347 results about "Scenario simulation" patented technology

The invention belongs to the technical field of circuit breaker management, and discloses a control system for managing a primary and secondary fusion circuit breaker, and the system collects the electrical parameters, mechanical states and environmental conditions of the circuit breaker through multiple channels, and constructs a standardized operation data set; establishing a circuit breaker health characteristic spectrum based on deep characteristic learning; establishing an environmental adaptability control parameter library through environmental factor correlation analysis and multi-scene simulation; performing fault mode identification and predictive diagnosis in combination with the health characteristic spectrum, and generating a fault risk early warning matrix; optimizing a multi-circuit-breaker cooperative control strategy based on the early warning matrix, and generating an optimal control instruction sequence; and reliable execution and effect feedback of the control instruction are realized through security encryption verification and a hierarchical execution mechanism. The problems that a traditional circuit breaker control system is difficult in data integration, insufficient in environment adaptability, weak in fault prediction capacity, incomplete in cooperative control and the like are solved, and the safety and reliability of power grid operation are remarkably improved.

The invention discloses an interdisciplinary scientific research potential assessment method based on a dynamic multi-modal knowledge graph, relates to the technical field of scientific research management and intelligence analysis, and aims at the dynamic requirements of college scientific research ecology by relying on an incremental assessment framework. Comprising the steps of multi-source data acquisition and incremental knowledge graph construction, time sequence trend identification, online and transfer learning optimization, scene simulation and multi-scene strategy verification and multi-modal data fusion. The map structure is updated in real time through concept drift detection and ontology extension, and emerging hotspots are identified by combining time sequence difference indexes such as citation acceleration and a cooperative network; and the accuracy and continuous iteration capability of the evaluation model are kept in multiple environments by means of online learning and a cross-domain migration strategy. Finally, potential evolution is quantified through scene simulation, strategy suggestions are output, the sensitivity to the cross domain is further enhanced with the assistance of multi-mode embedding, a closed-loop evaluation system from data to decision is formed, and college subject cross layout and resource allocation are assisted.

The invention belongs to the technical field of risk prediction, and discloses a landslide risk prediction method and system based on data intelligent analysis, and the method comprises the steps: obtaining corresponding multi-source heterogeneous information, carrying out the feature extraction and data fusion of the information, and obtaining a mountain monitoring basic data set; constructing a mountain twinborn feature model based on the mountain monitoring basic data set, and performing landslide scene simulation based on the mountain twinborn feature model to obtain corresponding risk feature information; constructing a trigger factor association network based on the risk feature information, and performing zoning evaluation and grading on the target landslide risk in combination with the mountain monitoring basic data set; constructing a corresponding grading risk zoning map; obtaining a landslide risk dynamic prediction result based on the grading risk zoning map; a corresponding grading early warning rule base is constructed; and the target mountain area is monitored in real time based on the grading early warning rule base, and the monitoring result is fed back. According to the invention, a comprehensive and efficient solution is provided for prevention and treatment of landslide disasters.

The invention discloses an efficient intelligent warehousing system and a storage method, and relates to the technical field of warehousing management, the system comprises the following components: a virtual digital twinborn model construction module, a business scene simulation module, a potential problem prediction module and an operation process optimization module; according to the system, the virtual digital twinborn model in 1: 1 mapping with the actual storage environment is constructed, synchronous updating is carried out in combination with data collected by the sensor network in real time, the system can accurately reflect the dynamic condition of the actual storage environment, and the service scene simulation module is utilized to simulate the real storage environment. The system can simulate warehousing operation processes in different business scenes in a virtual environment, automatically adjust cargo storage positions, equipment scheduling schemes and personnel task allocation, so that the efficiency and precision of warehousing management are remarkably improved, and in addition, the operation process optimization module can predict and improve the efficiency and accuracy of warehousing management according to simulation results and potential problems. The operation process of the actual warehousing system is automatically optimized, and the overall operation efficiency is further improved.

The invention discloses a virtual power plant optimization system and method, and the system comprises a virtualization platform module which is used for integrating distributed energy, energy storage equipment, an electric vehicle, a flexible load and other resources, and achieves the virtualization and centralized management of the resources; the dynamic resource aggregation module is used for dynamically matching resource characteristics with power system requirements; the market transaction module is used for optimizing the earnings of the virtual power plant; and the core algorithm module is used for optimizing the load prediction precision. The market transaction module implements two-stage market bidding based on a multi-agent game model, analyzes the uncertainty of quotation of competitors through a multi-scene simulation technology, optimizes a dynamic transaction strategy, and achieves the maximization of spot market benefits and the controllability of risks. Through cooperative work of a virtualization platform module, a dynamic resource aggregation module, a market transaction module, a core algorithm module, a security management module and the like, efficient management of resources and maximization of market benefits are realized.

The invention discloses a system combat ability dynamic game comprehensive evaluation method based on deep learning, and relates to the technical field of combat ability evaluation.According to the method, key features of time and space in a battlefield environment are dynamically extracted by combining a multi-sensor fusion technology with a time sequence convolutional network and a graph neural network, a situation model is updated in real time, and the dynamic game of the system combat ability is comprehensively evaluated. The optimization process of unmanned cluster marshalling and task allocation is accelerated by utilizing a near-end strategy optimization PPO and transfer learning technology, and adaptive adjustment of a marshalling scheme on complex task requirements is realized by defining a multi-task collaborative efficiency index; in the aspect of strategy optimization, a multi-agent game model driven by deep reinforcement learning is constructed, friend or foe resource allocation, dynamic environment change and uncertainty factors are integrated, an optimal strategy is effectively generated, and low-efficiency schemes are eliminated through combat scene simulation; and meanwhile, through a real-time monitoring and dynamic planning mechanism, emergencies such as target change and emergency task insertion are dealt with, and the task execution continuity and cooperative efficiency are improved.

The invention discloses a disaster emergency rescue nursing skill training system based on virtual reality, and relates to the technical field of virtual reality. A high-simulation virtual disaster scene is constructed based on real data, diversified injury condition virtual objects matched with the scene are generated, a secondary disaster risk diffusion effect and emergency prompt information are overlaid in real time, physiological state changes such as blood pressure and respiration generated by nursing operation differences in the rescue process of wounded personnel are dynamically simulated, and the rescue effect of the wounded personnel is improved. The problems of single scene and fixed injury condition in traditional training are solved, real-time and multi-modal feedback of student operation is realized through accurate comparison and hierarchical identification of multi-dimensional operation characteristics, the defects of guidance lagging and general are overcome, a personalized and adaptive training scheme is generated according to a comprehensive evaluation result, the progress is dynamically adjusted, and the training efficiency is improved. And scene simulation, operation practice, accurate feedback and personalized improvement are integrated.

A system and method for predictive analysis, scenario simulation, and decision optimization is provided. The system includes a prediction management system executed on a distributed computing infrastructure, and a prediction engine configured to receive input data, including event parameters, user-defined constraints, real-time data feeds, and historical trends. The prediction engine generates predictive models using algorithms trained on historical event outcomes, assigns probability scores and confidence intervals to potential outcomes, and dynamically updates the models based on new input data. Actionable insights are generated and ranked according to predefined success criteria. A non-transitory computer-readable medium is used to store the predictive models, outcome probabilities, and actionable insights for subsequent analysis and reporting. This system facilitates enhanced decision-making by offering real-time insights and continuously refined predictions, thereby optimizing responses to complex events and scenarios.

The invention relates to the technical field of forestry investigation, and discloses a forestry investigation system for carbon sink forest management, which comprises a data acquisition module, a data processing module, a data integration module, a model construction and analysis module, a decision and early warning module, an output module and an implementation monitoring module. Through multi-dimensional index investigation, information can be obtained from multiple levels of an ecological system, the carbon cycle process and ecological functions of the carbon sink forest are comprehensively known, more comprehensive data support is provided for scientific management, in addition, more variables influencing carbon sink are introduced, so that the model better conforms to the actual situation, the accuracy and generalization ability of the model are enhanced, and the method is suitable for popularization and application. According to the method, carbon reserve changes of the carbon sink forest under different conditions can be better predicted, finally, effect prediction of multiple management schemes is provided for managers through scene simulation and model analysis, scientific and reasonable management decision making is assisted, and meanwhile, an early warning mechanism can find potential risks in time and guarantee stable development of the carbon sink forest.

The invention relates to the technical field of intelligent risk analysis, in particular to an intelligent risk analysis system of a financial system. The system comprises a data flow analysis module, a relational graph construction module, an abnormal mode detection module, a security boundary monitoring module, a staged strategy planning module, a scene simulation evaluation module, a decision support module and a comprehensive risk management module. A graph database and a graph convolutional network are utilized to deeply analyze a financial entity relationship, reveal a risk association network, improve abnormal behavior recognition through a K-mean value and an isolated forest algorithm, enhance security boundary monitoring through a random forest algorithm, enable risk threshold adjustment to be more dynamic, combine a decision tree with a genetic algorithm, optimize a risk management strategy, and improve risk management efficiency. The system dynamics and proxy model technology in scene simulation evaluation strengthens risk prediction and increases foresight, principal component analysis and risk matrix evaluation are applied in a comprehensive risk management module, a quantitative analysis tool is provided, and more systematic and comprehensive risk management is realized.

The invention discloses a semantic judicial contract compliance automatic generation and examination system based on a DIKWP artificial consciousness model. The system is constructed according to five layers of data, information, knowledge, wisdom and intention, wherein the data layer integrates multi-source information; the information layer enables terms to be semantized and disambiguated; the knowledge layer performs rule matching and compliance judgment by using a legal knowledge graph; the wisdom layer automatically corrects the risk terms based on a fair principle and performs scene simulation; and the intention layer is embedded into targets of all parties to ensure that the contract is consistent with the compliance intention. The system process covers the whole process from intention analysis, knowledge reasoning to intelligent generation and intention negotiation, and finally a compliance contract and an audit report are output. The system is provided with a multi-language semantic adaptation and intelligent negotiation interface, and convenient access can be realized through an API (Application Program Interface). The system realizes integration of contract generation and review, intention driving and decision interpretability, can effectively reduce compliance cost and dispute risks, and is suitable for multiple scenes such as finance, e-commerce, government purchase and the like.

The invention discloses a multi-objective optimization water resource allocation scheduling method, which combines an LSTM-Prophet hybrid prediction model with an attention mechanism, synchronously captures climate periodicity, policy regulation sensitivity and industrial development tendency characteristics in water demand prediction, and improves water demand prediction precision through a genetic algorithm. Through an improved NSGA-III algorithm and a PSO collaborative optimization mechanism, the convergence problem of a high-dimensional target space is effectively solved in combination with a chaotic mapping technology, and the multi-target optimization efficiency is improved by 40% in cooperation with a dynamic weight adjustment strategy of deep reinforcement learning. And multi-scenario simulation verification of a scheduling scheme is realized by utilizing deep coupling of a digital twin system and a three-dimensional GIS, and a real-time feedback correction mechanism of a Markov decision process is realized. A finally constructed entropy weight-TOPSIS multi-dimensional evaluation system is combined with AR visualization and intelligent contract traceability technologies, and a Pareto optimal solution giving consideration to social fair, economic benefits and ecological integrity is provided for decision makers.

The invention discloses a vehicle automatic braking system parameter adjusting method and system based on artificial intelligence. The method comprises the following steps: S1, collecting real-time data of an AEB system in a vehicle driving process by using various sensors assembled on a vehicle, and transmitting the real-time data to a cloud platform; s2, the cloud platform firstly carries out time sequence and space alignment processing and processing on the collected data; s3, an appropriate algorithm is automatically selected through artificial intelligence, and various parameters of the AEB system are calculated and adjusted according to the processed data; and S4, after AEB parameter adjustment is completed, performing a multi-scene simulation test in a virtual environment, and evaluating the performance of the AEB system in different driving scenes. By introducing an AEB parameter adjustment method based on artificial intelligence, real-time dynamic adjustment of the AEB system is realized, manual intervention is reduced, continuous optimization is performed by using real-time data feedback, and the intelligence and adaptive ability of the system are improved, so that the performance and safety of the AEB system in different driving scenes are improved.

The invention relates to the technical field of occupational simulation training evaluation, and discloses a system for college student occupational scene simulation training evaluation. The system comprises a task analysis unit, a dynamic behavior modeling unit, a multi-mode interaction management unit, a state evolution tracking unit, a strategy adaptation unit and a comprehensive evaluation generation unit. The system receives the initial scene description and generates a structured task framework, and behavior parameters are configured for student roles; constructing a multi-modal interaction atlas by fusing aligned voice, action and sight line data in real time; identifying a key decision node, and dynamically tracking a team state evolution path; matching and adjusting strategies in a behavior rule base according to the evolution sequence, and outputting an adaptive intervention scheme; and finally generating a multi-dimensional structured evaluation report. According to the system, deep insight and dynamic and objective intelligent evaluation of complex interaction behaviors in the simulation training process are realized.

The invention discloses a distributed adjustable resource layered dynamic aggregation method and system for a virtual power plant. The method comprises the steps of collecting operation data, environment data, user behavior data and market data of a distributed power supply, a flexible load and an energy storage facility, extracting core features, extracting feature parameters by adopting a quantification method, and constructing an adjustable resource feature database; constructing an operation capability index model, and obtaining a resource comprehensive operation capability value based on the index and the weight thereof; scheduling the resources in a classified, partitioned and graded manner; establishing a three-layer structure of a bottom-layer resource model, a middle-layer aggregation model and an upper-layer optimization model, and constructing a multi-objective optimization model; by executing a marketization transaction strategy, a power grid dispatching response strategy and an income distribution strategy, collaborative optimization operation of the virtual power plant, the power market and power grid dispatching is achieved, and finally multi-scene simulation verification and model parameter optimization are conducted. According to the scheme of the invention, efficient aggregation and collaborative optimization scheduling of adjustable resources are realized.

The invention discloses a burying point analysis system for customer behavior analysis, and relates to the field of customer behavior analysis, the system comprises the following components: a data acquisition module, a digital twin model construction module, a business scene simulation module and a behavior prediction and decision support module; according to the invention, the digital twinborn model which accurately reflects customer behavior characteristics is constructed by using the digital twinborn model construction module and combining a deep learning algorithm and a data mining technology, and the model is imported into a diversified virtual business scene for behavior simulation through the business scene simulation module, so that the customer behavior simulation efficiency is improved. And finally, the behavior prediction and decision support module accurately predicts customer behaviors and generates a personalized decision plan by applying a space-time correlation prediction algorithm and an intelligent decision recommendation algorithm based on a knowledge graph, so that the customer behaviors can be accurately predicted. The functions jointly enhance the insight ability of enterprises for customer behaviors.

The invention discloses a territorial space planning layout method based on multi-target constraint and dynamic weight adjustment. The method comprises the following steps: S1, constructing a multi-dimensional target system comprising a basic constraint layer, a development demand layer and a dynamic adaptation layer; s2, establishing a target space mapping model, generating a basic space unit and endowing the basic space unit with a target correlation coefficient; s3, a dynamic weight adjustment mechanism is designed, and after initial weight assignment, automatic adjustment is carried out when the monitoring data exceed a threshold value; s4, constructing a multi-objective optimization algorithm, and performing coupling calculation to generate an initial scheme; and S5, carrying out multi-scene simulation verification, and outputting an optimal scheme with the highest target collaboration degree. According to the method, the scientificity and adaptability of a territorial space planning layout scheme are improved through cooperation of multiple targets and dynamic weight adjustment.

The invention discloses a method for determining the suitable development area of a large-scale drip irrigation farmland in an underground water shallow-buried area, and the method comprises the following steps: coupling an MODFLOW model and an SWNCM-2D model based on programming software, and developing a coupling model suitable for water and salt migration and crop growth simulation of a saturated zone and an unsaturated zone of the large-scale drip irrigation farmland in the underground water shallow-buried area; according to lysimeter underground water burial depth control test data, calibrating and verifying key parameters of the coupling model, performing multi-scenario simulation of different underground water burial depths, and determining an appropriate underground water burial depth under a drip irrigation condition; setting scenes with different drip irrigation farmland area proportions, simulating by adopting a coupling model, and determining a suitable development area of the large-scale drip irrigation farmland in the underground water shallow buried area by taking a suitable underground water buried depth as a control standard; according to the scheme, through multi-model coupling, multi-process simulation and multi-scene analysis, technical support and quantitative basis are provided for development and field management of large-scale drip irrigation farmland.

The invention relates to a scene simulation-based multi-space-time supply and demand risk identification method for a power system, and the method comprises the steps: generating a database with a space-time label through a data collection and preprocessing unit, and constructing a power grid model; the risk identification module, the scene simulation module and the dynamic mapping module are used for displaying the risk and adequacy data of each region and each time period in the form of a thermodynamic diagram and a distribution diagram to form a power grid fluctuation region; the method comprises the following steps: acquiring different variables in a power grid system to generate dynamic nodes, forming edges among the nodes by an interdependence relationship among the variables, constructing a time-varying relationship network of each time period, combining the time-varying relationship network with a machine learning model, and constructing a prediction model reflecting nonlinear dynamic change of the power grid; a power grid model is adjusted by constructing a time-varying relationship network to carry out a nonlinear dynamic change prediction model, and the evaluation precision of power grid space-time distribution is ensured; the method has the advantages that the time-varying relationship network is established, the prediction precision and the response speed are improved, and risk factors are accurately captured.

The invention belongs to the technical field of data processing, and discloses a deep learning optimization system and method for intelligent equipment. Comprising the steps of collecting data and performing data cleaning to obtain accurate equipment parameters; identifying a target intelligent device resource level based on the accurate device parameters; performing energy consumption scheduling on the target intelligent device based on the resource level to obtain a scheduled intelligent device; performing disturbance simulation on the accurate equipment parameters, and outputting a disturbance stability index; appropriate parameter screening is carried out on the accurate equipment parameters based on the disturbance stability index, and stable equipment parameters are output; performing risk assessment on the stable equipment parameters to obtain parameter risk indexes; performing model matching on the scheduling intelligent equipment based on the parameter risk index to generate a model adjustment strategy; performing scene simulation based on the model adjustment strategy, performing loading optimization on the model adjustment strategy based on a simulation effect, and outputting an optimization model strategy; the efficient deep learning optimization method for the intelligent equipment is realized.

The invention discloses a water resource bearing capacity early warning and response decision-making method, which relates to the technical field of water resource early warning, and comprises the following steps: analyzing water resource bearing capacity, and establishing a water resource bearing capacity system; based on the DPSIRM conceptual model, establishing a dynamic model of the water resource bearing capacity early warning system, performing comprehensive weight calculation on index data of the dynamic model of the water resource bearing capacity early warning system through an analytic hierarchy process and an entropy weight method, and obtaining a comprehensive evaluation result of the water resource bearing capacity in combination with a TOPSIS evaluation model; dividing a comprehensive evaluation result of the water resource bearing capacity, and discriminating key indexes influencing the water resource bearing capacity in combination with a geographic detector model; and taking the key index as the input of a Bayesian network, obtaining an output result, and meanwhile, carrying out variable scene simulation to obtain the influence of different variables on the bearing capacity. According to the method, overload condition risks occurring in different scenes are simulated, and the probability and possibility of occurrence of water resource overload events are calculated.

The invention belongs to the technical field of construction management, and particularly relates to a construction data processing method and system based on big data, and the system comprises a data collection and editing preprocessing module, a time-space correlation modeling module, a multi-dimensional risk deduction module, a decision feedback optimization module and a construction supervision terminal. Multi-source heterogeneous data are efficiently accessed and processed through the data collecting and editing preprocessing module, the efficiency and accuracy of data processing are improved, the space-time correlation modeling module constructs dynamic digital twinborn bodies of construction elements, real-time mapping and correlation analysis of a physical space and a digital space are achieved, powerful support is provided for risk prevention and control, and the method is suitable for large-scale popularization and application. The multi-dimensional risk deduction module carries out risk quantitative evaluation and scene simulation based on the digital twinborn body, potential risks can be found in advance and early warning signals can be generated, the decision feedback optimization module converts risk early warning into a specific disposal scheme, the construction supervision difficulty can be reduced, and a powerful guarantee is provided for smooth proceeding of a construction project.

The invention relates to the technical field of ecological environment management, and provides a multi-scale ecological environment damage assessment model construction and optimization management system, which comprises a multi-scale data acquisition module used for acquiring various basic data related to an ecological environment under different space, time and other scales; the parameter calibration and analysis module is used for verifying and adjusting parameters required by model calculation and evaluation according to the acquired data to ensure that the parameters are adaptive to the actual ecological environment condition; and the scene simulation calibration module is used for setting different ecological environment change scenes, simulating the development process of the different ecological environment change scenes, calibrating simulation logic in combination with the actual situation, and providing a simulation scene for analyzing the ecological environment damage trend and testing the management strategy effect. Through a multi-scale scene simulation and calibration mechanism, the system can accurately simulate ecological damage trends under different environment change scenes, and a reliable simulation scene is provided for testing a management strategy effect.

The invention discloses an ecological vulnerability evaluation method based on road domain landscape pattern optimization, and the method comprises the steps: obtaining expressway road domain environment data as training data, and obtaining ecological environment data; calculating an ecological environment quality index of the ecological environment data, and obtaining landscape structure features in the target area; integrating the landscape pattern index into an ecological sensitive factor, and constructing an ecological vulnerability evaluation model by adopting an SRP structure; performing spatial autocorrelation analysis on space-time evolution of the ecological vulnerability of the road domain according to the ecological vulnerability evaluation index, establishing an ecological vulnerability multi-scene simulation model, performing overlay analysis on an ecological vulnerability evaluation result and a land utilization type, obtaining a specific restoration strategy, tracking space-time evolution characteristics of the ecological vulnerability, and performing road region ecological vulnerability evaluation. Ecological vulnerability influence factors are adjusted based on different scenes, future possible ecological vulnerability risks are simulated, specific restoration strategies are made according to different partition standards, and effective configuration and use efficiency of resources are ensured.

The invention discloses a multi-dimensional situation deduction method for flood disaster prevention in a closed or semi-closed space. The method comprises the following steps: S1, collecting and acquiring geographical and building data and hydrological and meteorological data related to a specified underground space; s2, creating a 3D digital model of the specified underground space according to geographical and building data; s3, scene simulation is carried out in the specified 3D digital model according to the hydrological and meteorological data, a fluid dynamic model is established, the mutual influence relation between the specified underground space and the flood factors is analyzed according to the fluid dynamic model, and the associated characteristics of flood disaster occurrence of the specified underground space in the time sequence are calculated according to the mutual influence relation. And different prevention and treatment schemes are implemented according to the associated characteristics. According to the invention, multi-dimensional simulation and analysis are carried out according to different rainfall scenes, flood risks under different conditions can be evaluated, high-risk areas can be identified more accurately, and specific prevention and control schemes are provided according to different scenes.

The invention discloses a vehicle energy consumption simulation system and platform, the vehicle energy consumption simulation system comprises a plurality of vehicle in-the-loop, each vehicle in-the-loop comprises a scene simulation module, and the scene simulation module is used for simulating various simulation road condition scenes of a vehicle; and the energy consumption calculation module is connected with the plurality of vehicles in the loop and is used for calculating the energy consumption information corresponding to the vehicles in the various simulated road condition scenes in the loop of each vehicle. Therefore, energy consumption calculation when the vehicle is controlled by different driving behaviors and intelligent driving algorithms in various scenes can be realized, and the test cost is reduced.

The invention discloses a real-time flood control scheduling method for a water project group. The method comprises the following steps: constructing a component system of project entities, disaster-bearing targets and law and regulation knowledge; real-time water and rain work conditions are obtained, the five-dimensional indexes are fused and combined with the aging correction factor, and a composite risk index is calculated; based on the real-time water and rain work condition and the assembly system, combining a marginal benefit ratio, and dynamically identifying an effective water engineering group; according to the threshold value of the composite risk index, implementing a low-level layered activation strategy, a middle-level layered activation strategy and a high-level layered activation strategy on the effective water project group; and performing multi-scene simulation optimization on the activated project by adopting a dual-mode workflow combining an agent model and a high-precision physical model, and outputting a final flood control scheduling scheme. According to the invention, accurate perception of risks, dynamic optimization of projects and fine configuration of scheduling strategies are realized.

The invention discloses an enterprise market segmentation and positioning method based on data mining, and relates to the technical field of enterprise market analysis and decision making. According to the method, through dynamic relation modeling and real-time interaction mode tracking, in combination with time sequence analysis and an iterative updating mechanism, the market dynamic change can be accurately captured, and the problem that a traditional method is slow in response is solved. Meanwhile, potential relations among data points are deeply mined by adopting information correlation analysis and a graph network algorithm, the limitation of a traditional method is broken through, and more accurate market subdivision is realized; besides, based on prediction scene generation and decision path optimization, a scene simulation technology and external verification data are combined to generate a high-confidence prediction scene, scientific, comprehensive and dynamically optimized decision support is provided for enterprises, and it is ensured that the enterprises keep competitive power in a complex and changeable market.

The invention discloses an automatic performance testing method and device based on an HDFS cluster and a server. According to the method, corresponding HDFS cluster built-in test tools are called according to different test targets to execute corresponding performance test items, different scene simulations are realized through configuration of different test targets, and multi-dimensional tests can be performed for different cluster configurations. The performance in multiple aspects of throughput, metadata operation capability, high concurrency and the like can be covered, so that the performance of the cluster can be tested more comprehensively; besides, the method integrates self-contained test tools of the HDFS, and performs unified test based on standardized tools and configuration, thereby facilitating performance comparison among different clusters; according to the method, the test efficiency can be improved to the maximum extent and the human intervention is reduced through the writing of the automatic script and the assistance of the intelligent algorithm, so that the automatic performance test which is uniform in standard, efficient and reusable is realized by the method aiming at the HDFS cluster.

The invention discloses a subway transport capacity matching and passenger flow collaborative management and control method based on multi-agent reinforcement learning, and relates to the technical field of urban rail transit operation management. The method comprises the following components: S1, a subway system digital twin model construction step, S2, a multi-agent reinforcement learning training environment construction step, S3, an extreme scene simulation and agent training step, S4, a virtual-real data interaction and model iteration step and S5, an actual system deployment and decision execution step. According to the method, a high-fidelity digital twin model of a subway system is constructed, extreme scenes including passenger flow retention caused by rainstorm and instantaneous large passenger flow of a large competition field are simulated in the model, and a multi-stage sampling method based on scene clustering is combined to perform training for ten millions of times; and the decision-making capability and the cooperation efficiency of the multiple agents in the face of complex and extreme conditions are obviously improved.