32 results about "Risk model" patented technology

The invention relates to the technical field of invoice risk control management, and discloses an invoice risk control management method and system based on multi-source data linkage. According to the method, multi-source data of the whole invoice business process is collected in real time through a multi-source data fusion gateway. And performing streaming ETL processing and encryption integration on the multi-source data to generate an encrypted unified data view. And based on the view, constructing an association hypergraph by utilizing a dynamic graph association technology, analyzing an entity relationship by virtue of a graph neural network, and identifying false invoice making gang and repeated financing risks. And calculating a dynamic risk score by adopting a risk quantification and traceability technology, and outputting a risk level, a responsibility node identifier and a capital flow thermodynamic diagram. When the risk score exceeds a threshold value, risk gradient information is safely shared among the group headquarters, the molecular companies and the tax-bank institutions, and linkage processing actions such as invoice freezing, red character notification or credit adjustment are triggered. According to a manual reexamination result, the risk model is finely adjusted through a knowledge self-updating technology, and the rule base is hot-updated.

A fraud detection system preemptively identifies and mitigates fraudulent financial transactions in real-time across a diverse range of digital and physical transaction sources. Transaction data may be acquired from various platforms and categorized into rule sets specific to transaction types. Categorized data is aligned with existing risk profiles to construct a dynamic hysteresis model. This model, evaluated by a decision tree algorithm, identifies potential fraud by integrating immediate transaction details with a comprehensive historical data analysis, thus enabling advanced trend analysis and pattern recognition. Key features identified by the decision tree are used to form a heuristics model, which is then analyzed by a transformer network risk model. A feedback loop enhances the system's effectiveness by incorporating decision outcomes back into the model training server, thus refining the training dataset and continuously improving the accuracy of the risk model.

The invention discloses a camera gun video resource positioning method and related equipment. The method comprises the following steps: acquiring camera gun information of each financial network; obtaining structured risk model data for the daily recovery high-risk model troubleshooting index; determining a target financial network point corresponding to each piece of risk model data in the structured risk model data; according to the structured risk model data, the target financial network point corresponding to each piece of risk model data, the camera gun information of each financial network point and the current popularity value of each camera gun, determining a plurality of current retrieval camera guns; according to the current user operation log, updating the current popularity value corresponding to each camera gun; and according to the updated current popularity value corresponding to each camera gun, determining a plurality of updated current retrieval camera guns. The method can achieve the precise pushing of the video resources needed by the daily redisk of the website, improves the video verification efficiency, and can be widely applied to the technical field of artificial intelligence.

The invention discloses an enterprise financial risk real-time early warning and visualization method based on stream-oriented computing, and the method comprises the following steps: 1) multi-source heterogeneous data real-time collection and access: collecting stream-oriented data from a plurality of data sources in real time, the data sources comprising internal business data and external financial data; 2) stream data cleaning and standardization: preprocessing the data accessed in real time to ensure that the formats of the data from different sources are uniform and can be used for subsequent calculation; 3) real-time financial index calculation and risk model evaluation: 3.1) real-time index calculation; (3.2) carrying out real-time risk assessment; 4) risk early warning and graded pushing; 5) performing real-time visualization and interactive analysis; according to the method, efficient analysis, visual presentation and man-machine interaction of complex data are achieved in an automatic and intelligent mode, and therefore support is provided for decision making.

The embodiment of the invention relates to the technical field of artificial intelligence, and provides an apartment financial management intelligent auxiliary method and system based on artificial intelligence, and the method comprises the steps: obtaining apartment management data, hotel management data and transaction data disclosed by a market, and obtaining multi-source data; storing the multi-source data to a cloud financial management center and encrypting the multi-source data; outputting a prediction result of the multi-source data through a financial analysis prediction network; the financial analysis and prediction network comprises an income prediction model and a component analysis optimization model which run in parallel; constructing a visual report form and an analysis report based on the prediction result, and dynamically displaying the report form and the analysis report to the user; and inputting the multi-source data into the financial management model, performing analysis through an auditing rule in the financial management model to generate a financial auditing report, calling the financial risk model to monitor the financial auditing report, and synchronously pushing the financial auditing report to a manual auditing terminal for verification and approval processing. According to the method, the data utilization rate is increased, and the cost optimization accuracy, the financial management efficiency and the safety are improved.

The invention provides a risk list supervision system and method, the risk list supervision system comprises a database, a risk analysis unit, a risk list generation unit and a server, the database is used for storing account data of accounts and transaction cash flow data; a transaction risk model of the risk analysis unit is used for analyzing transaction cash flow data to generate at least one risk factor corresponding to the transaction cash flow data and calculating the weight of the at least one risk factor to generate a risk score, and when the risk score is larger than a risk standard threshold value, the risk list generation unit generates and sends a risk account list, and the risk account list is used for generating a risk account. The server marks the account corresponding to the account data in the risk account list as a temporary forbidden state; therefore, the risk list supervision system provided by the invention can identify the high-risk account timely, efficiently, quickly and automatically, so as to improve the efficiency and reduce the labor cost.

Methods and systems are presented for dynamically modifying a risk model based on detected shifts of input features. Input values corresponding to an input feature and associated with transactions may be obtained. A distribution of the input values is determined, and compared against a benchmark distribution. An anomaly is detected when a difference between the distribution of the input values and the benchmark distribution exceeds a threshold. Based on the detected anomaly, a risk model configured to perform risk predictions for incoming transaction requests may be modified. Input values corresponding to the input feature may be monitored to determine if the anomaly is sustained or receded. The modified risk model may be reverted back to the original risk model when the anomaly no longer exists.

A kind of multi-risk management method based on worst-case scenario conditional value at risk model, by setting the operation mode of virtual power plant in single electricity market, and after analyzing its bidding profit and constraint, the typical distribution scene of uncertain variable that will bring risk is constructed by using Monte Carlo simulation method and fast pre-generation elimination technology based on probability distance, then the conditional value at risk model under worst-case scenario is constructed, and the maximum conditional value at risk under worst-case scenario is taken as the goal, max-min problem is converted into semi-definite programming problem by using dual theory to solve, and the optimal bidding strategy of virtual power plant after management risk is solved.The present application can be used as a powerful tool for decision-making, provide theoretical support for virtual power plant to formulate scheme to improve the prediction accuracy of random variable, so as to minimize the market risk caused by prediction error, and make the transaction strategy closer to the optimal strategy under accurate situation.

The invention relates to the technical field of financial credit risk control, in particular to a risk control model construction method and system for identifying customer credit risks, and the method comprises the steps: constructing a cross-product dichotomy task data set; training a sample similarity screening model; outputting a probability score; performing equal-frequency division according to probability scores and calculating the concentration and multiple of new product positive samples in each subgroup; selecting the group with the highest multiple as a high-similarity candidate region, carrying out multi-round equal-frequency division, judging whether equal-frequency division is stopped or not by combining a convergence judgment mechanism, and determining to supplement positive samples; and integrating the new product positive sample and the supplementary positive sample to carry out weighted training. According to the method and the device, the sample similarity screening model is constructed, and multiple rounds of equal-frequency segmentation, KS index monitoring and a target sample multiple evaluation mechanism are combined, so that old product samples highly similar to target positive sample features are dynamically identified, high-quality expansion of an original positive sample set is realized, and the training effect and generalization ability of a subsequent risk model are improved.

This application discloses a risk model iteration method, apparatus, device, and product, relating to the field of model iteration technology. The method includes: collecting operational data of an initial risk model in a production environment; detecting the operational data using detection indicators; when the operational data reaches the iteration trigger condition, creating a model iteration task and loading a pre-configured business dataset; collaboratively optimizing the hyperparameters of the initial risk model using the business dataset to obtain a globally optimal feature subset and an optimal hyperparameter combination; and iterating the initial risk model using the globally optimal feature subset and the optimal hyperparameter combination to obtain a final risk model. This solves the problems of lacking automated closed-loop iteration, delayed response, and the need for professional personnel to operate the risk model, thus failing to quickly adapt to dynamic business changes and improving the efficiency of risk model iteration.

The invention relates to the field of artificial intelligence, and provides a distributed training method and device of a risk control model, equipment and a medium, which are applied to the financial field, and the method comprises the following steps: separately fragmenting risk control data of each mechanism node to obtain a plurality of pieces of target fragmented data; inputting the plurality of pieces of target fragment data and the global parameters into a risk control model to carry out distributed training and output first target parameters; aggregating, adjusting and collecting the first target parameter to obtain feedback data; and predicting the feedback data to obtain a prediction error value, updating the training parameters by using the prediction error value to obtain updated training parameters, and re-initializing the global parameters according to the updated training parameters to start a new round of distributed training. By implementing the embodiment of the invention, distributed training and parallel computing of each node of the risk model are realized, the model training time is shortened, the risk control model can quickly respond to the risk change of the current insurance market, the timeliness and accuracy of risk early warning are improved, and thus the efficiency is improved.

The invention belongs to the technical field of artificial intelligence, and relates to a data generation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining disaster intensity data, and calculating corresponding disaster intensity change data based on the disaster intensity data; judging whether the disaster intensity change data meets a dynamic optimization condition or not; if yes, updating the initial loss rate function based on the disaster intensity data to obtain a target loss rate function; performing function updating processing on the risk model based on the target loss rate function to obtain a target risk model; solving the target risk model based on a quantum annealing strategy to obtain target reinsurance proportion data; generating a target reinsurance scheme based on the target reinsurance proportion data and outputting the target reinsurance scheme; in addition, the invention also relates to a block chain technology, and the target reinsurance scheme can be stored in a block chain. The method can be applied to an insurance risk assessment scene in the field of financial science and technology, and the generation efficiency and accuracy of the target reinsurance scheme are effectively improved.

The invention relates to the technical field of financial data analysis, in particular to a fund product analysis system based on big data, which comprises an event flow analysis module, a correlation analysis module, a dynamic optimization module, a strategy configuration module and a data synchronization verification module. The system collects financial market data in real time, generates an event feature matrix, combines a graph neural network and reinforcement learning technology, dynamically adjusts risk model parameters, generates a risk early warning and strategy optimization scheme, and monitors the consistency of a physical data source and a virtual model at the same time. According to the method, the accuracy and the real-time performance of fund product analysis can be improved, and the scientificity and the reliability of investment decision making are enhanced.

The invention relates to the technical field of big data, and provides a financial business risk control management system based on a big data model, and the system comprises the steps: accessing labor data in multiple platforms and financial data of different accounts, carrying out the cross-domain convergence and disambiguation of different accounts of a user, and forming a corresponding unified identity ID; the method comprises the following steps of: collecting multi-source time sequence events from each business system and risk control system by taking a unified identity (ID) as a main key, merging and connecting in series according to a time sequence, and generating a behavior time axis reflecting cross-platform working intensity and stability; carrying out statistics and operation on the labor behavior time axis and the fund behavior time axis, and generating a health degree index which simultaneously represents credit stability and fraud suspiciousness; and based on the health degree index and a preset label sample, jointly training a credit risk model and a fraud risk model, outputting a risk score and a strategy decision result at a business risk control node, and carrying out cooperative control on credit admission, quota management and fraud interception of the zero worker crowd.

A computer-implemented method for testing a risk model trained to output a risk determination for open banking transactions that includes: unit testing the risk model implemented in an application programming interface (API) platform; performing manual and automated feature validation of the risk model by comparing feature outputs from the risk model to expected feature output values; performing functional validation of the risk model according to an accuracy metric; benchmark testing the risk model, implemented in the API platform, using simulated scenario test data sets; load testing the risk model; after performing the foregoing, deploying the risk model as a production risk model with a web portal in a production environment; and dog-food testing the production risk model using a plurality of simulated scenario test data sets configured to simulate real production usage.

The application relates to the technical field of invoice risk control management, and discloses an invoice risk control management method and system based on multi-source data linkage. The method realizes real-time collection of multi-source data of an invoice business whole process through a multi-source data fusion gateway. The multi-source data is subjected to flow ETL processing and encryption integration to generate an encrypted unified data view. Based on the view, a correlation hypergraph is constructed by using a dynamic graph correlation technology, and entity relationships are analyzed by means of a graph neural network to identify virtual invoice gang and repeated financing risks. Risk quantification and traceability technologies are adopted to calculate a dynamic risk score, and a risk level, a responsibility node identifier and a fund flow direction heat map are output. When the risk score exceeds a threshold value, risk gradient information is safely shared among a group headquarters, a branch company and a tax and bank institution to trigger linkage disposal actions such as invoice freezing, red letter notification or credit adjustment. According to an artificial review result, a risk model is fine-tuned and a rule library is hot-updated by using a knowledge self-updating technology.

A computer-implemented method for testing a risk model trained to output a risk determination for open banking transactions that includes: unit testing the risk model implemented in an application programming interface (API) platform; performing manual and automated feature validation of the risk model by comparing feature outputs from the risk model to expected feature output values; performing functional validation of the risk model according to an accuracy metric; benchmark testing the risk model, implemented in the API platform, using simulated scenario test data sets; load testing the risk model; after performing the foregoing, deploying the risk model as a production risk model with a web portal in a production environment; and dog-food testing the production risk model using a plurality of simulated scenario test data sets configured to simulate real production usage.

The present invention relates to a system and method for quantum-classical agentic orchestration for real-time financial risk modeling and architectural drift remediation in multi-cloud environments. The invention provides an integrated computing arrangement comprising at least one classical processing unit, a quantum interface controller, data acquisition and normalization processors, a risk modeling processor, an orchestration control unit, an architectural state monitoring unit, a drift detection processor, and a remediation execution unit configured to operate in coordination. The system continuously receives financial data streams and infrastructure telemetry from distributed cloud environments, processes the data to generate standardized analytical representations, and performs hybrid computational analysis by combining classical evaluation with quantum-assisted optimization for complex financial risk scenarios. The system further monitors configuration states, deployment topology, and resource allocation parameters to detect deviations from predefined architectural baselines.

The invention relates to the technical field of financial data management and control, in particular to a financial multi-source heterogeneous data real-time fusion and risk identification method, which comprises the steps of data acquisition, time alignment and metadata annotation, multi-modal preprocessing, real-time fusion mapping, risk modeling analysis, signal fusion decision, real-time early warning, credible evidence storage and online learning optimization. According to the invention, by introducing a distributed acquisition agent module and a nanosecond timestamp synchronization mechanism, the problems of time desynchrony and non-uniform formats among different data sources are solved; by combining metadata annotation and a micro-service preprocessing engine, structured, semi-structured and non-structured data can be standardized, the availability and semantic consistency of multi-modal data are remarkably improved, and a high-quality data basis is provided for subsequent risk identification.

The invention discloses a financial investment user operation optimization method based on big data, and relates to the technical field of data analysis, and the method comprises the following steps: setting a first constraint condition, constructing a risk model, setting an inspection index, inspecting the risk model according to the inspection index, and compensating the risk model according to an inspection result. And outputting a new investment type proportion according to the new risk model. Through accurate risk assessment and personalized investment suggestions, a user can obtain an investment scheme better meeting own requirements, big data and a machine learning technology can analyze market trends in real time, investors can be helped to make more scientific investment decisions, and by dynamically adjusting investment portfolios, financial institutions better cope with market fluctuations, and the investment portfolios can be dynamically adjusted. Potential risks are reduced, and the optimized portfolio can better balance risks and earnings, so that the rate of return on investment is improved.

The application discloses a medium and long term spot green certificate fusion intelligent power transaction management platform, relates to the technical field of power transaction management, and synchronously collects real-time data, adopts linear optimization to generate a dynamic reference vector, uses the vector to calculate a cross fluctuation coupling index and a certificate power synchronous deviation index, and generates a synergistic risk adjustment coefficient through a Gaussian-Laplacian hybrid risk model to guide risk management; assembles a hedging package based on a smart contract, atomizes and locks power and corresponding green certificates, and ensures compliance and traceability by means of a blockchain; real-time tracking of the profit and loss and margin state of the hedging package is performed, and an adaptive threshold is used to trigger additional or released margin; through a prediction model, settlement profit and loss data are used to iteratively correct the reference vector; and the application significantly improves price discovery, renewable energy integration and market stability, and provides double benefits of economy and environment.

The invention provides a risk control result acquisition method and device, equipment, a medium and a program product, relates to the technical field of big data analysis, and aims to solve the problems of poor accuracy and low efficiency of risk control result determination. According to the technical scheme, the method comprises the steps that historical default data, market environment information and operation risk parameters of all links in the vehicle mortgage process are acquired; the historical default data, the market environment information and operation risk parameters of all links in the vehicle mortgage process are input into a target risk model, risk loss corresponding to at least one risk level is obtained, and the target risk model is obtained through training of a risk control data set of vehicle mortgage; based on the vehicle mortgage risk identification cost, the vehicle mortgage income and the risk loss corresponding to the at least one risk level, performing strategy analysis to obtain a target strategy set; and based on the target strategy set, outputting a risk control result of the customer mortgage the vehicle. And obtaining a risk control result of the customer mortgage the goods.

The invention discloses an intelligent risk control method, system and device, a storage medium and a product, index processing and rule multi-version management are supported by constructing a risk model and configuring a risk system and a risk index, and a monitoring scheme is generated based on a preset combination; after a data source and a knowledge base are accessed, when a service action is triggered, a receipt type, action and service data are transmitted, a monitoring scheme is matched, a rule engine is called, an index value is obtained, a rule is executed, traceability information is recorded, a processing result is generated and returned, and meanwhile real-time monitoring and timing monitoring are supported; executing event registration, rectification task allocation, process recording and auditing confirmation after risk identification to form a risk disposal closed loop; analysis is carried out based on a risk board and a report, and case precipitation and rule and index optimization are fed back to risk modeling, so that continuous iteration is realized. According to the invention, through data unification, rule configuration, real-time monitoring and whole-process closed-loop management, the intelligence and operation efficiency of enterprise risk control are significantly improved.

A fraud detection system preemptively identifies and mitigates fraudulent financial transactions in real-time across a diverse range of digital and physical transaction sources. Transaction data may be acquired from various platforms and categorized into rule sets specific to transaction types. Categorized data is aligned with existing risk profiles to construct a dynamic hysteresis model. This model, evaluated by a decision tree algorithm, identifies potential fraud by integrating immediate transaction details with a comprehensive historical data analysis, thus enabling advanced trend analysis and pattern recognition. Key features identified by the decision tree arc used to form a heuristics model, which is then analyzed by a transformer network risk model. A feedback loop enhances the system's effectiveness by incorporating decision outcomes back into the model training server, thus refining the training dataset and continuously improving the accuracy of the risk model.

The invention relates to an intelligent financial risk assessment method based on machine learning and deep learning, and belongs to the technical field of artificial intelligence. The technical problem to be solved by the method is that a traditional general risk model neglects industry specificity to cause evaluation deviation, for example, high research and development investment of a scientific and technological enterprise is misjudged to be high risk. According to the technical scheme, the method comprises the steps of obtaining target enterprise financial data and industry identifiers; extracting a historical financial distribution data set of the corresponding industry; calculating dynamic distribution similarity and generating an industry context matching vector; generating an industry customization feature weight vector through dynamic interpolation; and performing weighted aggregation to generate an industry adaptation risk score. According to the invention, industry adaptive weight configuration is realized through machine learning, the cross-industry risk assessment accuracy is improved, and the method is mainly used for bank credit decision and risk management and control.

The invention discloses a risk prevention and control method, device and equipment based on a settlement and clearing platform and a medium, and relates to the field of carbon transactions, the method comprises the following steps: collecting carbon transaction related data, the carbon transaction related data comprising internal data from an internal system of an enterprise and external data from an external system of the enterprise; constructing a hybrid risk model based on the internal data, the external data and the data weight coefficient; in response to a carbon transaction request initiated by a user, executing a settlement and clearing process; calculating a carbon transaction risk value based on the real-time carbon transaction related data and the mixed risk model; determining an intervention level according to the carbon transaction risk value and the user comprehensive value so as to realize risk prevention and control of the settlement and clearing process; according to the method, by integrating internal and external multi-source data, the limitation of a single data source is solved, the sensitivity to external risks such as carbon price fluctuation and policy adjustment is improved, passive risk control is changed into active intervention, and loss caused by risk early warning lag is avoided.

The invention provides a risk model training method and device, equipment, a medium and a program product, relates to the technical field of artificial intelligence, and can solve the problem of poor accuracy of a risk identification result output by a risk model. According to the specific technical scheme, a risk control data set is obtained, wherein the risk control data set comprises customer record data, market environment data and customer network behavior data of a resource provider; acquiring features related to the target business risk from the risk control data set by adopting EDA to obtain a first feature set; based on the data types of the features in the first feature set, using correlation analysis and chi-square test to obtain features satisfying correlation conditions from the first feature set to obtain a second feature set; performing feature dimension reduction processing on the second feature set to obtain a target feature set; and based on the target feature set, performing model training on the random forest model to obtain a target risk model. And obtaining a risk identification result of the business account.

The invention relates to the field of consumer finance risk model management systems, and discloses a consumer finance risk control model management method, which comprises the following steps of: packaging a model file into a Docker container mirror image, capturing metadata to generate a list, and pushing the list to a mirror image warehouse and a metadata database after quality detection; a version dependency graph is constructed, a difference recognition index is obtained through comparative analysis, and mirror image differential deployment is achieved; after deployment, obtaining a consumer financial data stream, extracting real-time features and fusing the real-time features with historical features, and using a feature access prediction model to optimize comprehensive feature value storage; combining the optimized comprehensive characteristic value with historical training data, and retraining the model to generate a candidate new model; and online model performance is monitored in real time, attenuation is identified by using a multi-modal model, and if the performance is attenuated, cause and effect reasoning is adopted to analyze reasons and early warning is performed. Through multi-link optimization, model deployment and data utilization efficiency are improved, and model performance monitoring accuracy and problem response speed are enhanced.

The invention discloses a method, equipment, a storage medium and a program product for screening clients according with credit card handling qualification. The method for screening clients according with credit card handling qualification comprises the following steps: a collection and fusion step: collecting structured data and unstructured data of clients, and carrying out multi-modal data fusion; a weighted evaluation step of setting an initial weight for the fused data in the acquisition fusion step, dynamically adjusting the weight, and performing quantitative evaluation and threshold judgment to perform optimization; a risk modeling step: carrying out industry risk space-time conduction modeling and risk slow release according to the data evaluated in the weighted evaluation step; a self-adaptive matching step in which the industry risk space-time conduction modeling is learned to generate a matching strategy so as to execute the screening of credit card handling; and a feedback step of feeding back a screening result of credit card handling. The adaptive matching step comprises a state space definition step, a reward function design step, a small sample adaptive matching step and a negative feedback closed loop optimization step.

The invention discloses a financial analysis management platform and a management method thereof, and relates to the technical field of supply chain finance. Comprising a data acquisition module, a feature processing module, a risk modeling module, a cooperative training module and a result display module, wherein the data acquisition module is used for acquiring multi-dimensional data in a supply chain financial scene and outputting an original data set. The risk control foundation is built through multi-dimensional data acquisition and verification and dynamic feature optimization: a data acquisition module is in butt joint with multiple systems to obtain key data such as credit investigation and logistics, a block chain interface is compatible to confirm right, and the data integrity rate is ensured to be greater than or equal to 95% through triple verification; and the feature processing module uses a 3 sigma principle to remove abnormal values, builds three feature groups, adjusts weights according to a random forest Gini importance quarter, and outputs a 20-30-dimensional feature vector set, so that the problem of weak risk assessment basis caused by information fragmentation, low data quality and poor feature adaptability in a supply chain financial scene is solved, the'light asset 'characteristic of the supply chain financial scene is adapted, and the risk assessment efficiency is improved. And reliable input is provided for risk modeling.