52 results about "Decision rule" patented technology

The present application belongs to the field of weld weight prediction, and particularly relates to a bus steel structure weld weight prediction method and system, which comprises the following steps: reading a three-dimensional model and generating an initial weld path set; filtering, continuity repairing and logical segmentation based on process avoidance features are performed on the path to obtain an effective weld information set; the information set is input into a process decision rule library, and process specification parameters are decided according to structural features, wherein at least the large-section profile specific joint is decided as intermittent welding and the conversion rate is determined; finally, the weld weight is calculated and summarized according to the process parameters and geometric features. The method realizes the full-process automation and intelligentization from the model to the weight prediction, and significantly improves the prediction accuracy and efficiency.

Disclosed in the present description are a multivariate decision processing method and apparatus, a storage medium, and an electronic device. The method comprises: acquiring an initial multivariate decision rule system configured by a user end on the basis of standard DSL grammar rule information, wherein the standard DSL grammar rule information is DSL grammar rule information preset for a multivariate transaction decision development scenario; determining all multivariate decision rule combinations corresponding to the initial multivariate decision rule system, and determining reference transaction workflows corresponding to the multivariate decision rule combinations; constructing a multivariate combination instance library for the initial multivariate decision rule system, and on the basis of the multivariate combination instance library, performing engineering language conflict detection processing on the initial multivariate decision rule system, so as to obtain a target multivariate decision rule system after conflict detection; and using the target multivariate decision rule system to perform transaction workflow decision processing on transaction data.

This invention provides an autonomous control method for a drone swarm based on VGG16 and virtual game theory. The drones utilize a pre-trained attitude recognition model to identify the historical movement information of their opponents and calculate the opponent's strategy tendency at the previous moment based on this information. Then, the drones select a candidate action from a set of potential actions, calculating the opponent's strategy tendency and probability of choosing that action according to the game theory formula. A reward function is designed, and the drones select their own action based on the obtained opponent's strategy probability using the optimal response decision rule, observing the changes in the opponent's actions until the entire drone swarm reaches a stable state. This enables the analysis and game theory of multiple surrounding drones. When encountering signal interference, this invention allows some drone units to malfunction while the drone itself can adjust its movement attitude, maintaining relative stability for the entire swarm.

This invention belongs to the field of flight simulator maintenance technology, specifically relating to a machine learning-based predictive maintenance method for flight simulators. It addresses the problems of existing maintenance methods relying on periodic inspections and passive repairs, delayed fault warnings, and high false alarm / missing rate. This invention acquires historical operational data, sensor time-series data, fault records, and environmental parameters from the flight simulator, and performs preprocessing including cleaning, labeling, and feature fusion. It constructs a composite health feature set containing statistical features, dynamic health status values, and aircraft material reliability parameters. A hybrid prediction model (random forest feature selection + LSTM time-series prediction + adaptive correction reliability assessment) is used to train the model. Combining prediction result fusion analysis and multi-level decision rule post-processing, maintenance work orders and spare parts demand plans are output. This invention improves the accuracy and timeliness of fault prediction, realizing a shift from passive response to proactive prediction in maintenance, significantly reducing maintenance costs and the risk of unplanned downtime.

The application discloses a kind of based on the experience updating method, system and medium of security research and judge intelligent agent, is especially related to network security technical field, the method includes: under the condition that the reuse value score of candidate experience entity meets preset threshold condition, candidate experience entity is compared with the historical experience entity stored in experience memory base, and the comparison result is obtained;The comparison result is input into the preset multi-node decision rule tree, and according to the entity matching degree condition, attribute change type condition and confidence difference condition set in the multi-node decision rule tree, the update operation of candidate experience entity relative to historical experience entity is determined;The write request for candidate experience entity sent by security research and judge intelligent agent is obtained, and semantic logic verification and cross-source cross-validation are executed on candidate experience entity;In the case where semantic logic verification and cross-source cross-validation are both passed, candidate experience entity is updated into experience memory base according to update operation.

The present application belongs to the technical field of biological manufacturing data analysis, and discloses a biological manufacturing data analysis system based on artificial intelligence. The present application realizes intelligent biological processes, discusses the intelligent technology route of the entire subject according to the existing biological multiscale theory and the AI research system, starts the preparation work of connecting the AI system software and programming with the equipment manufacturing unit technology, and establishes the system. The double-track strategy of "general large model + parallel experiment data" is adopted: the general model provides basic cognition, and the experiment data forms the decision rule through the state-action-reward mechanism. The multiscale related curves, AI1.0 to 2.0 versions are related, the experiment data is associated with the relevant research in various places through the general large model, and the internal research is formed into a confidential database.

This application relates to a method and system for risk early warning of geotechnical infrastructure based on a multi-scale damage model. The method includes: acquiring environmental monitoring data of a target geotechnical area based on a preset monitoring scale; transforming the environmental monitoring data into a multi-scale damage model through multi-scale coupling analysis modeling; extracting spatiotemporal features of damage from the multi-scale damage model using a pre-trained convolutional neural network, and determining risk patterns by matching with a preset risk pattern library; inputting the spatiotemporal features of damage and risk patterns into a pre-trained risk diffusion probability prediction model to obtain risk propagation prediction results; constructing a multi-dimensional risk decision boundary using a nonlinear classifier based on the risk patterns and risk propagation prediction results; and generating graded early warning instructions through preset dynamic risk decision rules. This method can achieve accurate and dynamic early warning of risks to geotechnical infrastructure, preventing safety accidents caused by multi-scale damage evolution.

This invention discloses a multi-mode simulation and adaptive decision-making method for mixed-line assembly of aircraft, belonging to the field of system assembly simulation analysis. The invention constructs a unified simulation model including a set of entities, a set of activities, and a list of future events. It establishes a model initialization mapping function, mapping external input data to the initial state of entities or the initial list of future events according to order simulation mode, online simulation mode, or planned simulation mode. When a change in entity state triggers a decision, the invention calculates the score value of each decision rule based on the observation set, selecting the rule with the highest score for execution. The invention calculates the decision reward value based on the reward function, extracts decision samples and stores them in a sample library, and updates the scoring parameters by extracting samples at fixed time intervals. This invention enables order evaluation, risk prediction, and plan verification under a unified model architecture, improving the prediction accuracy and decision availability in mixed-line assembly scenarios.

This invention discloses a spacecraft autonomous mission decision-making method for complex stochastic tasks, belonging to the field of spacecraft mission decision-making technology. The method includes the following steps: S1, establishing a spacecraft mission decision-making model considering disjoint robustness; S2, transforming the model into a two-stage optimization framework problem; S3, introducing fuzzy sets to perform cone optimization transformation on the second-stage decision; S4, transforming the model into a numerically solvable cone optimization problem based on duality theory; S5, solving the cone optimization problem to complete mission scheduling. This invention adapts uncertainty through WKS-format fuzzy sets, combines resource consumption matrices and affine decision rules to avoid resource mismatch, significantly improving the efficiency and robustness of spacecraft mission decision-making and meeting the requirements of real-time dynamic scheduling.

The embodiment of the present disclosure provides a molten salt heat storage and coal power unit multimode optimization combined peak shaving method and system. The method comprises the following steps: collecting the power grid dispatching instruction, new energy and load prediction data and combined system operation state data in real time; identifying the feasible operation modes of the combined system in the current and future dispatching period, including pure condensing power generation, steam extraction heat storage, heat release power generation and cogeneration mode; for each mode, a multi-objective collaborative optimization model containing specific coupling constraints is established, and the total operation cost, peak shaving income, equipment life consumption and carbon dioxide emission are optimized simultaneously; a multi-objective optimization algorithm is used to solve each mode model in parallel, and based on a preset decision rule, a final dispatching scheme is selected from the global Pareto optimal solution set; the scheme is analyzed into control instructions and executed, and the system state is monitored to form a closed loop control. The multimode intelligent collaboration and multi-objective comprehensive optimization are realized, and the flexibility, economy and environmental protection of the combined system peak shaving are improved.

The application discloses a kind of based on extreme weather electric power transaction auxiliary decision processing method and system, it is related to electric power transaction decision-making technical field, including obtaining extreme weather early warning message formation original meteorological early warning data set;Space reference alignment is executed to the data set, and the grid chart containing meteorological intensity matrix and power generation facility distribution index is generated;Meteorological intensity matrix is mapped to obtain meteorological sensitivity coefficient matrix, and power generation facility distribution index topological correlation obtains power generation side asset vulnerability correlation table;Coupling deduction is generated in the risk transmission calculation engine by inputting both, and the electric power supply and demand imbalance risk thermodynamic diagram is generated;Based on the thermodynamic diagram, construct transaction price elasticity prediction model, form transaction strategy reference matrix;Through decision rule base matching generation offer interval suggestion, and conversion is standardized declaration instruction stream and is pushed to transaction interface end.This method can accurately connect extreme weather information and electric power transaction decision-making, improve the accuracy and standardization of transaction decision-making.

The present application belongs to the field of agricultural information technology and data processing, and specifically relates to a multi-modal data standardization processing method and system for phenology recognition, and a medium. The method comprises: (1) obtaining a multi-modal original data set of various state parameters of crops; and determining statistical characteristics of each state parameter according to the multi-modal original data set; (2) assigning a suitable standardization strategy to each state parameter according to the statistical characteristics and a preset decision rule; (3) standardizing each state parameter according to the assigned standardization strategy; and fusing the data set of each state parameter after standardization into a standardized multi-modal data set for phenology recognition. The present application solves the technical problem that a single and fixed standardization method in the prior art can introduce bias and reduce the accuracy of a subsequent phenology recognition model.

The application provides a method and system for quickly extracting three-branch cause rules of highway tunnel traffic risk at multiple granularity levels, and belongs to the technical field of three-branch concept analysis. The method comprises the following steps: S1, obtaining a three-branch concept lattice derived from objects after attribute granularity refinement; S2, obtaining representative three-branch decision association rules after attribute granularity refinement; and S3, obtaining three-branch cause rules of highway tunnel traffic risk at different granularity levels. The application proposes a quick updating method for a concept lattice (OE3W concept lattice for short) derived from objects after attribute granularity refinement, a method for quickly updating three-branch decision association rules (representative three-branch decision association rules) based on the OE3W concept lattice, and applies the method to updating of traffic risk three-branch cause rules, thereby solving the problems of the traditional traffic risk cause rules (single granularity level decision rules) in the aspects of rule updating efficiency and knowledge expression degree.

The application provides a pump-driven two-phase flow loop fault diagnosis method and device based on Naive Bayes, a medium and equipment. The method comprises the following steps: acquiring real-time monitoring data of a pump-driven two-phase flow loop; converting a target characteristic parameter of the real-time monitoring data into a discrete state value based on a preset discretization rule; inputting the discrete state value into a pre-trained fault diagnosis model to generate a probability curve corresponding to each of a plurality of fault types defined by the fault diagnosis model; determining a diagnosis result of the pump-driven two-phase flow loop based on a preset multi-threshold decision rule and the probability curve; wherein the multi-threshold decision rule is used to determine a fault occurrence, and the multi-threshold decision rule comprises an absolute probability condition, a relative probability value condition and a relative threshold length condition that need to be met by the probability curve of each fault type. The application constrains the model through the multi-threshold decision rule, improves the accuracy of the fault diagnosis result, and the obtained result has interpretability.

This invention relates to the field of power distribution cabinet technology and provides an intelligent monitoring system and method for environmentally adaptive power distribution cabinets. The system includes: S1, integrating several environmental sensors within the cabinet to collect environmental data during a collection period; S2, pre-setting an environmental state recognition model to obtain an environmental state pattern; S3, using the environmental state pattern as a judgment condition and external environmental data as a constraint condition, inputting them into a pre-set environmental decision rule to obtain a set of decision actions; S4, prioritizing the decision actions within the decision action set to obtain the optimal set of decision actions; S5, executing the decision actions and recording the decision results; and S6, performing backtracking analysis on the historical database according to a backtracking period to optimize the decision threshold. This invention achieves adaptive adjustment of the power distribution cabinet to the environment through a pre-set environmental state recognition model and environmental decision rules, and realizes adaptive optimization of the decision threshold through backtracking analysis of the historical database during the backtracking period.

The application relates to a steel production cost calculation and sales order decision method and system, wherein the method comprises the following steps: synchronously collecting various data of a steel enterprise to form a multi-source data set; converting the multi-source data set into decision rules for steel production, constructing an optimal process path of steel production and constraint conditions of each process of the optimal process path of steel production based on the decision rules; simultaneously realizing the collaborative optimization of the whole-process cost of steel production and the cost of each process based on the multi-source data set, the optimal process path and the constraint conditions of each process to obtain a cost calculation result of steel production; and outputting a steel production suggestion and a cost report based on the cost calculation result of steel production to provide guidance for sales order. The application can provide effective steel cost calculation and guidance for sales order.

The method for transient voltage stability rule mining based on shapelet and inclined decision tree learning first mines a plurality of key local dynamic features related to a stable state from transient voltage time sequence samples to form a shapelet set with interpretability; then, constructs sample feature representation based on the shapelet set, and generates transient voltage stability decision rules by using inclined decision tree learning of a hierarchical decision relationship corresponding to the key time sequence features; finally, extracts, expresses and analyzes the generated decision rules in combination with the shapelet set and the inclined decision tree decision path to obtain key time sequence dynamic features related to transient voltage stability state and decision basis thereof. The method can extract key time sequence features with physical interpretability from transient voltage time sequence responses, mine clear transient voltage stability decision rules, and provide support for power system transient voltage stability mechanism analysis and auxiliary decision making.

This invention proposes a multi-level serial intelligent auditing method, system, and storage medium for environmental monitoring data. The method includes: acquiring multiple environmental data streams from a distributed environmental monitoring network; filtering all environmental data streams to select data carrying a backfill identifier as valid candidate data; performing parallel anomaly detection on the valid candidate data across multiple dimensions to generate a multi-dimensional anomaly feature vector; wherein the multiple dimensions include at least anomalies in the data's numerical characteristics, equipment operating status, station environment, impact of maintenance activities, and impact of equipment anomaly recovery period; inputting the multi-dimensional anomaly feature vector into a preset multi-level decision rule tree; the multi-level decision rule tree performs fusion reasoning based on different combinations of anomaly features across dimensions and preset decision logic to output an audit conclusion. This invention achieves efficient and accurate auditing of backfilled data, significantly reducing the proportion of manual spot checks and the rate of missed and false detections.

The application discloses a tampering processing method and device, electronic equipment, storage medium and product. The method comprises the following steps: acquiring multiple rounds of tampering detection results for a protected object; determining repeatedly occurring tampered content and occurrence round information of the tampered content in multiple rounds; mapping the tampered content to at least one tampering behavior category; organizing the tampering behavior categories of multiple rounds and the respective corresponding evidence strengths into a node sequence to generate a tampering behavior chain; matching the tampering behavior categories and behavior change patterns in the tampering behavior chain with a preset decision rule set; and determining a target object affected by the tampering behavior category according to prompt information and the tampering behavior category, and determining an affected degree index of the target object. The application solves the technical problem that related tampering detection only outputs a single snapshot type tampered file list and a tampering rate, lacks a time-varying evidence structure, and it is difficult to attribute file-level evidence to an operable disposal stage.

The present disclosure is a kind of radiation source individual open set identification method based on dynamic spherical boundary adaptation, comprising: data acquisition and preprocessing;Feature extraction and spherical measurement discrimination;Extract the positive sample distance of the prediction correct sample to its real class prototype vector, calculate the quantile of the positive sample distance set of each class to obtain the boundary estimation value of the class and update;Two-stage training strategy and open set joint loss;Self-calibration of decision scale and reasoning decision rule.This embodiment uses the open set identification framework of dynamic spherical boundary adaptation, realizes reliable rejection of unknown under the premise of high known acceptance rate without introducing real unknown samples;By constructing a spherical measurement feature space, the reasoning efficiency and discrimination consistency are improved;Introducing class adaptive dynamic boundary, realizing controllable coverage of different classes;Constructing pseudo-unknown and joint constraint training, improving unknown separation ability and robustness;Based on the known acceptance rate constraint, the decision scale is automatically calibrated, and the manual parameter adjustment cost is reduced.

The application provides a method and device for extracting text of interest in a webpage. The method can accurately extract text of interest corresponding to a to-be-matched term from a webpage region based on various statistical features and a semantic matching model of the webpage, and is suitable for any structure and template of the webpage. The method comprises: obtaining a DOM tree of a to-be-processed webpage; determining a decision rule according to the content of the to-be-matched term, wherein the decision rule is used to define conditions that need to be met by statistical features of a candidate DOM block corresponding to the to-be-matched term, and the DOM block is a subtree of the DOM tree; screening candidate DOM blocks that meet the conditions in the decision rule according to the statistical features of each DOM block containing text; determining a target DOM block that is semantically matched with the to-be-matched term from at least one candidate DOM block by using a semantic matching model, wherein the semantic matching model is based on a Transformer structure; and extracting text of interest corresponding to the to-be-matched term in a webpage region corresponding to the target DOM block.

This application relates to the fields of artificial intelligence and data analysis technology, and discloses a task processing method and system. The method includes: acquiring user task text, wherein the user task text describes the target task to be completed; extracting multi-dimensional features from the user task text to obtain task features; using a pre-set link decision rule base and a lightweight routing model to perform link decision on the task features, determining the processing link type corresponding to the task features; processing the task features according to the processing link type to obtain the execution results of multiple atomic tasks, wherein the multiple atomic tasks are execution units for completing the target task; and fusing the execution results of the multiple atomic tasks to obtain the task processing result. This method can improve the adaptability to complex tasks and ensure the processing quality of complex tasks.

The application discloses a kind of real-time routing switching method and device based on multi-rule decision engine.The method is calculated by the real-time feedback data of the combined node collected, and the investment return rate of each node is obtained;Through routing decision engine, according to the investment return rate, the pre-defined multi-dimensional performance evaluation and decision rule is executed, and the performance of the combined node is evaluated and compared, and the routing switching decision is generated;During marketing activity, according to the routing switching decision, the routing switching between suppliers or strategies is executed;The routing switching decision and the corresponding execution effect are recorded to the strategy effect knowledge base.The application can achieve the technical effect of automatically switching data from inefficient suppliers or strategies to efficient suppliers or strategies by monitoring ROI data in real time.

The application discloses a kind of methods and systems for judging ship movement situation by ship 3 to 6 posture information, comprising: 3 to 6 posture core data, environment and control data are collected, and after pretreatment, 3 to 6 posture dynamic coupling coefficient and dynamic confidence are calculated;Based on this, construct weighted optimization objective function and constraint condition, and obtain optimized attitude parameter by solving;Combining parameters, coupling coefficient and confidence, train LSTM network to build adaptive swing risk short-term prediction model, for predicting future ship swing risk level and posture;According to risk level, posture, ship type and sea state query decision rule base, generate structured suggestion, collect execution feedback and be used for model updating;The application solves the reliability and efficiency problem of data acquisition, provides high-quality, continuous, synchronous data basis for subsequent processing;Solve the problem of isolated parameter optimization, fixed and rigid coupling coefficient, realize high-precision, strong adaptation attitude parameter optimization.

The application discloses a kind of underground fluid prediction method, equipment and medium considering geological body weight, method includes: well logging gas content curve is converted from depth domain to time domain and is matched with corresponding well seismic record;Well logging gas content curve is matched with well seismic record and is formed into label set by square wave processing, training sample set is formed by using short-time Fourier transform to well seismic record, the k value of KNN algorithm, distance measurement mode and classification decision rule are determined, wherein, consider geological body weight in the classification decision process of KNN algorithm, give the training sample of more close to the predicted sample greater weight, output the predicted sample and the gas sample in the first k most close training sample of predicted sample with the probability attribute of considering geological body weight;The predicted data is segmented into the predicted data block of equal size with training sample, and the predicted data block is input into KNN algorithm and is predicted.The accuracy of underground fluid distribution prediction is improved.

A technical control system for predictive fault detection and autonomous recovery in microservice networks, including: a monitoring module configured to collect real-time operational data from a variety of microservices, including at least latency, throughput, error rates, and resource utilization; an analysis and prediction engine that is functionally coupled with the monitoring module and configured to process the collected data using machine learning models, statistical procedures and rule-based algorithms to detect anomalies and predict potential failures based on historical and real-time data, including the identification of chain failures through dependency analysis; a control and orchestration module that is functionally coupled with the analysis and prediction engine and configured to automatically define and execute recovery measures in response to detected anomalies or predicted failures, the recovery measures including at least restarting services, reallocating resources, rerouting traffic, isolating faulty services, and resetting deployments; a policy management module configured to define thresholds, decision rules, and recovery strategies; and a feedback and learning module configured to evaluate the effectiveness of predictions and recovery measures and to update predictive models and control policies, the system is configured to continuously monitor, predict and autonomously restore microservices to reduce downtime and improve system resilience.

This invention belongs to the field of online detection technology for metal impurities in food, and particularly relates to an intelligent sensing-based online detection method and system for metal impurities in food. It simultaneously transmits and receives multiple discrete frequency band electromagnetic signals, generating a multi-dimensional original signal matrix by leveraging the differences in their responses to metals, food, packaging, and the environment. Based on the fusion application of an improved FastICA blind source separation algorithm and wavelet packet transform, a multi-frequency feature-blind source separation dual-layer model is constructed. The effectiveness of signal separation is verified using a multi-scenario standard signal feature library and cosine similarity matching. After feature extraction and combined dimensionality reduction processing, the output is fused through a hybrid model of traditional machine learning and lightweight deep learning. The D-S evidence theory is introduced and combined with real-time parameters from the production line to dynamically adjust the decision rules.