Search

CN-121981348-A - Evacuation path planning method and device, electronic equipment and storage medium

CN121981348ACN 121981348 ACN121981348 ACN 121981348ACN-121981348-A

Abstract

The invention relates to an evacuation path planning method, an evacuation path planning device, electronic equipment and a storage medium, wherein the method comprises the steps of responding to an emergency evacuation instruction, and acquiring environment risk perception data, personnel state data and channel congestion coefficients in real time; the personnel state data comprise evacuation personnel positions, environment risk perception data, personnel state data and channel congestion coefficients are processed to construct a dynamic emergency situation map, each path edge in the dynamic emergency situation map is associated with a dynamic weight, the dynamic weight is calculated based on the real-time risk coefficients, the channel congestion coefficients and basic transit time, a target optimization model of multiple optimization targets is constructed based on the dynamic emergency situation map aiming at the evacuation personnel positions, the target optimization model is solved to obtain a target evacuation path, the target evacuation path is converted into an evacuation guiding instruction, and the evacuation guiding instruction is issued, so that the intellectualization, the precision and the safety level of emergency evacuation are improved.

Inventors

  • Ke Xiaoqi

Assignees

  • 苏州真趣信息科技有限公司

Dates

Publication Date
20260505
Application Date
20251209

Claims (10)

  1. 1. An evacuation path planning method, characterized in that the method comprises: responding to an emergency evacuation instruction, and acquiring environmental risk perception data, personnel state data and channel congestion coefficients in real time, wherein the personnel state data comprises evacuation personnel positions corresponding to personnel to be evacuated; Carrying out space-time fusion processing on the environmental risk perception data, the personnel state data and the channel congestion coefficient to construct a dynamic emergency situation map represented by a graph structure, wherein each path edge in the dynamic emergency situation map is associated with a dynamic weight, and the dynamic weight is obtained by calculation based on the real-time risk coefficient, the channel congestion coefficient and the basic transit time of the corresponding edge; constructing a target optimization model of multiple optimization targets based on the dynamic emergency situation map aiming at each evacuation personnel position, and solving the target optimization model by utilizing a search algorithm to obtain a target evacuation path of each personnel to be evacuated; The target evacuation path is converted into evacuation guiding instructions, and the evacuation guiding instructions corresponding to each person to be evacuated are issued through an issuing platform.
  2. 2. The method of claim 1, wherein performing a space-time fusion process on the environmental risk perception data, the personnel status data and the channel congestion coefficients, and constructing a dynamic emergency situation map represented by a graph structure comprises: carrying out alignment processing on the space dimension on the environment risk perception data, the personnel state data and the channel congestion coefficient to obtain the environment risk perception data, the personnel state data and the channel congestion coefficient in the same dimension; Carrying out data fusion on the environment risk perception data, the personnel state data and the channel congestion coefficient in the same dimension to obtain graph construction data; and constructing the dynamic emergency situation map based on the map construction data.
  3. 3. The method of claim 1, wherein the determining of the dynamic weights comprises: acquiring a time weight, a risk weight and a congestion weight, wherein the risk weight is greater than the time weight and the congestion weight; Determining a time passing importance value based on the time weight and the basic passing time; Determining a current risk importance value based on the risk weight and the real-time risk coefficient; determining a current congestion importance value based on the congestion weight and the channel congestion coefficient; and determining the dynamic weight based on the time passing importance value, the current risk importance value and the current congestion importance value.
  4. 4. The method of claim 1, wherein constructing a target optimization model of multiple optimization targets based on the dynamic emergency situation map for each evacuee location comprises: Acquiring a safety exit position; Aiming at the position of the evacuee where the evacuee is located, obtaining a feasible path set from the position of the evacuee to at least one safety exit position in the dynamic emergency situation map; And constructing a target optimization model comprising at least two optimization targets of minimizing estimated evacuation time of the path, minimizing accumulated risk of the path and maximizing adaptation degree of the path to the individual attribute of the personnel to be evacuated for each candidate path in the feasible path set.
  5. 5. The method according to claim 4, wherein the method further comprises: Adding and calculating based on the dynamic weights of all sides of each candidate path to obtain the estimated evacuation time of each candidate path; and carrying out addition calculation based on the real-time risk coefficients of all sides of each candidate path to obtain the accumulated risk of each candidate path.
  6. 6. The method of claim 4, wherein the individual attributes include at least a mobility grade, and wherein in evaluating the path to maximize the adaptation of the path to the individual attributes of the person to be evacuated, the method further comprises: For people with mobility grade being inconvenient to move, introducing at least one path attribute constraint in the process of evaluating the adaptation degree of the maximized path to the individual attribute of the people to be evacuated: The number of times of using stairs or steps in the path does not exceed a preset threshold value; the whole gradient or flatness of the path meets the barrier-free passing requirement; The number of known obstacles in the path is below a preset number.
  7. 7. The method of claim 1, wherein the acquiring environmental risk awareness data and personnel status data in real time comprises: the method comprises the steps of acquiring current sensing data in real time through an Internet of things sensor network, analyzing a video stream in real time through video monitoring equipment by utilizing a pre-trained computer vision model to obtain identification risk data, and acquiring three-dimensional coordinates, a moving speed vector and static attribute information of each person to be evacuated in real time through an indoor positioning system; fusing the current sensing data with the identification risk data to generate the environmental risk perception data; and associating the three-dimensional coordinates, the moving speed vector and the static attribute information to form the personnel state data.
  8. 8. An evacuation path planning apparatus, the apparatus comprising: the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for responding to an emergency evacuation instruction and acquiring environmental risk perception data, personnel state data and channel congestion coefficients in real time, wherein the personnel state data comprises evacuation personnel positions corresponding to personnel to be evacuated; The construction module is used for carrying out space-time fusion processing on the environmental risk perception data, the personnel state data and the channel congestion coefficient to construct a dynamic emergency situation map represented by a graph structure, wherein each path edge in the dynamic emergency situation map is associated with a dynamic weight, and the dynamic weight is obtained by calculation based on the real-time risk coefficient, the channel congestion coefficient and the basic transit time of the corresponding edge; the solving module is used for constructing a target optimizing model of a plurality of optimizing targets based on the dynamic emergency situation map aiming at each evacuation personnel position, and solving the target optimizing model by utilizing a searching algorithm to obtain a target evacuation path of each personnel to be evacuated; the evacuation module is used for converting the target evacuation path into evacuation guiding instructions and issuing the evacuation guiding instructions corresponding to each person to be evacuated through the issuing platform.
  9. 9. An electronic device, comprising: A processor; A memory for storing the processor-executable instructions; Wherein the processor is configured to execute the instructions to implement an evacuation path planning method according to any one of claims 1 to 7.
  10. 10. A computer readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform an evacuation path planning method according to any one of claims 1 to 7.

Description

Evacuation path planning method and device, electronic equipment and storage medium Technical Field The invention relates to the technical field of emergency management and intelligent navigation, in particular to an evacuation path planning method, an evacuation path planning device, electronic equipment and a storage medium. Background In complex environments such as various buildings, industrial parks, large public places, etc., sudden public safety events such as fire, dangerous chemical leakage, terrorist attacks, etc. occur. Whether people can be evacuated after the occurrence of an event in a rapid, safe and orderly manner is a key for measuring the emergency management level and reducing casualties to the greatest extent. Currently, the mainstream emergency management system generally adopts a preset static evacuation scheme. Such schemes are typically based on building drawings, preset risk points and standard personnel flow models, planning fixed evacuation paths and resource allocation plans before an event occurs. However, real emergencies have significant dynamics, uncertainty and complexity, which results in that such static schemes expose serious defects in practical application, firstly, the real-time adaptability is lacking, secondary risks exist, and static preset paths cannot sense and respond to dynamic changes of accident sites in real time, such as flame spreading, toxic smoke spreading, channel blockage caused by local collapse of buildings, and the like. The system can continuously guide evacuees to a region which becomes highly dangerous, so that serious secondary injury is caused, life safety is greatly threatened, and the individual variability of the evacuees is ignored, so that accurate guiding cannot be realized, and a static scheme is usually planned on the basis of a 'standard person' assumption, so that real-time positions, movement capacities (such as normal adults, old people, children and handicapped people), psychological states and familiarity degree of the different persons to the environment cannot be considered. The guiding mode of 'one-cut' can not provide 'custom-made' optimal evacuation path for individuals, so that the overall evacuation efficiency is low, and particularly, higher risks are formed for weak groups with weak mobility, the resource allocation is rigidified, global dynamic coordination is lacking, and the opening strategy of an emergency exit, deployment of rescue force and the putting point of emergency materials are difficult to dynamically adjust according to the distribution density and the change trend of people flow generated in real time by a preset scheme. The method can cause serious congestion of some key evacuation channels caused by excessive collection of people flows to form a new dangerous bottleneck, and other available channels or resources are not effectively utilized to cause resource waste and evacuation efficiency loss. In summary, the static emergency evacuation planning method in the prior art is difficult to meet urgent demands for dynamics, individuation and global cooperativity in a real and instant disaster environment. Therefore, a new evacuation path planning method is needed in the art, which can sense the environment and the personnel state in real time, and dynamically and cooperatively optimize multiple targets through an intelligent algorithm on the basis, so as to generate an intelligent solution of a safe, efficient and personalized evacuation path for each evacuated personnel in real time. Disclosure of Invention In view of this, the embodiment of the invention provides a method, a device, electronic equipment and a storage medium for planning an evacuation path, which solve the problems of dangerous guiding paths, low evacuation efficiency, poor global safety and the like in the prior art. One aspect of the present invention provides an evacuation path planning method, including the steps of: responding to an emergency evacuation instruction, and acquiring environmental risk perception data, personnel state data and channel congestion coefficients in real time, wherein the personnel state data comprises evacuation personnel positions corresponding to personnel to be evacuated; Carrying out space-time fusion processing on the environmental risk perception data, the personnel state data and the channel congestion coefficient to construct a dynamic emergency situation map represented by a graph structure, wherein each path edge in the dynamic emergency situation map is associated with a dynamic weight, and the dynamic weight is obtained by calculation based on the real-time risk coefficient, the channel congestion coefficient and the basic transit time of the corresponding edge; constructing a target optimization model of multiple optimization targets based on the dynamic emergency situation map aiming at each evacuation personnel position, and solving the target optimization model by utilizing a search algorithm to