25 results about "IT risk" patented technology

The invention discloses an autoregressive language model training process-oriented data leakage risk quantification method, which comprises the following steps of: executing enhanced member data division processing on an original training text set, and generating a ternary partition text set containing member, non-member and key boundary texts through an optimization function; for each text, using the target model to extract member attributes from three channels of forward reasoning, back propagation and state evolution, and fusing the member attributes into member attribute vectors; inputting the member attribute vector into a hierarchical comparison embedded network, and mapping the member attribute vector into an optimized embedded representation vector through comparison learning including similar clustering, heterogeneous separation and boundary positioning; and inputting the embedded representation vector into a dynamic reasoning classifier capable of perceiving a training stage, judging the risk membership degree of the dynamic reasoning classifier, and generating a data leakage risk quantification result. According to the invention, real-time and fine-grained dynamic quantification can be carried out on the leakage risk, and timely early warning is provided for model training.

The invention discloses an AI-based digital value-added service method for claim and debt demand analysis, and the method comprises the steps: receiving a claim and debt original file set uploaded by a client, and generating a structured clause element set which comprises clause types, core elements and expression mode features; generating a risk quantification label of each key term based on the structured term element set; inputting the structured clause element set and the risk quantification label into a pre-trained clause value-risk collaborative optimization model, and generating a group of optimization clause revision suggestion sets for maximizing a user set value target on the premise of risk controllability; revising the suggestion set for the optimization terms, and generating a feasible revision strategy sequence sorted according to the adaptation degree; and based on the feasible revision strategy sequence, determining a final term revision scheme and matched risk slow release measure suggestions, and taking the final term revision scheme and the matched risk slow release measure suggestions as output of the digital value-added service. According to the embodiment of the invention, the accuracy and decision-making efficiency of credit and debt management can be improved.

The invention discloses a multi-modal fusion short message compliance and security dual auditing method and system, and the method comprises the steps: encrypting account information through employing an irreversible algorithm based on SHA256 and a random salt value, and decomposing the content of a short message into a text stream, a link stream and a symbol stream through employing a regular expression; traversing each character in the short message content by adopting a prefix mode based on a Trie tree in combination with an AC automaton algorithm to detect sensitive words; performing symbol semantic classification mapping and analysis on the special symbol feature data extracted from the symbol stream; carrying out sending behavior analysis on the text feature data extracted from the text stream; performing special detection on link feature data extracted from the link stream; based on the factors corresponding to the sensitive words, the semantics, the behaviors and the links and the weights of the factors, a multi-modal feature fusion decision risk assessment algorithm is adopted to output a risk score value and a risk decision rule of the risk score value so as to execute short message interception operation or short message release operation. According to the invention, full-dimension perception and dynamic defense of risks can be realized.

The invention discloses an enterprise risk data determination method and device, a storage medium and an electronic device, and the method comprises the steps: constructing an enterprise relation graph corresponding to an enterprise set according to the risk of each enterprise in the to-be-predicted enterprise set and the incidence relation between the enterprises, each enterprise serves as a node in the enterprise relation graph, and the nodes of the enterprises with the incidence relation are mutually connected; nodes with self risks larger than a first threshold value in the enterprise relation graph serve as risk nodes; respectively spreading the risk signal of the risk node to all non-risk nodes which are connected with the risk node and meet the spreading condition; and determining and updating the risk data of the non-risk node according to the risk data of the non-risk node and received risk signals transmitted by all risk nodes connected with the non-risk node. Accurate prediction of enterprise risks is realized by simulating diffusion of risk signals in an enterprise network.

The invention provides an artificial intelligence dialogue compliance examination method and system based on a local small model, and the method comprises the steps: obtaining a user input request and related contents, sending the user input request and related contents to the local small model (LSM), and carrying out the examination before sending according to a preset rule; if the content is compliant, sending the content to an external large language model (LLM) to obtain a response; external LLM response content is returned in a streaming mode or a complete mode, the LSM performs real-time examination on each data fragment returned in the streaming mode, if illegal fragments exist, the illegal fragments are processed according to risk levels, and if no illegal fragments exist, the illegal fragments are displayed; and the complete response is directly displayed. The system also performs overall post-review on all contents, and if problems are found, the problems are processed according to risk levels, otherwise, the problems are displayed to users. According to the invention, on one hand, the local small model is deployed to carry out multi-stage compliance examination on the whole process of user input and LLM output, and data privacy protection and content security control are realized; and on the other hand, real-time interruption and cross validation can be performed on high-risk contents, mechanisms such as log recording, objection feedback, service degradation and the like are supported, and the reliability, stability and traceability of system review are ensured.

The present invention discloses a method and system for monitoring the safety of the production process of cylindrical equipment, which relates to the field of industrial safety monitoring technology, including: real-time acquisition of video streams of the production area of ​​cylindrical equipment and uploading; automatic identification of which process segment of the production process the current operation content belongs to based on the video stream information; if no identification result is found, returning to step one and continuously looping monitoring; if there is an identification result, calling the corresponding detection algorithm based on the identified process segment to identify the safety risks existing in the production of the process segment; outputting the result of the safety monitoring based on the obtained detection result according to the set risk judgment conditions; if the monitoring result is that there is no safety risk, returning to step one; if the monitoring result is that there is a safety risk, triggering a safety alarm. The present invention can effectively prevent the occurrence of safety accidents and reduce the false recognition rate by classifying and identifying different scenarios in the entire production process according to their risk characteristics, thereby improving the overall production safety level and production efficiency.

This invention discloses a cloud gaming vulnerability analysis and monitoring system based on cloud computing, relating to the field of game vulnerability analysis technology. The system includes a game monitoring module, an intelligent aggregation module, and a resource scheduling module. The game monitoring module collects performance parameters and interaction parameters of game instances through a lightweight monitor, and calculates anomaly frequency, coefficient of determination, kurtosis, and temporal anomalies using multidimensional modeling and statistical analysis. Based on this, it performs comprehensive calculations to generate risk assessment values ​​and screen suspicious targets. The intelligent aggregation module performs similarity calculations and undirected graph clustering on suspicious targets and their risk parameters to aggregate scattered suspicious targets into vulnerability analysis tasks. The resource scheduling module calculates an evidence collection index based on parameters such as task size, latency, average risk, and similarity. Based on the evidence collection index, it allocates vulnerability analysis tasks to parallel analysis lines in an isolated analysis cluster for execution, thereby achieving in-depth forensics and dynamic detection.

The application discloses a kind of multi-energy collaborative heating system risk assessment and regulation method and device, based on improved GNOME model, risk source in multi-energy collaborative heating system is analogized as oil spill source, risk propagation is analogized as oil spill diffusion, by defining risk particle and giving its risk type, risk level, initial position and influence range etc. Property, using similar convection and diffusion mechanism in oil spill model, in combination with energy flow and information transmission in heating system and other factors, the propagation path and change of risk in heating network are simulated. The present application helps to master the risk development trend in real time, early warning potential risks, provides strong support for formulating targeted risk control measures, and ensures the safe, stable and efficient operation of multi-energy collaborative heating system.

The invention relates to a resource-pooling system and to a corresponding method for risk sharing of a variable number of risk exposure components. The risk exposure components are connected to the resource-pooling system by means of a plurality of payment receiving modules configured to receive and store payments from risk exposure components for the pooling of their risks. The total risk of the pooled risk exposure components comprises a first risk contribution associated to risk exposure in relation to loan losses, and a second risk contribution associated to risk exposure based on emergency expenses. The pooled risk is divided in a parameterizable risk part and a non-parameterizable risk part by means of an indexing module. In case of triggering a loss by means of a trigger module, the suffered loss is covered by releasing associated loans and emergency expenses of the risk exposure components.

The invention relates to a method for analyzing the IT risk of a network of interest (20) directly or indirectly exchanging network flows with at least one third-party network (30, 40, 50), comprising the following steps: - retrieval of network flows captured by at least one firewall (32, 42, 52) belonging to at least one third-party network; - comparison of the destination and origin internet addresses of each retrieved network flow with at least one database of toxic internet addresses (64); each network flow incorporating at least one destination or origin internet address stored in said database of toxic internet addresses corresponding to a toxic flow; and - identification, for each toxic flow, of the nature of the risk in order to determine whether each toxic flow presents a risk to the network of interest or to one of said at least one third-party network. Figure 2.

This invention discloses a blockchain address association analysis method based on graph database risk propagation, belonging to the field of blockchain association analysis technology. The invention includes attribute graph modeling, risk propagation analysis, and incremental risk mechanism updates. It is based on modeling blockchain transaction data as an attribute graph and storing it in a graph database. Then, using marked risk addresses as seed nodes, a multi-hop risk propagation algorithm with a decay factor propagates risk scores along transaction edges. Finally, combined with community detection and threshold truncation mechanisms, it outputs a set of associated risk addresses and their risk levels, achieving quantitative identification of hidden associated risk addresses. Simultaneously, it accurately and efficiently discovers organized abnormal networks and fund loops, enabling timely risk prediction and prevention, effectively controlling the propagation range, and meeting the real-time requirements of risk control and early warning scenarios.

The present invention discloses a data leakage risk quantification method for the autoregressive language model training process, comprising: performing enhanced member data partitioning processing on the original training text set, generating a ternary partitioned text set containing member, non-member, and key boundary text through an optimization function; for each text, using a target model to extract member attributes from three channels: forward reasoning, backpropagation, and state evolution, and fusing them into a member attribute vector; inputting the member attribute vector into a hierarchical contrast embedding network, mapping it into an optimized embedding representation vector through contrastive learning including similar clustering, heterogeneous separation, and boundary positioning; inputting the embedding representation vector into a dynamic reasoning classifier that can perceive the training stage, determining its risk membership, and generating a data leakage risk quantification result. The present invention can perform real-time, fine-grained dynamic quantification of leakage risk, providing timely warning for model training.

A digital assets investments platform that allows investors to modulate their risk and volatility. The platform includes seven components; (1) a risk engine module containing quantitative derivative pricing and volatility models that are used to determine valuation of new synthetic instruments on an ongoing basis; (2) a reference asset of which the new synthetic instruments are derivatives; (3) a collateral asset that is deposited with the platform and has a value that underwrites the value of the new synthetic instruments; (4) a tokenization module into which some amount of the collateral asset is deposited; (5) a settlement period at the end of which the synthetic instruments are settled and a new period of time begins; (6) embedded derivative exposures that are embedded in the new synthetic instruments; and (7) derivatives parameters which define the embedded derivatives. Also disclosed are a related system and computer-readable non-transitory storage media embodying software.

A digital assets investments platform that allows investors to modulate their risk and volatility. The platform includes seven components; (1) a risk engine module containing quantitative derivative pricing and volatility models that are used to determine valuation of new synthetic instruments on an ongoing basis; (2) a reference asset of which the new synthetic instruments are derivatives; (3) a collateral asset that is deposited with the platform and has a value that underwrites the value of the new synthetic instruments; (4) a tokenization module into which some amount of the collateral asset is deposited; (5) a settlement period at the end of which the synthetic instruments are settled and a new period of time begins; (6) embedded derivative exposures that are embedded in the new synthetic instruments; and (7) derivatives parameters which define the embedded derivatives. Also disclosed are a related system and computer-readable non-transitory storage media embodying software.

We provide the system. [Solution] Means of obtaining information from users regarding their risk tolerance and asset goals, A means of collecting and analyzing market data in real time, A means of determining investment strategies using machine learning models based on collected data, A means for automatically adjusting a resource portfolio based on a determined investment strategy, and generating and executing buy and sell orders, A means of notifying users of the status of their asset portfolio and providing feedback via smart devices, A system that includes this.

The application discloses a kind of movables pledge monitoring methods based on Internet of Things, specifically related to financial risk control technical field, including the following steps: collection pledge individual multi-modal data, generate the value vector containing current individual value, value confidence and value change trend;Baseline is constructed based on group distribution, deviating individual is identified and marked to be confirmed abnormal event;According to signal continuity, node state and network log, distinguish abnormal source, filter false alarm and output real risk event;According to its risk level and confidence, adjust pledge rate and disposal intensity, and execute corresponding disposal operation;The application realizes individual value dynamic evaluation by generating value vector;By constructing group baseline and distinguishing abnormal source, filter false alarm event, improve risk identification accuracy;By dynamically adjusting pledge rate and disposal intensity according to risk level and confidence, realize flexible self-adapting risk control.

The invention relates to the field of power system security risk assessment, and discloses a power system software security risk assessment method based on a software bill of material (SBOM), comprising a core component identification module, the core component identification module extracts component metadata from an SBOM, judges whether a component belongs to a key function module in combination with a power system business logic, and sends the component metadata to the SBOM; the core component identification module is connected with the risk weight calculation module, and the risk weight calculation module dynamically adjusts the risk weight coefficient of the core component according to the identification result of the core component identification module and whether the component is a power core component. And the risk judgment index is more accurate. According to the method, the TF-I DF algorithm of the function keyword matching module is utilized, the graph traversal algorithm of the control flow risk module is combined, SBOM component metadata is deeply mined, key components are accurately judged according to power business logic, software security risks are comprehensively captured, and the identification problem in the prior art is solved.

The invention relates to the technical field of computer security monitoring, in particular to a terminal security monitoring and response solving method and device, equipment and a storage medium. The terminal security monitoring and response solution method comprises the following steps: acquiring historical security event data, mining an association rule in the historical security event data, calculating an abnormal score of each piece of historical security event data according to the association rule, and generating a risk value according to the abnormal score; training a pre-constructed basic model by adopting the historical event data and the risk values thereof to obtain a decision tree model; acquiring real-time security event data, system logs and network activity records, encrypting the data and transmitting the data to the cloud platform; analyzing the encrypted data, classifying the analyzed data by adopting a pre-constructed rule, and generating a preliminary report; and analyzing the preliminary report by adopting a decision tree model to generate a response action and a comprehensive report. Through correlation analysis of the data, the monitoring efficiency and the response speed of the terminal equipment can be improved.

The invention discloses a high-precision well lid risk identification and early warning system for urban fine management, and relates to the technical field of urban infrastructure management, and the system comprises a data acquisition module, a model management module, a risk identification module, an early warning generation module and a result display module. A well lid image is received through a data acquisition module; the risk identification module calls a pre-training model selected by a user according to computing power or precision requirements in the model management module for reasoning so as to identify the position of the well lid and classify the risk state of the well lid; and the early warning generation module generates early warning information according to the result, and the result display module visually displays the early warning information. In addition, a model is converted into an ONNX format through a model optimization processing unit to improve CPU reasoning efficiency, continuous optimization of system performance is achieved through a model iteration training module, the problems that traditional inspection efficiency is low and an existing intelligent scheme is insufficient in flexibility are solved, and efficient, accurate and low-cost manhole cover risk management is achieved.

This invention discloses a method for predicting GIS equipment failure risk based on minimum cut set probability propagation. The method includes acquiring GIS equipment structural information, constructing a fault tree model containing top events, intermediate events, and bottom events, and performing qualitative analysis to determine the minimum cut set corresponding to the top event. Combining historical failure information of the basic components corresponding to each bottom event, the method calculates the weighted failure rate and failure probability, and performs probability propagation based on the minimum cut set structure to obtain the occurrence probability of each minimum cut set and its risk contribution to the top event. An adaptive threshold is used to identify the dominant failure mode. Real-time operating status information of each basic component is acquired, a bottom event status deviation index is constructed, the failure probability of bottom events is dynamically corrected, and the occurrence probability of the dominant failure mode is updated to predict the real-time failure risk of the GIS equipment. This invention can integrate historical and real-time data to achieve dynamic assessment of equipment failure risk, improving prediction accuracy and operational reliability.

This application provides a method for determining data risk levels. It can be applied in the fields of artificial intelligence and big data technologies. The method includes: acquiring original component update data and update data of n changed components; constructing a knowledge graph based on the n preset business strategies and historical fault data of the n changed components to generate a fault association knowledge graph of the n changed components; performing differential analysis on the original component update data and each changed component update data to generate differential data; inputting the differential data and the fault association knowledge graph into a pre-trained risk model to output a risk score for each changed component update data; and determining the risk level of each changed component update data based on its risk score. This application also provides a data risk level determination apparatus, device, storage medium, and program product.

The system will allow users to identify their risk of incidents occurring based on electronically stored support record document data. [Solution] To predict incidents occurring among users of welfare support facilities, the present invention provides an incident prediction program for welfare support facilities characterized by the following functions: a support record acquisition means that acquires support record text data from a support record database where support records of users of welfare support facilities are stored; a risk value derivation means that extracts entries correlated with incident occurrence (incident correlation entries) from the support record text data acquired by the support record acquisition means, scores each extracted incident correlation entry to derive an incident risk value for each user; and a risk value transmission means that transmits the risk value derived by the risk value derivation means to a user terminal.

This invention discloses a method and apparatus for AI Agent security protection. In this embodiment, user prompt information is input into an input protection layer, where it is detected according to a first detection rule base to determine its risk level. If the risk level is not high, the user prompt information is automatically anonymized and filtered for harmful content to generate safe user prompt information. The safe user prompt information is then input into a behavior protection layer, where it is detected according to a second detection rule base to determine the risk level of the called toolchain. If the risk level is not high, the content returned by the called toolchain is obtained. The target content returned by the called toolchain is then input into an output protection layer, where it is detected according to a third detection rule base to determine its risk level. If the risk level is not high, the target content is automatically anonymized and filtered for harmful content to generate safe output content. This method provides efficient and accurate security protection for AI Agents.

This invention proposes a method for determining key sections of urban gas pipelines using spatial coordinate information services. It relates to the field of key area identification technology. The method involves collecting, organizing, and fusion map information on the urban gas pipeline environment to obtain real-time spatial fusion information. This real-time spatial fusion information is then analyzed and segmented to obtain first spatial sections. Pressure assessment is performed on the first spatial sections to obtain second spatial sections and their risk level assessment information. An impact level assessment is then performed on each second spatial section to obtain section level determination information and its impact level assessment information. Based on the risk level assessment information and the impact level assessment information, the second spatial sections are analyzed and segmented to obtain key section determination information. This invention achieves accurate identification of urban gas pipeline areas through information collection, area segmentation, risk and impact assessment, and weight determination.

This invention relates to the fields of artificial intelligence and reasoning technology, and discloses a hierarchical attention-based large-scale model reasoning system and method for complex decision-making. The system includes a target intent module; a path planning module; an operation verification module; a potential energy processing module; and a reasoning decision-making module. The method includes: receiving a query, decomposing it into a target kernel and constructing an ideal potential energy profile; generating multiple parallel reasoning paths based on this profile; aggregating each path into a single polarized potential energy vector through evidence retrieval and quantification; calculating the potential energy alignment of each path and monitoring whether its risk component exceeds a safety threshold; if it exceeds the threshold, generating a hedging subtask to adjust the path based on feedback, and finally selecting the safe and reliable optimal solution. This invention significantly improves the reliability, objectivity, and security of complex decision-making by uniformly quantifying the target, evidence, and risk, and establishing a risk monitoring and closed-loop feedback mechanism.