An emergency evacuation deployment method for water transportation based on the equilibrium assignment model

Abstract

The present invention discloses a method for emergency evacuation deployment of water transportation based on a balanced distribution model, which relates to the technical field of emergency management. The method includes collecting vessel distribution data and vessel behavior data, and preprocessing the vessel distribution data and vessel behavior data; predicting the evacuation demand intensity of each evacuation area according to the preprocessed vessel distribution data and behavior data; collecting hydrological data and meteorological data, and conducting risk assessment on each evacuation area; constructing a balanced distribution model, and predicting the evacuation priority score of each evacuation area based on the evacuation demand intensity and risk assessment results of each evacuation area; generating a vessel evacuation scheduling plan according to the evacuation priority scores of each evacuation area; executing the vessel evacuation scheduling plan and making real-time adjustments. By receiving vessel feedback data in real time and dynamically updating the balanced distribution model and scheduling plan, the present invention realizes the whole process of efficient resource allocation, real-time adjustment and precise evacuation deployment.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency management, and particularly to a method for emergency evacuation deployment of water transportation based on a balanced distribution model. Background Art

[0002] With the rapid development of the global economy and the continuous growth of water transportation demand, water transportation plays an increasingly important role in logistics transportation, urban evacuation, and emergency response to emergencies. However, the complexity of the water transportation network and its high sensitivity to the dynamic environment make it an important problem to be solved urgently how to efficiently dispatch ships, reasonably deploy evacuation resources, quickly respond and evacuate threatened ships and personnel in the face of emergencies. In the prior art, water evacuation scheduling methods based on static models are relatively common, and these methods usually rely on a single environmental variable or a simple linear programming model. However, the water environment is highly dynamic and variable, and factors such as wind speed, tide height, and flow velocity will have complex effects on ship scheduling and resource allocation. In addition, the distribution of evacuation demands is often non-uniform, and how to dynamically adjust evacuation priorities based on risk assessment to ensure the efficient use of resources is a difficult point in the prior art.

[0003] The existing water transportation emergency evacuation technologies mainly have the following two deficiencies: First, the existing methods usually rely on simple statistical models in evacuation demand prediction and cannot fully capture the complex dynamic characteristics of ship distribution and behavior states. Information such as the real-time speed, load status, and sailing direction of ships is not effectively integrated in the existing methods, resulting in low accuracy of evacuation demand prediction and easy imbalance of resource allocation. Second, in terms of risk assessment and evacuation priority setting, the prior art mostly uses a single risk factor or a simple weighted model, ignoring the non-linear interaction relationships between multiple dynamic variables, such as the combined effects of hydrological and meteorological conditions, and the potential risk amplification effects of the uncertainties of these conditions on evacuation efficiency. This deficiency may lead to the difficulty of the evacuation scheduling plan to adapt to complex and changeable actual scenarios and unable to fully meet the resource scheduling requirements in emergency situations. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for emergency evacuation deployment of water transportation based on a balanced distribution model to solve the problems of inaccurate evacuation demand prediction and incomplete risk assessment in the prior art.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for emergency evacuation deployment of water transportation based on a balanced distribution model, which includes collecting vessel distribution data and vessel behavior data, and preprocessing the vessel distribution data and vessel behavior data; predicting the evacuation demand intensity of each evacuation area according to the preprocessed vessel distribution data and behavior data; collecting hydrological data and meteorological data, and conducting a risk assessment on each evacuation area; constructing a balanced distribution model, and predicting the evacuation priority score of each evacuation area based on the evacuation demand intensity and risk assessment results of each evacuation area; generating a vessel evacuation scheduling plan according to the evacuation priority scores of each evacuation area; implementing the vessel evacuation scheduling plan, and making real-time adjustments.

[0008] As a preferred embodiment of the method for emergency evacuation deployment of water transportation based on the balanced distribution model of the present invention, wherein: the vessel distribution data includes the position, quantity, and load status of the vessels;

[0009] The vessel behavior data includes the heading, speed, and navigation status of the vessels.

[0010] As a preferred embodiment of the method for emergency evacuation deployment of water transportation based on the balanced distribution model of the present invention, wherein: the specific steps of preprocessing the vessel distribution data and vessel behavior data are as follows,

[0011] Adopt data cleaning to eliminate invalid data and abnormal data in the vessel distribution data and vessel behavior data;

[0012] Through data format conversion, unify the formats of the vessel distribution data and vessel behavior data;

[0013] Standardize the vessel distribution data and vessel behavior data through data filtering and conversion rules.

[0014] As a preferred embodiment of the method for emergency evacuation deployment of water transportation based on the balanced distribution model of the present invention, wherein: the specific steps of predicting the evacuation demand intensity of each evacuation area according to the preprocessed vessel distribution data and behavior data are as follows,

[0015] Through vessel density analysis combined with weight adjustment of vessel behavior status, and combined with non-linear correction of evacuation resource availability, predict the evacuation demand intensity of each evacuation area through dynamic interaction between the preprocessed vessel distribution data and behavior data. The expression is:

[0016]

[0017] Wherein, S i represents the evacuation demand intensity of the i-th evacuation area, N i represents the total number of vessels in the i-th evacuation area, Represents the average load status of vessels in the \(i\)-th evacuation area, \(A\) i Represents the area of the \(i\)-th evacuation area, \(V\) j Represents the speed of the \(j\)-th vessel, \(H\) j Represents the rate of change of the course of the \(j\)-th vessel, \(Z\) j Represents the navigation status coefficient of the \(j\)-th vessel.

[0018] As a preferred solution of the water transportation emergency evacuation deployment method based on the equilibrium assignment model described in the present invention, wherein: collecting hydrological data and meteorological data, and conducting risk assessment on each evacuation area, the specific steps are as follows

[0019] Utilize SAR satellite images and real-time hydrological monitoring stations to collect the water flow velocity, flow direction, tide height, and water depth of each evacuation area in real time;

[0020] Use meteorological radars and wind profile radars to collect the wind speed, wind direction, rainfall, and visibility of each evacuation area in real time;

[0021] Taking hydrological data and meteorological data as dynamic variables, analyze the comprehensive interaction relationship between different risks, integrate the interaction of dynamic variables based on geometric characteristics, calculate the risk level, and at the same time, considering the uncertainty of the distribution of dynamic variables, adjust the overall risk level through information entropy, and perform non-linear amplification processing on the risk using the variance of rainfall volatility, and finally obtain the comprehensive risk assessment level of the evacuation area. The expression is:

[0022]

[0023] Among them, \(R\) i Is the comprehensive risk level of the \(i\)-th evacuation area, \(T\) is the evaluation time interval, \(G(t)\) represents the geometric characteristic value changing with time \(t\), \(H\) is the information entropy value, \(\delta\) is the information entropy value adjustment factor, \(r\) is the variance of rainfall volatility, and \(\gamma\) is the rainfall volatility amplification coefficient.

[0024] As a preferred solution of the water transportation emergency evacuation deployment method based on the equilibrium assignment model described in the present invention, wherein: constructing the equilibrium assignment model, and predicting the evacuation priority score of each evacuation area based on the evacuation demand intensity and risk assessment results of each evacuation area. The specific steps are as follows

[0025] According to the speed and load capacity of the vessels in each evacuation area, and introducing the non-linear influence of the area of the evacuation area, analyze the resource circulation capacity value of each evacuation area. The expression is:

[0026]

[0027] Among them, \(C\) i Is the resource circulation capacity value of the \(i\)-th evacuation area, \(L\) jis the load capacity of the j-th ship, and λ is the non-linear adjustment coefficient of the regional area;

[0028] Based on the evacuation demand intensity S i and the comprehensive risk level R i of the dynamic interaction, as well as the non-linear effects of the ship's speed, load capacity and regional area, the priority is weighted through a non-linear relationship, and the evacuation demand intensity S i and the comprehensive risk level R i and the resource circulation capacity value C i and the dynamic regulation mechanism of the resource response efficiency are combined to construct a balanced distribution model to predict the evacuation priority scores of each evacuation area. The expression is:

[0029]

[0030] where P i is the evacuation priority score of the i-th evacuation area, φ is the circulation adjustment smoothing factor, M i represents the total number of resource distribution sources in the i-th evacuation area, E l is the available resource amount of the l-th resource source, T l is the response time of the l-th resource source, ψ is the response time smoothing factor, and η is the non-linear adjustment coefficient of the resource distribution.

[0031] As a preferred solution of the water transportation emergency evacuation deployment method based on the balanced distribution model of the present invention, wherein: generating a ship evacuation scheduling plan according to the evacuation priority scores of each evacuation area, the specific steps are as follows,

[0032] Arrange each evacuation area in descending order according to the evacuation priority score P i and preferentially select the area with the highest priority score as the target evacuation area;

[0033] Arrange all ships in ascending order according to the time when all ships arrive at the target evacuation area;

[0034] Perform ship scheduling in sequence according to the ship sorting result until the resource circulation capacity value of the target evacuation area is exhausted, and automatically allocate it to the evacuation area of the next priority. Finally, generate a complete evacuation scheduling plan including the target evacuation areas and scheduling times of all ships.

[0035] As a preferred solution of the water transportation emergency evacuation deployment method based on the balanced distribution model of the present invention, wherein: executing the ship evacuation scheduling plan and making real-time adjustments, the specific steps are as follows,

[0036] During the process of ships executing the evacuation scheduling plan for evacuation, receive ship feedback data in real time through GPS and AIS;

[0037] Optimize the balanced flow distribution model based on vessel feedback data. According to the optimized balanced flow distribution model, the evacuation priority scores of the evacuation areas are updated in real time, and the vessel evacuation scheduling plan is adjusted in real time.

[0038] In a second aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the water transportation emergency evacuation deployment method based on the balanced flow distribution model as described in the first aspect of the present invention is implemented.

[0039] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the water transportation emergency evacuation deployment method based on the balanced flow distribution model as described in the first aspect of the present invention is implemented.

[0040] The beneficial effects of the present invention are as follows: By collecting vessel distribution data and behavior data, and combining hydrological data and meteorological data for preprocessing and dynamic analysis, first predict the evacuation demand intensity of each evacuation area, and then based on the balanced flow distribution model, dynamically combine the demand intensity with multiple factors such as the comprehensive risk level and resource circulation capacity value to generate the priority scores of each evacuation area; On this basis, use the priority scores to generate an optimized vessel evacuation scheduling plan, and by receiving vessel feedback data in real time, dynamically update the balanced flow distribution model and the scheduling plan, thus realizing the whole process of efficient resource allocation, real-time adjustment and precise evacuation deployment. Description of the Drawings

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of the water transportation emergency evacuation deployment method based on the balanced flow distribution model in Embodiment 1.

[0043] Figure 2 It is a flowchart of generating a vessel evacuation scheduling plan according to the evacuation priority scores of each evacuation area in Embodiment 1. Detailed Embodiments

[0044] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification.

[0045] In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways than those specifically described herein. Those skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0046] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0047] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides a method for emergency evacuation deployment of water transportation based on a balanced distribution model, including the following steps:

[0048] S1: Collect vessel distribution data and vessel behavior data, and preprocess the vessel distribution data and vessel behavior data.

[0049] S1.1: The vessel distribution data includes the position, quantity, and load status of the vessels.

[0050] Furthermore, the vessel distribution data is collected through a real-time monitoring system (such as an AIS system and radar monitoring equipment), which can accurately reflect the dynamic layout characteristics of vessels in each area.

[0051] S1.2: The vessel behavior data includes the course, speed, and navigation status of the vessels.

[0052] Furthermore, the vessel behavior data is obtained through multi-source sensors (such as GPS devices and ship status monitoring systems), which can accurately reflect the behavior patterns of vessels in each area.

[0053] S1.3: Use data cleaning to remove invalid and abnormal data from the vessel distribution data and vessel behavior data.

[0054] For example, when there are obvious errors in the collected vessel position data (such as the vessel position exceeding the water area range or repeated invalid position points), or when the speed in the vessel behavior data shows a negative value or exceeds the upper limit of the ship design speed, these invalid or abnormal data are removed through cleaning rules to ensure that subsequent analysis is based on true and reliable data.

[0055] S1.4: Through data format conversion, unify the formats of the vessel distribution data and vessel behavior data.

[0056] For example, if part of the vessel position data is represented by longitude and latitude, while the data from other sources is represented by grid coordinates, all position data is uniformly converted to the same format (such as the standard WGS84 longitude and latitude format) through format conversion rules; at the same time, the vessel speed data is converted from "meters per second" to "knots" (1 knot = 1.852 kilometers per hour) so that data from different sources can be directly compared and processed.

[0057] S1.5: Standardize the vessel distribution data and vessel behavior data through data filtering and conversion rules.

[0058] For example, convert the vessel load status from multiple inconsistent descriptions (such as "fully loaded", "partially loaded", "empty") to a standardized numerical ratio (such as 1 represents fully loaded, 0 represents empty); at the same time, use the normalization method to map data such as speed, load status, and heading change rate to the [0,1] interval to eliminate the influence between different variable dimensions and provide a unified input data format for subsequent model calculation and analysis.

[0059] S2: Predict the evacuation demand intensity of each evacuation area based on the preprocessed vessel distribution data and behavior data;

[0060] S2.1: Predict the evacuation demand intensity of each evacuation area through the dynamic interaction between the preprocessed vessel distribution data and behavior data by combining vessel density analysis with weight adjustment of vessel behavior status and non - linear correction of evacuation resource availability. The expression is:

[0061]

[0062] where, S i represents the evacuation demand intensity of the i - th evacuation area, N i represents the total number of vessels in the i - th evacuation area, represents the average load status of vessels in the i - th evacuation area, A i represents the area of the i - th evacuation area, V j represents the speed of the j - th vessel, H j represents the heading change rate of the j - th vessel, Z j represents the navigation status coefficient of the j - th vessel.

[0063] The specific process is to conduct vessel density analysis on the preprocessed vessel distribution data and behavior data, combined with weight adjustment of vessel behavior status (such as heading, speed, navigation status). Specifically, we calculate the number of vessels N i in each evacuation area and the average load status of these vessels, while considering the influence of the area A i of this area on the evacuation capacity. Next, by introducing the speed V of each vesselj , the course change rate H j and the navigation state coefficient Z j , to evaluate the dynamic behavior characteristics of the vessels and integrate these factors to reflect the response capabilities and requirements of the vessels in emergency situations.

[0064] On this basis, combined with the non-linear correction of the availability of evacuation resources, considering the actual allocation and limitations of rescue resources, to ensure that the prediction results are closer to the actual situation. The whole process involves complex analysis of the dynamic interactions between vessels, that is, not only focusing on the state of individual vessels, but also attaching importance to the mutual influence between vessels and its impact on the overall evacuation demand. Finally, through the integration of all the above factors, the evacuation demand intensity S of each evacuation area can be accurately predicted i , providing an important basis for formulating an effective evacuation scheduling plan subsequently. This method ensures that the prediction model can not only reflect the current vessel distribution and behavior patterns, but also adapt to the changing emergency evacuation demands

[0065] It should be noted that the availability of evacuation resources refers to the actual available degree of the resources that can be dispatched and allocated during the emergency evacuation process within a specific time and area, including the dynamic characteristics such as the number of vessels, load capacity, current location, speed and navigation state, etc. At the same time, the environmental adaptability of the evacuation area (such as water depth, flow velocity, tidal height and meteorological conditions) and the response time and accessibility of the resources should also be considered. This indicator reflects the effectiveness and reliability of the resources in a complex dynamic environment.

[0066] The vessel behavior states include course, speed, navigation state, load state, speed change rate, course change rate and navigation state coefficient, etc.

[0067] S3: Collect hydrological data and meteorological data, and conduct risk assessment on each evacuation area;

[0068] S3.1: Use SAR satellite images and real-time hydrological monitoring stations to collect the water flow velocity, flow direction, tidal height and water depth of each evacuation area in real time;

[0069] S3.2: Use meteorological radar and wind profiler radar to collect the wind speed, wind direction, rainfall and visibility of each evacuation area in real time;

[0070] S3.3: Take the hydrological data and meteorological data as dynamic variables, analyze the comprehensive interaction relationship between different risks, integrate the interaction of dynamic variables based on geometric characteristics, calculate the risk level, and at the same time combine the uncertainty of the dynamic variable distribution, adjust the overall risk level through information entropy, and perform non-linear amplification processing on the risk using the rainfall volatility variance, and finally obtain the comprehensive risk assessment level of the evacuation area, and the expression is:

[0071]

[0072] Among them, R i is the comprehensive risk level of the i-th evacuation area, T is the evaluation time interval, G(t) represents the geometric characteristic value that changes with time t, H is the information entropy value, δ is the information entropy value adjustment factor, r is the volatility variance of rainfall, and γ is the rainfall volatility amplification coefficient.

[0073] The specific process is as follows: collect hydrological and meteorological data, including factors such as water flow velocity, tide height, wind speed, and rainfall, through real-time monitoring systems such as SAR satellite images and hydrological and meteorological radars, and use these data as dynamic variables to analyze the interaction relationships between different risks. Then, considering the geometric characteristics of the evacuation area, such as shape and size, integrate the interactions between these dynamic variables to more accurately reflect the actual risk situation. At the same time, in order to handle the uncertainty in the data, the method of information entropy is used to adjust the risk assessment results to ensure their accuracy. In addition, pay special attention to the impact of rainfall volatility on risk, and emphasize the additional risks that extreme weather may bring through non-linear amplification processing. Finally, all these analyses and adjustments help to obtain the comprehensive risk assessment level of each evacuation area, providing a scientific basis for formulating effective emergency evacuation plans.

[0074] Furthermore, the expression of the geometric characteristic value G(t) that changes with time t is:

[0075]

[0076] Among them, f(t) is the water flow velocity at time t, h(t) is the tide height at time t, w(t) is the wind speed at time t, α is the weight coefficient of the tide height, and β is the adjustment coefficient of the wind speed;

[0077] The expression of the information entropy value H is:

[0078]

[0079] Among them, n is the total number of dynamic variables, p k represents the normalized weight coefficient of the k-th variable;

[0080] The expression of the volatility variance r of rainfall is:

[0081]

[0082] Among them, m is the total number of time steps, r(t u ) is the rainfall value at the u-th time step, is the average value of rainfall, t u represents the time step;

[0083] S4: Construct a balanced flow distribution model, and predict the evacuation priority scores of each evacuation area based on the evacuation demand intensity and risk assessment results of each evacuation area.

[0084] S4.1: According to the ship speed and load capacity in each evacuation area, and introducing the non-linear influence of the evacuation area area at the same time, analyze the resource circulation capacity value of each evacuation area. The expression is:

[0085]

[0086] Among them, C i is the resource circulation capacity value of the i-th evacuation area, L j is the load capacity of the j-th ship, and λ is the non-linear adjustment coefficient of the area.

[0087] It should be noted that by calculating the resource circulation capacity value according to the ship speed and load capacity in each evacuation area and introducing the non-linear influence of the evacuation area area at the same time, the resource transportation and distribution capacity of each evacuation area under specific conditions can be accurately evaluated. This calculation method comprehensively considers the dynamic performance of the ship (such as speed and load) and regional characteristics (such as the influence of area on resource circulation efficiency), and corrects the actual constraint effect of the area on the circulation capacity through a non-linear adjustment factor. Through this evaluation, the circulation efficiency of the available resources in each evacuation area can be objectively reflected, providing an accurate quantitative basis for formulating a scientific and reasonable evacuation scheduling plan, thereby improving the resource allocation efficiency and the overall optimization level of the evacuation process.

[0088] S4.2: Based on the dynamic interaction between the evacuation demand intensity S i and the comprehensive risk level R i , as well as the non-linear influence of ship speed, load capacity and area, weight the priority through a non-linear relationship, and combine the evacuation demand intensity S i , the comprehensive risk level R i , the resource circulation capacity value C i and the dynamic regulation mechanism of resource response efficiency to construct a balanced flow distribution model to predict the evacuation priority scores of each evacuation area. The expression is:

[0089]

[0090] Among them, P i is the evacuation priority score of the i-th evacuation area, φ is the circulation adjustment smoothing factor, M i represents the total number of resource distribution sources in the i-th evacuation area, E l is the available resource volume of the l-th resource source, T l is the response time of the l-th resource source, ψ is the response time smoothing factor, and η is the non-linear adjustment coefficient of resource distribution.

[0091] It should be noted that the "total number of resource distribution sources" refers to the number of all sources that can provide resource support for a certain evacuation area, such as nearby ports, moored rescue ships, resources allocated from other evacuation areas, etc.

[0092] For "M i indicating the total number of resource distribution sources in the i-th evacuation area", it is obtained by counting all resource sources associated with the evacuation area, including the number of ports that can be supported based on geographical location, the number of ship resources in adjacent areas, and the comprehensive evaluation of the number of externally allocated resources that meet the response time requirements, etc. This indicator reflects the diversity and abundance of resource supply in the evacuation area and is an important parameter for evaluating the regional evacuation capacity.

[0093] S5: Generate a ship evacuation scheduling plan according to the evacuation priority scores of each evacuation area;

[0094] S5.1: According to the evacuation priority score P i Arrange each evacuation area in descending order, and preferentially select the area with the highest priority score as the target evacuation area;

[0095] Specifically, the higher the priority score P i the higher the evacuation demand intensity, the greater the risk level, and the lower the resource circulation capacity in this area. Therefore, resources need to be preferentially scheduled for evacuation.

[0096] For example, assume there are three evacuation areas A, B, and C, and their priority scores are PA = 85, PB = 70, and PC = 60 respectively. Then, first select the area A with the highest priority score for evacuation. After the demand in area A is met or the resources are exhausted, then select areas B and C with higher scores in turn for evacuation. Through this process, it can ensure that limited resources are preferentially allocated to high-risk and high-demand areas, thereby maximizing the evacuation efficiency and reducing the overall risk.

[0097] S5.2: Arrange all ships in ascending order according to the time when all ships arrive at the target evacuation area;

[0098] Specifically, the arrival time can be calculated based on the current position of the ship, the speed, and the position of the target evacuation area. For example, arrival time = distance / speed. For instance, assume the current evacuation area is area A, and there are three ships 1, 2, and 3, and their arrival times at area A are T1 = 10 minutes, T2 = 15 minutes, and T3 = 5 minutes respectively. Then, after arranging them in ascending order according to the arrival time, the scheduling order is ship 3 → ship 1 → ship 2. In this way, available resources can be utilized as soon as possible, accelerating the evacuation efficiency and reducing the waiting time.

[0099] S5.3: Conduct vessel dispatching in sequence according to the vessel sorting result until the resource circulation capacity value of the target evacuation area is exhausted, then automatically allocate to the evacuation area of the next priority level. Finally, generate a complete evacuation dispatching plan that includes the target evacuation areas and dispatching times of all vessels.

[0100] Specifically: According to the result of sorting vessels in ascending order of arrival time, dispatch vessels in sequence to the current evacuation area to perform evacuation tasks until the resource circulation capacity value of this evacuation area is exhausted. When the current evacuation area can no longer accommodate or dispatch more vessels, automatically switch to the evacuation area of the next priority level and continue to sort and dispatch vessels in the same way until all vessels are allocated to the target evacuation areas. Finally, generate a complete evacuation dispatching plan that includes the target evacuation areas and dispatching times of each vessel.

[0101] For example, assume that the currently highest-priority evacuation area is Area A, and its resource circulation capacity value is CA = 100. After vessels 1, 2, and 3 are sorted in sequence, their load capacities are 30, 50, and 40 respectively. First, dispatch vessel 1 to Area A, and CA is reduced to 70; then dispatch vessel 2, and CA is reduced to 20; since the load capacity of vessel 3 is 40, which exceeds the remaining circulation capacity, it cannot be dispatched to Area A anymore. At this time, switch to the next-priority evacuation area, Area B, and continue to sort and dispatch the remaining vessels. Through this process, ensure that evacuation resources are reasonably allocated and efficiently utilized, and finally form a complete dispatching plan, such as "Vessel 1 is dispatched to Area A at time T1; Vessel 2 is dispatched to Area A at time T2; Vessel 3 is dispatched to Area B at time T3".

[0102] S6: Execute the vessel evacuation dispatching plan and make real-time adjustments.

[0103] S6.1: During the process of vessels executing the evacuation dispatching plan for evacuation, receive real-time feedback data from vessels through GPS and AIS;

[0104] It should be noted that the vessel feedback data includes the current position, speed, heading, estimated time to reach the target evacuation area, and the current load status.

[0105] S6.2: Optimize the balanced flow distribution model based on the vessel feedback data. According to the optimized balanced flow distribution model, update the evacuation priority scores of the evacuation areas in real time and adjust the vessel evacuation dispatching plan in real time.

[0106] Specifically, during the implementation of the evacuation scheduling plan by vessels, real-time feedback data (such as the current position, speed, heading, estimated arrival time, and load status of the vessels) is received through GPS and AIS. Based on this feedback data, the input parameters of the balanced flow distribution model are dynamically adjusted, including key factors such as evacuation demand intensity, resource circulation capacity, and comprehensive risk level. The optimized balanced flow distribution model will recalculate the priority scores of the evacuation areas in real time, thereby dynamically updating the evacuation scheduling plan. For example, assume that the priority score of an evacuation area A decreases due to real-time data updates, while the priority score of evacuation area B increases. Then, the vessels with uncompleted evacuation tasks will be redistributed and preferentially dispatched to area B. In addition, if a vessel cannot reach the target area as planned due to unexpected situations (such as reduced speed or navigation delay), the target evacuation area of the vessel will be adjusted according to the feedback data or the task will be rescheduled. Through this process, it is ensured that the evacuation task can flexibly adapt to dynamic changes, improving the overall evacuation efficiency and emergency response capabilities.

[0107] This embodiment also provides a computer device, which is applicable to the situation of the water transportation emergency evacuation deployment method based on the balanced flow distribution model, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the water transportation emergency evacuation deployment method based on the balanced flow distribution model as proposed in the above embodiment.

[0108] This computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, operator networks, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0109] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for emergency evacuation deployment of water transportation based on the equilibrium assignment model proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0110] In summary, the present invention: collects vessel distribution data and behavior data, combines hydrological data and meteorological data for preprocessing and dynamic analysis, first predicts the evacuation demand intensity of each evacuation area, and then based on the equilibrium assignment model, dynamically combines the demand intensity with multiple factors such as the comprehensive risk level and resource circulation capacity value to generate a priority score for each evacuation area; on this basis, uses the priority score to generate an optimized vessel evacuation scheduling plan, and dynamically updates the equilibrium assignment model and the scheduling plan by real-time receiving vessel feedback data, thereby realizing the whole process of efficient resource allocation, real-time adjustment and precise evacuation deployment.

[0111] Embodiment 2 is the second embodiment of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the method for emergency evacuation deployment of water transportation based on the equilibrium assignment model are given.

[0112] To verify the effectiveness of the method for emergency evacuation deployment of water transportation based on the equilibrium assignment model, a simulation experiment was designed. Three evacuation areas (A, B, C) in a coastal waters and 8 vessels were selected to simulate the emergency evacuation process in a complex environment, and the advantages and disadvantages of the present invention and the existing static priority assignment method were compared in terms of evacuation efficiency, risk control and resource utilization.

[0113] First, the experiment collected distribution data (such as position, speed, and load status) and behavior data (such as heading and navigation status) of 8 vessels through AIS and GPS devices. Meanwhile, hydrological data (such as water flow velocity and tide height) and meteorological data (such as wind speed and rainfall) of the evacuation areas were obtained using SAR satellite images and hydrological monitoring stations. And these data were preprocessed to ensure data accuracy and consistency, providing reliable inputs for subsequent calculations.

[0114] Second, based on the preprocessed vessel distribution and behavior data, combined with the availability of regional evacuation resources, the evacuation demand intensity (S i ) of each evacuation area was calculated, and the comprehensive risk level (R i ) of each area was evaluated through a dynamic interaction model combined with hydrological and meteorological data. These calculation results laid the foundation for constructing a balanced flow allocation model and clarified the initial evacuation priorities of each area.

[0115] Then, through the balanced flow allocation model, combined with the evacuation demand intensity, risk level, and resource circulation capacity value, the priority score (P i ) of each evacuation area was dynamically calculated, and the evacuation areas were sorted in descending order according to the scores. Vessels were preferentially dispatched to the area with the highest score. Sorted by the arrival time of the vessels, vessels were allocated in turn until the resource circulation capacity of the priority area was exhausted, and then switched to the sub-optimal area. During the dispatching process, the system received real-time feedback data of the vessels through GPS and AIS, dynamically adjusted the model, and re-optimized the evacuation plan.

[0116] Finally, the experiment generated a complete vessel dispatching plan and recorded the target evacuation area and arrival time of each vessel. Through the analysis of the experimental data, it was found that the method of the present invention showed significant advantages in dynamically adjusting priorities, improving evacuation efficiency, optimizing resource utilization rate, and reducing risks. Compared with the traditional static priority model, the dispatching time of the present invention was shortened by about 22%, the resource utilization rate was higher, and at the same time, the over-concentration of resources in high-risk areas was effectively avoided, verifying the innovation and practicality of the method.

[0117] Through the data analysis, it was obvious that the method for emergency evacuation deployment of water transportation based on the balanced flow allocation model of the present invention had significant advantages in vessel dispatching priority, resource allocation efficiency, and evacuation time control. The data clearly showed that through the dynamic adjustment of the priority scores of the evacuation areas, more efficient resource allocation and shorter evacuation time could be achieved during the actual evacuation process.

[0118] For example, Ship 1 and Ship 2 are preferentially assigned to Evacuation Area B, with their speeds being 10.2 knots and 11.8 knots respectively, and the arrival times being relatively short, 14.8 minutes and 18.2 minutes. As the evacuation area with the highest priority score, Area B can quickly respond to emergency evacuation needs and ensure efficient utilization of its resource circulation capacity. In contrast, although Ships 3 and 4 are located at relatively far distances (2.67 km and 4.05 km), due to the sub-optimal priority score of Evacuation Area A, they can still be reasonably scheduled and complete the evacuation tasks within 12.5 minutes and 14.2 minutes respectively.

[0119] In summary, the present invention can adjust the scheduling plan in real time according to the ship feedback data and the risk status of the evacuation area, thereby significantly improving the evacuation efficiency. Compared with the static priority scheduling method, it reduces the evacuation time, optimizes the resource utilization rate, and effectively reduces the resource scheduling pressure in high-risk areas, and has innovation and practicality.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An emergency evacuation deployment method for water transportation based on a balanced distribution model, characterized in that: including, collecting vessel distribution data including the position, quantity and load status of vessels and vessel behavior data including the course, speed and navigation status of vessels, and preprocessing the vessel distribution data and the vessel behavior data; predicting the evacuation demand intensity of each evacuation area through dynamic interaction between the preprocessed vessel distribution data and behavior data by combining vessel density analysis with weight adjustment of vessel behavior status and non-linear correction of evacuation resource availability, and the expression is as follows: Among them, S i represents the evacuation demand intensity of the i-th evacuation area, N i represents the total number of ships in the i-th evacuation area, represents the average load state of the ships in the i-th evacuation area, A i represents the area of the i-th evacuation area, V j represents the sailing speed of the j-th ship, H j represents the course change rate of the j-th ship, Z j represents the sailing state coefficient of the j-th ship; collecting hydrological data and meteorological data and conducting risk assessment on each evacuation area; constructing a balanced flow assignment model and predicting the evacuation priority score of each evacuation area based on the evacuation demand intensity and risk assessment results of each evacuation area. The specific steps are as follows: analyzing the resource circulation capacity value of each evacuation area according to the vessel speed and load capacity in each evacuation area and introducing the non-linear influence of the evacuation area area at the same time. The expression is: Among them, C i is the resource circulation capacity value of the i-th evacuation area, L j is the load capacity of the j-th ship, and λ is the non-linear adjustment coefficient of the area of the area; Based on the evacuation demand intensity S i and the comprehensive risk level R i Considering the dynamic interaction between them, as well as the non-linear effects of vessel speed, load capacity, and area, the priorities are weighted through non-linear relationships. By combining the evacuation demand intensity S i , the comprehensive risk level R i , the resource circulation capacity value C i with the dynamic regulation mechanism of resource response efficiency, a balanced distribution model is constructed to predict the evacuation priority scores of each evacuation area. The expression is as follows: Among them, P i is the evacuation priority score of the i-th evacuation area, φ is the flow regulation smoothing factor, M i represents the total number of resource distribution sources of the i-th evacuation area, E l is the available resource quantity of the l-th resource source, T l is the response time of the l-th resource source, ψ is the response time smoothing factor, and η is the non-linear regulation coefficient of resource distribution; generating a vessel evacuation scheduling plan according to the evacuation priority score of each evacuation area; executing the vessel evacuation scheduling plan and making real-time adjustments; the specific steps of collecting hydrological data and meteorological data and conducting risk assessment on each evacuation area are as follows: using SAR satellite images and real-time hydrological monitoring stations to collect the water flow speed, flow direction, tide height and water depth of each evacuation area in real time; using meteorological radar and wind profiler radar to collect the wind speed, wind direction, rainfall and visibility of each evacuation area in real time; taking the hydrological data and meteorological data as dynamic variables, analyzing the comprehensive interaction relationship between different risks, integrating the interaction of dynamic variables based on geometric characteristics, calculating the risk level, and at the same time combining the uncertainty of the dynamic variable distribution, adjusting the overall risk level through information entropy, and performing non-linear amplification processing on the risk by using the rainfall volatility variance to finally obtain the comprehensive risk assessment level of the evacuation area.

2. The method for emergency evacuation deployment of water transportation based on the balanced distribution model according to claim 1, wherein: the specific steps of preprocessing the vessel distribution data and the vessel behavior data are as follows: adopting data cleaning to eliminate invalid data and abnormal data in the vessel distribution data and the vessel behavior data; unifying the formats of the vessel distribution data and the vessel behavior data through data format conversion; standardizing the vessel distribution data and the vessel behavior data through data filtering and conversion rules.

3. The method for emergency evacuation deployment of water transportation based on the balanced distribution model according to claim 2, wherein: calculating the comprehensive risk assessment level of the evacuation area through the following formula: Among them, R i is the comprehensive risk level of the i-th evacuation area, T is the evaluation time interval, G(t) represents the geometric characteristic value that changes with time t, H is the information entropy value, δ is the information entropy value adjustment factor, r is the volatility variance of rainfall, and γ is the rainfall volatility amplification coefficient.

4. The method for emergency evacuation deployment of water transportation based on the balanced flow distribution model according to claim 3, characterized in that: the specific steps of generating a vessel evacuation scheduling plan according to the evacuation priority score of each evacuation area are as follows: According to the evacuation priority score P i Arrange each evacuation area in descending order, and preferentially select the area with the highest priority score as the target evacuation area; sorting all vessels in ascending order according to the time when all vessels reach the target evacuation area; conducting vessel scheduling in sequence according to the vessel sorting result until the resource circulation capacity value of the target evacuation area is exhausted and automatically allocating to the next priority evacuation area. Finally, generating a complete evacuation scheduling plan including the target evacuation area and scheduling time of all vessels.

5. The method for emergency evacuation deployment of water transportation based on the balanced distribution model according to claim 4, characterized in that: the specific steps of executing the vessel evacuation scheduling plan and making real-time adjustments are as follows: during the process of vessels executing the evacuation scheduling plan for evacuation, receiving vessel feedback data in real time through GPS and AIS; Optimize the balanced flow allocation model based on vessel feedback data. According to the optimized balanced flow allocation model, the evacuation priority scores of the evacuation areas are updated in real time, and the vessel evacuation scheduling plan is adjusted in real time.

6. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for emergency evacuation deployment of water transportation based on the balanced flow allocation model according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for emergency evacuation deployment of water transportation based on the balanced flow allocation model according to any one of claims 1 to 5.

Images