Emergency material real-time monitoring and allocation method and system based on Internet of Things, electronic equipment and storage medium

Abstract

The invention belongs to the field of emergency resource management, and discloses an emergency material real-time monitoring and allocation method and system based on the Internet of Things, electronic equipment and a storage medium, and the method comprises the steps: collecting the field data of an accident in real time through a sensor network of the Internet of Things; based on the field data, predicting material and equipment demands; based on the prediction result, warehouse material matching is carried out, and a logistics distribution path is generated; determining an entry opportunity based on the logistics distribution path; the whole scheduling process is monitored in the whole process through the Internet of Things technology, field feedback information is collected at the same time, and the scheduling scheme is dynamically adjusted. According to the invention, the real-time collection and monitoring of accident site data are realized through the Internet of Things sensor network, the material and equipment requirements can be accurately predicted, and the warehouse materials are efficiently matched and the optimal logistics distribution path is generated based on the multi-objective optimization model and the improved ant colony algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency resource management, and in particular to a method, system, electronic device and storage medium for real-time monitoring and allocation of emergency materials based on the Internet of Things. Background Art

[0002] In the field of emergency resource management, especially in the process of emergency material allocation when disasters occur, traditional methods have many shortcomings. Existing technologies mainly rely on manual experience or simple information systems, which makes it difficult to achieve real-time data collection and analysis of accident sites, resulting in inaccurate material demand forecasts, delayed allocation plans, and inability to effectively respond to complex and changeable disaster site environments. In addition, the existing logistics distribution route planning and on-site timing decisions lack intelligent means, and cannot comprehensively consider the dynamic changes of the disaster site, traffic conditions, and the timeliness and priority of materials, which can easily lead to resource waste, delayed response, and even secondary disaster risks. Against the background of the rapid development of Internet of Things technology, how to use advanced sensor networks, data analysis, and intelligent algorithms to improve the real-time monitoring and allocation capabilities of emergency materials has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides a real-time monitoring and deployment method for emergency materials based on the Internet of Things, the method comprising:

[0004] Using IoT sensor networks to collect on-site data of accidents in real time;

[0005] Based on the field data, forecast the demand for materials and equipment;

[0006] Based on the prediction results, warehouse materials are matched and logistics distribution routes are generated;

[0007] Determine the time of entry based on the logistics distribution route;

[0008] The Internet of Things technology is used to monitor the entire dispatching process, collect on-site feedback information, and dynamically adjust the dispatching plan.

[0009] Preferably, the on-site data includes: damage scope, topography and weather conditions; and combined with satellite remote sensing images and drone reconnaissance data to further assess the characteristics, type and scale of the damage event.

[0010] Preferably, the method for predicting the demand for materials and equipment includes: extracting key features based on the field data, and building a prediction model based on the key features to predict the demand for materials and equipment; wherein the method for extracting the key features includes:

[0011]

[0012] Among them, I(X; Y) represents the mutual information between random variables X and Y; x and y represent the possible values of X and Y; p(x, y) represents the joint probability distribution of X and Y; p(x) represents the marginal probability distribution of X; p(y) represents the marginal probability distribution of Y.

[0013] Preferably, a gradient boosting tree is used to construct the prediction model:

[0014]

[0015] Among them, F M (x) represents the final output of the M-th iteration; F0(x) represents the predicted value of the initial model; v represents the learning rate; γ m represents the optimal step size at the m-th iteration; h m (x) represents the base learner at the m-th iteration.

[0016] Preferably, the method for generating the logistics distribution path includes: based on the predicted material demand result, first matching the warehouse node closest to the disaster area through a multi-objective optimization model, preferentially selecting the warehouse with sufficient inventory and the lowest transportation cost, and at the same time considering the material type matching degree and timeliness constraint; subsequently, combining the real-time traffic data and the state of the distribution vehicle, using an improved ant colony algorithm to generate the optimal distribution path for multi-vehicle collaboration.

[0017] Preferably, the method for determining the approach time includes: first calculating the earliest arrival time and safety time window of each distribution vehicle, dynamically weighing timeliness and safety through a multi-constraint optimization model; at the same time, introducing a game theory framework to coordinate the approach order of multi-vehicles, avoiding path conflicts and resource congestion, and finally generating a sub-batch approach plan.

[0018] Preferably, the multi-constraint optimization model is as follows:

[0019]

[0020] Among them, U represents the total utility or the sum of the urgency of the emergency material demand; λ i represents the weight or demand of the i-th material demand point; μ represents the attenuation coefficient; t i represents the time of the i-th material demand point; t 紧急 represents the time when the emergency event occurs.

[0021] The present invention also provides an emergency material real-time monitoring and allocation system based on the Internet of Things. The system is used to implement the above method and includes: a collection module, a prediction module, a planning module, a scheduling module, and a feedback module;

[0022] The acquisition module is used to collect the on-site data of the accident in real time by using the Internet of Things sensor network;

[0023] The prediction module is used to predict the material and equipment requirements based on the on-site data;

[0024] The planning module is used to match the warehouse materials and generate the logistics distribution path based on the prediction results;

[0025] The scheduling module is used to determine the entry time based on the logistics distribution path;

[0026] The feedback module is used to monitor the entire scheduling process by using the Internet of Things technology, and at the same time collect the on-site feedback information to dynamically adjust the scheduling plan.

[0027] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above method is implemented.

[0028] The present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed, the above method is implemented.

[0029] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0030] The present invention realizes the real-time collection and monitoring of the on-site data of the accident through the Internet of Things sensor network, can accurately predict the material and equipment requirements, and efficiently match the warehouse materials and generate the optimal logistics distribution path based on the multi-objective optimization model and the improved ant colony algorithm. At the same time, a multi-constraint optimization model and a game theory framework are introduced to dynamically determine the entry time to ensure the timeliness and safety of the emergency material allocation. In addition, the present invention uses the Internet of Things technology to monitor the entire scheduling process and give real-time feedback for adjustment, significantly improving the intelligent level of emergency resource management and the emergency response efficiency, effectively reducing the disaster losses, and having significant economic and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the present invention, the following briefly introduces the drawings required to be used in the embodiments. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 It is a schematic flowchart of the method according to the embodiment of the present invention;

[0033] Figure 2 It is a schematic structural diagram of the electronic device according to the embodiment of the present invention.

[0034] Description of Reference Numerals

[0035] 1010 processor; 1020 memory; 1030 input / output interface; 1040 communication interface; 1050 bus. Detailed Embodiment

[0036] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0037] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the ordinary meaning understood by those of ordinary skill in the art to which the present disclosure belongs. The "first", "second" and similar terms used in the embodiments of the present disclosure do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "include" or "comprise" mean that the elements or items appearing before this term cover the elements or items listed after this term and their equivalents, without excluding other elements or items. The terms such as "connect" or "couple" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right" are only used to represent relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0038] To make the above objects, features and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0039] Embodiment 1

[0040] The embodiment of the present invention provides a method for real-time monitoring and allocation of emergency supplies based on the Internet of Things, as Figure 1 shown, the steps include:

[0041] First, the acquisition module uses the Internet of Things sensor network to collect the on-site data of the accident in real time.

[0042] In this embodiment, the on-site data includes but is not limited to the damage range, terrain and landform, weather conditions, etc. At the same time, combined with satellite remote sensing images and unmanned aerial vehicle reconnaissance data, the characteristics, types and scales of the damage events are further evaluated.

[0043] Specifically, the sensors include environmental sensors, geographical sensors, vision sensors, and infrastructure sensors.

[0044] Among them, environmental sensors: include temperature sensors, humidity sensors, gas sensors (such as detecting harmful gases like CO, methane, etc.), air quality sensors (PM2.5 / PM10), etc., which are used to monitor environmental parameters at the accident scene.

[0045] Geographical sensors: GPS modules, acceleration sensors, tilt sensors, etc., which are used to locate the accident position and sense terrain changes.

[0046] Vision sensors: high-definition cameras, infrared cameras, and multi-spectral sensors carried by drones to capture on-site images and thermal maps in real time.

[0047] Infrastructure sensors: vibration sensors or stress sensors deployed on roads, bridges, and buildings, which are used to evaluate the damage degree.

[0048] Multi-modal communication technology is adopted, including low-power wide-area networks (LPWAN, such as LoRaWAN, NB-IoT) to achieve long-distance data transmission, combined with Wi-Fi / 5G for high-bandwidth image backhaul. Sensor nodes dynamically form a network through a self-organizing network (Mesh Network) to ensure network connectivity even when some nodes fail. During the acquisition process, a swarm of drones carries disposable sensors to quickly cover the core area of the accident, and ground mobile robots are deployed to supplement blind spots. The sensors are designed with low power consumption, combined with solar cells, supercapacitors, and a dynamic sleep mechanism to ensure continuous operation for more than 72 hours.

[0049] After that, the prediction module predicts the material and equipment requirements based on the on-site data.

[0050] Combining the environmental data (temperature, gas concentration), geographical data (terrain damage, traffic blockage), vision data (drone images, thermal maps) collected in S1 and the historical disaster case library, a multi-dimensional data set is constructed. Key features are extracted, such as disaster type (fire / earthquake / flood), affected area, population density, infrastructure damage level, real-time weather trend (such as rainfall prediction), etc., as the prediction input.

[0051] The extraction of key features is achieved by combining multi-source data fusion and domain knowledge: First, the on-site data (such as temperature, gas concentration, terrain damage degree, drone images) are standardized and normalized to eliminate the dimension difference; then the mutual information (MI) is used to quantify the correlation between the features and the target variable (such as material demand), and the formula is:

[0052]

[0053] Where I(X; Y) represents the mutual information between random variables X and Y; x and y represent the possible values of X and Y; p(x, y) represents the joint probability distribution of X and Y; p(x) represents the marginal probability distribution of X; and p(y) represents the marginal probability distribution of Y.

[0054] Features with mutual information values higher than the threshold (0.2 in this embodiment) are retained, and high-dimensional features (such as multispectral image pixels) are reduced in dimension by combining principal component analysis (PCA) to extract principal components to reduce computational complexity. At the same time, composite features are constructed, such as calculating the "rescue pressure index per unit area" based on damage sensor data and population density: pressure index = (damage level × population density) / traffic accessibility.

[0055] The variance inflation factor (VIF) was used to detect multicollinearity and features with VIF>10 were removed. The formula is:

[0056]

[0057] in, It represents the linear regression determination coefficient of the ith feature on other features. The final retained feature set includes disaster type code, pressure index, real-time weather trend code, historical disaster similarity, etc.

[0058] The extracted features are then input into the trained prediction model to predict the demand for materials and equipment. This embodiment uses a gradient boosting decision tree (GBDT) to build a prediction model, and the steps are as follows:

[0059] Initialize the model prediction value to the mean of the target variable (such as the demand for medical supplies):

[0060]

[0061] Among them, F0(x) represents the frequency of the target variable; n represents the total number of samples; y i Represents the state of the i-th observation.

[0062] Iteratively train M decision trees. In each iteration m (1≤m≤M), the steps include:

[0063] (1) Calculate the residual of the current model for all samples (when the loss function is mean square error, the residual is the difference between the true value and the current predicted value);

[0064] (2) Fit a regression tree h m (x) is the predicted residual r im , select the split point and leaf node value by minimizing the square error. Calculate the optimal step length γ of the tree m To update the model:

[0065]

[0066] Among them, γ m represents the optimal step size at the m-th iteration; represents finding a parameter γ such that the subsequent expression (i.e., the loss function) reaches the minimum; n represents the total number of samples; F m-1 (x i ) represents the predicted value of the i-th sample at the (m - 1)-th iteration; h m (x i ) represents the base learner.

[0067] After that, update the overall model and add a learning rate v (such as 0.1) to prevent overfitting:

[0068] F m (x) = F m-1 (x) + νγ m h m (x)

[0069] Among them, F m (x) represents the predicted value of the model for the input at the m-th iteration; v represents the learning rate; h m (x) represents the base learner at the m-th iteration.

[0070] Repeat the above steps until the preset number of iterations is reached or the residual converges. The final predicted value is the sum of the weighted outputs of all trees:

[0071]

[0072] Among them, F M (x) represents the final output; F0(x) represents the predicted value of the initial model.

[0073] During model training, the early stopping method (EarlyStopping) is adopted to stop the iteration based on the validation set loss, and the key driving factors (such as the influence weight of the pressure index on the material demand) are explained through feature importance ranking (based on the loss reduction during splitting). This method can adapt to non-linear relationships and feature interactions, and accurately predict the multi-category material demand in disaster scenarios.

[0074] Based on the prediction results, the planning module performs warehouse material matching and generates a logistics distribution path.

[0075] In step S3, based on the predicted material demand results, first, the multi-objective optimization model is used to match the warehouse node closest to the disaster area, and the warehouse with sufficient inventory and the lowest transportation cost is preferentially selected, while considering the material type matching degree and timeliness constraints:

[0076] minZ = αT + βC where T represents time; C represents cost; α and β both represent weight coefficients.

[0077] Subsequently, combining real-time traffic data with the status of delivery vehicles (load, cruising range), an improved ant colony algorithm is used to generate the optimal delivery path for multi-vehicle collaboration. The formula of the improved ant colony algorithm is as follows:

[0078] τ ij (t + 1) = (1 - ρ)·τ ij (t) + Δτ ij

[0079] Among them, τ ij (t) represents the pheromone concentration from the i-th node to the j-th node at time t, ρ represents the pheromone evaporation coefficient (0 < ρ < 1), and Δτ ij represents the pheromone increment from the i-th node to the j-th node.

[0080]

[0081] Among them, represents the probability that ant colony k goes from the i-th node to the j-th node at time t; η ij (t) represents the heuristic information; allowed k represents the set of nodes that ant colony k is allowed to choose.

[0082] After that, the path is dynamically adjusted to cope with sudden road condition changes (such as new obstacle points transmitted by drones). Finally, a path plan with time sequence constraints and a global allocation mapping table of warehouse-vehicle-materials are output to ensure the efficient use of resources and the timeliness of emergency response.

[0083] The scheduling module determines the approach time based on the logistics distribution path.

[0084] First, calculate the earliest arrival time (ETA) and safety time window of each delivery vehicle (based on on-site safety thresholds, such as gas concentration below 50 ppm and structural stability score ≥ 0.7), and dynamically balance timeliness and safety through a multi-constraint optimization model; at the same time, introduce a game theory framework to coordinate the approach order of multiple vehicles to avoid path conflicts and resource squeezing. Finally, a batch approach plan is generated (for example, the first batch of high-priority material vehicles enter immediately after the safety window opens, and subsequent vehicles are dynamically adjusted according to real-time risk assessment), and the approach instructions and obstacle avoidance navigation information are synchronously pushed to the drivers and the on-site command center through the Internet of Things platform to ensure the efficient and orderly rescue operation. The multi-constraint optimization model is as follows:

[0085]

[0086] Among them, U represents the total utility or the sum of the urgency of the emergency material demand; λi represents the weight or demand quantity of the \(i\)-th material demand point; \(\mu\) represents the attenuation coefficient; \(t\) i represents the time of the \(i\)-th material demand point; \(t\) 紧急 represents the time when the emergency occurs.

[0087] Finally, the feedback module uses Internet of Things technology to monitor the entire scheduling process, collect on-site feedback information, and dynamically adjust the scheduling plan.

[0088] Use Internet of Things technology to monitor the entire scheduling process, including the transportation, arrival, and usage of materials and equipment. Collect on-site feedback information and dynamically adjust the scheduling plan to respond to sudden changes.

[0089] The technical solution of the present invention realizes the real-time collection and monitoring of accident site data through the Internet of Things sensor network, can accurately predict the demand for materials and equipment, and efficiently match warehouse materials and generate the optimal logistics distribution path based on the multi-objective optimization model and the improved ant colony algorithm. At the same time, a multi-constraint optimization model and a game theory framework are introduced to dynamically determine the arrival time, ensuring the timeliness and safety of emergency material allocation. In addition, the present invention uses Internet of Things technology to monitor the entire scheduling process and provide real-time feedback for adjustment, significantly improving the intelligent level of emergency resource management and the emergency response efficiency, effectively reducing disaster losses, and having significant economic and social benefits.

[0090] It should be noted that the method of the embodiments of the present disclosure can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiments of the present disclosure, and these multiple devices will interact with each other to complete the described method.

[0091] It should be noted that some embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the order of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention. The actions or steps recited in the claims can be executed in a different order from that in the above embodiments and still achieve the desired result. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In certain embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

[0092] Embodiment 2

[0093] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure further provides an emergency material real-time monitoring and allocation system based on the Internet of Things, including: a collection module, a prediction module, a planning module, a scheduling module, and a feedback module; the collection module is used to use the Internet of Things sensor network to collect the on-site data of the accident in real time; the prediction module is used to predict the material and equipment requirements based on the on-site data; the planning module is used to match the warehouse materials and generate the logistics distribution path based on the prediction results; the scheduling module is used to determine the entry time based on the logistics distribution path; the feedback module is used to use the Internet of Things technology to monitor the entire scheduling process, and at the same time collect on-site feedback information and dynamically adjust the scheduling plan.

[0094] Next, this embodiment will be used to detail how the present invention solves the technical problems in actual work.

[0095] Use the Internet of Things sensor network to collect the on-site data of the accident in real time.

[0096] In this embodiment, the on-site data includes but is not limited to the damage range, terrain and landform, weather conditions, etc. At the same time, combined with satellite remote sensing images and unmanned aerial vehicle reconnaissance data, the characteristics, types, and scales of the damage events are further evaluated.

[0097] Specifically, the sensors include environmental sensors, geographical sensors, visual sensors, and infrastructure sensors.

[0098] Among them, the environmental sensors: include temperature sensors, humidity sensors, gas sensors (such as harmful gas detection of CO, methane, etc.), air quality sensors (PM2.5 / PM10), etc., for monitoring the environmental parameters of the accident site.

[0099] The geographical sensors: GPS modules, acceleration sensors, tilt sensors, etc., for positioning the accident location and perceiving terrain changes.

[0100] The visual sensors: high-definition cameras, infrared cameras, and multi-spectral sensors carried by unmanned aerial vehicles to capture on-site images and thermal maps in real time.

[0101] The infrastructure sensors: vibration sensors or stress sensors deployed on roads, bridges, and buildings for evaluating the damage degree.

[0102] Multimodal communication technology is used, including low-power wide area network (LPWAN, such as LoRaWAN, NB-IoT) to achieve long-distance data transmission, combined with Wi-Fi / 5G for high-bandwidth image backhaul. Sensor nodes are dynamically networked through self-organizing networks (MeshNetwork) to ensure that network connectivity is maintained when some nodes fail. During the collection process, drone swarms carry throwable sensors to quickly cover the core area of the accident, and ground mobile robots are deployed to supplement blind spots. The sensor adopts a low-power design, combined with solar cells, supercapacitors and dynamic sleep mechanisms to ensure continuous operation for more than 72 hours.

[0103] S2. Based on the field data, forecast the demand for materials and equipment.

[0104] Combine environmental data (temperature, gas concentration), geographic data (terrain damage, traffic blockage), visual data (drone images, heat maps) and historical disaster case libraries collected by S1 to build a multidimensional data set. Extract key features such as disaster type (fire / earthquake / flood), impact range, population density, infrastructure damage level, real-time weather trends (such as rainfall forecast), etc. as prediction input.

[0105] Extraction of key features is achieved by combining multi-source data fusion with domain knowledge: first, the field data (such as temperature, gas concentration, terrain damage, and drone images) are standardized and normalized to eliminate dimensional differences; then, mutual information (MI) is used to quantify the correlation between features and target variables (such as material demand), and the formula is:

[0106]

[0107] Where I(X; Y) represents the mutual information between random variables X and Y; x and y represent the possible values of X and Y; p(x, y) represents the joint probability distribution of X and Y; p(x) represents the marginal probability distribution of X; and p(y) represents the marginal probability distribution of Y.

[0108] Features with mutual information values higher than the threshold (0.2 in this embodiment) are retained, and high-dimensional features (such as multispectral image pixels) are reduced in dimension by combining principal component analysis (PCA) to extract principal components to reduce computational complexity. At the same time, composite features are constructed, such as calculating the "rescue pressure index per unit area" based on damage sensor data and population density: pressure index = (damage level × population density) / traffic accessibility.

[0109] The variance inflation factor (VIF) was used to detect multicollinearity and features with VIF>10 were removed. The formula is:

[0110]

[0111] Among them, represents the linear regression determination coefficient of the \(i\)-th feature with respect to other features. The finally retained feature set includes disaster type coding, stress index, real-time weather trend coding, historical disaster situation similarity, etc.

[0112] After that, the extracted features are input into the trained prediction model to predict the demand for materials and equipment. In this embodiment, Gradient Boosting Decision Tree (GBDT) is used to construct the prediction model, and the steps are as follows:

[0113] Initialize the model prediction value to the mean of the target variable (such as the demand for medical supplies):

[0114]

[0115] Among them, \(F_0(x)\) represents the frequency of the target variable; \(n\) represents the total number of samples; \(y\) i represents the state of the \(i\)-th observation.

[0116] Iteratively train \(M\) decision trees. In each round of iteration \(m\) (\(1\leq m\leq M\)), the steps include:

[0117] (1) Calculate the residuals of the current model for all samples (when the loss function is the mean square error, the residual is the difference between the true value and the current prediction value);

[0118] (2) Fit a regression tree \(h\) m (x) to predict the residual \(r\) im , and select the split point and leaf node value by minimizing the squared error. Calculate the optimal step size \(\gamma\) m to update the model:

[0119]

[0120] Among them, \(\gamma\) m represents the optimal step size at the \(m\)-th iteration; means finding a parameter \(\gamma\) such that the following expression (i.e., the loss function) reaches the minimum; \(n\) represents the total number of samples; \(F\) m-1 (x i ) represents the predicted value of the \(i\)-th sample at the \((m - 1)\)-th iteration; \(h\) m (x i ) represents the base learner.

[0121] After that, update the overall model and add a learning rate \(v\) (such as 0.1) to prevent overfitting:

[0122] F m (x) = F m-1 (x) + \(\nu\gamma\) m hm (x)

[0123] Among them, F m (x) represents the predicted value of the model for the input at the m-th iteration; v represents the learning rate; h m (x) represents the base learner at the m-th iteration.

[0124] Repeat the above steps until the preset number of iterations is reached or the residual converges. The final predicted value is the sum of the weighted outputs of all trees:

[0125]

[0126] Among them, F M (x) represents the final output; F0(x) represents the predicted value of the initial model.

[0127] During model training, the early stopping method (EarlyStopping) is adopted to stop the iteration based on the validation set loss, and the key driving factors (such as the influence weight of the pressure index on the material demand) are explained by feature importance ranking (based on the loss reduction during splitting). This method can adapt to non-linear relationships and feature interactions, and accurately predict the multi-category material demand in disaster scenarios.

[0128] S3. Based on the prediction results, conduct warehouse material matching and generate the logistics distribution path.

[0129] In step S3, based on the predicted material demand results, first match the warehouse nodes closest to the disaster area through a multi-objective optimization model, and preferentially select the warehouses with sufficient inventory and the lowest transportation cost, while considering the material type matching degree and timeliness constraints:

[0130] minZ = αT + βC

[0131] Among them, T represents time; C represents cost; α and β both represent weight coefficients.

[0132] Subsequently, combined with real-time traffic data and the status of distribution vehicles (load, cruising range), use the improved ant colony algorithm to generate the optimal distribution path for multi-vehicle collaboration. The formula of the improved ant colony algorithm is as follows:

[0133] τ ij (t + 1) = (1 - ρ)·τ ij (t) + Δτ ij

[0134] Among them, τ ij (t) represents the pheromone concentration from the i-th node to the j-th node at time t, ρ represents the pheromone evaporation coefficient (0 < ρ < 1), and Δτ ij represents the pheromone increment from the i-th node to the j-th node.

[0135]

[0136] Among them, represents the probability that the ant colony k moves from the i-th node to the j-th node at time t; η ij (t) represents the heuristic information; allowed k represents the set of nodes that the ant colony k is allowed to choose.

[0137] After that, the path is dynamically adjusted to cope with sudden road condition changes (such as new obstacle points transmitted back by drones). Finally, a path plan with time sequence constraints and a global allocation mapping table of warehouse-vehicle-materials are output to ensure the efficient use of resources and the timeliness of emergency response.

[0138] S4. Determine the approach time based on the logistics distribution path.

[0139] First, calculate the earliest arrival time (ETA) and safety time window of each delivery vehicle (based on on-site safety thresholds, such as gas concentration below 50 ppm and structural stability score ≥ 0.7). Dynamically balance timeliness and safety through a multi-constraint optimization model; at the same time, introduce a game theory framework to coordinate the approach order of multiple vehicles to avoid path conflicts and resource squeezing. Finally, generate a batch approach plan (for example, the first batch of high-priority material vehicles enter immediately after the safety window opens, and subsequent vehicles are dynamically adjusted according to real-time risk assessment), and synchronously push approach instructions and obstacle avoidance navigation information to drivers and the on-site command center through the Internet of Things platform to ensure the efficient and orderly progress of rescue operations. The multi-constraint optimization model is as follows:

[0140]

[0141] Among them, U represents the total utility or the sum of the urgency of emergency material requirements; λ i represents the weight or demand of the i-th material demand point; μ represents the attenuation coefficient; t i represents the time of the i-th material demand point; t 紧急 represents the time when the emergency event occurs.

[0142] S5. Use Internet of Things technology to monitor the entire scheduling process, and at the same time collect on-site feedback information to dynamically adjust the scheduling plan.

[0143] Use Internet of Things technology to monitor the entire scheduling process, including the transportation, approach, and use of materials and equipment. Collect on-site feedback information and dynamically adjust the scheduling plan to cope with sudden changes.

[0144] The system of the above embodiments is used to implement a corresponding real-time monitoring and allocation method of emergency supplies based on the Internet of Things in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0145] It should be noted that the above real-time monitoring and allocation system of emergency supplies based on the Internet of Things is embodied in the form of functional units. The term "module" here can be implemented in the form of software and / or hardware, and no specific limitation is made thereto.

[0146] For example, the "module" can be a software program, a hardware circuit, or a combination of the two that implements the above functions. The hardware circuit may include an application-specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a proprietary processor, or a group of processors, etc.) for executing one or more software or firmware programs, and a memory, a combined logic circuit, and / or other suitable components that support the described functions.

[0147] Embodiment III

[0148] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements a real-time monitoring and allocation method of emergency supplies based on the Internet of Things described in any of the above embodiments.

[0149] Figure 2 FIG. shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0150] The processor 1010 can be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0151] The memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and called and executed by the processor 1010.

[0152] The input / output interface 1030 is used to connect to an input / output module to implement information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0153] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module may implement communication in a wired manner (such as USB (Universal Serial Bus), network cable, etc.) or in a wireless manner (such as a mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0154] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0155] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary for implementing the solutions of the embodiments of this specification, and do not have to include all the components shown in the figure.

[0156] The system of the above embodiment is used to implement the corresponding real-time monitoring and allocation method of emergency supplies based on the Internet of Things in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0157] Embodiment Four

[0158] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute a method for real-time monitoring and allocation of emergency supplies based on the Internet of Things as described in any one of the above embodiments.

[0159] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0160] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute a method for real-time monitoring and allocation of emergency supplies based on the Internet of Things as described in any one of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0161] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the concept of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of brevity.

[0162] In addition, for simplicity of explanation and discussion, and so as not to make the embodiments of the present disclosure difficult to understand, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Further, the devices may be shown in block diagram form in order to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that details regarding the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure are to be implemented (i.e., these details should be entirely within the understanding of those skilled in the art). In cases where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that the embodiments of the present disclosure may be practiced without these specific details or with variations of these specific details. Accordingly, these descriptions should be regarded as illustrative rather than restrictive.

[0163] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0164] Thus, the units of the examples described in the embodiments of this application can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0165] The embodiments of the present disclosure are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A real-time monitoring and allocation method for emergency supplies based on the Internet of Things, characterized in that, The method includes: Using the Internet of Things sensor network to collect on-site data of the accident in real time; Based on the on-site data, predicting the demand for materials and equipment; Based on the prediction results, matching the warehouse materials and generating a logistics distribution path; Based on the logistics distribution path, determining the arrival time; Using Internet of Things technology to monitor the entire scheduling process, and at the same time collecting on-site feedback information to dynamically adjust the scheduling plan.

2. The real-time monitoring and allocation method of emergency supplies based on the Internet of Things according to claim 1, characterized in that, The on-site data includes: the damaged range, topography and weather conditions; at the same time, combining satellite remote sensing images and unmanned aerial vehicle reconnaissance data to further evaluate the characteristics, types and scales of the damage events.

3. The real-time monitoring and allocation method of emergency supplies based on the Internet of Things according to claim 1, wherein, The method for predicting the demand for materials and equipment includes: based on the on-site data, extracting key features, and based on the key features, constructing a prediction model to predict the demand for materials and equipment; wherein, the method for extracting the key features includes: Wherein, I(X; Y) represents the mutual information between the random variables X and Y; x and y represent the possible values of X and Y; p(x, y) represents the joint probability distribution of X and Y; p(x) represents the marginal probability distribution of X; p(y) represents the marginal probability distribution of Y.

4. The real-time monitoring and allocation method of emergency supplies based on the Internet of Things according to claim 3, characterized in that, Using gradient boosting trees to construct a prediction model: Among them, F M (x) represents the final output of the M-th iteration; F0(x) represents the predicted value of the initial model; v represents the learning rate; γ m represents the optimal step size at the m-th iteration; h m (x) represents the base learner at the m-th iteration.

5. The real-time monitoring and allocation method of emergency supplies based on the Internet of Things according to claim 1, characterized in that, The method for generating the logistics distribution path includes: based on the predicted material demand results, first matching the warehouse node closest to the disaster area through a multi-objective optimization model, preferentially selecting the warehouse with sufficient inventory and the lowest transportation cost, and at the same time considering the material type matching degree and timeliness constraints; subsequently, combining real-time traffic data and the status of distribution vehicles, using an improved ant colony algorithm to generate an optimal distribution path for multi-vehicle collaboration.

6. The method for real-time monitoring and allocation of emergency supplies based on the Internet of Things according to claim 1, characterized in that, The method for determining the arrival time includes: first calculating the earliest arrival time and safety time window of each distribution vehicle, dynamically weighing timeliness and safety through a multi-constraint optimization model; at the same time, introducing a game theory framework to coordinate the arrival order of multi-vehicles, avoiding path conflicts and resource congestion, and finally generating a batch-by-batch arrival plan.

7. The method for real-time monitoring and allocation of emergency supplies based on the Internet of Things according to claim 6, characterized in that, The multi-constraint optimization model is as follows: Among them, U represents the total utility of the emergency material demand or the sum of the emergency levels; λ i represents the weight or demand quantity of the i-th material demand point; μ represents the attenuation coefficient; t i represents the time of the i-th material demand point; t 紧急 represents the time when the emergency event occurs.

8. An emergency material real-time monitoring and allocation system based on the Internet of Things, the system is used to implement the method described in any one of claims 1-7, characterized in that, Including: An acquisition module, a prediction module, a planning module, a scheduling module and a feedback module; The acquisition module is used to use the Internet of Things sensor network to collect on-site data of the accident in real time; The prediction module is used to predict the demand for materials and equipment based on the on-site data; The planning module is used to match the warehouse materials and generate a logistics distribution path based on the prediction results; The scheduling module is used to determine the arrival time based on the logistics distribution path; The feedback module is used to use Internet of Things technology to monitor the entire scheduling process, and at the same time collect on-site feedback information to dynamically adjust the scheduling plan.

9. An electronic device, characterized in that, Including a memory, a processor and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed, the method described in any one of claims 1 to 7 is implemented.

Images