271 results about "Computational intelligence" patented technology

The invention discloses a self-adaptive load balancing ring main unit, relates to the technical field of power distribution network protection, and solves the problems that the load balancing strategy of the existing ring main unit is not flexible enough and the monitoring and early warning capabilities are insufficient. The system comprises a data acquisition module, a data processing and analysis module, a load balance control module, a monitoring and early warning module and an expansion and compatibility module. Load distribution is intelligently optimized through real-time data and edge calculation; pID control and fuzzy logic are integrated, parameters are dynamically adjusted, and efficient operation of a power system is ensured; a non-dominated sorting genetic algorithm and an ant colony optimization algorithm are applied to balance energy consumption and stability on the basis of meeting load balance, and an optimal load scheme is generated; safety is improved through closed-loop control and an early warning system, network resource management is enhanced through the software defined network technology, and it is ensured that the system is flexible and extensible; according to the invention, the intelligent load balancing capability of the existing ring main unit is greatly improved, and the operation efficiency and stability are enhanced.

The invention provides a virtual workplace training task allocation method and system based on multi-agent collaboration, and relates to the technical field of intelligent training, and the method comprises the steps: decomposing a training task into subtasks through constructing a knowledge dependence graph; calculating intellectual body knowledge complementarity, cooperation proficiency and task bearing capacity scores, and fusing the scores into a collaborative score; establishing a knowledge topology network based on the difficulty coefficient and the collaborative score, and selecting an optimal agent combination; and recording a training data optimization distribution mechanism. According to the invention, the training efficiency is improved, the optimal configuration of agent resources is realized, and the pertinence and adaptability of training are enhanced.

The invention provides an enterprise product intelligent quotation collaborative decision-making platform. A platform architecture comprises a user interaction layer, a data processing layer and a decision-making layer, and platform functions are realized by relying on an intelligent agent. When a user releases a product quotation task, an authority management agent verifies the identity and access authority of the user, and a user interaction and demand analysis agent in a user interaction layer converts the natural language demand of the user into a structured instruction; the data processing layer receives an instruction, basic data and a special cost agent in the layer pull data from an external system through a cross-system calling agent, and a price calculation agent integrates the data through multi-objective optimization to generate candidate quoted prices; and finally, a man-machine cooperation and intelligent decision-making auxiliary agent in a decision-making layer displays all candidate schemes, and an expert performs fine adjustment to select an optimal quotation. According to the invention, rapid and accurate quotation is realized for enterprise products, the quotation model is continuously optimized through continuous feedback and self-learning, and finally a highly autonomous intelligent quotation system is formed.

The invention discloses a centralized control method and system based on an intelligent conference room and an intelligent exhibition hall, and the method comprises the steps: collecting the people flow data of the intelligent conference room and the intelligent exhibition hall, and carrying out the regional grid division of the intelligent conference room and the intelligent exhibition hall; according to the people flow data, determining the personnel density of each grid area of the intelligent conference room and the intelligent exhibition hall, and according to the personnel density, intensively regulating and controlling the environment state of each grid area; environment data in the adjusted intelligent conference room and the adjusted intelligent exhibition hall are collected, and the overall environment suitability degree of the intelligent conference room and the overall environment suitability degree of the intelligent exhibition hall are calculated based on the environment data; and according to the overall environment suitability, continuously regulating and controlling the environment state of each grid region, and intensively regulating and controlling the energy consumption state of the intelligent conference room and the intelligent exhibition hall. According to the embodiment of the invention, the people flow data is collected in real time, the environmental parameters are monitored, the environmental state is dynamically regulated and controlled according to the people density, the suitability of the environment is improved, the energy consumption is effectively reduced, and the optimal configuration of resources is achieved.

The invention relates to the technical field of electrical digital data processing, and provides a task scheduling optimization method and system based on collaborative analysis. Initializing task information of the target task, and disassembling the target task into a task set composed of a plurality of sub-tasks; performing priority ranking on the sub-tasks according to the emergency degrees, the important parameters and the resource requirements of the sub-tasks; obtaining current execution resources through a resource manager to generate an execution unit set, and generating a collaborative strategy in combination with the priority ranking of the subtasks; and according to the priority ranking and the collaborative strategy, calculating a target value of each task scheduling mode in the intelligent scheduling algorithm to select the scheduling mode, and finally arranging the sub-tasks to the corresponding execution units. Through fine task disassembly, priority ranking, real-time resource monitoring and an intelligent scheduling algorithm, the accuracy and efficiency of task execution are improved, and the flexibility and expandability of the system are enhanced.

The invention relates to the technical field of edge computing, and discloses an edge computing intelligent terminal based on the Internet of Things technology, which comprises a data acquisition module, a network state monitoring module and the like. The data acquisition module can dynamically adjust the acquisition frequency and precision according to network and equipment parameters; the network state monitoring and evaluation module can accurately judge the network risk and timely switch the network to guarantee data transmission; and the equipment operation monitoring and state evaluation module can effectively maintain the stability of the equipment. And the data processing decision module optimizes the data processing flow by using a self-adaptive algorithm. Meanwhile, the system performance is improved by adjusting the weight coefficient according to the scene, and the security encryption system protects the data security comprehensively. The edge computing intelligent terminal effectively solves the existing technical problems, has remarkable effects in the aspects of improving data processing efficiency, guaranteeing equipment stability, enhancing safety, adapting to different scenes and the like, and is of great significance in promoting development of the Internet of Things industry.

The invention relates to the technical field of artificial intelligence, in particular to a self-organizing knowledge base construction method, system and device based on a multi-agent system and a storage medium, and the method comprises the steps: S1, monitoring a dialogue information flow, calculating the self-reply confidence coefficient of an agent, and if the self-reply confidence coefficient exceeds a preset dynamic threshold value, judging that a potential knowledge value exists and triggering an extraction request; s2, in response to the request, performing semantic coding on a dialogue fragment, extracting knowledge elements, and generating a structured knowledge unit by utilizing graph neural network modeling and relation calibration; s3, through a pre-training semantic coding model, mapping the multi-dimensional semantic coding model into a multi-dimensional semantic vector; s4, carrying out hierarchical clustering comparison and combination, and if a threshold value is exceeded, establishing a new classification and adjusting a knowledge base index; and S5, knowledge fingerprints are generated and compared, and fusion updating is carried out based on the reputation scoring model when semantics conflict or redundancy occurs. According to the method, unstructured dialogue high-precision knowledge extraction is realized, so that the knowledge base structure is dynamically self-organized according to semantics, multi-source knowledge is coordinated, and the knowledge management automation level and quality are improved.

The invention belongs to the field of multi-agent reinforcement learning, and discloses a relation-driven multi-agent reinforcement learning method and system based on a mixed game, and the method comprises the steps: enabling a strategy network to generate an agent action, and carrying out the interaction of an environment, so as to collect sample data; the centralized value evaluator calculates marginal influence values of the agents based on samples, and deduces a social influence weight set; assigning group external rewards as individual external social rewards based on the weights; processing the global state by using a random network distillation-driven method, updating a prediction network parameter to minimize a prediction error, and outputting an internal reward set; the external social rewards and the internal rewards are fused to form comprehensive rewards; and updating the strategy network and the value network by using the comprehensive reward, and circularly training until convergence. By adopting the method, accurate modeling of the individual interaction relationship is enhanced, invalid exploration is remarkably reduced, the learning efficiency and the strategy reliability are improved, and the overall performance of the system is enhanced through an explicit social mechanism.

The invention provides an automatic driving decision-making and planning algorithm applied to a complex intersection. The automatic driving decision-making and planning algorithm comprises a prediction module and a planning module, the prediction module is provided with a condition prediction model and is used for predicting and outputting predicted trajectories of surrounding intelligent agents under different candidate trajectories by taking the candidate trajectories of the vehicle as conditions; the planning module comprises a trajectory tree construction module which is used for generating candidate trajectories of a vehicle and forming a trajectory tree; the scene tree construction module is used for generating predicted trajectories of other traffic participants around the vehicle to form a scene tree; the cost evaluation module is combined with a neural network-based feature extractor and a weight decoder to calculate the cost of each planning trajectory branch in the joint trajectory of the intelligent agent; the dynamic planning module is used for exporting candidate planning trajectories from the candidate trajectories output by the trajectory tree construction module and outputting the candidate planning trajectories to a vehicle control system; and the node pruning module is used for pruning low-fraction nodes in the trajectory tree and reducing the number of branches in the scene tree.

The invention discloses an edge computing intelligent power grid resource scheduling method and system based on reinforcement learning, and relates to the technical field of intelligent power grid resource scheduling, and the method comprises the steps: constructing an intelligent power grid environment, initializing an intelligent agent at a key node, and endowing an initial resource scheduling strategy; collecting real-time data points, screening abnormal data and extracting key feature information; and updating the state of the intelligent agent by using the key feature information, and generating and optimizing a scheduling strategy. According to the method, by collecting real-time data points, screening abnormal data and extracting key feature information, efficient data screening and processing are achieved, an intelligent agent can make a decision quickly and accurately when facing a complex and dynamic power grid environment, the state of the intelligent agent is updated by using the key feature information, and the intelligent agent can be quickly and accurately determined. The scheduling strategy is generated and optimized, so that the whole performance of the system can be improved while the intelligent agent continuously optimizes the scheduling strategy, and efficient and reliable utilization of power grid resources is ensured.

The invention discloses a property operation report generation method and device based on multiple agents and a related medium, and the method comprises the steps: calling an intention recognition agent to carry out intention analysis, and then calling a task planning agent to carry out path construction and scheme solving; determining an execution sequence of tasks in combination with the task planning data to obtain task processing data; calling a data collection agent to carry out data collection on the task processing data to obtain primary processing data; and calling a code calculation agent to carry out code generation and model operation on the primary processing data, calling an outline making agent to carry out outline arrangement and report generation processing, calling a report writing agent to complete report packaging, and outputting a property operation report. According to the invention, the structured analysis result obtained through calculation is subjected to outline arrangement and report generation processing, and the property operation report is packaged and output, so that manual report arrangement is not needed, the process is simplified, and the report output efficiency is improved.

There are provided systems and methods for enriching AI models during data call failures using real-time IoT tokens. A service provider, such as an electronic transaction processor for digital transactions, may provide computing services to users including those for electronic transaction processing. In order to provide computing services, machine learning engines and neural networks may be used to compute scores ingested by computing services for intelligent decisions, predictions, classifications, and the like. The scores may though have inaccuracies and decay, which may be made worse when data fails to load for particular model or network features. As such, the service provider may utilize a framework to enrich scores through computing their entropy as a function of errors and randomness with their decay as a function of inaccuracies over time. IoT tokens may then be used to enrich and provide further accuracy or validity time based corresponding real-time data.

The invention relates to the technical field of edge computing, and discloses an edge computing intelligent decision-making system based on edge cloud collaboration, which comprises a terminal sensing layer, an edge computing layer, a network transmission layer and a cloud center layer. The terminal sensing layer is configured to collect original data; the edge computing layer comprises edge computing equipment, a resource scheduling module and a distributed synchronous triggering module which are respectively used for data preprocessing and model reasoning, dynamic resource allocation based on multi-agent deep reinforcement learning and multi-equipment synchronous acquisition realized through a precision time protocol; the network transmission layer dynamically adjusts a transmission strategy based on a reinforcement learning algorithm during data transmission; and the cloud center layer carries out training optimization on the model through a federal learning mechanism and issues the model to an edge side. According to the method, millisecond-level real-time intelligent decision making of an industrial site and sustainable evolution of the AI model are realized through a side cloud collaborative architecture, and the efficiency, the reliability and the self-adaptive capability of the system are effectively improved.

The invention provides a trailing suction dredger loading operation parameter optimization real-time recommendation system and method, and relates to the technical field of trailing suction dredger dredging engineering.The system comprises a data collection layer, a real-time calculation layer, an intelligent recommendation layer and a feedback control layer, the data collection layer is used for collecting trailing suction dredger loading operation parameters in real time, and the real-time calculation layer is used for calculating the real-time calculation layer; the real-time calculation layer can calculate energy consumption and yield in real time based on edge calculation equipment, the intelligent recommendation layer can generate a Pareto optimal solution set through a multi-objective optimization algorithm, and the dynamic weight adjustment module adjusts energy consumption and yield weight coefficients in real time according to the construction stage. The feedback control layer issues the collected loading operation parameters of the trailing suction dredger to an execution mechanism in real time through a PLC, and monitors the operation state of equipment to update a historical database, so that collaborative optimization of energy consumption and yield can be achieved, and the optimization precision is continuously improved through historical data.

The invention discloses an agent sorting method for a trust domain multi-agent reinforcement learning algorithm, and relates to the technical field of reinforcement learning. The invention provides an agent sorting method for a trust domain multi-agent reinforcement learning algorithm in order to solve the defects that in the prior art, a training sequence cannot be reasonably arranged according to agent observation similarity and information richness, and consequently training stability and collaboration are insufficient. Comprising the following steps: collecting observation information of each agent; calculating the observation similarity between the intelligent agents; sorting is carried out according to the similarity, and an intelligent agent training sequence is generated; the sorting comprises the following steps: preferentially selecting agents with low observation similarity, and performing clustering optimization in combination with a centralization mechanism so as to determine a final sorting sequence. The method is suitable for a complex task decision-making system which needs to improve the multi-agent reinforcement learning training stability and cooperation performance.

The invention discloses a secondary water supply tail end pressure balance edge computing AI intelligent gateway, and relates to the technical field of secondary water supply. The secondary water supply tail end pressure balance edge calculation AI intelligent gateway comprises a data acquisition and transmission module, an edge calculation and intelligent analysis module and a control instruction generation and execution module, and the secondary water supply tail end pressure balance edge calculation AI intelligent gateway disclosed by the invention brings significant improvement in multiple aspects for a secondary water supply system; in the aspect of pressure balance performance, the terminal pressure can be accurately monitored and dynamically regulated in real time by means of advanced edge computing power and an intelligent algorithm, pressure change can be effectively predicted and measures can be taken in advance by continuously analyzing a large amount of pressure data and a water consumption trend, and the fluctuation range of the terminal pressure is strictly controlled within an extremely small range. And the pressure can be stabilized within + / -0.01 MPa of a set pressure value, so that users on all floors can enjoy stable and sufficient water pressure at any time, and inconvenience in water use caused by pressure fluctuation is eliminated.

The “Industrial Digestive System” encapsulates a novel paradigm in waste management and resource recovery, bridging the gap between sophisticated computational intelligence and industrial automation. The hardware component replicates the natural digestive system's efficiency in processing a diverse range of inputs, including municipal and industrial waste, transforming them into valuable outputs like biofuels, chemicals, and advanced composite / conglomerate materials. This process is achieved through a series of mechanized operations. Complementing the hardware, the software facet of the invention is rooted in advanced machine learning and optimization algorithms that optimize multivariable functions for the most efficient conversion of input to resources, orchestrating the transformation from varied waste streams, elements, and molecules into solid, liquid, and gaseous outputs. The result is an automated, intelligent manufacturing machine that enhances product quality and operational efficacy. “The Industrial Digestive System” can be seen as a new branch of cybernetics, a cyber-physical system inspired by nature.

The invention relates to a semantic collaborative SLAM map fusion and splicing method based on a multi-modal large model. The method comprises the following steps: deploying a plurality of intelligent agents, collecting original data and preprocessing the original data to obtain multi-modal perception data; inputting the data into a local SLAM (Simultaneous Localization and Mapping) module, combining with a semantic consistency loss fine-tuning multi-modal large model, and constructing a local geometric and semantic map of each agent; fusing the features and mapping to obtain a local and global semantic feature map, and calculating relative poses between the intelligent agents to register the map; and finally, optimizing, reasoning and integrating the initial global map to form a final global semantic map with complete semantics and standard geometric accuracy. According to the method, the problems of insufficient precision, poor robustness, lack of semantic information, difficulty in adapting to dynamic scenes and the like in the existing map splicing process can be effectively solved, and the efficiency, the accuracy and the intelligent level of global map construction are effectively improved.

The invention relates to the technical field of artificial intelligence, in particular to a storage supervision-oriented AIoT edge computing intelligent analysis system and method, and the system comprises an edge computing node, a multi-modal data collection module, an intelligent analysis engine, a dynamic resource optimization module and a secure communication module. The system has the beneficial effects that real-time data acquisition and localized intelligent analysis of storage environments (temperature and humidity, illumination, gas concentration and the like) and cargo states (stacking integrity, displacement, damage and the like) are realized by integrating edge computing nodes and a multi-mode sensor; and the deep learning algorithm is used to carry out autonomous identification and early warning on abnormal events (such as cargo dumping, environment exceeding and illegal invasion).

The invention relates to the field of data processing, in particular to a remote detection method and system for an electric energy meter, and the method comprises the steps: obtaining the operation data of the electric energy meter, carrying out the window division of the operation data according to a time sequence through a variational mode decomposition algorithm, obtaining a comprehensive frequency distribution curve of the operation data in a window, and generating a time-frequency diagram; the method comprises the steps of performing peak point detection based on a time-frequency diagram, determining a main frequency peak point and an interference peak point, calculating a harmonic interference degree value of the frequency of electric energy meter data based on distribution characteristics between the main frequency peak point and the interference peak point, and using change consistency and frequency amplitude of the interference degree value to calculate an abnormal degree value of an intelligent voltmeter. And the abnormal condition of the electric energy meter is judged. According to the method, the change consistency of data of different dimensions is calculated, so that single-dimension noise interference is suppressed, and the reliability of abnormal criteria is improved.

The invention discloses a method for realizing intelligent millimeter-level elevation measurement based on a laser technology, which comprises the following steps of: navigating to a measurement point by an intelligent navigation robot according to a measurement task, adjusting a horizontal platform to a horizontal state, and enabling a two-dimensional coordinate of an RTK (Real-Time Kinematic) module to be equal to a two-dimensional coordinate of the measurement point; the intelligent navigation robot drives the light source mounting rod to rotate through the horizontal turntable, so that the laser transmitter searches and aims at the axis of the laser receiving reference rod to project horizontal laser; the AIOT platform notifies the reference rod to move to receive the laser, records a moving distance value output by the incremental encoder and uploads the moving distance value to the AIOT platform; a laser distance measuring sensor is turned on to emit vertical laser to a measuring point, and the measured distance is output and uploaded to the AIOT platform; and the AIOT platform calculates the millimeter-level elevation of the measurement point where the intelligent navigation robot is located through an expression. According to the invention, millimeter-level elevation measurement and automation and digitization of measurement operation can be realized.

The invention discloses a battlefield multi-agent dynamic cooperation method based on an attention mechanism. The method comprises the following steps: S10, acquiring local observation information; s20, establishing a strategy network and a value network, embedding a multi-head attention mechanism in each of the strategy network and the value network, allowing each agent to dynamically query the internal representation of a teammate, and converting a search problem of an exponential level joint action space into dynamic attention on key information; s30, the strategy network generates action probability distribution of the intelligent agent through the attention layer, and the intelligent agent is forced to depend on a cooperation signal; the value network outputs the value estimation of each agent and provides a reference function; the collaborative loss function calculates similarity penalty between agents based on the embedded representation output by the attention layer; and S40, the training process is updated by adopting a strategy gradient method, strategy network parameters are updated to maximize accumulated rewards, value network parameters are updated by minimizing total loss, and a highly cooperative joint strategy is output. According to the invention, the agent is ensured to always integrate team information during decision making.

The present application relates to a constant space data compression method, device and computer equipment that does not require metadata. The method represents high-dimensional data as a vector, and uses the array offset of each element of the vector in the vector storage area as a coordinate index; maps the corresponding vector to a bucket array according to the coordinate index; uses a cumulative function to update the vector elements of each bucket; when querying, the query vector coordinates are processed in the same way as the compression process, the same bucket array is selected, and the bucket array is processed by an aggregation function to obtain the query result. The method supports compressing vectors of arbitrary length into constant space storage through in-situ mapping, updating, and aggregation, and can decouple the relationship between data size and storage space; there is no need to maintain metadata, and the space occupancy of the compressed data structure can be flexibly set according to the computing environment, and is widely applicable to computing environments such as data centers, edge computing, smart phones, and the Internet of Things.

The invention discloses an intelligent factory maturity evaluation method, which comprises the steps of constructing a capability domain index system and a sub-capability domain index system corresponding to the capability domain index system, and enabling one capability domain index to correspond to a plurality of sub-capability domain indexes; calculating the weight of the capability domain index of the capability domain index system; calculating the weight of the sub-capability domain index of the sub-capability domain index system; obtaining evaluation data of the intelligent factory; based on the evaluation data, satisfaction degree scoring coefficients of the intelligent factory are determined, and one sub-capability domain index corresponds to one satisfaction degree scoring coefficient; and based on the weight of the capability domain index, the weight of the sub-capability domain index and the satisfaction degree scoring coefficient, calculating an intelligent factory maturity evaluation total score of the intelligent factory, the intelligent factory maturity evaluation total score being used for evaluating the maturity level of the intelligent factory.

The invention provides a dynamic frame rate control multi-target tracking method based on reinforcement learning, and aims to improve the adaptive capability and tracking performance of a video processing system in a computing resource limited environment. According to the method, a video is divided into fixed time windows, multi-dimensional features including target motion features, frame rates, system state information and the like in the windows are extracted, and state vectors are constructed and input into a reinforcement learning model to predict frame rate adjustment actions of the next window. The system controls frame rate switching according to the action confidence, and calculates an award by comparing the current tracking performance with the reference performance for feedback policy performance. The method combines proportional frame rate control, frame rate smooth transition and a cooling period mechanism, realizes dynamic balance between tracking performance and computing resources, and is suitable for scenes of edge computing, intelligent monitoring and the like.

The invention relates to the field of multi-agent reinforcement learning, and discloses a reinforcement learning method based on causal reasoning and a hierarchical attention mechanism, which makes up the defects of inaccurate role allocation and low cooperation efficiency in a traditional multi-agent system and improves the overall cooperation performance. According to the method, a causal perception multi-agent cooperation model is constructed, firstly, a dynamic causal graph is constructed by using a structural causal model, and a causal influence vector between agents is calculated by using an optimized variational distribution estimator; then generating a causal-guided hierarchical attention weight based on a causal influence vector; then cooperative information transmission is realized through a cross-agent attention sharing mechanism, and enhanced feature representation is generated by using a cross-layer fusion mechanism; a causal perception role selector is further designed based on the global causal contribution degree and the local causal contribution degree, and dynamic allocation of agent roles is achieved; and finally, performing model training optimization through a causal influence internal reward mechanism.

The invention discloses a mobile robot adaptive path planning method based on enhanced Q learning and multi-strategy cooperation, and relates to the field of robot autonomous navigation and computing intelligence. The method comprises the following steps: firstly, establishing a two-dimensional grid map model containing obstacle information through an environment sensing module; the initial position of a gold scrubber population is generated by utilizing the low-difference characteristic of a golden section sequence to enhance the global ergodicity of a solution space, three stages of migration, gold scrubber and cooperation of a gold scrubber optimization algorithm are modeled into a discrete action space, an optimal search action is dynamically selected through a nonlinear attenuation greedy strategy, and the optimal search action is realized. According to the method, adaptive switching of exploration and development behaviors is realized, a search gradient is constructed by using a differential vector of survival of the survival of the survival of the population, and a lens imaging reverse learning strategy is introduced to dynamically disturb an elite individual so as to jump out of a local extremum trap. And finally, outputting an optimal collision-free path through a multi-objective evaluation function including path length, safety and smoothness.

The invention discloses an RIS deployment and beamforming joint optimization method based on reinforcement learning, and the method comprises the steps: initializing an experience playback memory, training subnet parameters and target subnet parameters of reinforcement learning before deployment; initializing a passive beamforming vector of the RIS and resetting the position of the RIS at the beginning of transmission each time; performing channel estimation to obtain an initial state of the intelligent agent; in transmission of each frame, estimating a Q value of each action by using a learning action subnet; selecting actions according to the Q value; adjusting an RIS deployment position and a beam forming vector according to the action; estimating a channel and updating the state of the agent; calculating an active beamforming vector, and calculating an agent reward; storing the experience in a playback memory; when the network is trained, experience is extracted from the playback memory, the training action subnet is updated, and when transmission of each frame is finished, soft updating is carried out on the target action subnet. According to the method, the potential of joint design of RIS deployment and beam forming is fully excavated, the performance is good, and the adaptive capacity is high.

The invention relates to the technical field of public safety personnel evacuation, discloses a public emergency emotional infection simulation method, and aims to solve the problems that an existing emotional infection simulation model does not fully consider a group emotional propagation theoretical mechanism and the influence of personality characteristics of an intelligent agent and is insufficient in simulation precision and authenticity. The method is based on an improved SIRS (Susceptable-Infected-Recovery-Susceptable) model and an OCEAN large five-personality model, and is realized through the following six core steps: 1) constructing a three-dimensional simulation model of a public place; 2) initializing personality characteristics, emotional states and behavior states of the agents; 3) calculating an emotion propagation process (including a propagation range, an influence value, a distance weight and emotion conflict processing) between the intelligent agents; the method comprises the steps of (1) acquiring the emotion of the intelligent agent, (2) calculating the emotion attenuation of the intelligent agent, (3) determining the evacuation speed and completing analogue simulation, (4) realizing the behavior logic of the intelligent agent in different emotion states, (5) calculating the emotion attenuation of the intelligent agent, and (6) determining the evacuation speed and completing analogue simulation. The method can accurately restore the emotion infection and evacuation behaviors of the crowd in an emergency scene, improves the simulation authenticity and lightweight level, and provides decision support for emergency evacuation scheme making and emergency management.

The invention belongs to the cross technical field of computational intelligence and machine learning, and discloses a particle swarm optimization method for a high-dimensional expensive problem fusing a DBN and an agent model, and the method comprises the steps: extracting the features of a high-dimensional optimization problem through an IDBN dynamic dimension reduction module, and carrying out the dynamic dimension reduction of the features; filling a multi-stage collaborative screening mechanism of the samples, and selecting a plurality of representative samples; according to the local search strategy of the elite solution, local development is carried out on the elite solution so as to improve the convergence speed and the precision of the algorithm. According to the particle swarm optimization method for the high-dimensional expensive problem fusing the DBN and the proxy model, through the IDBN dimension reduction module, the search efficiency of an algorithm in a high-dimensional space is remarkably improved, and the construction cost of the proxy model is reduced; through a multi-stage collaborative screening mechanism of filling samples, the precision of the agent model in a desired area and a potential area is enhanced; a local search strategy of an elite solution is introduced, so that the local development capability of the algorithm is improved, and the precision of an optimal solution is improved.