209 results about "Risk threshold" patented technology

The invention relates to a risk management and control method and system based on real-time behavior analysis, and the method comprises the steps: carrying out the structural processing of multi-source behavior data through lightweight protocol decoding and behavior label embedding, and constructing an original behavior data set of a user and an entity; extracting multi-dimensional behavior characteristics by using a sliding window analysis and sparse representation mechanism, and constructing a user behavior graph by combining graph embedding learning; constructing a time-sensitive behavior trend model through streaming modeling and an incremental learning strategy, identifying an abnormal evolution trajectory in real time, and introducing a dynamic risk threshold regulation and control mechanism; adopting a high-throughput flow data processing and fast similarity matching algorithm to construct a fusion discrimination model, giving risk levels to abnormal behaviors and classifying the abnormal behaviors; and finally, performing closed-loop optimization in combination with a historical treatment effect. The system has the advantages of high real-time performance, high calculation efficiency, adaptability to complex network environments and the like, and the network security protection capability can be effectively improved.

The invention relates to the technical field of pipeline risk monitoring, and discloses a pipeline risk monitoring method and system based on artificial intelligence, and the method comprises the steps: collecting multi-source sensing data of a pipeline operation environment, and carrying out the preprocessing of the data, and obtaining a multi-scale time sequence feature set; and constructing a pipe network diagram model, and embedding the multi-scale time sequence feature set into the pipe network diagram model. And learning the pipe network diagram model by using a space-time diagram attention network to obtain a target prediction result. And constructing an expected economic loss function, and determining an optimal risk threshold based on the expected economic loss function. And comparing the optimal risk threshold with a corrosion event probability prediction value to obtain a risk level, and determining a maintenance priority sequence of each risk point according to the risk level, a historical maintenance record and the importance of a pipeline section. And generating a maintenance work order based on the maintenance priority sequence. According to the invention, dynamic and prospective risk prediction is realized, and the economy and operability of pipeline risk monitoring management are improved.

The invention relates to the technical field of computers, and discloses a model content security control method and system, electronic equipment and a storage medium, and the method comprises the steps: combining a received user input with a historical dialogue record of a current session to form a dialogue context; performing risk identification based on the dialogue context, generating at least one risk category and a corresponding initial risk value, and generating a risk integral corresponding to the current input according to a preset integral strategy; accumulating the risk points to accumulated risk points of the current session; comparing the accumulated risk integral with a dynamic risk threshold value obtained by calculation according to a reference threshold value, a logarithmic function attenuation item of the dialogue round and a user historical behavior adjustment item; and when the accumulated risk integral reaches or exceeds a dynamic risk threshold value, triggering a preset risk management and control measure. According to the method, the risk content can be effectively identified and controlled, attacks bypassing a security mechanism through slow induction can be defended, and the security boundary is not easy to detect.

The invention discloses a small sample modeling stability evaluation method and system based on Bootstrap resampling, and particularly relates to the technical field of computers and data intellectualization, the method comprises the following steps: completing data preprocessing and stable stage identification under a unified time base, and forming a segment set; an average block length is used as a decision quantity, an SBB is optimized to construct a sample space, and an optimal block length is determined in combination with variance consistency and nominal coverage rate consistency criteria; carrying out re-sampling training around short / medium / long scales, and collecting layered indexes such as prediction, parameters and features; stability calculation and empirical coverage rate calibration are completed based on intra-scale statistics and inter-scale weighted mixing, and a pseudo-stationary diagnosis score is output; and finally, engineering judgment and backspacing optimization are carried out according to the coverage rate, the correlation maintenance and the risk threshold. The system records random seeds, block metadata and model version generation evidence pointers, has the characteristics of traceability and reverifiability, and is suitable for scenes of production lines, network traffic, finance and the like.

The invention relates to the technical field of agent testing, and particularly provides an agent dynamic behavior safety testing method and system based on a risk conduction quantification model, and the method comprises the steps: collecting agent behavior data which comprises a plurality of pieces of risk operation information and a risk association relationship; constructing a behavior risk association map by taking the risk operation as a node and the association relationship as an edge, labeling a risk attribute and an aging factor for the node, and labeling risk conduction intensity for the edge; constructing a risk rule base based on the risk labeling result and a preset risk judgment logic; inputting the behavior data, the behavior risk association map and the rule base into a trained quantitative model, and calculating a risk conduction probability, an influence range and a critical node; monitoring a behavior track in real time, suspending a task when a multi-dimensional risk threshold is triggered, backtracking an inference chain and generating an intervention record; and fusing the multi-dimensional data to generate a test report. According to the method, the problems of correlation risk missed judgment and response lag in the traditional test are solved, and the pertinence and reliability of the safety test are improved.

The invention relates to the technical field of financial risk assessment, in particular to a financial risk assessment method and system fusing multi-dimensional indexes and combined weights, and the method comprises the steps: constructing a financial cooperation risk index system containing multi-dimensional heterogeneous data; executing a combined weight calculation process based on Bayesian inference logic; performing weighted aggregation on the standardized index data and the posterior combination weight, and calculating a comprehensive financial risk index of the target assessment object; and based on the comprehensive financial risk index, in combination with a preset risk threshold model, generating a systematic risk assessment result and a structural risk distribution map for a specific financial cooperation scene. According to the method, complex risk factors are converted into visual quantitative indexes, and macroscopic decisions in transnational financial cooperation are directly supported.

The invention discloses a large model generation content risk identification and intervention method based on deep learning, and the method comprises the steps: collecting multi-modal data outputted by a content generation system, carrying out the preprocessing of the multi-modal data, and generating the preprocessed multi-modal input data; encoding and fusing the features of the multi-modal perception model to generate global risk feature representation data; inputting global risk features into a hunting optimization algorithm, and optimizing model structure parameters, risk thresholds and intervention strategy parameters; optimizing parameter-driven risk identification and hierarchical intervention, and outputting risk levels, categories and hierarchical intervention measures; an intervention effect and user feedback are collected, and continuous optimization and self-adaptive evolution of parameters are driven. According to the method, efficient risk identification and intelligent intervention on the large model generation content are realized, and the accuracy and the automation level of content security management are remarkably improved.

The invention provides a low-altitude Internet of Things design simulation system based on an urban CIM model, relates to the field of low-altitude flight, and solves the technical problem that the deviation between path planning and actual operation is large due to the fact that an existing simulation system cannot effectively support dynamic migration of a service function chain. The method comprises the following steps: constructing a city three-dimensional model through a CIM technology, and carrying out grid division on the city three-dimensional model; acquiring environment information; acquiring a grid basic safety risk index of the urban three-dimensional model based on the environment information; the method comprises the following steps: collecting low-altitude internet-of-things sensing data through a plurality of sensors, and preprocessing the low-altitude internet-of-things sensing data; constructing a risk model algorithm based on the grid basic security risk index and the low-altitude internet-of-things perception data; obtaining a comprehensive risk index of each grid through a risk model algorithm; and if the comprehensive risk index is greater than a preset risk threshold, sending a risk airspace early warning signal of the corresponding grid. The method is used in the low-altitude Internet of Things design simulation process.

The invention belongs to the field of safety monitoring of wind power equipment, and provides a multi-source data fusion and safety early warning system and method in the hoisting process of a wind turbine generator, and the system comprises a data collection and preprocessing module which collects and preprocesses multi-source sensor data such as a tower inclination angle and a suspension arm inclination angle; the state manifold construction module is used for mapping the preprocessed data to a multi-dimensional space to construct a state manifold and generating an ideal geodesic line; the trajectory analysis and risk assessment module is used for calculating the deviation degree between the real-time state trajectory and the ideal geodesic line and generating a risk score; the dynamic threshold generation module constructs a risk tensor field based on environmental parameters, and extracts a risk threshold curved surface after wind speed adjustment; the early warning decision module is used for comparing the risk score with a threshold curved surface to determine an early warning level and sending information; and the visual display module is used for displaying the state manifold, the track, the tensor field and the early warning information. By introducing a differential geometry theory, state manifold representation and geodesic deviation measurement are constructed, and accurate assessment of the hoisting process risk is realized.

The invention provides an engineering dynamic risk assessment early warning system and method, and belongs to the technical field of engineering risk assessment. According to the method, engineering stages are divided, a stage label incidence matrix is constructed, historical cases are collected, an engineering stage-risk feature incidence matrix is constructed, a weight dynamic adjustment mechanism is set, construction data are collected in real time, the current stage is identified, risk features are extracted, risk weights are automatically adjusted, and dynamic risk comprehensive scores are calculated. And then the preset risk threshold is automatically called to divide the risk early warning level, so that scientific and dynamic assessment and early warning of the engineering risk are realized, core risk characteristics of different engineering stages can be accurately identified, the risk weight is dynamically adjusted according to real-time data, the risk assessment is enabled to better fit the actual construction condition, the risk early warning level is timely and accurately divided, and the risk early warning efficiency is improved. Powerful support is provided for engineering safety management, and the probability of occurrence of engineering accidents is effectively reduced.

The invention provides a semi-trailer rollover early warning method and system based on dynamic threshold value prediction. The early warning method comprises the steps that the transverse acceleration, the yaw velocity, the vehicle speed, the suspension pressure and the front lane curvature of a semi-trailer are obtained in real time; according to the collected and calculated data and a linear trend extrapolation method, constructing a dynamic rollover risk threshold function and a comprehensive risk index function, and calculating a rollover risk threshold, a real-time risk value and a predicted risk value; the item with the higher value in the real-time risk value and the predicted risk value is selected and compared with a rollover risk threshold value, and whether early warning is triggered or not is judged, and a control instruction is issued; the early warning system comprises a semitrailer state monitoring unit, a lane curvature recognition unit, a rollover risk threshold calculation unit, a real-time risk value calculation unit, a predicted risk value calculation unit and an early warning control unit, and is used for realizing the early warning method, so that the response speed and the judgment accuracy of the semitrailer rollover early warning system under variable working conditions are improved.

The invention provides a project risk dynamic prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: collecting multi-dimensional original data in a whole life cycle of a target project, carrying out the preprocessing of the multi-dimensional original data to generate a standardized data set, building a case decision model based on the standardized data set, and carrying out the prediction of a project risk. And inputting real-time project data into the case decision model to obtain a prediction result, finally performing risk assessment according to the prediction result, and triggering early warning when the risk assessment result exceeds a risk threshold value, so that the problems of poor data quality and low risk caused by the fact that only single-dimensional data collection can be realized and data lacks standardized processing in the prior art can be solved. The problems of low project risk prediction precision and early warning lagging caused by a static evaluation mode are solved, and the technical effects of improving project risk prediction accuracy and realizing project full life cycle risk management real-time performance and effectiveness are achieved.

The invention discloses a traffic public opinion risk tag classification early warning method based on a large model. At least one tag corresponding to each of multiple pieces of first public opinion data in a preset time window is determined based on the large model; determining a plurality of pieces of second public opinion data in the preset area, and for at least one tag, determining the number of the public opinion data corresponding to the tag in the plurality of pieces of second public opinion data, the emotional property corresponding to the plurality of pieces of second public opinion data and the number of collection channels corresponding to the plurality of pieces of second public opinion data, according to a preset distance value, the number of the public opinion data corresponding to the tag in the plurality of pieces of second public opinion data; determining a popularity index corresponding to the tag; determining a plurality of label combinations, screening out high-popularity label combinations, and determining risk indexes of the high-popularity label combinations; and if the risk index is greater than a preset risk threshold, performing early warning on the high-popularity label combination. The accuracy of traffic public opinion risk label classification early warning is improved.

The invention provides an intelligent risk screening system and method based on distribution network load prediction, and relates to the technical field of intelligent power grids, and the method comprises the steps: carrying out the multi-scale decomposition processing and bidirectional feature coding of historical load data of a distribution network, and obtaining a time sequence coding feature; graph structure features are extracted from the multi-node load graph of the distribution network, feature fusion is carried out on the graph structure features and the time sequence coding features, and a multi-dimensional prediction matrix is obtained; performing a back propagation neural network model optimization operation based on genetic algorithm learning on the multi-dimensional prediction matrix through the environmental influence data to obtain a load prediction curve and a prediction confidence coefficient, and determining overload risk early warning of the distribution network load according to the load prediction curve and a preset risk threshold value; according to the method and the device, accurate screening of the overload risk of the distribution network based on space-time modeling and a prediction confidence mechanism can be realized, so that the accuracy of load early warning is improved.

The invention discloses a credible data space dynamic risk assessment method and system based on a space-time sequence, and relates to the technical field of credible authentication, and the method comprises the steps: collecting initial space-time sequence data, and processing the initial space-time sequence data to obtain standardized space-time sequence data; according to the space-time sequence data, extracting a security feature set of each time point, and calculating a space aggregation degree and a time attenuation coefficient of the security event; a dynamic risk assessment model is constructed, adjustable risk weight parameters are introduced, and the risk weight parameters are subjected to feedback iteration adjustment; and according to the adjusted risk weight parameter and the current time-space sequence data, calculating a dynamic risk value of the target data space, and when the risk value exceeds a preset risk threshold, triggering a safety response. The technical problem that the prior art lacks an effective means for dynamically evaluating the data space risk and is difficult to adapt to a complex environment in which data is continuously changed and updated is solved.

The invention discloses a power grid regulation capability evaluation method, system and equipment based on a large industrial load, and a medium, and belongs to the technical field of power management, and the method comprises the steps: collecting power data, carrying out the preprocessing, and generating a load multi-source data set; constructing a load prediction model, extracting time sequence features in the load multi-source data set, and dynamically fusing sequences in the time sequence features to generate a load prediction value; nodes, edges and attributes are defined, a load prediction value is evaluated, and a risk knowledge graph is generated; through a traditional graph algorithm, node importance scores are calculated and normalized, load risk scores are generated, risk threshold values are set, and load risk levels are marked; setting an adjustment rule, and adjusting the load prediction value; based on the load risk level and the time-of-use electricity price in the load multi-source data set, enterprise compensation cost and upstream and downstream economic losses are calculated, and an economic influence quantification table is generated. According to the method, dynamic coupling quantification and positioning of the power grid regulation risk are realized by constructing the risk knowledge graph.

The invention provides an industrial process risk prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining production data in an industrial process and a corresponding timestamp, dividing the production data into a plurality of pieces of time slice data based on the timestamp, constructing a text prototype set based on a pre-trained time sequence word vector space, and carrying out the prediction of the risk of the industrial process. And based on a cross attention mechanism, carrying out mutual mapping on the time slice data and the text prototype set to obtain a reprogramming language under a plurality of time slices, inputting the reprogramming language and preset prompt information into a preset large language model for reasoning to obtain a risk score, and sending the risk score to a server. And determining the risk level of the industrial process according to the risk score and the preset risk threshold. Through the method, the technical problems of high manual dependence degree and high calculation power requirement in risk prediction in related technologies can be solved.

The invention relates to the technical field of databases, in particular to a database circulation track auditing method based on multi-source data fusion. The method comprises the following steps: collecting multi-source data of different logs, preprocessing to obtain preprocessed multi-source data, extracting key features of the preprocessed multi-source data, and serially connecting the key features according to a time sequence to generate a database circulation track; collecting operation behavior data of a user, calculating a mean value and a standard deviation corresponding to the operation behavior data to determine a normal range and generate an initial baseline, and designing an automatic trigger updating mechanism to dynamically update the initial baseline to generate a dynamic baseline; and calculating the deviation degree between the actual value of each operation behavior dimension and the dynamic baseline, carrying out weighted summation to calculate a total risk value, comparing the total risk value with a risk threshold, and classifying the total risk value into low risk, middle risk and high risk. According to the invention, the false alarm rate can be reduced, and multiple times of missing report of few hidden anomalies can be avoided; the auditing resources can be focused on the high risk preferentially, manual intervention of low-risk abnormity is reduced, and compared with single-dimension grading, the auditing efficiency is improved.

The invention discloses a phishing website detection method and device, equipment and a storage medium, and relates to the technical field of computers.The method comprises the steps that firstly, a URL of a to-be-detected website is obtained, and a risk score of the URL is calculated; when the score is between the first risk threshold value and the second risk threshold value, collecting the residual electric quantity, the load, the network delay, the detection accuracy and the trust score of the candidate cooperative equipment; and determining target candidate cooperative equipment, forwarding the URL and receiving a detection result of the URL. According to the method, target candidate cooperative equipment is screened by calculating candidate scores of candidate cooperative equipment, and score calculation is combined with weights corresponding to indexes; the weights are determined based on business scenario requirements and may be adjusted according to environmental state vectors and candidate scores. Meanwhile, screening and quitting conditions of the candidate cooperative equipment are set, and an environment perception triggering and weight oscillation suppression mechanism is also included, so that the accuracy and efficiency of detection and the system stability are improved.

The invention discloses a multi-experiment task production scheduling method, device and equipment and a storage medium, and the method comprises the steps: carrying out the sampling of a preset number of times for each production scheduling scheme based on the prior distribution of the duration of each experiment stage, and determining the starting time of each experiment operation, constructing a global time resource scheduling problem under the constraint conditions that the time window constraint of the experimental operation, the time period of the experimental operation belongs to the idle time period of the operation equipment and the time periods of the experimental operation distributed on the same operation equipment are not overlapped, and calculating the ratio of the infeasible times of the global time resource scheduling problem to the preset times; and if the risk value is lower than the risk threshold value, taking the production scheduling scheme as a target production scheduling scheme, and performing online scheduling of the experimental tasks according to the target production scheduling scheme, so that the method is suitable for production scheduling of high-throughput and diversified experimental tasks, and the risk of equipment resource conflict is reduced.

The invention discloses a complex fund chain intelligent management and anomaly detection method based on a deep learning model, and the method comprises the steps: capturing a fund flow network structure between accounts through building a fund topological relation, extracting the periodicity and trend characteristics of a transaction sequence through combining a time sequence neural network, and calculating a reconstruction error through an anomaly detection model, thereby achieving the intelligent management of a fund chain. Quantifying transaction deviations and identifying anomalies; if the abnormal score exceeds a threshold value, backtracking a risk conduction chain through a path tracking method, revealing an abnormal fund propagation path, simulating future fund transfer scale and direction by using a flow prediction model, comparing with a historical risk threshold value, judging potential fluctuation, and generating a real-time early warning signal; according to the method, full-chain analysis from anomaly detection to risk prediction is realized through multi-model fusion, the accuracy and timeliness of risk identification in financial transactions are remarkably improved, and effective technical support is provided for prevention of systematic financial risks.

The invention discloses a roadway surrounding rock impact risk prediction method and system based on a neural network, and relates to the field of roadway surrounding rock safety monitoring, and the method comprises the steps: obtaining anchor rod cluster monitoring data, carrying out the preprocessing to obtain anchor rod parameter data, and constructing an anchor rod space adjacency matrix based on the unique identification code and the position coordinate of an anchor rod; inputting the anchor rod parameter data and the anchor rod space adjacency matrix into a space-time correlation prediction model, carrying out nonlinear fitting on the stress-strain space-time evolution law of the surrounding rock of the roadway, dynamically updating model parameters by adopting an autoregression mode, and outputting a prediction numerical value sequence of an anchor rod cluster; the risk probability density of each anchor rod is calculated by adopting a probability density function, a risk cloud picture is generated, the expansion and contraction rate of the anchor rods and the risk threshold value of the pre-tightening force of the anchor rod bolts are dynamically set, risk level areas are divided, the area of each risk area is calculated, and the roadway surrounding rock impact risk is quantitatively evaluated, so that the subjective limitation of a traditional method is broken through; and objective quantitative evaluation of the impact risk is realized.

The invention discloses a power grid construction project management and control system, method, device and equipment, and a medium, and the system comprises a power grid construction project node construction module which is used for obtaining historical capital construction project data corresponding to a current power grid construction project, and constructing a standardized node library of the current power grid construction project; the management and control module is used for acquiring construction information of a current power grid construction project; calculating the current progress based on the operation card punching information of the current project node; determining construction progress deviation information based on the current progress and the standardized node library; determining a risk type and a risk threshold value of the current project node based on the environment information, the material information and the standardized node library of the current project node; generating alarm information based on the construction progress deviation information, the risk type and the risk threshold; according to the method, the standardized node library is constructed by acquiring the historical data, and risk early warning is generated by integrating the construction information, the card punching progress and other information, so that the management and control of the construction progress and risk of the power grid construction project are effectively realized.

The invention belongs to the technical field of glaze icing risk prediction, and discloses a spatio-temporal feature fused glaze icing risk prediction method for a plain power transmission line. The method comprises the following steps: S4, processing a feature data set based on a risk prediction model to obtain a risk prediction value; s5, the risk degree of glaze icing is judged based on the risk prediction value, and an auxiliary decision report is generated according to the risk degree of glaze icing; s6, analyzing the historical rule data of glaze icing to obtain a risk threshold correction interval; s7, dynamically adjusting the content of the auxiliary decision rule base based on the risk threshold interval in combination with the deicing cost and the power failure loss; s8, the line redundancy design and the auxiliary decision making rule base are comprehensively evaluated, the reasonability of the auxiliary decision making report is judged according to the evaluation result, and in general, the method has the remarkable advantages that the risk prediction accuracy degree is high, the risk coping auxiliary effect is good, and the coping measure economic balance capacity is high.

The invention discloses a data flow safety supervision system and method based on a big data platform, and relates to the technical field of safety supervision and data analysis, and the method comprises the following steps: collecting transmission process data and user operation data; the transmission process data comprises network flow data and encrypted information data; the user operation data comprises user behavior data, operation frequency and authority information data; analyzing the collected data, extracting risk factors, and carrying out standardization processing on risk factor data; constructing a dynamic data flow model by taking the preprocessed risk factor data as a base; analyzing potential risks in data flow, and constructing a comprehensive risk scoring model through deep learning; setting a risk threshold value; and according to the set risk threshold, dividing risk levels, and performing management according to the risk levels. According to the invention, through dynamic analysis of user behaviors and potential risks in a data transmission process, accurate risk assessment and intelligent level-to-level management are realized.

The invention discloses a multi-party risk control assessment system and method for data asset transaction, and relates to the technical field of data asset transaction, and the method comprises the steps: extracting a risk feature set based on a federated learning framework, deploying a local model training module in a distributed environment, and extracting a global risk feature set; performing noise addition processing on the global risk feature set to generate an intermediate feature data set; integrating the intermediate feature data set by using a global aggregation server, and performing weighted fusion on the intermediate features of all parties to obtain global features; constructing a risk assessment model based on a gradient boosting decision tree, calculating the risk probability of global features in a distributed environment, and calculating key indexes of systematic risks; and if the key index of the systematic risk is greater than the risk threshold, risk early warning is distributed to each participant through the global aggregation server, so that the intelligent level and cooperative efficiency of risk control are improved.

The invention discloses an appeal subject risk identification method, device and equipment and a computer program product, which can be applied to the technical field of natural language processing. According to the method, the historical work order data is labeled through the large language model, the historical work order data after labeling adjustment is obtained, the pre-training language model is trained in combination with the risk classification rule information, and then the target work order data is input into the trained pre-training language model for risk prediction to obtain the first score; inputting the target work order data into a large language model according to the first score to carry out risk prediction to obtain a second score, and carrying out risk level analysis according to the first score, the second score and a preset risk threshold range to obtain target risk information of the litigation subject; according to the embodiment, after the big language model and the pre-training language model are combined, risk analysis is performed on the target work order data of the litigation subject, so that the risk identification accuracy of the litigation subject can be effectively improved.

The invention belongs to the technical field of artificial intelligence, and relates to a business adjustment method and device, equipment and a storage medium thereof. Carrying out time sequence arrangement to obtain time sequence historical business data; inputting into a pre-trained business risk prediction model; outputting a predicted risk value; identifying a relationship between the predicted risk value and a preset risk threshold through comparison; and according to the relationship, screening different service adjustment measures to carry out service adjustment on the target user. The business adjustment method is applied to financial business risk prediction scenes such as investment risk prediction, financial management risk prediction and car insurance underwriting risk prediction, and business risk value prediction is carried out by adopting an artificial intelligence prediction model and combining historical business data of a user. The business risk value is predicted more intelligently and accurately, certain business risks are avoided for related parties, and business adjustment is carried out for risk users in time.

The invention discloses a work order change abnormity detection method and device, a storage medium and computer equipment, relates to the technical field of information processing, and mainly aims to solve the problems of high omission ratio and low recognition accuracy caused by dependence on a preset rule base and audit path solidification in the existing detection technology. Comprising the steps of performing natural language processing on a to-be-processed change work order to extract dominant factor values; obtaining an implicit factor value in a system execution process in real time; performing dynamic risk assessment processing on the to-be-processed change work order based on the dominant factor value and the implicit factor value to obtain a risk value; when the risk value exceeds a risk threshold value, a multi-department joint approval mechanism is started, and an audit path is automatically distributed based on the risk value; based on the auditing path, parallelly pushing the approval requests to related departments, and setting grading response timeliness associated with each approval request; and after the joint approval is finished, generating a change execution script corresponding to the to-be-processed change work order, and executing a change operation based on the change execution script.

The invention relates to the technical field of information processing, in particular to a reverse order full-link identification and risk control method, device and equipment and a storage medium, and the method comprises the steps: regularly pulling order basic information of a merchant from a plurality of open APIs, and employing a CRF model to identify a waybill reverse label in the order basic information, cross-platform reverse order data streams are automatically processed, the multi-source heterogeneous data integration capability is achieved, the data processing efficiency is improved, accurate recognition and standardized management of reverse order customer information are achieved, sending and receiving information corresponding to reverse waybill numbers is inquired, whole-process processing of order data is covered, the data management quality is improved, and the data management efficiency is improved. Calling a naive Bayesian classification model to calculate a first risk probability of the sending and receiving information, improving the intelligent degree of risk identification, fusing the first risk probability and the historical total return rate of the user to obtain a second risk probability, and generating abnormal order interception information when the second risk probability is greater than a preset risk threshold value. And risk control decision-making efficiency is improved.