14 results about "Crowd simulation" patented technology

The invention is suitable for the technical field of crowd simulation and emergency evacuation, and provides an emotional infection and social force model coupling-based crowd evacuation method, which comprises the following steps of: constructing an emotional infection model based on an SEIRS framework, dividing individual emotional states into a susceptible state, an exposed state, an infected state and a recovery state, the infection rate and the recovery rate are dynamically adjusted through a feedback function; establishing a social force model, and embedding an emotion value into calculation of a target driving force and a repulsive force between individuals to realize real-time adjustment of the motion behavior by the emotion; global path planning and an ant colony pheromone mechanism are fused, a density perception cost function and pheromone guiding force are introduced, and dynamic blockage avoidance is achieved; a bidirectional feedback mechanism is designed, and local path reconstruction is triggered when congestion is detected. According to the method, bidirectional coupling of emotion propagation and behavior decision is realized, the authenticity and adaptability of evacuation simulation are improved, and a scientific basis can be provided for emergency management and evacuation strategy optimization in public places.

The invention provides a crowd simulation and spatial layout optimization method and system based on an open source engine and related equipment. The method comprises the following steps: receiving user input in an interactive interface constructed by a three-dimensional engine, creating and editing three-dimensional scene data, and mapping the three-dimensional scene data into a scene object set with an identification attribute; receiving crowd behavior parameters set by a user based on the scene object set, and associating the crowd behavior parameters to the corresponding scene objects to generate parameter binding information; a configuration generation module is called, a configuration file compatible with an open source crowd simulation framework is generated according to the scene object set and the parameter binding information, and the configuration file comprises structured data describing the relation between scene object space attributes and crowd behavior parameters; and inputting the configuration file into an open source crowd simulation framework, executing simulation calculation of crowd agency behaviors, and generating trajectory data corresponding to the configuration file.

The invention is suitable for the field of crowd motion simulation, and provides a crowd motion simulation method fused with walking aid equipment, a computer readable storage medium and computer equipment. Comprising the following steps: constructing a building scene model, and configuring crowd parameters in the building scene model; according to the crowd parameters in the building scene model, calling and instantiating a corresponding number of intelligent agents, corresponding types and corresponding initial positions in the building scene model from a preset multi-mode intelligent agent model library, and endowing each intelligent agent with a corresponding parameter; and according to the intelligent agent at the corresponding initial position in the building scene model, based on a time stepping simulation cycle mechanism, dynamically simulating and deducing all the intelligent agents in the building scene model to carry out motion and interaction in the building scene model to obtain a simulation result. Compared with a traditional simplified model, the obtained crowd motion simulation result is closer to reality, the accuracy is greatly improved, and the crowd simulation precision is improved.

The application provides a multi-agent interaction simulation method based on stereoscopic vision information, which comprises the following steps: providing each agent with a virtual binocular camera, dividing the field of view into multiple sectors and performing nearest neighbor search, generating a focus list, and then calculating the physical speed of the agent; at the same time, training the agent navigation strategy by using a reinforcement learning network, generating a navigation decision speed in combination with a multi-level reward mechanism; adaptively weighting and fusing the navigation decision speed and the physical speed, dynamically adjusting the weight proportion according to the environmental conditions, and generating a final speed instruction; finally, executing the instruction in a simulation environment, driving the agent to move, and outputting simulation results containing trajectories and performance indicators. The application breaks through the assumption that the agent has perfect perception ability in traditional crowd simulation, significantly improves the realism, behavior rationality and robustness in complex scenes of the simulation, and can be widely applied to the fields of evacuation simulation, game development and virtual reality.

The invention provides a mesoscopic crowd simulation model construction method, a mesoscopic crowd simulation method and mesoscopic crowd simulation equipment, and relates to the technical field of computer simulation. Based on dynamic self-organizing domain decomposition of a leader following model, dividing historical individual movement track data according to all historical individual information to obtain multiple pieces of historical group movement track data; training the initial BPINN sub-networks according to the training set to obtain a plurality of predicted group motion trajectory data; carrying out loss calculation on all predicted group movement track data and a test set to obtain a global total loss function; and adjusting model parameters of the initial BPINN sub-network through the global total loss function until the global total loss function meets a preset condition, and taking the initial BPINN sub-network after parameter adjustment as a mesoscopic crowd simulation model. According to the method, the simulation precision of the simulation model of the mesoscopic crowd is improved.

This disclosure belongs to the field of crowd evacuation simulation technology, and provides a data-driven crowd group movement simulation method and system, including the following steps: acquiring crowd video data; dividing the acquired crowd video data into crowd groups; extracting crowd movement attributes based on the divided crowd groups; quantifying the extracted crowd movement attributes into group attributes to obtain group attribute quantification results; and obtaining a simulation animation of crowd group movement based on the obtained group attribute quantification results and a crowd simulation platform to realize the simulation of crowd group movement.

The invention discloses a crowd passing management system and method and computer equipment. The crowd passing management system comprises a crowd simulator and a large language model (LLM) planning agent, the crowd simulator is configured to respond to the first decision scheme output by the LLM planning intelligent agent, simulate pedestrian motion behaviors and crowd dynamics in a scene marked with a passing area, obstacles, vertical traffic and function nodes, and output real-time data streams; the LLM planning intelligent agent is configured to analyze the real-time data flow through a semantic understanding technology and calculate a multi-dimensional congestion index according to the analyzed real-time data flow; and optimizing the first decision scheme according to the multi-dimensional congestion index, outputting a second decision scheme, and sending the second decision scheme to the crowd simulator. In the embodiment of the invention, a dual-core coupling architecture of microscopic simulation and a macroscopic semantic agent forms a data-driven and knowledge-driven fused collaborative mechanism, so that the congestion is relieved and the traffic efficiency is improved.

The present application provides a kind of embodied perception crowd simulation method based on imperfect stereovision, to make the local behavior in crowd simulation more realistically reflect the perception constraint.The method is to set agent with different individual physiological attributes in 3D scene;For each agent, construct a differentiated embodied stereovision perception model;Through the model, binocular view is collected and converted into depth map, the depth map is divided into sectors and the depth information is aggregated, the sectorized free space representation is obtained;Based on the cognitive delay characteristics determined from individual physiological attributes, time filtering is performed on the free space representation to generate internal free space estimate;According to the internal free space estimate, the sector passability is judged, and the expected speed is generated based on the evaluation result of passable sector, and the non-collision position is updated.The present application unifies embodied difference, depth perception error and reaction time delay into behavior chain, so that the simulated movement is more naturally adapted to the change of visible space.

The application discloses a natural disaster early warning and tourism safety emergency response system, comprising: a data layer constructs a space-time disaster causal network, a root node is configured with a disaster characteristic matrix containing an influence radius and a disaster-causing intensity, nodes and edges have geographic coordinates and time delay attributes, each edge has a time lag coefficient, an intermediate node is activated and needs an upstream weighted summation value to be greater than 0.7, a decision layer establishes disaster interaction edges and coupling operators when multiple root nodes are concurrent, forms a dynamic composite causal graph, outputs a nonlinear superposition effect of facility preservation and evacuation efficiency by a graph neural network, calls a real-time crowd simulation engine to generate a pareto optimal response scheme set, and an edge layer deploys the engine and a decision tree model obtained by knowledge distillation. An interaction layer converts the scheme into differentiated instructions and forcibly pushes the differentiated instructions to a guide and a tourist terminal through a three-level permission system, and the instructions are attached with digital signatures.

The invention provides a multi-agent interactive simulation method based on stereoscopic vision information, and the method comprises the steps: configuring a virtual binocular camera for each agent, dividing a visual field into a plurality of sectors, carrying out the nearest neighbor search, generating a focus list, and then calculating the physical speed of the agent; meanwhile, a reinforcement learning network is adopted to train an agent navigation strategy, and a navigation decision speed is generated in combination with a multi-level reward mechanism; carrying out adaptive weighted fusion on the navigation decision speed and the physical speed, dynamically adjusting a weight ratio according to environmental conditions, and generating a final speed instruction; and finally, executing the instruction in a simulation environment, driving the intelligent body to move and outputting a simulation result containing a track and a performance index. According to the method, the hypothesis that the intelligent agent has perfect perception ability in traditional crowd simulation is broken through, the reality sense of simulation, the behavior rationality and the robustness in complex scenes are remarkably improved, and the method can be widely applied to the fields of evacuation simulation, game development, virtual reality and the like.

The application is suitable for the field of crowd simulation and emergency evacuation, and provides a crowd evacuation method based on emotion contagion and social force model coupling, which comprises the following steps: constructing an emotion contagion model based on SEIRS framework, dividing individual emotion state into susceptible state, exposed state, infected state and recovered state, and dynamically adjusting infection rate and recovery rate through feedback function; establishing a social force model, embedding emotion value into target driving force and individual repulsive force calculation, realizing real-time adjustment of emotion on movement behavior; fusing global path planning and ant colony pheromone mechanism, introducing density perception cost function and pheromone guiding force, realizing dynamic congestion avoidance; designing a bidirectional feedback mechanism, triggering local path reconstruction when congestion is detected. The application realizes the bidirectional coupling of emotion transmission and behavior decision, improves the reality and adaptability of evacuation simulation, and can provide a scientific basis for public place emergency management and evacuation strategy optimization.

The application is suitable for the technical field of crowd simulation, and provides a crowd evacuation simulation method, device and terminal equipment, which comprises the following steps: constructing a scene model; constructing a pedestrian model and an attacker model based on the scene model, wherein the pedestrian model comprises a pedestrian motion rule, and the attacker model comprises an attacker motion rule; constructing an interaction model based on the pedestrian model and the attacker model, wherein the interaction model comprises multiple interaction modes, and the multiple interaction modes can be converted to each other; and performing crowd evacuation simulation based on the scene model, the pedestrian model, the attacker model and the interaction model. The application can more realistically simulate the crowd evacuation movement in a terrorist attack, and provides data support and scientific basis for the construction and management of public places, so as to reduce the casualties of the crowd in a terrorist attack.

The invention discloses a pedestrian behavior simulation scene construction method and system, a terminal and a storage medium, and relates to the technical field of crowd simulation, and the method comprises the steps: obtaining a static three-dimensional virtual scene, and determining simulation environment data according to the static three-dimensional virtual scene, the simulation environment data comprising a two-dimensional structured navigation map and at least one global reference trajectory; obtaining state data corresponding to the virtual pedestrian, and obtaining a predicted motion trajectory corresponding to the virtual pedestrian through a trained trajectory diffusion generation model according to the state data and the simulation environment data; and controlling the virtual pedestrian to move in the static three-dimensional virtual scene according to the predicted motion track. Therefore, the pedestrian motion trail closer to the real scene can be generated based on the pre-trained trail diffusion generation model, so that the motion trail of the virtual pedestrian is closer to the pedestrian motion trail in the real scene, the authenticity of pedestrian behaviors can be improved, and the authenticity of the constructed pedestrian behavior simulation scene can be improved.

An embodiment of the present application provides a method and a device for calculating a building-related load. The method for calculating a building-related load comprises the steps of: acquiring simulation activity features of a plurality of virtual persons on the basis of simulation activity in a virtual building environment simulating an environment in a building, performed by the plurality of virtual persons simulating a crowd in the building, the simulation activity features including heat generation amounts of the plurality of virtual persons; and calculating a building-related load on the basis of at least the heat generation amounts of the plurality of virtual persons. Due to this configuration, it is possible, by a simple and efficient method, to simulate crowd activity features that are more realistic and accurate than preset fixed values, i.e., crowd simulation activity features. Given the above, it is possible, by a simple and efficient method, to simulate crowd activity features that are more realistic and accurate than preset fixed values, i.e., crowd simulation activity features, thereby improving the calculation accuracy of the building-related load on the basis of the simulation activity features.