294 results about "Decision maker" patented technology

The invention relates to the technical field of computing power scheduling, and discloses a heterogeneous resource computing power intelligent scheduling method and system. According to the method, real-time state monitoring is conducted on heterogeneous computing resources, and resource state parameters such as the computing unit utilization rate and the memory occupancy rate are obtained; task attributes and user request parameters of the task queue are collected, historical task data are processed based on the genetic algorithm optimization model to execute task demand prediction, and predicted demand parameters are generated. A dependency graph containing resource unit nodes and communication link roadsides is constructed through a resource topology analysis tool, predicted demand parameters are input into a scheduling priority classifier trained by a graph neural network, and an actual scheduling priority is identified. And executing resource conflict prediction based on the priority, inputting task feature vectors into a conflict resolution module of a fuzzy logic decision maker, outputting actual conflict resolution parameters, and finally integrating to generate a scheduling scheme containing a resource allocation sequence and an execution time table.

The invention relates to a multi-source data fusion-based urban physical examination evaluation index calculation method and system. The method comprises the steps of extracting a multi-source data sequence; identifying a data source of the urban physical examination index set, and extracting an independent time sequence data sequence; calculating the information entropy of the independent time sequence data sequence, and distributing a basic fusion weight; calculating a dynamic state evaluation value of the independent time sequence data sequence, and performing weighted fusion on the basic fusion weight and the dynamic state evaluation value to obtain a comprehensive state evaluation value; obtaining a distribution variance of the basic fusion weight, inputting the distribution variance into the uncertainty quantification model, and obtaining an index calculation result containing uncertainty measurement; the real-time performance of the evaluation result is enhanced through an aging attenuation mechanism, and the latest state of the city system is accurately reflected; the output uncertainty measurement index provides a quantitative basis of result credibility for a decision maker, and the decision risk caused by a data fusion error is reduced.

The invention discloses a building facade optimization method and system based on sustainable analysis, and relates to the technical field of data processing. According to the method, parametric modeling is carried out on the external facade of a target building, and a design space is defined; training a machine learning model integrating energy consumption, carbon emission, cost and lighting prediction functions by using historical data; building an optimization problem by taking external facade parameters as decision variables and taking minimization of energy consumption, carbon emission and cost and maximization of lighting as targets, and automatically generating an optimal scheme set by adopting a multi-target optimization algorithm; a decision maker is assisted to select a final scheme through a visual interface, and a corresponding BIM model is output; the method effectively solves the problems that a traditional design method is difficult to coordinate multi-target conflicts, depends on experience and is low in efficiency, and can automatically and intelligently generate an optimal design scheme which is energy-saving, low-carbon, low-cost and good in lighting performance.

The invention discloses a Token level cache matching method and system of a large language model and a storage medium. The method comprises the following steps: constructing a local context fragment; generating a context embedding vector of the current Token, and calculating a context entropy value, a semantic consistency index and a semantic change gradient; for the target Token, determining a semantic category of the target Token; inputting the semantic category to which the target Token belongs into a Hash decision maker to obtain a Hash granularity level; if the Hash is the first-level Hash, executing fixed-length Hash and mapping the Hash to a semantic cache bucket based on a semantic theme or a context range of the first-level Hash; if the first-level hash is the second-level hash, dynamically adjusting the hash length according to the semantic similarity with the adjacent Token; if the Hash granularity level of the target Token is a third-level Hash, constructing a high-dimension context representation and executing a fine Hash operation; and matching the hash result with the KV in the pre-stored cache, and executing corresponding operation according to the matching result.

The invention discloses a multi-objective optimization-based multi-commodity order fulfillment method and device, equipment and a medium, and relates to the technical field of supply chain management. The multi-commodity order fulfillment method comprises the following steps: acquiring order and inventory information including a current order set, a commodity set and a warehouse inventory set; and modeling an order fulfillment problem based on an actual demand of fulfillment of a multi-commodity order in the order and inventory information. The established model is a multi-objective optimization problem containing three objectives. Generating an initial population by adopting a heuristic method based on priority and inventory feasibility; and carrying out iterative optimization on the initial population by adopting a rapid non-dominated sorting genetic algorithm with elitism based on a double-layer elitism strategy to obtain a Pareto non-dominated solution set. And selecting a final order fulfillment scheme from the Pareto non-dominated solution set according to the preference of a decision maker. According to the method, three core operation indexes are synchronously improved under the condition of meeting feasibility constraints such as inventory, processing capability and demand.

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 provides an intelligent recommendation method, system and device for MySQL dynamic parameters and a medium, and belongs to the technical field of databases. The method comprises the following steps: collecting structured performance indexes in real time, extracting unstructured text knowledge, and storing the unstructured text knowledge into a data lake; performing cleaning, fusion and feature extraction processing on the acquired data, constructing a time sequence data set, and generating a multi-modal feature vector; constructing a parameter optimization model fusing the text encoder, the parameter dependency graph encoder and the reinforcement learning decision maker, and training the parameter optimization model; according to the real-time system state vector and the user optimization target, using the parameter optimization model to output parameter adjustment suggestions, generating a parameter adjustment suggestion list, and predicting potential risks; according to the parameter adjustment suggestion, a progressive adjustment strategy is adopted to execute parameter adjustment operation, and the adjusted performance index is monitored in real time; and feeding back a parameter adjustment implementation result to a parameter optimization model training process, updating a model weight, generating a parameter adjustment case and storing the parameter adjustment case in a knowledge base.

The invention discloses a multi-agent collaborative visual navigation reasoning enhancement method and system, and the method comprises the steps: an inference agent analyzes input data, and generates structured output containing a reasoning process and an initial answer; independently analyzing the input data by the evaluator agent, generating an evaluation answer and reviewing the output of the inference agent; comparing whether the initial answer is consistent with the evaluation answer, and if yes, outputting a final answer; if not, calling a bifurcation feedback agent, and generating a core bifurcation point abstract and a visual evidence verification plan; and calling a final decision maker agent to directionally retrieve the video evidence according to the visual evidence verification plan, and outputting a final answer. Four roles of an inference person, an evaluator, a divergence feedback person and a final decision maker are introduced, a complete'generation-evaluation-feedback-optimization 'decision link is constructed, and the cognition and inference accuracy in a complex scene is remarkably improved.

The invention belongs to the technical field of robot task planning, and particularly relates to a robot closed-loop task planning method and system based on a double-track re-planning strategy. Comprises: using a large language model to generate an action sequence based on a to-be-executed task; before the action of each step is actually executed, the action executability of the action of the current step is judged; after each step of action is actually executed, action execution success judgment is carried out on the current step of action; when it is judged that the action cannot be executed or execution of the current-step action fails, a replanning decision maker based on a large language model is triggered, selection is conducted between two replanning strategies of plan reconstruction and task replacement, a plan reconstruction or task replacement result is executed, and robot closed-loop task planning is achieved. According to the method, planning flexibility and environment constraint perception are considered, invalid attempts can be reduced, and the success rate and robustness of long-time tasks in a complex scene are improved.

The invention relates to the technical field of computers, and discloses an intelligent scheduling system and method for a high-efficiency charging platform, and the method comprises the steps: constructing a four-dimensional constraint model integrating the power grid load, the user demand, the equipment health degree and electricity price prediction, and employing a depth deterministic strategy gradient algorithm to drive a multi-target dynamic scheduling decision maker, the global optimization distribution of the charging resources in the space-time power dimension is realized, and strategy reconstruction is completed within 10s when a power grid emergency instruction or a device fault occurs. The system comprises a power grid sensing module, a user acquisition module, a health assessment module, an electricity price response module, a scheduling decision module, an instruction execution module and an emergency reconstruction module, and supports millisecond-level adaptive evolution. According to the method, the weighted reward function is constructed by quantifying the four indexes of power grid stability, user satisfaction, equipment loss and platform income, and the instruction verification and steady-state adaptive mechanism is combined, so that the user experience is synchronously improved, the service life of the equipment is prolonged, and the operation energy consumption is reduced on the premise of ensuring the safety.

The invention relates to a drip irrigation pipe network zoning irrigation control method and system based on multi-objective optimization, and belongs to the technical field of artificial intelligence. The method comprises the following steps of collecting multi-source heterogeneous data and sampling point space coordinates, after abnormal value elimination and normalization processing, splicing features and normalized coordinates to form a joint feature vector, and obtaining irrigation partitions with continuous space and similar features through K-means clustering; constructing a multi-objective optimization model taking the zoning irrigation duration and the inlet target flow as decision variables; solving by adopting a hybrid strategy multi-objective evolutionary algorithm of chaotic mapping initialization and adaptive hybrid variation to obtain a Pareto optimal solution set; and finally, combining an entropy weight method and decision maker preference, determining an optimal irrigation parameter through a superior and inferior solution distance method, and introducing a real-time soil moisture monitoring feedback correction parameter. Partitioned precise irrigation of the drip irrigation pipe network can be achieved, multiple optimization objectives are balanced, the irrigation effect and the resource utilization efficiency are improved, and system energy consumption is reduced.

The invention provides an anti-fraud method and system based on multi-modal perception and cross-time feature modeling. The method comprises the following steps: receiving a multi-modal financial transaction graph sent by an edge computing node; inputting the multi-modal financial transaction graph into a risk control model for risk analysis to obtain a node risk score of each node, an edge risk score of each edge and a gang risk score of each sub-graph; the risk control model is a multi-scale ST-Transform-GCN framework, and the risk control model is a multi-scale ST-Transform-GCN framework; processing the node risk score, the edge risk score and the gang risk score through a gating fusion mechanism to obtain a comprehensive risk score; based on the node risk score, the edge risk score and the gang risk score, extracting a suspicious transaction sub-graph from the multi-modal financial transaction graph; and inputting the comprehensive risk score and the suspicious transaction sub-graph into a preset reinforcement learning decision maker to obtain an anti-fraud strategy, and executing the anti-fraud strategy to achieve the purpose of accurately identifying the complex collaborative fraud behavior.

The invention discloses an intelligent decision-making method and system based on deep learning, and relates to the field of data processing. The method comprises the steps of obtaining place data and corresponding attribute data of a to-be-decided project; establishing a fuzzy relation matrix between the places and the attributes; generating a network model reflecting trust relationship strength among users through trust propagation operation of the graph neural network; identifying a community structure containing a community overlapping degree through a community discovery algorithm; and according to the trust relationship strength between the users and the community overlapping degree, calculating an influence weight of a decision maker, forming a group consensus through a robust optimization method, and generating a decision result of the project to be decided. Aiming at low network relation modeling precision caused by multi-source heterogeneous data in bus station layout decision making in the prior art, the method and the device have the advantages that the network relation modeling precision is low through accurate modeling of an information propagation path in a complex trusted network, effective dimension reduction representation of a high-dimensional feature space and robust optimization solution in an uncertain environment; therefore, the calculation precision and robustness of the bus station layout intelligent decision-making system are improved.

The invention provides a power transmission and transformation project full-life-cycle carbon emission design system based on multi-objective optimization, and the system comprises a full-life-cycle carbon emission database module which is used for storing carbon emission factors and technological parameters of a power transmission and transformation project in each stage; the engineering scheme modeling module is used for generating an engineering scheme including a standardized bill of materials and a construction list based on the carbon emission factors and the process parameters in combination with engineering parameters and design data; the carbon emission evaluation module is used for evaluating the full-life-cycle carbon emission of the engineering scheme; the multi-objective optimization module is used for realizing synchronous optimization of the carbon emission and various constraint conditions to obtain a plurality of engineering scheme solution sets; and the decision support and visualization module is used for visually displaying the target optimization solution set and the carbon emission of the whole life cycle, automatically generating an engineering scheme for comparative analysis, and assisting a decision maker to quickly select an optimal scheme. And through a multi-objective collaborative optimization method, synchronous optimization of full-life-cycle carbon emission and economic objectives is realized.

An equipment system optimization method driven by deep reinforcement learning comprises the following steps: sequentially constructing an equipment system architecture model and a combat scene simulation model based on a DoDAF framework, then carrying out parameter space sampling in the equipment system architecture model by using a uniform design method, and according to capability items and equipment elements defined by the equipment system architecture model, carrying out parameter space sampling on the equipment system architecture model; constructing a combat effectiveness evaluation model and a system cost evaluation model for evaluating the system; constructing a parameter-modulated deep reinforcement learning (PM-DRL) model to explicitly embed system parameters into an agent state space, and performing data collection and evaluation through the trained PM-DRL model to obtain lt; system parameter-evaluation result gt; a data set; and finally, constructing an optimization model by taking the agent model as a target function, and determining an optimal solution, namely system parameter configuration, by combining the solved Pareto frontier with the preference of a decision maker. According to the method, under the same combat effectiveness requirement, system parameter configuration with lower construction cost can be obtained through optimization.

The invention provides a power transaction agent system based on AI auxiliary decision making, the system can provide intelligent power transaction service based on an intelligent contract, the system is responsible for processing massive, high-frequency and multi-dimensional data, providing deep insight and accurate prediction, liberating traders from heavy data work, and improving the working efficiency of the traders. The method focuses on strategy formulation and risk control of transactions. The system can provide questioning and answering services for power transactions for users, and can perform power transaction prediction and visualization in each mode based on collected power transaction big data, so that power market intelligent analysis, retrieval and other services of traders, analysts and decision makers can be deeply endowed, multiple functions are integrated, and the user experience is improved. The system assists traders, users, managers and the like, realizes intelligent service and lightweight service of power transaction, reduces transaction cost, and improves market circulation efficiency and benefits of power transaction.

The invention belongs to the field of intelligent workshop scheduling, and particularly discloses a large model enabled workshop scheduling end-to-end self-decision engine, method and device. According to the method, the large model is positioned as a core decision maker instead of a traditional auxiliary tool, so that the powerful capabilities of the large model in the aspects of natural language understanding, context learning, complex logical reasoning and content generation are fully utilized; according to workshop real-time state information, a dynamically changing workpiece pool, a scheduling target input by a user through a natural language and emergency description, an autonomous and end-to-end scheduling decision can be directly carried out, so that the rapid response capability and intelligent processing level of a scheduling system to dynamic events are improved, and the scheduling efficiency is improved. And the application threshold is reduced through natural language interaction, the dependence on explicit programming and rule customization is reduced, a low-code development paradigm is developed, and the method has a far-sighted decision potential exceeding a traditional heuristic rule.

The invention provides a remote sensing image interpretation method based on large model reasoning and tool enhancement, which comprises the following steps: generating an initial reasoning node of a reasoning tree by using a large language model as an active decision maker based on system cue words and input remote sensing image features; based on the current inference tree state, the active decision maker executes inference and generates a new inference node, so that the inference tree is expanded; based on node scores, adopting a pruning strategy to eliminate reasoning paths with low scores; repeating the steps until a reasoning termination condition is met, and selecting a path with the highest accumulated score from the reasoning tree as an optimal reasoning path; and key information is extracted and organized into a structured intelligence report to be output. According to the method, a complete interpretation chain of'thinking-tool-observation 'is explicitly modeled through a tree reasoning mechanism, so that the generation logic of each intelligence conclusion is clear and visible, and the problems of trust crisis and insufficient interpretability caused by'black box' decision of a traditional deep learning model are solved.

The invention discloses a Transform-based digital textbook automatic hierarchical design method. The method comprises the steps of obtaining digital textbook content, performing structured analysis, dividing the digital textbook content into a plurality of content units, and allocating a unique identifier; an improved Transform model is input, semantic modeling is executed, the cognitive hierarchy is controlled, and folding representation is generated; based on the folded semantic representation, initial layering is executed, a layered structure is constructed, and a sequence and hierarchical relationship is generated; constructing a self-evolution hierarchical decision maker, detecting conflicts in a hierarchical structure, and identifying a hierarchical inconsistent relationship; re-executing hierarchical processing based on the conflict relation updating rule to generate an updated hierarchical structure; and performing disturbance processing on the textbook structure, repeating modeling and layering processes, and verifying a hierarchical stability result. According to the method, the stable and automatic hierarchical design of the digital textbook is realized by improving Transform semantic modeling and self-evolution hierarchical decision.

The invention provides a hierarchical autonomous behavior decision and joint control method for expressway and ramp scenes, and belongs to the technical field of auxiliary driving. Comprising the steps of S1, a training stage; s1.1, collecting expert data and training an IL decision maker; s1.2, an RL control module is trained; s1.3, performing combined overall verification and fine adjustment; s2, an execution stage; s2.1, environment perception and state construction are carried out; s2.2, performing upper layer imitation learning decision making; s2.3, calling a lower layer reinforcement learning control module; s2.4, a lower layer MPC control module is called; and S2.5, vehicle execution and environment updating are carried out. According to the invention, control mode switching is more adaptive and learnable, and dependence on artificial experience is reduced; strategy flexibility and control feasibility or safety are considered; complex tasks such as highway main road lane changing, ramp confluence and ramp diversion can be processed under the same framework; according to the method, smooth and comfortable control behaviors can be generated on the premise of ensuring the safety margin.

The invention discloses a class preloading method and device for Java micro-service cold start acceleration, and belongs to the technical field of cloud computing and Java virtual machine optimization. The method comprises the steps of class dependency analysis based on a historical call chain, hierarchical class preloading execution and shared memory snapshot management. The device comprises a class analysis engine, a preloading decision maker and a memory snapshot management and JVM optimization adaptation module. Through intelligent analysis of class popularity, hierarchical preloading and combination of a cross-JVM instance memory sharing technology, the Java micro-service cold start time is reduced from average 4.2 s to 0.8 s, memory occupation is reduced by 45%, compatibility with a standard JVM and a mainstream framework is kept, and the method is suitable for financial transaction, real-time recommendation and other micro-service applications in a Serverless scene.

The invention discloses a green robust independent parallel locomotive scheduling method with uncertain processing time. The method comprises the following steps: acquiring a to-be-scheduled parameter set; constructing an irrelevant parallel machine scheduling model taking worst scene completion time WC and scene average energy consumption MTEC as double targets based on the parameters; a scene-driven double-population discrete artificial bee colony algorithm is adopted for solving, and the method comprises the steps of population initialization, employed bee global search based on ternary championics and two-point crossing, division into two sub-populations according to MTEC, MN local search based on a mean value scene, WN local search based on a worst scene, LN observation bee self-adaptive neighborhood search based on Q-learning and scout bee disturbance. And finally, outputting a robust scheduling solution set with both robustness and low-carbon property according to a Pareto criterion. And a plurality of scheduling schemes considering robustness and energy consumption optimization are provided for decision makers.

The invention provides a reinforcement learning steering control method and system based on a safety barrier, electronic equipment and a storage medium, and relates to the field of automatic driving safety control. The method comprises the following steps: sensing current states of each participating object and a vehicle in an environment; respectively performing state estimation and future moment position prediction on the participating objects and the vehicle by applying Kalman filtering to obtain relative position probability distribution of each participating object and the vehicle in a plurality of steps in the future; calculating the collision probability of the vehicle and each participating object, and determining the overall collision risk according to the probability; the total collision risk is compared with a preset collision safety barrier threshold value, when the total collision risk is larger than the collision safety barrier threshold value, a safety barrier is triggered, candidate wheel turning angles are projected into an action set meeting safety constraints based on minimum change projection, and the projected wheel turning angles are issued and executed; if not, triggering is not conducted, and a reinforcement learning decision maker is adopted to output candidate wheel rotation angles and issue for execution.

The invention discloses an intelligent analysis system for the running state of a 3C vehicle-mounted contact network, and belongs to the technical field of crossing of intelligent operation and maintenance of rail transit and industrial artificial intelligence. And the system associates the multi-source heterogeneous observation data to a specific equipment unit through an equipment centralized data binding module. And the multi-modal feature extraction and state management unit processes the data and maintains a multi-dimensional state vector of the equipment by using the Kalman filtering updating unit. And the physical-data hybrid decision maker fuses the data driving rule and the simplified physical model to output a diagnosis result. The topology analyzer performs global verification based on a mechanical transfer rule. The system further comprises a long-term health state prediction and feedback module, early failure risks are predicted through a hidden Markov model, Kalman filtering process noise is dynamically fed back and adjusted, and cooperation of long-term prediction and short-term estimation is achieved. According to the method, the technical problems of multi-source data splitting, lack of physical basis in diagnosis and incapability of predictive maintenance are solved.

The invention discloses an unplanned operation early warning method and system fused with multi-source data mining. According to the method, vehicle tracks, operation plans and electronic fence data are collected, cleaning and map matching preprocessing are carried out on the tracks, and then track sequences are mapped into low-dimensional embedded vectors through a track representation learning model; recognizing an abnormal behavior mode through clustering based on the vector, and constructing a dynamic risk index and predicting the future state of the vehicle in combination with real-time data; inputting the abnormal mode, the risk index and the prediction result into a fuzzy logic decision maker for multi-source fusion, outputting a comprehensive risk level and triggering graded early warning; a reinforcement learning mechanism is adopted to dynamically optimize decision maker parameters according to the early warning effect, and finally early warning information is pushed to a management platform and feedback is received to form closed-loop management. According to the invention, accurate and adaptive early warning of unplanned operation behaviors is realized, and the intelligent level of operation safety supervision is significantly improved.

The invention belongs to the technical field of water supply system toughness evaluation and optimization decision making, particularly relates to an urban water supply system toughness evaluation and optimization decision making method and system, and solves the problems that a traditional evaluation method is difficult to deal with uncertainty and large in subjective interference, and an improved method is subjective in weight and lacks dynamic performance and visualization. According to the method, qualitative toughness grade fuzziness and evaluation factor randomness are quantified through a cloud model, index cloudization, a weight cloud model and a multi-level cloud integration mechanism are constructed, toughness grade judgment and cloud parameter optimization are combined, and qualitative-quantitative natural conversion is achieved. According to the method, evaluation scientificity and reliability are improved, decision makers are helped to position short boards and adapt to system time-varying characteristics by means of the visual cloud picture and toughness-impact response corresponding relation, a basis is provided for operation and maintenance improvement and resource allocation, and a stable and adaptive water supply system toughness guarantee system is helped to be constructed.

A global intelligence platform integrating satellite imagery, media analysis, and AI-driven insights. The system comprises a data integration module for processing real-time data streams, an AI analytics engine with machine learning models for each data type, a data fusion module for correlating insights, and a user interface. The AI engine includes models for analyzing satellite imagery, translating, and summarizing news, and processing social media sentiment. The data fusion module spatiotemporally aligns the heterogeneous data to identify relationships and generate a unified knowledge representation. The user interface enables querying, filtering, and customizing intelligence reports. By leveraging advanced AI techniques and diverse data sources, the invention provides comprehensive, real-time intelligence for decision-makers across various sectors, empowering informed responses to global events, trends, and public sentiment.

The invention discloses a multi-target NSGA-III hydrogen production system optimization method based on interactive fuzzy preference. The method comprises the steps that a hybrid energy storage renewable energy source off-grid hydrogen production system model, hybrid energy storage working logic, a target function and constraint conditions are established; constructing a fuzzy preference function, and processing the target function by using the function to obtain an effect function value; and the decision maker selects a preference solution according to the effect function value, updates the reference point by taking the preference solution as a center, optimizes the multi-target NSGA-III algorithm based on interactive fuzzy preference until a set optimization frequency is reached, outputs a preference region of the decision maker, and finally performs optimization on the multi-target NSGA-III algorithm based on interactive fuzzy preference. And a decision maker selects the most preferred solution in the preference area according to the set requirement of the target function, and hydrogen production system optimization is completed. According to the invention, the time complexity of the algorithm is reduced, and decision maker preference optimization of system economy and hydrogen production power supply reliability is realized.

The invention provides a soft rock damming safety evaluation method and system based on fuzzy analytic hierarchy process, and belongs to the technical field of water conservancy and hydropower engineering safety evaluation, and the method comprises the steps: constructing a target layer-criterion layer-index layer three-level evaluation model framework; determining indexes in the index layer according to the evaluation items of the item layer; calculating the weight of each index by adopting an analytic hierarchy process; establishing a fuzzy relation matrix; performing synthesis operation on the weight of each index and the fuzzy relation matrix by using a fuzzy synthesis operator to obtain an evaluation vector; and judging the safety level of damming according to the evaluation vector. According to the method, the confidence interval based on credibility distribution is constructed, a traditional single evaluation result is replaced, uncertainty in the evaluation process is fully reflected, a more comprehensive and scientific information basis is provided for decision makers, and therefore the decision makers are assisted to make more reasonable and reliable engineering decisions.

The invention belongs to the technical field of automated guided vehicles, and particularly relates to a multi-source positioning fusion and navigation correction method and system for an AGV, and the method comprises the steps: carrying out the pose estimation through the bidirectional coupling of extended Kalman filtering and particle filtering, and the estimation uncertainty is fed back to the extended Kalman filter to dynamically adjust the noise parameter. And further introducing sliding window factor graph optimization to carry out back-end smoothing. In the navigation stage, a dynamic decision maker based on deep reinforcement learning is adopted, and optimal control parameters are generated according to real-time positioning, map semantics and historical performance. The system can also enable the filtering model and the decision strategy to adapt to the current environment through periodic online fine tuning. Through innovatively and deeply fusing a classical state estimation method and a leading-edge machine learning method, the positioning precision, the environment understanding capability and the navigation intelligence of the AGV in a complex dynamic scene are remarkably improved.