3139 results about "Monte carlo em" patented technology

A scalable platform for orchestrating networks of specialized AI multi-agent networks that enables secure collaboration through token-based protocols and real-time result streaming with advanced dynamic chain-of-thought pruning. The central orchestration engine manages domain-specific agents, implementing sophisticated multi-branch reasoning with contribution-estimation layers that evaluate each agent's utility using Shapley value-inspired metrics. The system employs information-theoretic and gradient-based surprise metric to guide memory updates and dynamic reasoning expansion, preventing local minima stagnation while preserving valuable insights through adaptive forgetting mechanisms. The platform unifies Monte Carlo tree search with contribution-aware estimation to detect high-synergy expert combinations while maintaining privacy through partial data approaches. It scales across distributed computing environments, enabling complex collaborative tasks like materials discovery, product engineering and manufacturing process design, biomedical research, and drug development. The system supports multi-party economic rewards through systematic contribution effort, cost and importance tracking, while standardized interfaces manage security, privacy, and policy constraints across heterogeneous agents.

Disclosed is a microgrid optimal scheduling method taking into consideration a system operation risk and user satisfaction, comprising: generating a power prediction curve of wind power and photovoltaic new energy output in a microgrid, using a Monte Carlo simulation method to obtain a prediction error range to generate a typical scene set, and by means of a data fitting method, acquiring a wind-photovoltaic prediction error probability density distribution function; using value-at-risk and conditional value-at-risk theories to quantify a microgrid operation risk which is increased by slightly high or low output caused by wind power and photovoltaics; obtaining the scheduling cost of an adjustable load in a microgrid system; taking the minimum sum of conditional value-at-risk cost and microgrid system operation cost as an objective function and a user satisfaction level under a demand-side response as a constraint, establishing a microgrid optimal scheduling model taking into consideration the operation risk and the user satisfaction; and using a genetic algorithm to solve the model, and obtaining an optimal result of grid-connected microgrid system optimal scheduling. The safety, economic efficiency, stability and reliability of the microgrid are enhanced.

The invention discloses a dam safety monitoring system and method based on digital twinning, and belongs to the technical field of data processing, and the method comprises the steps: collecting dam surface acoustic emission signals and internal infrared thermal image data in real time through a multi-source sensor, and generating a multi-dimensional damage feature matrix; constructing a disaster node topology network in combination with density peak clustering and dynamic weight; on the basis of gravitational field intensity calculation and improved Monte Carlo simulation, a damage chain reaction path is accurately predicted; generating a dynamic risk thermodynamic diagram through space-time folding mapping and a bidirectional diffraction equation; and extracting hidden danger indexes by adopting multi-axis domain characteristic distillation, dynamically comparing a safety envelope function, and generating a flood discharge scheduling and reinforcing scheme on line. According to the method, cross-modal fusion, a gravitational field dynamic topology network and a time-space folding mapping technology are adopted, deep fusion of accurate simulation of a damage energy conduction path, carbonization-deformation bidirectional coupling prediction and intelligent risk hidden danger disposal decision can be realized, and the accuracy and initiative of dam safety early warning are improved.

The invention provides a virtual DPU power plant simulation fault restoration method and system based on digital twinning, and relates to the technical field of digital twinning, and the method comprises the steps: carrying out the preprocessing of collected DPU power plant operation data, including noise reduction, time sequence alignment and abnormal point elimination, carrying out the data quality evaluation, training a fault feature mapping model based on the processed data, and carrying out the fault restoration of the DPU power plant. The model is used for recognizing abnormal clusters in real time, a fault evolution path is searched and determined in combination with a conditional random field and a Monte Carlo tree, an optimal path is determined through a particle filtering algorithm, fault root causes are determined in combination with causal analysis, spectral clustering and a Bayesian network, and a fault diagnosis report is generated.

The invention discloses a turbofan engine operation monitoring method and system based on digital twinning, belongs to the technical field of turbofan engine monitoring, and aims to solve the problems that weak fault signals such as early cracks and abrasion are difficult to extract and the prediction precision of a multi-source fault propagation path is low under a strong noise background. An original operation signal is collected through a sensing array, and is processed by an adaptive resonance demodulation chain to generate a demodulation signal. The method comprises the following steps: carrying out time-frequency transformation on a demodulation signal, constructing an initial candidate feature set by combining feature frequency prior matching actual measurement and theoretical feature frequency, and generating an independent feature set by fusing multi-scale decoupling network separation features of digital twin constraints; for independent features, effective causal pairs are screened by adopting a physical coupling relationship combining Granger causal analysis and digital twinborn simulation, a dynamic Bayesian network is constructed to simulate fault propagation, a posterior probability is calculated through digital twinborn verification and Monte Carlo simulation, early warning is triggered, and a maintenance decision is generated. And weak signal extraction and accurate fault prediction under strong noise are realized.

The invention provides a Dores front-end node-based service proxy method and system, and relates to the technical field of database access request processing, and the method comprises the steps: collecting front-end node performance indexes, extracting node performance characteristics through employing multi-head recursive attention and causal convolution solution, extracting inter-node correlation characteristics through combining graph attention convolution, and obtaining a database access request; the method comprises the following steps: constructing a node state vector, optimizing a multi-layer connection pool parameter by utilizing an online learning algorithm, establishing a node incidence matrix based on comparative learning, constructing a node performance probability graph evolution model through variational reasoning and Monte Carlo sampling, predicting a node performance change trend, and receiving a database access request; and generating a query plan by adopting an edge attention message passing mechanism, carrying out resource evaluation in combination with performance trend prediction, carrying out scheduling decision making by utilizing multi-agent reinforcement learning and Monte Carlo tree search, carrying out fault detection and migration according to node performance deviation, and updating a probability graph evolution model.

The invention discloses a hybrid enhanced enterprise smart law platform system based on a generative language large model. Four modules including a hybrid enhanced legal knowledge engine, a multi-modal legal document analysis module, a risk quantitative evaluation module and a compliance verification workflow work cooperatively. The hybrid enhanced legal knowledge engine integrates multi-source data, realizes real-time updating and semantic reasoning, and comprises map construction, a rule base and an incremental learning mechanism; the multi-modal legal document analysis module performs structured analysis on the heterogeneous document to generate a feature vector; the risk quantitative evaluation module is combined with Monte Carlo simulation and an analytic hierarchy process, quantifies the risk according to a compliance reference and analysis characteristics, and outputs a thermodynamic diagram and a report; a compliance verification workflow is driven by a finite-state machine, a verification module and a conflict detection module are integrated, a generative language large model is called to generate an improved scheme, and audit records are solidified and fed back for optimization. And the system runs according to the processes of analysis, supply rule, bias calculation and verification correction, so that the intelligence and accuracy of legal affair processing are improved.

The invention relates to a lithium battery energy storage system fire-fighting ventilation and explosion venting safety assessment method based on multi-dimensional simulation. The method comprises the following steps: constructing an energy storage system digital twinborn model fusing structure parameters, material attributes and environmental parameters; generating a multi-mode failure scene set covering multiple temperature domains and aging states through mode recognition; simulating and quantifying dynamic interaction of a temperature field, a flow field and a stress field in the thermal runaway evolution process based on thermal-fluid-solid multi-physics field coupling; constructing a space-time associated dynamic safety evaluation matrix, and combining fuzzy comprehensive evaluation and Monte Carlo sampling to generate risk quantitative indexes; and iteratively correcting parameters of the fire-fighting ventilation and explosion venting system through a multi-objective optimization algorithm to form a graded safety assessment conclusion. According to the method, the technical bottlenecks of environmental parameter splitting and single failure scene in a traditional method are broken through, the thermal runaway suppression efficiency is improved, the combustible gas concentration control error is reduced, and collaborative optimization of explosion venting pressure fluctuation suppression and ventilation response is realized through a closed-loop evaluation mechanism.

The invention provides a bridge girder erection machine intelligent construction control method and system based on machine vision, and relates to the technical field of intelligent control. Image information of a construction site is collected through a plurality of high-definition cameras arranged on a bridge girder erection machine; inputting the image information into a pre-trained deep learning model, identifying and positioning a target in the construction scene, and constructing a digital twinborn model of the construction scene in combination with a graph structure of a construction scene topological structure subjected to spatial perception graph convolution operation; the intelligent decision agent generates an initial construction strategy according to the current construction scene state, an improved Monte Carlo tree is adopted to search and optimize the initial construction strategy, and an optimal construction strategy is generated through multi-objective solution; and after the construction is completed, based on the digital twin model and the whole process data, analyzing the construction quality and efficiency by using a graph neural network, and generating a multi-dimensional evaluation report and optimization suggestions.

The invention discloses a wide-area landslide rapid identification method based on an interpretable intelligent algorithm, and relates to the field of remote sensing science and technology, and the method comprises the steps: building a dual-channel feature extraction architecture through multi-source spatio-temporal data fusion and knowledge graph dynamic weighting: capturing image local textures through a lightweight CNN, modeling geological spatial correlation through a graph convolutional network, and carrying out the recognition of the landslide. Combining the SHAP value and causal reasoning to generate an interpretable contribution degree thermodynamic diagram and a rule chain; a knowledge graph bidirectional verification system is introduced, spatial logic contradictions are verified by using prior rules, and co-evolution of a model and a rule base is triggered based on misjudgment samples; outputting a multi-dimensional credibility report, quantifying uncertainty by Monte Carlo Dropout, and customizing interpretation granularity according to roles; a terrain-adaptive block-stream processing architecture is adopted, and edge lightweight deployment and federated learning are combined, so that wide-area real-time early warning and model dynamic updating are realized. According to the scheme, the limitation of a traditional black box model is broken through, and a disaster prevention closed loop with physical driving, transparent decision and second-level response is formed.

The invention provides a multi-level attribution and recommendation method and system for medical management decisions, and relates to the technical field of medical management decisions, and the method comprises the steps: extracting graph node evolution characteristics through a multi-level medical data knowledge graph and a decision knowledge base by employing a time sequence diagram convolutional network, constructing a decision influence propagation graph through a cross-layer interactive attention network, and carrying out the analysis of the decision influence propagation graph; calculating the contribution degree of each decision node to the medical effect, generating an attribution analysis result, determining a decision influence hierarchical system according to the attribution result, and generating and evaluating candidate decision paths in combination with a multi-objective optimization network, a hierarchical reinforcement learning network and a Monte Carlo search tree network. In conclusion, accurate attribution analysis and multi-objective optimization of the management decision can be realized, the hospital resource allocation efficiency is effectively improved, the operation cost is reduced, scientific decision support is provided for a hospital management layer, and the hospital fine management level and the overall operation efficiency are remarkably enhanced.

The invention relates to the technical field of power dispatching, in particular to a digital twin energy management method and system for source-network-load-storage cooperative dispatching, and the method comprises the steps: collecting source-network-load-storage multi-dimensional space-time operation data, and extracting space-time coupling features through a graph convolution-long and short-term memory network; establishing a simulation model of a digital twin environment, simulating an uncertain operation condition by using a Monte Carlo scene generator, and processing a power flow constraint by using a second-order cone relaxation technology; training an energy storage scheduling agent in a digital twin environment, and learning an energy storage charging and discharging strategy through a near-end strategy optimization algorithm; designing a source-network-load-storage hierarchical collaborative optimization framework, optimizing power output and load distribution by using an improved particle swarm optimization algorithm on the upper layer, and solving power flow distribution by using an alternating direction multiplier method on the lower layer; and establishing a self-adaptive feedback correction mechanism, and dynamically adjusting a cooperative scheduling strategy. According to the invention, intelligent collaborative scheduling of source network load storage is realized, and the operation efficiency and stability of a power system are improved.

The invention discloses a mechanical arm positioning and grabbing method based on machine vision, and relates to the technical field of machine vision and mechanical arm control, the method comprises the following steps: synchronously acquiring RGB-D images of a target scene through a multi-view camera array, and generating three-dimensional point cloud data through data fusion; an improved LSD algorithm and a PnP algorithm are adopted to calculate the initial pose of the target object, illumination distortion is eliminated in combination with the generative adversarial network, and three-dimensional coordinates are output; a mechanical arm motion error transfer model is constructed based on Monte Carlo simulation, and a candidate grabbing scheme set is generated through reinforcement learning; and an optimal grabbing scheme is screened through a preset priority evaluation rule, and a mechanical arm joint movement track and a control instruction set are generated. Through multi-modal data fusion and a nonlinear optimization algorithm, the technical problems of large target positioning deviation and sensitive illumination interference in a complex environment are solved, and the grabbing precision and robustness of the mechanical arm are improved.

The invention discloses a wind-light-hydrogen multi-energy complementary system cooperative operation optimization and comprehensive benefit evaluation method, which relates to the technical field of electric energy storage, and comprises the following steps: constructing a hybrid power flow model containing electricity, hydrogen and heat coupling, taking whole life cycle cost and new energy consumption as double targets, introducing grid-connected and off-grid risk constraints, and optimizing equipment capacity configuration; a scheduling baseline and an intra-day dynamic correction strategy are formulated in the day-ahead stage, and hybrid energy storage cooperative control is combined to improve the response speed and flexibility of the system to wind and light fluctuation; a peak regulation and frequency modulation mode is switched according to the power grid state, a power response model is established, fluctuation is stabilized through hydrogen energy storage, the stability of the power grid is enhanced, and auxiliary service benefits are created; the performance of the system is evaluated from the three dimensions of efficiency, economy and interactivity, dynamic weight and Monte Carlo simulation optimization are utilized, system parameters are continuously optimized through a feedback mechanism, and the self-evolution ability is formed. The problem that system instability and economy are difficult to take into account due to wind and light fluctuation is solved.

The invention discloses an artificial intelligence-based engineering resource allocation optimization method and system, and relates to the technical field of artificial intelligence and resource management crossing. The problems of resource configuration dynamic change and resource conflict coordination are solved. And processing the multi-modal heterogeneous data in the target engineering scene through space-time alignment and semantic coding to generate a dynamic data stream. A task, resource and environment node relationship is constructed based on a dynamic heterogeneous graph network, and a node dependency weight is updated through an event-driven mechanism. Two-stage collaborative optimization is executed, in the first stage, a baseline scheme is generated through Monte Carlo sampling, and in the second stage, resource conflicts are eliminated through back propagation negotiation. The resource dynamic entropy is monitored in real time, a rebalance algorithm is triggered during local overload, and a distribution scheme is adjusted in combination with security constraints. And finally, outputting the optimization scheme to an engineering management system for execution, dynamically returning updated graph network parameters, forming a data acquisition, optimization decision and feedback closed loop, and improving the intelligence and robustness of resource allocation.

The invention relates to the technical field of intelligent control of test equipment, and discloses a semiconductor device test equipment control system and method based on industrial data processing, and the method comprises the steps: collecting multi-source heterogeneous data of semiconductor device test equipment, and carrying out the preprocessing; constructing a structural causal model, and performing root cause identification through anti-fact reasoning by using the structural causal model; constructing an abnormal test fingerprint and a knowledge base; generating an intervention scheme, evaluating the generated intervention scheme, and selecting an optimal intervention scheme; processing the detected anomaly, and generating and implementing a preventive control strategy based on historical anomaly data and a causal analysis result; according to the invention, by introducing innovative technologies such as causal inference, anti-factual inference, abnormal test fingerprint identification and Monte Carlo tree search, intelligent control of semiconductor test equipment is realized.

The invention discloses an intelligent target allocation method and system based on deep reinforcement learning, particularly relates to the field of multi-agent systems, and is used for solving the real-time decision problem under multi-dimensional constraints in a dynamic confrontation simulation scene. Time, space and resource constraints are decomposed into independent models, and the decision complexity of a multi-agent system in a dynamic confrontation scene is reduced; by means of adaptive Monte Carlo sampling, prediction perception path planning and dynamic threshold value resource allocation, diversified high-quality candidate schemes are quickly generated; when the environment changes, the multi-layer influence propagation network and the spatial topological relation graph are used for positioning an affected agent, and scheme fragments are generated through local adjustment, so that global re-calculation is avoided, the overhead is reduced, and real-time response is ensured; meanwhile, an efficient and reliable optimal solution is screened out through resource delay coupling and path efficiency comprehensive evaluation in combination with multi-objective optimization and task consistency verification.

The invention relates to the technical field of robot path planning, and discloses a robot path planning method based on reinforcement learning. The method comprises the following steps: acquiring environment depth information and an obstacle movement track through a multi-sensor array, constructing a dynamic environment sensing network, and generating an environment state tensor under space-time constraint; building a hierarchical reinforcement learning framework, and optimizing the motion track of the robot in stages by adopting a strategy gradient algorithm to obtain an initial path strategy; designing a reward function calculation model based on an attention mechanism, and accounting an action value in real time according to an environment state tensor; deploying a distributed experience playback buffer pool, and performing priority sampling and track fragment recombination on historical decision data; and establishing a strategy iterative optimization mechanism, and searching and dynamically correcting an initial path strategy by utilizing a Monte Carlo tree. The method can accurately adapt to the dynamic environment, optimize the path decision efficiency, enhance the adaptability and reliability of robot path planning, and is suitable for various robot autonomous operation scenes.

The present invention provides a privacy-enhanced structured data simulation and generation method and system. The method comprises: step 1, a data conversion phase: performing normalization preprocessing on data; step 2, a probabilistic graphical model construction phase: on the basis of a Bayesian form, constructing the posterior distribution for variational inference from the data having undergone normalization preprocessing in step 1, obtaining an association relationship between the features of structured data by using a Stein variational gradient descent method, and when introducing differential privacy noise, using a Monte Carlo estimation algorithm to automatically obtain the amount of noise that needs to be added for each update step; and step 3: a data generation phase: using the association relationship obtained in step 2 as a metric set to generate more accurate simulation data than real data. The beneficial effect of the present invention is that: the method of the present invention avoids gradient clipping when applying DP-SGD, thereby avoiding the selection of clipping parameters and reducing the adverse effects of gradient clipping on an inference process.

The invention discloses a construction progress dynamic optimization method and system based on BIM and computer vision, and particularly relates to the technical field of building construction management, and the method comprises the steps: carrying out the automatic registration of a BIM model and a construction site image; processing the construction site image by adopting a visual identification algorithm to generate a visual identification result; constructing a four-dimensional dynamic BIM model, and mapping a visual identification result to a corresponding component in real time through multi-feature similarity calculation; the progress deviation is monitored by using key path dynamic identification and a deviation propagation matrix, and the risk is predicted by combining a Bayesian network and Monte Carlo simulation. The BIM and computer vision technologies are fused, a construction progress optimization system integrating automatic registration, dynamic monitoring, risk prediction and intelligent decision making is constructed, and the problems that traditional manual inspection data collection is low in efficiency, progress monitoring is lagged, risk prejudgment is fuzzy and resource allocation is extensive are solved; accurate monitoring, risk early warning and resource optimization configuration of the construction progress are realized.

The invention relates to the technical field of intelligent navigation and control of ships. The invention provides a complex channel ship intelligent navigation and emergency decision-making method and system. The method comprises the following steps: acquiring environment data through a multi-source heterogeneous sensor array, and establishing a channel three-dimensional dynamic environment model; establishing a multi-objective optimization function, and performing dynamic path planning by adopting an improved model prediction control algorithm; synchronizing motion state parameters of an actual ship and a virtual ship model in real time, constructing an emergency decision tree in combination with an expert knowledge base, and verifying the feasibility of an emergency decision through Monte Carlo simulation; carrying out local route optimization by adopting edge computing nodes, carrying out multi-ship trajectory prediction through a federated learning mechanism, and generating a corresponding collaborative collision avoidance strategy; and establishing a dynamic priority scheduling mechanism, implementing hierarchical response, and confirming a global avoidance scheme through a distributed consensus algorithm. The problems that an existing inland ship intelligent system is limited in perception, rigid in decision and weak in collaboration in a complex scene are solved.

The invention provides a self-adaptive network topology dynamic reconstruction method and system based on deep reinforcement learning, and relates to the technical field of deep reinforcement learning, and the method comprises the steps: obtaining the topology state information, service flow distribution information and historical reconstruction records of a current network; extracting topological correlation characteristics among nodes through graph convolution operation, and generating fusion state representation in combination with service flow information; inputting the fusion state representation into a deep reinforcement learning model to identify bottleneck nodes and redundant links, and outputting a reconstruction action candidate set; searching and evaluating the long-term cumulative income of the candidate actions through a Monte Carlo tree, and screening an optimal reconstruction action sequence; a graph coloring algorithm is utilized to allocate time slots and process resource conflicts, and a resource-feasible topology adjustment scheme is generated; and extracting a network evolution rule through tensor decomposition, and constructing a topological optimization association mapping graph. According to the method, the network bottleneck can be intelligently identified, the network topology structure is dynamically optimized, and the network performance and the resource utilization rate are effectively improved.

The invention relates to the technical field of intelligent early warning of digital twinning, and particularly discloses a slope multi-physics field fusion early warning decision-making system based on digital twinning, which is characterized in that physical monitoring data representing the macroscopic state of a slope and microscopic physical response signals reflecting internal damage evolution are synchronously acquired through a multi-modal data sensing module; space-time alignment, standardization and cross-modal fusion analysis are carried out through a damage eigenstate extraction module, and a unique eigendamage variable for quantitatively representing the real-time degradation degree of the material strength is interpreted; the twinborn self-evolution module takes the variable as a core observed quantity, and drives parameters and states of a slope mechanical model to be cooperatively and dynamically updated by adopting a data assimilation method, so that high-fidelity tracking of a digital model on physical reality is realized; and the prospective early warning decision module deduces a future spatio-temporal evolution path of the material strength parameters based on the calibrated model, and realizes graded early warning and intelligent decision support by combining Monte Carlo simulation and quantification of the instability risk probability.

An AI-driven financial planning system for real-time market adjustment, consisting of: a neural inference coprocessor configured to execute deep financial forecasting models, including recurrent neural networks and attention-based encoders, on the device, and wherein the processor dynamically updates portfolio parameters in response to market signals exhibiting volatility differences above a statistical threshold calculated using an exponentially weighted moving standard deviation; a financial data acquisition module configured to continuously receive and analyze heterogeneous data streams, including market indices, interest rates, stock and bond price fluctuations, economic indicators, regulatory updates, and financial news sentiment feeds; a behavioral analytics engine configured to create a dynamically evolving user-specific financial behavior profile based on real-time analysis of transaction history, income-expenditure cycles, psychometric test results, and temporal lifestyle patterns using supervised and unsupervised machine learning algorithms; A goal optimization module configured to transform high-level, user-defined financial goals into quantitatively tracked multi-level goals. It uses a reinforcement learning framework that predicts optimal asset allocations across multiple time horizons. a real-time strategy simulation engine configured to perform Monte Carlo simulations and deep Q-learning-based assessments to simulate the resilience of proposed financial strategies under different macroeconomic regimes and trigger redistribution events based on predefined confidence thresholds; a compliance-aware execution interface configured to interact with financial institutions through encrypted API channels, ensuring policy enforcement using a smart contract validator and a hardware-enabled secure transaction signing unit; and a recommendation display unit configured to render dynamic dashboards for visualizing investments, reallocation warnings, confidence intervals, and sensitivity sliders, and where user interaction with the unit flows back into the behavioral model for real-time learning.

The invention relates to the technical field of industrial production lines, and discloses an industrial production line multi-device dynamic collaborative scheduling method based on reinforcement learning, comprising the following steps: S1, modeling a three-dimensional state space; s2, hierarchical reinforcement learning architecture; and S3, edge-cloud cooperative execution. According to the industrial production line multi-device dynamic collaborative scheduling method and system based on reinforcement learning, device states, task constraints and resource occupation are integrated into a structured matrix through three-dimensional state space modeling, and a global decision-making layer captures production time sequence dependence by using a bidirectional long-short-term memory network; modeling equipment space association and process constraints through a graph attention network, and generating a global strategy including task allocation, capacity adjustment and resource pre-allocation; and after the edge layer detects the dynamic event, the cloud platform generates a candidate scheme through Monte Carlo tree search, and realizes dynamic event response and multi-target collaborative optimization by combining multiple targets such as global value network evaluation task completion time and equipment load balancing.

The invention relates to a campus Internet of Things terminal scheduling method based on digital twinning. The method comprises the following steps: defining a general twinning state representation structure; introducing a state mapping relationship, and establishing a one-to-many dynamic mapping relationship between a physical state and a virtual twinning state by using a finite state machine; when the state of the physical terminal changes, triggering multi-level response mapping of the twin in the virtual space; semantic fusion is carried out on twinborn real-time data, a scheduling sensitivity index is introduced, disturbance simulation is carried out based on past scheduling behaviors, and the potential influence of a certain scheduling behavior on the whole system is analyzed; carrying out local division on the situation map; using Bayesian estimation and Monte Carlo combination to sample and evaluate the feasibility and income of each solution set in a period of time in the future; simulating the expected influence of each scheduling strategy through a twin body, and selecting a scheduling path; unified modeling and semantic fusion of multiple types of terminals are realized, the intelligent level and predictive ability of scheduling decision are improved, the collaborative scheduling ability of the terminals is enhanced, and coupling unit level regulation is realized.

The invention belongs to the field of artificial intelligence and natural language processing, and provides a method and a system for determining a dynamic retrieval decision scheme based on Monte Carlo tree search in order to solve the problems of redundant retrieval and incapability of multi-step reasoning and dynamic planning of a traditional retrieval enhancement generation method. The dynamic retrieval decision scheme determination method based on Monte Carlo tree search comprises the following steps: receiving an initial query problem and taking the initial query problem as a starting point of a reasoning process to trigger and call a large language model operation; calling a large language model to execute sub-query generation and action selection operation, searching, iteratively and exploring inference actions of sub-query problems based on a Monte Carlo tree, and dynamically screening inference paths by considering self-confident degree scores and honesty degree scores of the large language model to obtain a complete inference track set; and on the basis of the complete reasoning track set, a preference pair is constructed for each sub-query problem, and a reasoning retrieval strategy is optimized, so that the optimal retrieval opportunity of the large language model is autonomously judged. According to the method, invalid retrieval and multi-step reasoning dynamic planning can be reduced.

The invention discloses a geothermal field parameter inversion calculation method, device and system, and a storage medium. The method comprises the following steps: establishing a geophysical stratified model; through Monte Carlo sampling of preset parameter spaces of the crustal heat generation rate and the heat conductivity, a temperature value is calculated in combination with a heat conduction equation, and a Gaussian likelihood function evaluation model is constructed to predict the matching degree of the temperature and the actually measured temperature; obtaining the optimal estimation of the thermal parameters, a confidence interval and a correlation matrix among the parameters based on the posterior probability distribution; and according to the correlation matrix, taking a high-confidence result generated by Monte Carlo inversion as priori knowledge of a physical guidance neural network PINNs, and finally outputting a thermal parameter spatial distribution prediction result of the target area through parameter initialization constraint, output layer range limitation and a physical regularization loss item. By adopting the technical scheme of the invention, the defects that the existing actually measured geothermal field parameters are rare and the regional characteristics cannot be described and the geophysical joint inversion of the geothermal field parameters cannot be realized in the prior art are overcome.

The invention discloses a semi-supervised identification method and system for a small target of a container, and belongs to the technical field of artificial intelligence and computer vision, and the method comprises the steps: carrying out the target detection of a container image through a pre-trained target detection model, intercepting a sub-image, and inputting the sub-image into an initial classification model, and obtaining a classification confidence coefficient; the uncertainty of the model on a sample classification result is quantified through a Monte Carlo Dropout method; a feature space distance filtering and dynamic threshold adjusting mechanism is combined, and samples with high confidence, low uncertainty and consistent feature space are screened out to serve as pseudo label data; pseudo label data and initial synthesis data are mixed, and the generalization ability of the model is gradually improved through semi-supervised iterative training. According to the method, the dependence on manual annotation can be remarkably reduced, meanwhile, the distribution difference between synthetic data and real scene data is gradually reduced, and finally, high-precision recognition and strong generalization ability of a classification model in a real scene are achieved.

The invention discloses a dynamic leakage prediction method and system for an old oil and gas pipeline, and the method comprises the steps: collecting pressure, flow and temperature parameters in real time through a multi-source sensor, and recognizing abnormal fluctuation through the combination of time sequence analysis and frequency domain feature extraction; calculating a pipeline state evaluation result based on the material degradation model; establishing a leakage prediction model fusing a wall thickness degradation kinetic equation and an LSTM neural network, calculating a leakage probability by adopting a Monte Carlo method, and generating a diffusion velocity and a concentration gradient through CFD numerical simulation; when the diffusion prediction exceeds a safety threshold value, a control strategy is optimized through fuzzy logic and a genetic algorithm; the verification model is fed back after real-time adjustment, and online learning is carried out through Bayesian optimization; and finally, calibrating the model by using experimental data, and deploying and generating risk early warning. The system comprises a multi-source sensor array, a data processing platform and other modules, and full-chain closed-loop control from sensing to early warning is achieved.