55 results about "Risk adjustment" patented technology

The invention is suitable for the technical field of fire prevention and control, and relates to a regional fire risk assessment method based on a fire risk prevention and control unit, which is based on a specific risk prevention and control unit, integrates static risk assessment and dynamic risk adjustment, and can realize refined assessment and visual display of regional fire risks. Compared with an existing assessment method, the method can more accurately reflect the distribution characteristics of specific risk points, makes up for the defect that the overall assessment result of a region cannot reflect details in a traditional method, and effectively solves the problem that assessment unit division is disjointed from actual fire-fighting management work. According to the assessment method based on the risk prevention and control unit, the efficiency and precision of regional fire risk assessment are remarkably improved, and fire risk prevention and control work can be carried out more scientifically and efficiently.

The invention discloses an automatic driving safety-efficiency decision-making method based on risk soft constraint, and belongs to the technical field of automatic driving decision-making. The problems that a traditional automatic driving decision-making method is poor in extreme scene adaptability and lagged in risk response in the prior art are solved. According to the method, an automatic driving safety-efficiency decision-making framework is constructed, the environment state of an environment perception layer is input into a multi-expert strategy layer, three experts are adopted to set the multi-expert strategy layer, and candidate car-following actions are output through the multi-expert strategy layer; embedding the risk adjustment mechanism into a loss function of each expert in a multi-expert strategy layer to obtain an Actor network loss function of each expert; on the basis of the output candidate car-following actions, taking a basic reward function as a basic behavior constraint of all experts; and generating an automatic driving safety-efficiency decision. The method effectively improves the interpretability of the automatic driving decision-making method and the robustness of the car-following strategy, and can be applied to automatic driving decision-making.

The invention discloses a homomorphic encryption-based cross-industry health insurance data sharing and privacy protection method, and relates to the technical field of health insurance data security, and the method specifically comprises the steps: standardizing medical and insurance industry core data, quantifying key indexes such as a disease clinical risk value and an occupational basic risk coefficient, achieving the format unification of cross-industry data, and achieving the privacy protection of the cross-industry data; further generating ownership, risk and business labels, carrying out encryption processing on data through homomorphic encryption on the risk labels based on three scenes of data sensitivity and business influence grading, business label binding pricing, underwriting and claim settlement prediction, adding an integrity check code to high-risk data, screening ciphertexts based on the labels, and then executing fusion calculation; the comprehensive risk adjustment coefficient ciphertext is generated, the data integrity is verified, the comprehensive risk adjustment coefficient is obtained after collaborative decryption, the comprehensive risk adjustment coefficient is applied to premium pricing, underwriting conclusion generation and claim risk pre-judgment, and the scientificity and accuracy of health insurance pricing and underwriting decision making are improved.

The invention relates to the field of digital security assessment, and discloses a data security compliance risk assessment system, which comprises the steps of automatically retrieving data related to a target industry based on a preset network model, extracting a structured risk factor and an aging identifier of the data, and judging whether an index difference exists or not; performing semantic alignment and difference comparison on the output knowledge fragment and a local risk index, and judging whether the credible score of the risk adjustment suggestion exceeds a set threshold value or not; according to the generated updating suggestion, judging whether the updating result identifies a high-risk item or not; in a virtualized security event simulation environment, based on a multi-dimensional logic deduction algorithm, constructing an attack path corresponding to a high-risk item, simulating a multi-scene risk propagation process, calculating a comprehensive risk index and outputting a deduction result; and based on a deduction result, recording a risk propagation path, forming a verified risk knowledge fragment and feeding back the fragment to a safety compliance evaluation database. The method has the advantage of improving the accuracy of the evaluation result.

The invention provides a forestry pest and disease damage real-time monitoring method and system, and relates to the technical field of data processing, and the method comprises the steps: selecting a position A of an early warning node, a node position B with the maximum yield per unit time in a past one hour, and a node position C with the maximum spatial distribution dispersion; forming a monitoring unit according to the position A, the node position B and the node position C of the early warning node; calculating the radius of a circumcircle of the measurement unit, and determining the grid division density based on the radius of the circumcircle; according to the grid division density, performing adaptive grid division on the monitoring unit to obtain a plurality of grid units; generating a space risk adjustment value according to the space distribution characteristics of the grid units; constructing a spatial diffusion model according to the regional and spatial risk adjustment values of the collaborative outbreak phenomenon; obtaining an insect condition risk level according to the spatial diffusion model; and generating a comprehensive insect condition early warning according to the insect condition risk level. According to the method, the time sequence mutation can be dynamically sensed, and the spatial diffusion risk can be accurately evaluated.

The invention discloses a coal cutter cutting interference prevention method and system based on point cloud and infrared images. The method comprises the steps that a radar sensing module and an infrared sensing module are installed; synchronously acquiring three-dimensional point cloud data and infrared image data of the target monitoring area; the three-dimensional point cloud data and the infrared image data are preprocessed, aligned in the time dimension and registered in a space coordinate system; performing feature extraction on the three-dimensional point cloud data and the infrared image data, performing feature fusion, and extracting space attitude parameters of the face guard; carrying out risk grade discrimination, and marking an interference position; and generating a risk avoiding control instruction according to the risk level, and executing a risk avoiding adjustment action. According to the system, a processing module comprises a data preprocessing module, a multi-modal information fusion module, an identification module and a decision control module, and the processing module is connected with a radar sensing module and an infrared sensing module. According to the invention, accurate monitoring and active prevention of the cutting interference state of the side protection plate and the coal mining machine roller can be realized.

The invention relates to a multi-factor dynamic correction investment benefit intelligent evaluation system, in particular to the field of investment evaluation, and aims to capture macroscopic event and project risk index impact in real time and dynamically generate factor impact coefficients through an event-driven factor correction module, so that the response speed and sensitivity of a model to project sudden change are remarkably improved, and the evaluation efficiency is improved. The self-adaptive weight optimization module utilizes a deep reinforcement learning framework to continuously optimize factor weight distribution based on revenue after risk adjustment in a rolling time window so as to realize self-adaptive adjustment of an investment strategy and optimization of a revenue-risk ratio, and the abnormal conduction early warning module constructs a dynamic directed graph and combines a graph neural network technology to realize early warning of the abnormal conduction. According to the method, abnormal factor conduction paths can be perspectively recognized, systematic engineering risks can be effectively warned, a strategy execution module fuses weight optimization results and risk warning signals, rebalance is executed under the condition that investment cost and risk control constraints are strictly met, and finally a project configuration scheme giving consideration to revenue, robustness and real-time performance is generated.

The invention provides an energy asset investment portfolio optimization analysis method, system and device based on three-dimensional risk conduction and a medium, and belongs to the technical field of energy finance and intelligent decision making. The method comprises the steps that multi-source heterogeneous data is collected and comprises electric power data, meteorological data, industry standard text data and electric power equipment state data; performing data cleaning, space-time alignment processing and multi-source heterogeneous data fusion processing on the multi-source heterogeneous data; constructing a three-dimensional risk conduction model for performing industry standard sensitivity, meteorological risk quantification and power market fluctuation analysis; and according to the output result of the three-dimensional risk conduction model, constructing a multi-objective optimization framework, and by taking the maximization of the difference value between the expected income and the risk adjustment item as the objective, generating an optimal weight scheme of the energy asset portfolio in combination with the constraint condition. According to the invention, low-threshold and high-timeliness investment decision and risk management are realized.

The invention relates to a method and a system for adjusting an airline operation strategy according to a civil aviation airline dynamic risk. The method comprises the following steps: calculating an abnormal confidence coefficient score according to an airline throughput; calculating a throughput deviation rate according to the route throughput and a preset throughput; calculating an environment risk factor according to the weather information and the season information; calculating a final risk value according to the abnormal confidence score, the throughput deviation rate and the environmental risk factor; adjusting a route operation strategy according to the final risk value; according to the method, the final risk value is calculated through factors such as the air line throughput, the weather information and the season information, automatic risk calculation can be realized, the air line operation risk can be obtained in time by considering various risk influence factors, and the risk early warning efficiency is improved; and an airline operation strategy is adjusted according to the final risk value, so that the airline operation loss is reduced, reference can be provided for aviation finance, and the investment risk of aviation finance is reduced.

The application discloses a risk management system based on offline reinforcement learning, comprising: an offline data set generation module: generating an offline data set according to a screening strategy and a four-tuple data format; a sequence data generation module: training a supervised learning model according to the offline data set, and generating sequence data according to the supervised learning model; a risk reconstruction module: calculating a risk adjustment value according to the change value of the sequence data and training data, and reconstructing a risk function according to the risk adjustment value; the training data comprises any one or a combination of multiple items of training times, training time, training completion degree; a minimum risk strategy generation module: calculating a minimum risk value according to the reconstructed risk function, inputting the minimum risk value into the supervised learning model, and obtaining a minimum risk strategy function. The application solves the problems of high policy trial and error cost, low interaction efficiency with the real environment and low policy optimization efficiency.

A risk-sensitive code generation computing system receives query data indicating a requested code section. A code attribute evaluation module determines attributes that indicate characteristics of the query data or the requested code section. Based on the attributes, the code attribute evaluation module calculates risk level data for the requested code section. A code generation module selects, based on the risk level data, a set of training resources. Based on the selected training resources, the risk-sensitive code generation computing system modifies training of a trained neural network model. The modified trained neural network model generates a risk-sensitive code data object based on the requested code section and the risk level data. The risk-sensitive code generation computing system provides at least a portion of the risk-sensitive code data object to an additional computing system.

This invention relates to the field of architecture deployment technology, specifically to an intelligent architecture deployment system and method based on a large language model. Specifically, it includes: an information interaction module storing a set of deployment strategy rules; a requirement parsing module parsing deployment intent primitives through preset mapping relationships to generate a structured target blueprint; a solution evaluation module dynamically calculating the adjudication weights of conflict identifiers based on the deployment strategy rule set to generate adjudication priorities, generating clarification queries and revising the structured target blueprint based on the adjudication priorities, and iteratively generating a comprehensive evaluation result; a deployment decision module combining multi-objective trade-offs with preset strategy axes to generate a candidate strategy matrix; quantifying risk adjustment utility scores and outputting an optimal execution parameter set through predictive reasoning on the candidate strategy matrix; and a solution generation module outputting an architecture deployment solution based on the optimal execution parameter set. This invention utilizes a large language model for intelligent reasoning, solution generation, and predictive decision-making, achieving autonomous decision-making and automated generation of architecture deployment.

A method is provided, comprising: a user device receiving a request from an identity service to approve the transmission of user identity credentials to a dependent party; a user of the user device requesting a one-time transaction identifier based on a request prompt; the user device requesting the one-time transaction identifier from the identity service based on first input from the user; in response to the request for the one-time transaction identifier, the user device receiving the one-time transaction identifier from the identity server and displaying the one-time transaction identifier on a first user device screen; the user entering the one-time transaction identifier on a second user device screen, and the user device transmitting the one-time transaction identifier to the identity service; and in response to receiving at least one input of the one-time transaction identifier, the dependent party determining whether to approve or reject the transaction.

This invention discloses an artificial intelligence-based dynamic credit risk assessment method. This method continuously integrates multi-source real-time data streams with static historical data, utilizes a deep reinforcement learning-trained agent to generate dynamic risk adjustment factors, and employs an attention mechanism to non-linearly couple these factors with a basic credit score. The final output is a real-time dynamic credit score and an interpretable credit decision. By constructing a closed-loop system from real-time perception and dynamic assessment to interpretable output, this invention achieves minute-level continuous monitoring and proactive early warning of borrower credit risk. This solves the problem of delayed risk capture caused by the static nature of data and models in traditional methods, significantly improving the timeliness, accuracy, and automation of risk management.

The present application relates to the technical field of informationization of oil exploration and development and digital processing of whole life cycle management of industrial assets, in particular to a whole life cycle operation and maintenance management system for an oil downhole transmitter, comprising: an asset data management module for building a whole life cycle data lake serving asset value analysis; a benchmark valuation modeling module for generating a theoretical asset value curve of the transmitter under the assumption of no environmental stress; a risk quantification correction module for outputting a risk-adjusted theoretical residual value; a management performance analysis module for calculating a management performance residual after stripping the influence of environmental risks; a decision and execution module for automatically generating differentiated management instructions for asset disposal, inventory strategy adjustment or supplier evaluation, and driving downstream enterprise resource planning systems or inventory control systems to perform closed-loop operations; the present application effectively solves the phenomenon of shirking operation and maintenance responsibilities due to poor well conditions.

The present application relates to the technical field of artificial intelligence, and especially relates to a multi-agent cooperation ability improving method based on agent self-supervised learning, which comprises the following steps: for each iteration of the Monte Carlo tree search self-refining algorithm, determining a parent node selected in each iteration in a search tree as a target parent node, obtaining a total number of historical visits of the target parent node and a child node value set of the target parent node; obtaining a benchmark value according to the total number of historical visits; constructing a risk adjustment compensation item of the target parent node according to the overall value change of the child node value set; optimizing and adjusting the benchmark value by using the risk adjustment compensation item to obtain a final updated value of the target parent node, updating the search tree by using the final updated value of the target parent node until a preset iteration condition is met to obtain a target search tree, and performing multi-agent cooperation according to the target search tree, which significantly improves the ability of multi-agent cooperation by using the Monte Carlo tree search self-refining algorithm.

The invention relates to the technical field of unmanned aerial vehicles, in particular to a multi-unmanned aerial vehicle cooperative investigation scheduling method based on real-time parameter judgment, and the method comprises the steps: dividing sub-regions; constructing a path; collecting historical data; calculating energy consumption; evaluating the risk; adjusting the task; and correcting the threshold value. According to the method, the to-be-surveyed area is scientifically divided into a plurality of controlled sub-areas by integrating geographic information, obstacle distribution, an electromagnetic environment and task requirements, and an optimized flight path and a task topological structure are constructed on the basis; dynamic monitoring and calculation of parameters such as energy consumption, residual electric quantity, task priority, obstacle proximity, height deviation and electromagnetic interference in the flight process of the unmanned aerial vehicle are realized, and a flight risk index is effectively generated. The problems of low task efficiency and limited flight safety caused by fixed path planning, insufficient energy consumption and risk assessment and environmental interference are effectively solved.

The invention discloses a pediatric sepsis clinical evaluation and diagnosis and treatment method based on a large model. The method includes: acquiring an input patient medical record; the illness state assessment task is decomposed into two stages of index analysis and risk prediction; then, an index classification template and a risk adjustment template are designed for the two stages respectively, an index classification result is used for generating a comprehensive illness condition summary report, and the risk probability is adjusted according to the summary report; according to the method, database retrieval knowledge is selected according to the condition summary, a retrieval result is discriminated through a discrimination model, then a better retrieval result is obtained through a reflection and modification mechanism, and a better treatment suggestion is finally helped to be obtained through multiple rounds of iteration. According to the method provided by the invention, the comprehensiveness of index evaluation, the accuracy of risk prediction and the quality of treatment suggestions are improved, and comprehensive evaluation and early warning and reasonable personalized diagnosis and treatment of the sepsis of children can be considered.

The present invention discloses a method for constructing a financial risk control prediction model, which relates to the technical field of financial risk control prediction. A data collection module is used to collect and store characteristics related to the current customer in this evaluation cycle. A prediction model constructed using the customer characteristic evaluation module is used to sequentially calculate and output a risk score F, a risk warning index FY, and a dynamic risk adjustment coefficient DT. The customer characteristic evaluation module is also used to evaluate and update the interest rate adjustment coefficient V for the next evaluation cycle of the current customer. The present invention comprehensively considers multi-dimensional risk factors, introduces square root operations to enhance nonlinear relationships, flexibly adjusts the interest rate adjustment coefficient V, combines historical and current risk information, quantifies the severity of overdue payments, considers the combined impact of credit score P and repayment capacity HN, introduces the latest credit score P for dynamic adjustment, and forms a cyclical influence mechanism. These innovations are intended to improve the accuracy and flexibility of risk prediction and provide more effective risk control support for financial institutions.

The present invention relates to a technology valuation method specialized for research and development technology and an apparatus therefor, which enable fair technology valuation to be performed by appropriately applying risk factors according to technology research and development activities. The technology valuation method specialized for research and development technology, according to the present invention, is provided to perform a fair valuation of research and development technology by calculating a technology value with respect to technology being researched and developed, by calculating: a net present value of total sales (a) from the first year to an expected product life cycle period (n); a risk-adjusted net present value of research and development costs (b) from the first year to a research and development completion year (k); a cost (c) required for sales creation after research and development activities from a research and development completion year (k +1) to the expected product life cycle period (n); and a residual value (d) after a product life cycle (PLC) is terminated, subtracting the risk-adjusted net present value (b) and the cost (c) required for sales creation after the research and development activities from the calculated net present value of total sales (a), and then adding the residual value (d).

A risk-sensitive code generation computing system receives query data indicating a requested code section. A code attribute evaluation module determines attributes that indicate characteristics of the query data or the requested code section. Based on the attributes, the code attribute evaluation module calculates risk level data for the requested code section. A code generation module selects, based on the risk level data, a set of training resources. Based on the selected training resources, the risk-sensitive code generation computing system modifies training of a trained neural network model. The modified trained neural network model generates a risk-sensitive code data object based on the requested code section and the risk level data. The risk-sensitive code generation computing system provides at least a portion of the risk-sensitive code data object to an additional computing system.

The invention relates to an electricity market transaction optimization decision-making system for micro-grid assets, and belongs to the technical field of electricity market transaction and financial risk management. The system obtains risk event signals such as market electricity price, plan power, financial data and extreme weather in real time; the risk quantification module constructs a risk factor reflecting the comprehensive financial risk level based on the quantified potential market opportunity income and the plan deviation penalty cost; the strategy decision and weight generation module dynamically generates weight coefficients of income and deviation penalty through a nonlinear mapping function according to the financial risk, and constructs a real-time optimization objective function with income maximization as an objective after risk adjustment. Finally, the system solves the function to determine an optimal transaction decision. According to the invention, the complex market financial risk is quantified as a dynamic decision basis, so that the transaction strategy can be adaptively adjusted between financial loss avoidance and arbitrage opportunity chasing.

Methods for determining risk-adjusted metrics are presented including a risk-adjusted process efficiency score, a risk adjusted process-based, enterprise-operating-model efficiency score, a risk-and-resource-utilization-adjusted, process-based enterprise-operating-model efficiency score, a risk-and-resource-utilization-adjusted, process-based enterprise-operating-model effectiveness score, and a risk-adjusted operating leverage. In addition, a method for assessing non-interest costs of a bank or non-banking finance company utilizing time-driven costs of resources for performance of the processes of the bank or non-banking finance company is presented.

The invention relates to the technical field of medical instruments, in particular to a track monitoring force feedback obstetric forceps method and system, and the method comprises the following steps: obtaining three-axis force and track coordinates, matching to generate a traction included angle sequence, extracting an included angle trend, recognizing an offset risk, adjusting a track node direction, analyzing a pressure distribution change trend, and positioning an abnormal stress region. And generating an attitude offset early warning signal. According to the method, the three-axis stress information and the tong head track space coordinates are fused and matched, accurate correlation between the traction angle and the path change can be achieved, the space offset risk is identified by combining the change trend of the included angle, the change direction of the traction track section is compared by utilizing the direction vector trend of the continuous time period, and the traction accuracy is improved. The traction direction and track consistency improvement is guided through path node fitting operation, the pressure intensity concentration trend position is recognized in combination with pressure intensity data distribution, the recognition capacity for clamping deviation and a risk contact area is improved, and real-time recognition, dynamic adjustment and risk prevention and control of the operation process are achieved.

A dynamic risk-adjusted access and control platform for drug delivery devices and associated consumable products is disclosed. The system includes requesting devices operable to generate requests triggered by request events made by requesting users. The platform also comprises a risk engine adapted to receive the request information from the requesting devices, behavioral information relating to operational characteristics of one or more devices associated with registered users and intrinsic information associated with personal characteristics of registered users. The risk engine is further adapted to infer risk scores associated with the registered users based on the request information, the behavioral information, and the intrinsic information, and the system is adapted to accept or deny the requests based on these risk score.

The application relates to the field of financial risk assessment, and specifically discloses a user financial risk intelligent assessment method and system, which comprises the following steps: constructing a three-dimensional big data security protection framework to control user multi-type and multi-modal data in all links; constructing a collaborative framework based on a federal learning hybrid architecture, intelligently analyzing data by adjusting an AI model cluster, a workflow engine and a financial large language model after adjustment through a reinforcement learning intelligent agent; constructing a three-dimensional portrait model, extracting special features of digital financial scenes such as internet loans, dynamically updating and outputting scene-based risk positioning results, and realizing accurate portrait; calculating a dynamic accurate pricing formula based on a formula dynamic interest rate pricing = benchmark interest rate * risk adjustment coefficient * scene adaptation coefficient * market fluctuation coefficient, optimizing coefficient weights through an intelligent agent, and realizing dynamic accurate pricing; and outputting three-layer interfaces of a regulatory level, a financial institution business level and a user level. The application provides a standardized and efficient technical solution for user financial risk intelligent assessment.

The present invention relates to a method and apparatus for evaluating the technical value of research and development technologies, which enables fair evaluation of technical value by appropriately applying risk factors associated with technology research and development activities. The method for evaluating the technical value of research and development technologies according to the present invention is provided to enable fair evaluation of research and development technologies by first calculating the net present value of total sales (a) from the first year to the expected product life cycle period (n), the risk-adjusted net present value of research and development expenses (b) from the first year to the research and development completion year (k), the costs required to generate sales after the research and development activities from the research and development completion year (k+1) to the expected product life cycle period (n) (c), and the residual value (d) after the end of the product life cycle (PLC).

The application provides a prediction method and device for diagnosing cardiac amyloidosis, and applies to the technical field of data processing. The first training sample set is subjected to data cleaning processing to generate a second training sample set; the second training sample set is subjected to missing value supplement processing to generate a target training sample set; a preset cardiac amyloidosis prediction model is processed based on the target training sample set and a verification sample set to generate a target cardiac amyloidosis prediction model; clinical parameter information of a target user is processed to generate target physiological parameter information; life habit information of the target user is processed to generate a dynamic risk adjustment factor; the target physiological parameter information and the dynamic risk adjustment factor are processed based on the target cardiac amyloidosis prediction model to generate early warning information, wherein the early warning information is used to represent the relevance of the target user to cardiac amyloidosis, hypertrophic cardiomyopathy and hypertensive left ventricular hypertrophy.

This reinforcement learning device learns a policy for determining the next action of an agent on the basis of an environmental state and a reward earned by the agent for the action thereof, the reinforcement learning device comprising: an estimation unit that uses, as an initial model, a base model which estimates an expected value of a reward and which does not take risk into consideration, to sequentially estimate a risk-corrected reward, which is a reward that takes risk into consideration; and a learning unit that sequentially learns an agent policy on the basis of the risk-corrected reward.

The invention discloses a turnout health assessment method and system based on an expert rule base, and relates to the field of turnout health assessment, which parses standardized sensor time sequence data through the expert rule base, completes basic identification and preliminary quantification of a single fault symptom, and forms a static and basic assessment dimension. On the basis, a dynamic risk adjustment mechanism is further introduced, the combination relation of triggered rules and real-time environment data are comprehensively analyzed, so that a risk multiplier capable of representing the multi-fault coupling effect and the environment stress is dynamically constructed, and the basic risk value is subjected to weighted correction by applying the risk multiplier. And finally, a comprehensive health assessment score is generated through driving. Therefore, non-linear and scenario comprehensive evaluation of the turnout health state can be realized, so that comprehensive diagnosis logic of experts under complex working conditions is simulated, and a health degree evaluation value closer to actual operation risks is obtained.