judging whether the comprehensive failure probability exceeds the risk threshold values corresponding to the power distribution network devices or not, optimizing power grid operation modes based on first multi-objective functions if the comprehensive failure probability exceeds the risk threshold values corresponding to the power distribution network devices, optimizing the power grid operation modes based on second multi-objective functions if not, and setting priorities of the power grid operation modes; 4 forecasting loads of power grids next moment based on a multi-classification regression tree algorithm, and calculating comprehensive stoppage probability and comprehensive risk probability of devices in the next moment; 5 determining whether optimization measures are executed or not. According to the method, the device failure probability and the power grid operation risks are fully considered, economical and reliable operation of the power grids is achieved by difference self-healing control without rejecting loads as far as possible.

The invention discloses an illness risk value prediction method and electronic equipment and is applied to hypertension analysis. The method comprises steps that static data and dynamic data of usersare acquired; the acquired static data and the dynamic data of the users are pre-processed; a dynamic early warning model is constructed through logistic regression and a dynamic vector machine; according to the pre-processed data, the dynamic early warning model is utilized to classify the users; according to classification of the users, corresponding risk values are calculated; the risk values stand for the hypertension risk of the users. The method is advantaged in that a dual-data system is employed, through improved logistic regression and the dynamic vector machine, the chronic illness risk dynamic hybrid early warning model is established, and the accurate illness risk probability value is provided.

The invention discloses an intelligent suspicious transaction monitoring method based on a semi-supervised graph neural network. The method comprises the steps of collecting and storing original transaction flow; constructing a fund transaction network based on a transaction relationship at the account level; dividing accounts in the fund transaction network into different transaction communities;performing risk assessment and screening on the transaction community to generate a high-risk-density fund transaction network; deriving individual transaction characteristics of the account; and inputting the individual transaction characteristics of the high-risk-density fund transaction network and the account into a semi-supervised graph neural network, outputting the fund transaction risk probability of the account by the semi-supervised graph neural network, and judging the account of which the fund transaction risk probability is higher than a first threshold value as a high-money laundering risk account. The method has the advantages that the abnormal risk of an individual account can be judged, an advanced semi-supervised classification model is constructed through deep data mining and graph algorithm mining, and a traditional risk control means can be remarkably improved.

A new business method involving the algorithmic use of data from a wide variety of sources to provide the actuarial information needed to accurately assess the exposure liability and risk probabilities associated with the performance of any specific medical (or other) procedure or service. The major factors include, but are not necessarily limited to, 1) the procedure, 2) the physician or individual, 3) the patient (procedure recipient), and 4) regional or geographic considerations. In the case of medical procedures, an algorithmic actuarial determination of a per-procedure, one-time application insurance policy specific to the procedure, physician, patient, and location of region (e.g., state, county, city, etc.), as well as any additional risk factors which my be applicable.

The invention discloses a data evaluation method and device. The method comprises steps that a data grade evaluation request of a target object is received; risk evaluation for the data grade evaluation request is carried out according to a pre-stored data grade model to acquire risk probability and a default generation loss rate corresponding to the target object; evaluation is carried out according to the risk probability and the default generation loss rate to acquire a data grade corresponding to the target object. The method is advantaged in that a technical problem of low data estimation precision caused by defects of user loan quota estimation based on experience and subjective expert determination in the prior art is solved.

The invention discloses a tunnel risk evaluation method based on a fuzzy polymorphic Bayesian network. The invention provides an investigation method combining a confidence index, a weight index and aprobability interval based on expert judgment. According to the method, a tunnel risk accident tree is constructed according to an existing tunnel accident case, a basic event of a tunnel risk accident and the occurrence probability of each factor under the current technical level are obtained, and a polymorphic Bayesian network is constructed by the accident tree. The probability obtained by expert investigation and the probability obtained by case accidents are processed by a subjective and objective method to obtain a conditional probability, so that a polymorphic fuzzy Bayesian network conditional probability construction method and a tunnel risk probability calculation method are provided. According to the method, the subjectivity of risk factor identification can be reduced, the risk prediction accuracy is improved, informatization management and whole-process dynamic evaluation of underground engineering construction are realized, and the construction safety is ensured.

The present invention discloses a public area crowd gathering early warning method and system based on risk probability evaluation. The method comprises that: images are collected in real time from anintelligent monitoring device and measurable parameters of the crowd are obtained from the image stream; a center master server builds a four-level early warning model based on the measurable parameter values of the crowd and a two-dimensional risk matrix; and based on the model, analysis is carried out through the input measurable parameters of the crowd, and the automatic alarm is issued basedon the prediction results. The method and system disclosed by the present invention are based on real-time determination and prediction, dynamically analyze and warn the crowd flow and other states, collect statistics of, analyze, and evaluate the measurable parameters of the crowd to form a risk probability evaluation result, and further generate corresponding early warning information; and the method and system has good real-time performance and high predictive accuracy, can provide warning as early as possible to minimize the occurrence of dangerous situations, and is suitable for airports,large transport hubs, and other regional facilities with large crowd mobility and high degree of crowdedness, so that public safety can be improved, and the loss of people and property can be effectively reduced.

A regeneration water factory effluent residual chorine risk prediction method comprises: data monitoring and collection are performed so that an index monitored and collected is obtained; the data is transmitted to a server through a communication system; effluent residual chorine risk prediction, analysis and decision are performed by the server according to the collected data: the corresponding monitoring data stored in a data base of the server is read, the monitoring data is input in a water quality model and the effluent residual chorine risk prediction of technology is performed; the index influencing effluent residual chorine risk probability is judged according to a potential of hydrogen (pH) value, the water temperature, ammonia concentration and chemical oxygen demand distribution situation monitored under different risk probabilities; and solutions under different effluent residual chorine risk probabilities are made. The regeneration water factory effluent residual chorine risk prediction method is good in model prediction accuracy (the accuracy is higher than 95%) so that when facing water quality change, a researcher can predict effluent residual chlorine risk accurately in time. The regeneration water factory effluent residual chorine risk prediction method offers a certain reference to operation and management of an actual water factory.

The embodiments of the invention disclose a charging method and a server of a risk control system. According to one embodiment, the charging method of a risk control system comprises the following step: a risk control system server gets current transaction data from an e-commerce platform server; the risk control system server calculates the risk probability of the current transaction by use of the current transaction data and based on big data; the risk control system server feeds the risk probability back to the e-commerce platform server; the risk control system server receives the result of the current transaction sent by the e-commerce platform server; and the risk control system server determines the amount of commission according to the current transaction result and the risk probability. According to the embodiment, the current transaction result and the risk probability given before can be considered in determination of the amount of commission, and the pricing mode is more reasonable.

The invention discloses a computation method of maximum longitudinal flight conflict risk of airport airspace, belonging to the field of flight safety analysis of airport airspace aircrafts. The method comprises the following steps of: firstly constructing a combined simulation platform of airport terminal area airspace to be estimated and the ground; acquiring annual takeoff and landing fight data, and predicting the annual flight flow of takeoff and landing fights in the airport airspace in an estimation year; analyzing time and space distribution characteristics of the traffic flow of the airport airspace to obtain an average daily maximum hour flow; and finally calculating the risk probability of the maximum longitudinal flight conflict according to the probability of the violation ofthe longitudinal flight safety interval standard of the terminal area airspace. The invention provides data support for airport airspace safe operation analysis and promotes the construction of the airport terminal area airspace.

The invention discloses a same-tower multi-loop transmission circuit risk probability assessment method, comprising the following steps of: assessing each external risk value of a same-tower multi-loop transmission circuit through a statistical analysis method; modeling in a combined manner, and assembling each internal risk value of the same-tower multi-loop transmission circuit by combining the statistical analysis method; and accessing a total probability risk index value by combining each external risk value and each internal risk value according to a total probability formula. The same-tower multi-loop transmission circuit risk probability assessment method provided by the invention can be comprehensively and entirely realized, and reliable parameter estimation and reasonability analysis can be carried out by operating statistical data through a power transmission and transformation facility with national and local calibers, so that a rigorous mould principle, reasonable parameters and a credible assessment result can be realized. The invention provides a probability risk assessment method in a super-grid popularization same-tower multi-loop technology, and provides quantitative reliable assessment and engineering auxiliary criterion for the super-grid popularization same-tower multi-loop technology.