First-aid material tracking method and system based on Internet of Things

Abstract

The invention provides a first-aid material tracking method and system based on the Internet of Things. Wherein a unique electronic tag identifier is allocated to each first-aid material, and a material information file is generated; acquiring the position information of the first-aid material and the surrounding environment parameters in real time to obtain an environment adaptability analysis result; setting a safety threshold range adapted to different types of first-aid materials, identifying an abnormal event, recording and updating an early warning mechanism triggering condition to the material information file, and obtaining latest state information; a plurality of potential optimal distribution routes are calculated, a scheme with the highest comprehensive benefit is selected, a path planning strategy is continuously adjusted, and an optimized distribution route is obtained; and constructing a resource allocation visual management platform based on the material information file, the environmental adaptability analysis result, the early warning mechanism triggering condition and the optimized distribution route. According to the technical scheme provided by the invention, the efficiency and reliability of first-aid material management and distribution are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of Internet of Things and intelligent logistics technology, and in particular to a method and system for tracking emergency supplies based on the Internet of Things. Background Art

[0002] In modern emergency supplies management and distribution, efficient and accurate tracking and dispatching of emergency supplies is crucial. Especially in emergency situations, such as natural disasters and public health events, rapid response and accurate deployment of emergency supplies can directly affect rescue effectiveness and life safety. Therefore, a solution is needed that can monitor the status of supplies in real time, predict environmental changes, optimize distribution routes, and provide visual management to ensure that emergency supplies can reach their destination in the shortest time and always remain in the best state of preservation.

[0003] At present, the management and distribution of emergency supplies mainly rely on traditional logistics systems and manual recording methods. Some advanced systems have begun to introduce radio frequency identification technology and GPS positioning systems to track the location of supplies, but the functions of these systems are relatively simple, mainly focusing on the location tracking of supplies. Existing systems have not yet fully covered functions such as real-time monitoring of environmental parameters around supplies, prediction of future environmental change trends, and assessment of material preservation based on environmental conditions. In addition, most existing route planning is based on static data and lacks consideration of real-time traffic conditions and dynamic factors, resulting in low distribution efficiency.

[0004] However, existing systems can usually only provide simple information about the location of materials, and are unable to monitor and analyze environmental parameters such as temperature and humidity around materials in real time. It is even more difficult to predict future environmental change trends, and thus it is impossible to effectively evaluate the impact of environmental conditions on material preservation. When an abnormal situation is detected, the warning mechanism of the existing system is not sensitive enough and lacks effective abnormal event identification and processing capabilities, resulting in slow emergency response and difficulty in taking timely measures to protect the safety of materials. Most of the existing route planning is based on static data and fails to combine real-time traffic condition prediction models and traffic flow simulation technology. It is impossible to dynamically adjust the distribution route, resulting in high transportation time and cost, and it is difficult to ensure the rapid delivery of materials in emergency situations.

[0005] In summary, the existing emergency material management and distribution system has many deficiencies in environmental monitoring, emergency response and path planning, and a more intelligent and comprehensive solution is urgently needed to improve the efficiency and reliability of emergency material management and distribution. To this end, a first aid material tracking method based on the Internet of Things is proposed, which aims to comprehensively improve the intelligent level of emergency material management and distribution through technical means such as electronic tag identifiers, real-time environmental monitoring, anomaly detection algorithms, genetic algorithm path planning and resource allocation visualization management platform. Summary of the invention

[0006] The embodiments of the present application provide an Internet of Things-based emergency supplies tracking method and system to solve the problems of low efficiency and reliability in the management and distribution of emergency supplies in the prior art.

[0007] In a first aspect, an embodiment of the present application provides an emergency supplies tracking method based on the Internet of Things, comprising:

[0008] Assign a unique electronic tag identifier to each emergency material, and securely bind it with the specific information of the emergency material to generate a material information file;

[0009] According to the material information file, the location information and surrounding environmental parameters of the emergency materials are collected in real time, and the environmental change trend in the future is predicted. The impact of environmental conditions on the preservation of materials is evaluated in combination with the material characteristics to obtain environmental adaptability analysis results;

[0010] Based on the results of the environmental adaptability analysis, a safety threshold range suitable for different types of emergency supplies is set. When the detected environmental parameters exceed the set safety threshold or unauthorized movement of supplies occurs, an abnormal event is identified using an anomaly detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the supply information file to obtain the latest status information;

[0011] Based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal delivery routes, and the transportation time and cost under different routes are simulated by combining the real-time traffic condition prediction model and traffic flow simulation technology, and the plan with the highest comprehensive benefit is selected. The path planning strategy is continuously adjusted based on the reinforcement learning algorithm to obtain the optimized delivery route;

[0012] Based on the material information archive, environmental adaptability analysis results, early warning mechanism triggering conditions and the optimized distribution routes, a resource allocation visualization management platform is constructed. The resource allocation visualization management platform allows managers to intuitively view the distribution, status and transportation progress of each emergency material through a map view, and supports the immediate issuance and adjustment of material dispatch instructions.

[0013] Optionally, based on the result of the environmental adaptability analysis, a safety threshold range adapted to different types of emergency supplies is set. When the detected environmental parameters exceed the set safety threshold or unauthorized movement of supplies occurs, an abnormal event is identified using an abnormality detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the supply information file to obtain the latest status information, including:

[0014] Based on the results of the environmental adaptability analysis, the environmental parameters are evaluated according to the storage requirements of different types of first aid supplies to obtain the safety threshold ranges suitable for the different types of first aid supplies, and the safety threshold ranges are stored in the central monitoring system;

[0015] Using sensor nodes deployed in the emergency material storage environment, the environmental parameters are collected in real time, and the data is transmitted to a central monitoring system. The central monitoring system monitors the changes in environmental parameters in real time based on the stored safety threshold range. When it is detected that the environmental parameters exceed the set safety threshold or the materials are moved without authorization, the current situation is evaluated based on the environmental parameters and the material location information using an anomaly detection algorithm to identify whether it is an abnormal event, generate an abnormal event identification result, and record the abnormal event identification result in the central monitoring system;

[0016] Based on the abnormal event identification result, when it is confirmed as an abnormal event, the early warning mechanism is immediately triggered, a notification is immediately sent to the preset contact, and an early warning report containing the nature, time, location and information of emergency supplies involved in the abnormal event is generated, and the early warning report is also stored in the central monitoring system;

[0017] According to the early warning report, the central monitoring system records the triggering of the early warning mechanism and updates it to the material information file to obtain the latest status information.

[0018] Optionally, the sensor nodes deployed in the emergency material storage environment are used to collect the environmental parameters in real time and transmit the data to a central monitoring system. The central monitoring system monitors the changes in environmental parameters in real time based on the stored safety threshold range. When it is detected that the environmental parameters exceed the set safety threshold or the materials are moved without authorization, the abnormality detection algorithm is used to evaluate the current situation according to the environmental parameters and the material location information, identify whether it is an abnormal event, generate an abnormal event identification result, and record the abnormal event identification result in the central monitoring system, including:

[0019] By using sensor nodes deployed in the emergency material storage environment, the environmental parameters are collected in real time, and the data is transmitted to the central monitoring system through a low-power wide area network to obtain the latest environmental parameter data;

[0020] Based on the latest environmental parameter data, the central monitoring system monitors the environmental parameter changes in real time according to the stored safety threshold range, and generates an environmental exceeding signal when it is detected that the environmental parameter exceeds the set safety threshold;

[0021] In addition to the environmental parameters, the sensor node also monitors the location information of the emergency supplies. When unauthorized movement of the supplies is detected, a corresponding alarm signal is immediately generated, and the alarm signal and the location information are transmitted to the central monitoring system to obtain unauthorized movement event data;

[0022] Based on the environmental excess signal and the unauthorized movement event data, the central monitoring system uses an anomaly detection algorithm to evaluate the current situation, identify whether it is an abnormal event, and generate an abnormal event evaluation result.

[0023] Optionally, based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal delivery routes, and the transportation time and cost under different routes are simulated in combination with a real-time traffic condition prediction model and traffic flow simulation technology, and the solution with the highest comprehensive benefit is selected. The path planning strategy is continuously adjusted based on a reinforcement learning algorithm to obtain an optimized delivery route, including:

[0024] Based on the latest status information, the location of emergency needs, and the location of all currently available emergency supplies, relevant information is collected and integrated to obtain accurate basic data;

[0025] Using a genetic algorithm, based on the accurate basic data, multiple potential delivery routes from the emergency material storage location to the emergency demand location are calculated to generate a candidate path set, and the paths in the candidate path set are recorded in the central monitoring system;

[0026] Based on the candidate path set and in combination with the real-time traffic condition prediction model, the traffic flow on each path is predicted, and based on the historical traffic data and the real-time traffic information, the traffic change trend in different time periods is predicted to obtain the traffic condition prediction result, and the traffic condition prediction result is stored in the central monitoring system;

[0027] According to the traffic condition prediction results, using traffic flow simulation technology, for each path in the candidate path set, simulating transportation time and cost, considering factors affecting transportation efficiency, generating a detailed transportation evaluation report for each route, and recording the detailed transportation evaluation report in the central monitoring system;

[0028] Based on the transport evaluation report, select the delivery route with the highest comprehensive benefit from the candidate route set, generate an optimal route selection result, and record the optimal route selection result in a central monitoring system;

[0029] Based on the optimal path selection results and implementation status, the reinforcement learning algorithm is used to continuously adjust the path planning strategy to generate an optimized delivery route.

[0030] Optionally, the method of using a genetic algorithm to calculate a plurality of potential delivery routes from a first aid material storage location to a first aid demand location based on the accurate basic data, generating a candidate path set, and recording the paths in the candidate path set in the central monitoring system includes:

[0031] Collect and integrate relevant information based on the latest status information, the location of emergency needs, and the location of all currently available emergency supplies to obtain accurate basic data;

[0032] Based on the accurate basic data, using a genetic algorithm, the distribution routes from the emergency material storage location to the emergency demand location are initialized, the basic parameters required by the genetic algorithm such as population size, selection crossover probability, and mutation probability are defined, and an initial population including randomly generated potential distribution routes is initialized to obtain an initial population;

[0033] Based on the basic data, a fitness function is designed to evaluate the pros and cons of each potential delivery route, wherein the fitness function considers factors including path length, estimated transportation time, traffic condition prediction results, and road construction conditions, and obtains a fitness evaluation standard;

[0034] Based on the fitness evaluation criteria, the potential delivery routes in the initial population are iteratively optimized using the selection, crossover and mutation operations of the genetic algorithm to generate an optimized population;

[0035] Based on the optimized population, multiple potential delivery routes that meet preset conditions are screened to form a candidate path set, and the paths in the candidate path set are recorded in a central monitoring system.

[0036] Optionally, the method predicts the traffic flow on each path based on the candidate path set and in combination with a real-time traffic condition prediction model, predicts the traffic change trend in different time periods based on historical traffic data and real-time traffic information, obtains traffic condition prediction results, and stores the traffic condition prediction results in the central monitoring system, including:

[0037] Based on the candidate path set, extract key section information of each path, organize the key section information, and obtain basic data for traffic flow prediction;

[0038] Based on the basic data, sensor nodes and traffic cameras are used to collect data on key sections in combination with historical traffic data and real-time road condition information to obtain comprehensive traffic data;

[0039] Based on the comprehensive traffic data, a real-time traffic condition prediction model is used to predict the traffic flow on each path, taking time factors and special events into consideration, predicting traffic change trends in different time periods, generating traffic condition prediction results, and recording the traffic condition prediction results in a central monitoring system.

[0040] Optionally, the location information and surrounding environmental parameters of the emergency supplies are collected in real time according to the supply information file, and the environmental change trend in the future is predicted, and the impact of environmental conditions on the preservation of supplies is evaluated in combination with the characteristics of the supplies to obtain environmental adaptability analysis results, including:

[0041] According to the material information file, the location information and surrounding environmental parameters of the first aid materials are collected in real time by using sensor nodes deployed at the storage location of the first aid materials, and the collected data is transmitted to the central monitoring system through a low-power wide area network to obtain the latest location and environmental parameter data;

[0042] Based on the latest location and environmental parameter data, combined with historical environmental data and weather forecast information, using an environmental prediction model, predict the environmental change trend of the area where the emergency supplies are located in the future, generate environmental change trend prediction results, and store the environmental change trend prediction results in a central monitoring system;

[0043] According to the characteristics of the emergency materials recorded in the material information file, the influence of different environmental conditions on the preservation of the emergency materials is evaluated to obtain a material characteristic evaluation result, and the material characteristic evaluation result is updated in the material information file;

[0044] In combination with the environmental change trend prediction results and the material characteristics assessment results, an environmental adaptability analysis algorithm is used to evaluate whether current and future environmental conditions meet the storage requirements for emergency supplies, obtain environmental adaptability analysis results, and update the environmental adaptability analysis results to the material information file.

[0045] In a second aspect, an embodiment of the present application provides an emergency supplies tracking system based on the Internet of Things, including:

[0046] An allocation and binding module is used to allocate a unique electronic tag identifier to each first aid material, and securely bind it with the specific information of the first aid material to generate a material information file;

[0047] The collection and prediction module is used to collect the location information and surrounding environmental parameters of the emergency supplies in real time according to the material information file, and predict the environmental change trend in the future, and evaluate the impact of environmental conditions on the preservation of materials in combination with the material characteristics to obtain environmental adaptability analysis results;

[0048] A detection and identification module is used to set a safety threshold range suitable for different types of emergency supplies based on the results of the environmental adaptability analysis. When the detected environmental parameters exceed the set safety threshold or unauthorized movement of supplies occurs, an abnormal event is identified using an abnormal detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the supply information file to obtain the latest status information;

[0049] A simulation selection module is used to calculate multiple potential optimal delivery routes based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies using a genetic algorithm, and to simulate the transportation time and cost under different routes by combining a real-time traffic condition prediction model and traffic flow simulation technology, and select the plan with the highest comprehensive benefit, and to continuously adjust the path planning strategy based on a reinforcement learning algorithm to obtain an optimized delivery route;

[0050] A construction module is used to build a resource allocation visualization management platform based on the material information archive, environmental adaptability analysis results, early warning mechanism triggering conditions and the optimized distribution routes. The resource allocation visualization management platform allows managers to intuitively view the distribution, status and transportation progress of various emergency materials through a map view, and supports the immediate issuance and adjustment of material dispatch instructions.

[0051] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an emergency material tracking method based on the Internet of Things as described in any one of the first aspect.

[0052] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a method for tracking emergency supplies based on the Internet of Things as described in any one of the first aspects.

[0053] In the embodiment of the present application, a unique electronic tag identifier is assigned to each first aid material, and is securely bound to the specific information of the first aid material to generate a material information file; based on the material information file, the location information and surrounding environmental parameters of the first aid material are collected in real time, and the environmental change trend in the future is predicted, and the impact of environmental conditions on the preservation of materials is evaluated in combination with the material characteristics to obtain an environmental adaptability analysis result; based on the results of the environmental adaptability analysis, a safety threshold range suitable for different types of first aid materials is set; when the detected environmental parameters exceed the set safety threshold or the material is unauthorizedly moved, the abnormal event is identified using an anomaly detection algorithm, and the triggering situation of the early warning mechanism is recorded and updated in the material information file to obtain the most accurate information. new status information; based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal distribution routes, and the real-time traffic condition prediction model and traffic flow simulation technology are combined to simulate the transportation time and cost under different routes, and the plan with the highest overall benefit is selected. The path planning strategy is continuously adjusted based on the reinforcement learning algorithm to obtain the optimized distribution route; based on the material information file, the environmental adaptability analysis results, the triggering of the early warning mechanism and the optimized distribution route, a resource allocation visualization management platform is constructed, and the resource allocation visualization management platform allows managers to intuitively view the distribution, status and transportation progress of each emergency material through a map view, and supports the immediate issuance and adjustment of material dispatch instructions.

[0054] The technical solution of this application has the following beneficial effects:

[0055] Each emergency material is assigned a unique electronic tag identifier, which is securely bound to specific information to generate a material information file to ensure that each material can be accurately tracked and managed. This not only improves the transparency of material management, but also reduces the possibility of manual operation errors. According to the material information file, the location information and surrounding environmental parameters of the emergency materials are collected in real time, the environmental change trend in the future is predicted, and the impact of environmental conditions on the preservation of materials is evaluated in combination with the characteristics of the materials. This dynamic monitoring and analysis mechanism can timely discover and deal with problems that may affect the preservation of materials to ensure that the materials are always in the best state of preservation. Based on the results of the environmental adaptability analysis, the safety threshold range suitable for different types of emergency materials is set. When the detected environmental parameters exceed the set safety threshold or the materials are moved unauthorizedly, the abnormal event is identified by the anomaly detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the material information file. This enables managers to respond to abnormal situations quickly and take necessary measures to protect the safety of materials. Based on the latest status information, the location of emergency needs and the location of all currently available emergency materials, a genetic algorithm is used to calculate multiple potential optimal distribution routes. Combined with the real-time traffic condition prediction model and traffic flow simulation technology, the transportation time and cost under different routes are simulated to select the plan with the highest comprehensive benefit. This method not only improves distribution efficiency, but also reduces transportation costs, ensuring that emergency supplies can reach their destination as quickly as possible. Based on the reinforcement learning algorithm, the path planning strategy is continuously adjusted, so that the system can automatically optimize the distribution route according to the actual transportation situation, further improving the accuracy and timeliness of distribution. Integrate material information archives, environmental adaptability analysis results, early warning mechanism triggering conditions, and optimized distribution routes to build a resource allocation visualization management platform. The platform allows managers to intuitively view the distribution, status, and transportation progress of each emergency material through a map view, and supports the immediate issuance and adjustment of material dispatch instructions. This visual management method greatly simplifies the workflow of managers and improves decision-making efficiency. Through the above series of measures, the overall emergency response capability of the emergency material management and distribution system has been improved, ensuring that emergency materials can be quickly and efficiently allocated and transported in emergency situations, and maximizing public safety and health.

[0056] Furthermore, the embodiment of the present application also evaluates environmental parameters according to the preservation requirements of different types of emergency supplies based on the results of environmental adaptability analysis, sets and stores a safety threshold range. Environmental parameters are collected in real time using sensor nodes deployed in the storage environment and transmitted to the central monitoring system for real-time monitoring. When it is detected that the environmental parameters exceed the safety threshold or the materials are moved unauthorizedly, the abnormal event is identified using an abnormal detection algorithm, the abnormal event identification result is generated, and recorded in the central monitoring system. Once it is confirmed as an abnormal event, the early warning mechanism is immediately triggered, a notification is sent to the preset contact immediately, and an early warning report containing the nature, time, location and information about emergency supplies of the abnormal event is generated, which is also stored in the central monitoring system. The triggering of the early warning mechanism is recorded and updated to the material information file to obtain the latest status information. Based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, accurate basic data is collected and integrated. Multiple potential optimal distribution routes are calculated using a genetic algorithm, and a candidate path set is generated and recorded in the central monitoring system. Combined with the real-time traffic condition prediction model and traffic flow simulation technology, the traffic change trend in different time periods is predicted, the transportation time and cost are simulated, and a detailed transportation evaluation report for each route is generated. According to the evaluation report, the delivery route with the highest overall benefit is selected, and the path planning strategy is continuously adjusted using the reinforcement learning algorithm to generate an optimized delivery route.

[0057] Through the above methods, the intelligence level and emergency response capabilities of emergency material management and distribution have been significantly improved. Through real-time environmental monitoring and anomaly detection algorithms, emergency materials are always kept in the best state of preservation, and abnormal situations can be discovered and handled in a timely manner, enhancing the reliability and safety of the system. In addition, through the comprehensive application of genetic algorithms, real-time traffic condition prediction models, and reinforcement learning algorithms, intelligent optimization of distribution routes is achieved, which not only improves distribution efficiency and accuracy, but also reduces transportation costs, ensuring that emergency materials can reach their destinations in the shortest time. Overall, this method greatly improves the efficiency of emergency material management and dispatch, ensures the smooth progress of rescue work in emergency situations, and maximizes the protection of public safety and health.

[0058] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 A flowchart of a method for tracking emergency supplies based on the Internet of Things provided in an embodiment of the present application;

[0061] Figure 2 A schematic diagram of the structure of an emergency material tracking system based on the Internet of Things provided in an embodiment of the present application;

[0062] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0064] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0065] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0066] Figure 1 A flowchart of a method for tracking emergency supplies based on the Internet of Things is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0067] 101. Allocate a unique electronic tag identifier to each item of emergency supplies, and securely bind it with the specific information of the emergency supplies to generate a supplies information file;

[0068] It involves assigning a unique electronic tag identifier (such as an RFID tag) to each emergency material, and securely binding it with the specific information of the emergency material (including material type, quantity, expiration date, storage conditions, etc.) to generate a detailed material information file. These information files are not only used to track and manage the location and status of each material, but also provide basic data support for subsequent environmental monitoring, route planning and emergency response.

[0069] First, each emergency material is assigned a unique electronic tag identifier, which is connected to the central monitoring system through the Internet of Things technology. Then, the specific information of the material is entered into the system and associated with the identifier to ensure that each material has a unique and accurate information record. The generated material information file is stored in the central database and can be queried and updated in real time to reflect the latest status of the material.

[0070] In a hospital emergency supplies management system, all emergency medicines and equipment are affixed with RFID tags. Every time a new item is put into storage, the staff uses a handheld device to scan the tag and enter the material information (such as drug name, batch number, expiration date, storage temperature requirements, etc.) into the system. This information is transmitted to the central monitoring system via a wireless network to generate a detailed material information file. After that, any movement or status change of the material will be automatically recorded to ensure that the management staff can keep abreast of the latest situation of each material at any time.

[0071] 102. According to the material information file, the location information and surrounding environmental parameters of the emergency materials are collected in real time, and the environmental change trend in the future is predicted. The influence of environmental conditions on the preservation of materials is evaluated in combination with the material characteristics to obtain the environmental adaptability analysis results;

[0072] The aim is to use the data in the material information archive to collect the location information and surrounding environmental parameters of emergency materials in real time through sensor nodes (such as temperature and humidity sensors, gas sensors, etc.) deployed in the storage environment. At the same time, based on historical data and machine learning models, predict future environmental change trends, and combine material characteristics to evaluate the impact of environmental conditions on material preservation, and obtain environmental adaptability analysis results. This step helps to identify potential risks in advance and ensure that materials are always in the best state of preservation.

[0073] The central monitoring system collects the location of emergency supplies and the environmental parameters around them (such as temperature, humidity, light intensity, etc.) in real time through a sensor network. The system's built-in prediction model uses historical data and machine learning algorithms to predict environmental change trends over a period of time. Then, combined with the characteristics of the supplies (such as temperature sensitivity, shelf life, etc.), it evaluates whether the current environmental conditions are suitable for the storage of supplies and ultimately generates an environmental adaptability analysis report.

[0074] Continuing with the above hospital emergency supplies management system, multiple temperature and humidity sensors are installed in the supplies storage area to monitor environmental parameters in real time. The central monitoring system receives sensor data on a regular basis every day and analyzes the temperature and humidity trends in the next week through the built-in prediction model. For vaccines that need to be stored at low temperatures, the system will pay special attention to temperature fluctuations and adjust storage conditions based on the analysis results to ensure that the quality of the supplies is not affected.

[0075] 103. Based on the results of the environmental adaptability analysis, set the safety threshold ranges suitable for different types of emergency supplies. When the detected environmental parameters exceed the set safety thresholds or unauthorized movement of supplies occurs, use anomaly detection algorithms to identify abnormal events, record and update the triggering of the early warning mechanism to the supplies information file, and obtain the latest status information;

[0076] According to the results of environmental adaptability analysis, safety threshold ranges (such as upper and lower temperature limits, humidity ranges, etc.) are set for different types of emergency supplies. When it is detected that environmental parameters exceed the safety threshold or unauthorized movement of supplies occurs, the system uses anomaly detection algorithms to identify abnormal events and immediately triggers an early warning mechanism. The early warning information is recorded and updated to the material information file to ensure that managers can take timely measures to deal with abnormal situations.

[0077] The central monitoring system sets corresponding safety threshold ranges for different types of emergency supplies based on the results of environmental adaptability analysis and stores them in the system. During real-time monitoring, once it is found that environmental parameters exceed the safety threshold or unauthorized movement of supplies occurs, the system immediately starts the anomaly detection algorithm to identify abnormal events. After confirmation, the system generates an early warning report and notifies the preset contacts through multiple channels (such as SMS, email, APP push, etc.), and updates the latest status information in the material information file.

[0078] In the hospital emergency supplies management system, strict temperature thresholds (such as 2-8 degrees Celsius) are set for refrigerated medicines. One night, due to a refrigeration equipment failure, the temperature in the refrigerator rose above the set upper limit. The central monitoring system immediately identified this abnormal situation, triggered the early warning mechanism, and sent an emergency notice to the staff on duty. The staff on duty responded quickly, checked and repaired the refrigeration equipment, avoiding the risk of medicines being damaged by high temperature. The entire process is recorded in detail in the material information file to ensure traceability.

[0079] 104. Based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal delivery routes, and the transportation time and cost under different routes are simulated by combining the real-time traffic condition prediction model and traffic flow simulation technology, and the plan with the highest comprehensive benefit is selected. The path planning strategy is continuously adjusted based on the reinforcement learning algorithm to obtain the optimized delivery route;

[0080] Using the latest status information, the location of emergency needs, and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal delivery routes. Combined with real-time traffic condition prediction models and traffic flow simulation technology, the system simulates the transportation time and cost under different routes and selects the delivery plan with the highest overall benefit. The system also continuously adjusts the path planning strategy based on the reinforcement learning algorithm to further optimize the delivery route and ensure that emergency supplies can reach their destination as quickly as possible.

[0081] The central monitoring system integrates the latest status information, emergency demand locations, and the locations of all currently available emergency supplies to form accurate basic data. The genetic algorithm calculates multiple potential optimal delivery routes based on this data and generates a set of candidate routes. Combined with the real-time traffic condition prediction model, the system simulates the transportation time and cost under different routes and generates a detailed transportation evaluation report for each route. Finally, the delivery route with the highest overall benefit is selected, and the path planning strategy is continuously optimized through the reinforcement learning algorithm to ensure that each delivery can achieve the best results.

[0082] During a major traffic accident rescue, the hospital needed to urgently dispatch a batch of emergency supplies to the accident site. The central monitoring system quickly integrated the latest status information in the material information file, the coordinates of the accident site, and the location of all available supplies, and used genetic algorithms to calculate multiple potential optimal distribution routes. The system combined the real-time traffic condition prediction model, simulated the transportation time and cost under different routes, and selected the distribution route with the highest comprehensive benefit. At the same time, the system continuously adjusted the path planning strategy through the reinforcement learning algorithm to ensure that the ambulance could arrive at the accident site in the shortest time and successfully completed the rescue mission.

[0083] 105. Based on the material information archive, environmental adaptability analysis results, early warning mechanism triggering conditions and the optimized distribution routes, a resource allocation visualization management platform is constructed. The resource allocation visualization management platform allows managers to intuitively view the distribution, status and transportation progress of each emergency material through a map view, and supports the immediate issuance and adjustment of material dispatch instructions.

[0084] The aim is to build a visual management platform for resource allocation, integrating material information archives, environmental adaptability analysis results, early warning mechanism triggering conditions and optimized distribution routes. The platform allows managers to intuitively view the distribution, status and transportation progress of various emergency materials through map views, and supports the immediate issuance and adjustment of material dispatch instructions. This visual management method greatly simplifies the workflow of managers and improves decision-making efficiency.

[0085] The central monitoring system integrates material information files, environmental adaptability analysis results, early warning mechanism triggering conditions and optimized distribution routes into a unified resource allocation visualization management platform. The platform provides a map view function, and managers can view the distribution, status and transportation progress of emergency materials through an intuitive map interface. In addition, the platform supports the immediate issuance and adjustment of material dispatch instructions, ensuring that managers can flexibly respond to various emergencies.

[0086] In the hospital emergency supplies management system, the resource allocation visualization management platform has become an important tool for daily management. Through the platform's map view, managers can view the distribution, status and transportation progress of all emergency supplies in real time. In a large-scale emergency, the platform helped managers quickly allocate the required emergency supplies and ensured that the supplies arrived at each emergency point on time by issuing dispatch instructions immediately. The platform's visual management and instant adjustment functions significantly improved the efficiency and accuracy of material allocation and ensured the smooth progress of rescue work.

[0087] Through the implementation of steps 101 to 105, this method realizes the intelligent management of the entire process of emergency supplies from allocation identification, environmental monitoring, anomaly detection, path optimization to visual management. Specifically, a unique identifier is assigned to each emergency supply and an information file is generated to ensure the accurate tracking of the supplies; through real-time monitoring and prediction of environmental parameters, the supplies are always kept in the best state of preservation; the use of anomaly detection algorithms and early warning mechanisms enhances the emergency response capabilities of the system; the combination of genetic algorithms and reinforcement learning algorithms optimizes the distribution routes, greatly improving the distribution efficiency and accuracy; finally, through the resource allocation visual management platform, the transparent and efficient management of material allocation is achieved. Overall, this method not only improves the level of intelligence in the management and distribution of emergency supplies, but also ensures that the allocation of materials can be completed quickly and efficiently in emergency situations, maximizing public safety and health.

[0088] In order to solve the problem of efficiency and accuracy of environmental monitoring data transmission, in some embodiments, the location information and surrounding environmental parameters of the emergency supplies are collected in real time according to the supply information file in step 102, and the environmental change trend in the future is predicted, and the impact of environmental conditions on the preservation of supplies is evaluated in combination with the characteristics of the supplies to obtain the environmental adaptability analysis results, including:

[0089] According to the material information archive, the location information and surrounding environmental parameters of the first aid materials are collected in real time, and the environmental change trend in the future is predicted. The impact of environmental conditions on the preservation of materials is evaluated in combination with the material characteristics to obtain environmental adaptability analysis results, including: according to the material information archive, the location information and surrounding environmental parameters of the first aid materials are collected in real time using sensor nodes deployed at the first aid material storage location, and the collected data is transmitted to the central monitoring system through a low-power wide area network to obtain the latest location and environmental parameter data; based on the latest location and environmental parameter data, combined with historical environmental data and weather forecast information, the environmental prediction model is used to The environmental change trend of the area where the materials are located in the future period is predicted, and the environmental change trend prediction result is generated, and the environmental change trend prediction result is stored in the central monitoring system; according to the first aid material characteristics recorded in the material information file, the impact of different environmental conditions on the preservation of the first aid materials is evaluated to obtain the material characteristic evaluation result, and the material characteristic evaluation result is updated to the material information file; in combination with the environmental change trend prediction result and the material characteristic evaluation result, an environmental adaptability analysis algorithm is used to evaluate whether the current and future environmental conditions meet the storage requirements of the first aid materials, and the environmental adaptability analysis result is obtained, and the environmental adaptability analysis result is updated to the material information file.

[0090] In this embodiment, the low-power wide area network is a network technology designed for long-distance, low-bandwidth communications, suitable for remote monitoring and data transmission. It has the characteristics of low power consumption, long-distance coverage and large-scale connection, and is very suitable for data transmission between sensor nodes at the storage location of emergency supplies and the central monitoring system. The environmental prediction model is a prediction model constructed by machine learning or statistical methods based on historical environmental data and weather forecast information, which is used to predict the environmental change trend in the area where the emergency supplies are located in the future. These models can consider a variety of factors, such as temperature, humidity, light intensity, etc., to provide accurate prediction results. The environmental adaptability analysis algorithm is an algorithm that comprehensively evaluates whether the current and future environmental conditions meet the storage requirements of emergency supplies. It combines the results of environmental change trend prediction and material characteristic evaluation to ensure that the emergency supplies are always in the best preservation state during storage.

[0091] In the embodiment of the present application, firstly, the sensor nodes deployed at the storage location of the emergency materials are used to collect the location information and surrounding environmental parameters (such as temperature, humidity, light intensity, etc.) of the emergency materials in real time, and the collected data is transmitted to the central monitoring system through the low-power wide area network to ensure the efficiency and stability of data transmission. Secondly, based on the latest location and environmental parameter data, combined with historical environmental data and weather forecast information, the environmental prediction model is used to predict the environmental change trend of the area where the emergency materials are located in the future, generate environmental change trend prediction results, and store these results in the central monitoring system for subsequent use. Then, according to the characteristics of the emergency materials recorded in the material information file (such as temperature sensitivity, shelf life requirements, etc.), the impact of different environmental conditions on the preservation of the emergency materials is evaluated, and the material characteristics evaluation results are obtained, and these evaluation results are updated to the material information file to ensure that the information of each material is always kept up to date. Finally, combining the environmental change trend prediction results and material characteristics assessment results, the environmental adaptability analysis algorithm is used to evaluate whether the current and future environmental conditions meet the storage requirements of emergency supplies, and the environmental adaptability analysis results are obtained. These results are updated to the material information file to ensure that managers can take timely measures to deal with potential risks.

[0092] Here is a specific example:

[0093] In a remote area emergency supplies management system, all emergency supplies are stored in multiple scattered warehouses. To ensure the safety and quality of supplies, the system uses low-power wide area network technology, and multiple sensor nodes are installed in each warehouse to monitor environmental parameters such as temperature, humidity, and light intensity in real time. These sensor nodes transmit the collected data to the central monitoring system at the headquarters through the low-power wide area network every few minutes.

[0094] After receiving the data, the central monitoring system first uses the environmental prediction model to predict the temperature and humidity trends in the next week based on the latest location and environmental parameter data, combined with the historical environmental data of the past year and the weather forecast information provided by the local weather station. For example, the forecast shows that a warehouse may experience a sudden drop in temperature and an increase in humidity in the next three days.

[0095] Next, the system evaluates the impact of different environmental conditions on the storage of emergency supplies based on the characteristics of each emergency supply recorded in the supply information file (for example, some medicines need to be kept in a low temperature environment of 2-8 degrees Celsius) and generates a detailed supply characteristic evaluation report. For medicines that are particularly sensitive to temperature changes, the system will pay special attention to changes in their storage environment.

[0096] Finally, combining the prediction results of environmental change trends and the evaluation results of material characteristics, the system uses the environmental adaptability analysis algorithm to evaluate whether the current and future environmental conditions meet the storage requirements of emergency materials. If it is found that a warehouse may not be able to meet the low-temperature storage requirements of medicines in the next few days, the system will immediately trigger the early warning mechanism and notify the warehouse manager to take measures in advance, such as adjusting refrigeration equipment or transferring materials, to ensure that the quality of the medicines is not affected.

[0097] In this way, the system not only achieves accurate management and real-time monitoring of emergency supplies, but also significantly improves emergency response capabilities, ensuring the safety and effectiveness of emergency supplies under any circumstances.

[0098] In order to solve the real-time and accuracy problems of environmental parameter monitoring and abnormal event identification, in some embodiments, the safety threshold range adapted to different types of first aid supplies is set based on the results of the environmental adaptability analysis in step 103. When the detected environmental parameters exceed the set safety threshold or unauthorized movement of supplies occurs, an abnormal event is identified using an abnormality detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the supply information file to obtain the latest status information, including:

[0099] Based on the results of the environmental adaptability analysis, a safety threshold range suitable for different types of first aid supplies is set. When the detected environmental parameters exceed the set safety threshold or unauthorized movement of supplies occurs, an abnormal event is identified using an anomaly detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the material information file to obtain the latest status information, including: based on the results of the environmental adaptability analysis, according to the storage requirements of different types of first aid supplies, the environmental parameters are evaluated to obtain the safety threshold range suitable for the different types of first aid supplies, and the safety threshold range is stored in the central monitoring system; the environmental parameters are collected in real time using sensor nodes deployed in the first aid storage environment, and the data is transmitted to the central monitoring system, and the central monitoring system is based on the stored safety thresholds. value range, monitor the changes of environmental parameters in real time, and when it is detected that the environmental parameters exceed the set safety threshold or the materials are moved without authorization, the current situation is evaluated by using the anomaly detection algorithm according to the environmental parameters and the material location information, and whether it is an abnormal event is identified, and an abnormal event identification result is generated, and the abnormal event identification result is recorded in the central monitoring system; based on the abnormal event identification result, when it is confirmed to be an abnormal event, the early warning mechanism is immediately triggered, and a notification is immediately sent to the preset contact person, and an early warning report containing the nature, time, location of the abnormal event and the information related to emergency materials is generated, and the early warning report is also stored in the central monitoring system; according to the early warning report, the central monitoring system records the triggering of the early warning mechanism, and updates it to the material information file to obtain the latest status information.

[0100] The method uses sensor nodes deployed in the emergency material storage environment to collect the environmental parameters in real time and transmit the data to a central monitoring system. The central monitoring system monitors the changes in environmental parameters in real time based on the stored safety threshold range. When it is detected that the environmental parameters exceed the set safety threshold or the materials are moved without authorization, an abnormality detection algorithm is used to evaluate the current situation according to the environmental parameters and the material location information, identify whether it is an abnormal event, generate an abnormal event identification result, and record the abnormal event identification result in the central monitoring system, including: using sensor nodes deployed in the emergency material storage environment to collect the environmental parameters in real time, and transmitting the data to the central monitoring system through a low-power wide area network, obtaining to the latest environmental parameter data; based on the latest environmental parameter data, the central monitoring system monitors the changes in environmental parameters in real time according to the stored safety threshold range, and generates an environmental excess signal when it is detected that the environmental parameters exceed the set safety threshold; in addition to the environmental parameters, the sensor nodes also monitor the location information of emergency supplies, and immediately generate a corresponding alarm signal when it is detected that the supplies are moved without authorization, and transmit the alarm signal together with the location information to the central monitoring system to obtain unauthorized movement event data; based on the environmental excess signal and the unauthorized movement event data, the central monitoring system uses an anomaly detection algorithm to evaluate the current situation, identify whether it is an abnormal event, and generate an abnormal event evaluation result.

[0101] In this embodiment, the safety threshold range is a safety range set by evaluating environmental parameters according to the storage requirements of different types of emergency supplies (such as temperature, humidity, light intensity, etc.). These thresholds are used to ensure that each emergency supply is always in the best storage condition during storage. Low-power wide area network is a network technology designed for long-distance, low-bandwidth communication, suitable for remote monitoring and data transmission. It has the characteristics of low power consumption, long-distance coverage and large-scale connection, and is very suitable for data transmission between sensor nodes and central monitoring systems at the storage location of emergency supplies. The environmental over-standard signal is a signal generated by the sensor node when the environmental parameters (such as temperature and humidity) exceed the set safety threshold, which is used to notify the central monitoring system that the current environmental conditions no longer meet the storage requirements of emergency supplies. The alarm signal is a signal generated immediately when the sensor node detects that the emergency supplies have been unauthorized moved, which is used to notify the central monitoring system that an unauthorized material movement event has occurred. The anomaly detection algorithm is an algorithm for identifying abnormal events. It combines the environmental over-standard signal and the unauthorized movement event data to evaluate whether the current situation constitutes an abnormal event and generate corresponding abnormal event evaluation results.

[0102] In the embodiment of the present application, firstly, based on the results of the environmental adaptability analysis, according to the preservation requirements of different types of first aid materials, the environmental parameters are evaluated to obtain the safety threshold ranges adapted to different types of first aid materials, and these safety threshold ranges are stored in the central monitoring system. Secondly, the sensor nodes deployed in the storage environment of the first aid materials are used to collect environmental parameters (such as temperature, humidity, light intensity, etc.) in real time, and the data is transmitted to the central monitoring system through the low power wide area network to ensure that the latest environmental parameter data can be updated in time. Then, the central monitoring system monitors the latest environmental parameter data in real time based on the stored safety threshold range. When it is detected that the environmental parameters exceed the set safety threshold, an environmental over-limit signal is generated; at the same time, the sensor node also monitors the location information of the first aid materials, and when it is detected that the materials are unauthorized to move, an alarm signal is immediately generated, and the alarm signal and the location information are transmitted to the central monitoring system together to obtain the unauthorized movement event data. Further, the central monitoring system uses an anomaly detection algorithm to evaluate the current situation based on the environmental over-limit signal and the unauthorized movement event data, identifies whether it is an abnormal event, and generates an abnormal event evaluation result. These results are recorded in the central monitoring system. Finally, based on the abnormal event identification results, when it is confirmed as an abnormal event, the early warning mechanism is triggered immediately, a notification is sent to the preset contact person, and an early warning report containing the nature, time, location and information about emergency supplies of the abnormal event is generated. The early warning report is also stored in the central monitoring system. The central monitoring system records the triggering of the early warning mechanism and updates it to the material information file to obtain the latest status information.

[0103] Here is a specific example:

[0104] In the emergency supplies management system of a large hospital, all emergency medicines and equipment are stored in multiple scattered warehouses. In order to ensure the safety and quality of supplies, the system uses low-power wide area network technology, and multiple sensor nodes are installed in each warehouse to monitor environmental parameters such as temperature, humidity, and light intensity in real time. These sensor nodes transmit the collected data to the central monitoring system at the headquarters through the low-power wide area network every few minutes.

[0105] First, the system sets the corresponding safety threshold range according to the storage requirements of each emergency material (such as some medicines need to be kept in a low temperature environment of 2-8 degrees Celsius), and stores these thresholds in the central monitoring system. For example, the upper temperature limit of refrigerated medicines is set at 8 degrees Celsius, and the upper humidity limit is set at 70%.

[0106] Next, the sensor nodes collect environmental parameters in real time and transmit the data to the central monitoring system through the low-power wide area network. The system monitors the latest environmental parameter data in real time based on the stored safety threshold range. One night, due to a refrigeration equipment failure, the temperature in a warehouse rose above the set upper limit of 8 degrees Celsius. The sensor node immediately generated an environmental over-limit signal and transmitted it to the central monitoring system.

[0107] At the same time, the sensor node also monitors the location information of emergency supplies. If a refrigerator door is accidentally opened, resulting in unauthorized movement of medicines inside, the sensor node immediately generates an alarm signal and transmits the alarm signal and location information to the central monitoring system to obtain unauthorized movement event data.

[0108] After receiving the environmental over-limit signal and unauthorized movement event data, the central monitoring system uses the anomaly detection algorithm to evaluate the current situation, confirm that this is an abnormal event, and generate an abnormal event evaluation result. The system immediately triggers the early warning mechanism, notifies the duty personnel through SMS and email, and generates a detailed early warning report. The report content includes the nature of the abnormal event (temperature over-limit and unauthorized movement), time, location and information on the emergency supplies involved. The early warning report is also stored in the central monitoring system.

[0109] Finally, the central monitoring system records the triggering of the early warning mechanism and updates it to the material information file to ensure that managers can view the latest status information at any time. The on-duty personnel responded quickly, checked and repaired the refrigeration equipment, and avoided the risk of drugs being damaged by high temperatures. The entire process is recorded in detail in the material information file to ensure traceability.

[0110] In this way, the system not only achieves accurate management and real-time monitoring of emergency supplies, but also significantly improves emergency response capabilities, ensuring the safety and effectiveness of emergency supplies under any circumstances.

[0111] In order to solve the accuracy and optimization problems of path planning, in some embodiments, the step 104 uses a genetic algorithm to calculate multiple potential optimal delivery routes based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, combines a real-time traffic condition prediction model and traffic flow simulation technology, simulates the transportation time and cost under different routes, selects the plan with the highest comprehensive benefit, and continuously adjusts the path planning strategy based on a reinforcement learning algorithm to obtain an optimized delivery route, including:

[0112] Based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal distribution routes, and the transportation time and cost under different routes are simulated in combination with the real-time traffic condition prediction model and traffic flow simulation technology, and the plan with the highest overall benefit is selected. The path planning strategy is continuously adjusted based on the reinforcement learning algorithm to obtain an optimized distribution route, including: based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, relevant information is collected and integrated to obtain accurate basic data; using a genetic algorithm, based on the accurate basic data, multiple potential distribution routes from the emergency supply storage location to the emergency need location are calculated to generate a candidate path set, and the paths in the candidate path set are recorded in the central monitoring system; based on the candidate path set, combined with the real-time traffic condition prediction model, The traffic flow on each path is predicted, and based on the historical traffic data and real-time road condition information, the traffic change trend in different time periods is predicted to obtain the traffic condition prediction result, and the traffic condition prediction result is stored in the central monitoring system; according to the traffic condition prediction result, the traffic flow simulation technology is used to simulate the transportation time and cost for each path in the candidate path set, and the factors affecting the transportation efficiency are considered to generate a detailed transportation evaluation report for each route, and the detailed transportation evaluation report is recorded in the central monitoring system; based on the transportation evaluation report, the distribution route with the highest comprehensive benefit is selected from the candidate path set, the optimal path selection result is generated, and the optimal path selection result is recorded in the central monitoring system; based on the optimal path selection result and the implementation status, the reinforcement learning algorithm is used to continuously adjust the path planning strategy to generate an optimized distribution route.

[0113] Using a genetic algorithm, based on the accurate basic data, multiple potential delivery routes from the emergency material storage location to the emergency demand location are calculated to generate a candidate path set, and the paths in the candidate path set are recorded in the central monitoring system, including: collecting and integrating relevant information based on the latest status information, the emergency demand location and the location of all currently available emergency materials to obtain accurate basic data; based on the accurate basic data, using a genetic algorithm, initializing the delivery route from the emergency material storage location to the emergency demand location, defining the basic parameters required by the genetic algorithm such as population size, selection crossover probability, and mutation probability, and initializing a The method comprises randomly generating an initial population of potential delivery routes to obtain an initial population; designing a fitness function based on the basic data to evaluate the pros and cons of each potential delivery route, wherein the fitness function considers factors including path length, estimated transportation time, traffic condition prediction results, and road construction conditions to obtain a fitness evaluation standard; based on the fitness evaluation standard, using the selection, crossover, and mutation operations of a genetic algorithm to iteratively optimize the potential delivery routes in the initial population to generate an optimized population; based on the optimized population, screening out a plurality of potential delivery routes that meet preset conditions to form a candidate path set, and recording the paths in the candidate path set in a central monitoring system.

[0114] In this embodiment, the basic data includes the latest status information (such as material location, environmental parameters), the location of emergency needs, and the location of all currently available emergency materials. These data are used to generate accurate basic data to ensure that the input information of path planning is the latest and most accurate. Genetic algorithm is an optimization algorithm that simulates natural selection and genetic mechanism. It iteratively optimizes potential distribution routes by initializing populations, defining fitness functions, performing selection, crossover and mutation operations, and finally generating a candidate path set. The fitness function is used to evaluate the pros and cons of each potential distribution route, and the factors considered include path length, estimated transportation time, traffic condition prediction results, and road construction conditions. The design of the fitness function determines the selection criteria of the path. The candidate path set is a set of multiple potential distribution routes that meet the preset conditions after being optimized by the genetic algorithm, forming a set containing multiple feasible solutions for further evaluation and selection. The real-time traffic condition prediction model is based on historical traffic data and real-time road condition information to predict traffic change trends in different time periods and provide traffic flow prediction results for a period of time in the future. Traffic flow simulation technology is used to simulate the transportation time and cost of different routes, taking into account various factors that affect transportation efficiency (such as traffic lights, speed limits, etc.), and generating detailed transportation evaluation reports for each route. Reinforcement learning algorithms optimize the selection of delivery routes by continuously learning and adjusting path planning strategies to ensure that each delivery can achieve the best results.

[0115] In the embodiment of the present application, first, according to the latest status information, the location of emergency needs and the location of all currently available emergency supplies, relevant information is collected and integrated to obtain accurate basic data to ensure that the input information of path planning is the latest and most accurate. Secondly, based on the accurate basic data, the distribution route from the storage location of emergency supplies to the location of emergency needs is initialized by using a genetic algorithm, and basic parameters such as population size, selection crossover probability, and mutation probability are defined, and an initial population containing randomly generated potential distribution routes is initialized to obtain an initial population. Then, based on the basic data, a fitness function is designed to evaluate the pros and cons of each potential distribution route. The factors considered in the fitness function include path length, estimated transportation time, traffic condition prediction results, and road construction conditions, and a fitness evaluation standard is obtained. Then, based on the fitness evaluation standard, the selection, crossover and mutation operations of the genetic algorithm are used to iteratively optimize the potential distribution routes in the initial population to generate an optimized population. According to the optimized population, multiple potential distribution routes that meet the preset conditions are screened out to form a candidate path set, and the paths in the candidate path set are recorded in the central monitoring system. Furthermore, based on the candidate path set and in combination with the real-time traffic condition prediction model, the traffic flow on each path is predicted, and based on the historical traffic data and real-time road condition information, the traffic change trend in different time periods is predicted to obtain traffic condition prediction results, and these results are stored in the central monitoring system. Furthermore, based on the traffic condition prediction results, using traffic flow simulation technology, for each path in the candidate path set, the transportation time and cost are simulated, and the factors affecting transportation efficiency are considered to generate detailed transportation evaluation reports for each route, and these reports are recorded in the central monitoring system.

[0116] Finally, based on the transportation evaluation report, the distribution route with the highest comprehensive benefit is selected from the candidate route set, the optimal route selection results are generated, and these results are recorded in the central monitoring system.

[0117] Based on the optimal path selection results and implementation status, the reinforcement learning algorithm is used to continuously adjust the path planning strategy and generate optimized delivery routes to ensure that each delivery can achieve the best results.

[0118] Here is a specific example:

[0119] In a city emergency supplies management system, a major traffic accident occurred one day, and a batch of emergency supplies needed to be urgently deployed to the accident site. In order to ensure that the supplies can reach the destination as quickly as possible, the system activated the intelligent path planning function.

[0120] First, the system collects and integrates relevant information based on the latest status information (such as the quantity and status of emergency supplies in each warehouse), the coordinates of the accident site, and the location of all currently available emergency supplies to obtain accurate basic data. This data includes the specific location of the supplies, the estimated transportation time, the traffic condition forecast results, and the road construction status.

[0121] Next, the system uses a genetic algorithm to initialize the delivery route from the emergency material storage location to the accident site. The system defines basic parameters such as a population size of 100, a crossover probability of 0.8, and a mutation probability of 0.1, and initializes an initial population of 100 randomly generated potential delivery routes.

[0122] The system then designs a fitness function to evaluate the pros and cons of each potential delivery route. The fitness function takes into account factors such as path length, estimated delivery time, traffic forecasts, and road construction. For example, if a path is shorter but has a longer estimated delivery time or passes through a construction section, its fitness score will be lower; otherwise, it will be higher.

[0123] Next, the system iteratively optimizes the potential delivery routes in the initial population based on the fitness evaluation criteria, using the selection, crossover, and mutation operations of the genetic algorithm. After multiple iterations, the system generates an optimized population and selects multiple potential delivery routes that meet the preset conditions to form a candidate route set. These routes are recorded in the central monitoring system for subsequent evaluation and selection.

[0124] The system then combines the real-time traffic condition prediction model to predict the traffic flow on each route. Based on historical traffic data and real-time road condition information, the system predicts traffic change trends in different time periods, obtains traffic condition prediction results, and stores these results in the central monitoring system.

[0125] Furthermore, the system uses traffic flow simulation technology to simulate the transportation time and cost for each path in the candidate path set, taking into account various factors that affect transportation efficiency (such as traffic lights, speed limits, etc.), and generates detailed transportation evaluation reports for each route. These reports are also recorded in the central monitoring system for management personnel to review and make decisions.

[0126] Finally, based on the transport evaluation report, the system selects the delivery route with the highest comprehensive benefits from the candidate route set, generates the best route selection results, and records these results in the central monitoring system. At the same time, the system uses reinforcement learning algorithms to continuously adjust the route planning strategy according to the actual delivery situation to ensure that each delivery can achieve the best results.

[0127] In this way, the system not only achieves accurate management and real-time monitoring of emergency supplies, but also significantly improves delivery efficiency and accuracy, ensuring that emergency supplies can reach their destination in the shortest time possible and successfully completing the rescue mission.

[0128] In order to solve the accuracy and real-time problems of traffic flow prediction, in some embodiments, the step 104 predicts the traffic flow on each path based on the candidate path set and the real-time traffic condition prediction model, predicts the traffic change trend in different time periods based on historical traffic data and real-time road condition information, obtains traffic condition prediction results, and stores the traffic condition prediction results in the central monitoring system, including:

[0129] Based on the candidate path set, combined with the real-time traffic condition prediction model, the traffic flow on each path is predicted, based on the historical traffic data and real-time road condition information, the traffic change trend in different time periods is predicted, the traffic condition prediction result is obtained, and the traffic condition prediction result is stored in the central monitoring system, including: based on the candidate path set, the key section information of each path is extracted, the key section information is sorted out, and the basic data for traffic flow prediction is obtained; according to the basic data, the sensor nodes and traffic cameras are used, combined with the historical traffic data and real-time road condition information, the data of the key sections are collected to obtain comprehensive traffic data; based on the comprehensive traffic data, the real-time traffic condition prediction model is used to predict the traffic flow on each path, considering the time factor and special events, the traffic change trend in different time periods is predicted, the traffic condition prediction result is generated, and the traffic condition prediction result is recorded in the central monitoring system.

[0130] In this embodiment, the key section information refers to the specific sections on each path in the candidate path set that have a greater impact on traffic flow, such as main roads, bridges, tunnels, etc. This information is used to extract and organize the basic data for traffic flow prediction. Comprehensive traffic data is data collected through sensor nodes (such as vehicle flow meters, speed sensors), traffic cameras, historical traffic data and real-time road condition information. After integration, these data provide a comprehensive description of traffic conditions for more accurate traffic flow prediction. The real-time traffic condition prediction model is a prediction model built based on machine learning or statistical methods, which uses comprehensive traffic data to predict the changing trend of traffic flow in the future. The model takes into account the influence of time factors (such as morning and evening rush hours) and special events (such as traffic accidents, large-scale events) to ensure the accuracy of the prediction results.

[0131] Traffic condition forecast results are generated by the prediction model, including traffic flow change trends in different time periods. These results are recorded in the central monitoring system for subsequent evaluation and decision-making.

[0132] In the embodiment of the present application, first, based on the candidate path set, the key section information of each path is extracted, and the information is sorted to obtain the basic data for traffic flow prediction. Key sections usually refer to specific sections that have a greater impact on traffic flow, such as main roads, bridges, tunnels, etc. Secondly, based on the sorted basic data, sensor nodes (such as vehicle flow meters, speed sensors) and traffic cameras deployed on key sections are used to collect data on key sections in combination with historical traffic data and real-time traffic information to obtain comprehensive traffic data. These data provide a comprehensive description of traffic conditions and provide support for subsequent predictions. Then, based on the comprehensive traffic data, the real-time traffic condition prediction model is used to predict the traffic flow on each path. The prediction model not only takes into account the current traffic conditions, but also combines time factors (such as morning and evening peaks) and special events (such as traffic accidents, large-scale events) to predict traffic change trends in different time periods and generate traffic condition prediction results. Finally, the generated traffic condition prediction results are recorded in the central monitoring system to ensure that managers can view the latest traffic forecast information at any time in order to make the best distribution route selection.

[0133] Here is a specific example:

[0134] In a city emergency supplies management system, a major traffic accident occurred one day, and a batch of emergency supplies needed to be urgently deployed to the accident site. In order to ensure that the supplies can reach the destination as quickly as possible, the system activated the intelligent path planning function and made detailed traffic flow predictions for the candidate paths.

[0135] First, based on the candidate path set, the system extracts the key section information of each path, such as main roads, bridges, tunnels, etc. These key sections are usually places with heavy traffic or prone to congestion. The system organizes this information and obtains the basic data for traffic flow prediction, ensuring that the basic information for prediction is the latest and most accurate.

[0136] Next, the system uses sensor nodes (such as traffic meters, speed sensors) and traffic cameras deployed on key sections of the road, combined with historical traffic data and real-time road conditions information, to collect data on key sections and obtain comprehensive traffic data. These data provide a comprehensive description of traffic conditions, including current traffic flow, average speed, road construction conditions, etc.

[0137] Then, based on the comprehensive traffic data, the system uses a real-time traffic condition prediction model to predict the traffic flow on each path. The prediction model not only takes into account the current traffic conditions, but also combines time factors (such as morning and evening rush hours) and special events (such as traffic accidents, large-scale events) to predict traffic trends in different time periods. For example, the system predicts that a certain path will be severely congested between 5pm and 7pm due to the rush hour, while another path will be relatively unobstructed.

[0138] Finally, the system records the generated traffic condition prediction results in the central monitoring system. Managers can view detailed prediction reports for each route through the system, including traffic flow trends in different time periods. Based on these prediction results, the system selects the delivery route with the highest comprehensive benefits and recommends this route to the dispatcher to ensure that emergency supplies can reach the accident site in the shortest time.

[0139] In this way, the system not only achieves accurate management and real-time monitoring of emergency supplies, but also significantly improves the efficiency and accuracy of distribution, ensuring that emergency supplies can reach their destination in the shortest time possible and successfully complete the rescue mission. In addition, the system's prediction model is constantly learning and optimizing, which improves the accuracy of future predictions and further enhances the system's emergency response capabilities.

[0140] This application takes into account that in the management and distribution of emergency supplies, it is crucial to quickly and accurately select the optimal distribution route. Traditional path planning methods are often based on static data and cannot fully consider real-time traffic conditions and dynamic factors (such as road construction), resulting in low distribution efficiency. In order to improve the intelligence level and emergency response capabilities of emergency supplies distribution, a method that can combine genetic algorithms, real-time traffic prediction models and complex fitness functions is needed to optimize the selection of distribution routes. Therefore, a new optional solution is proposed, which includes:

[0141] Using a genetic algorithm, based on the accurate basic data, multiple potential delivery routes from the emergency material storage location to the emergency demand location are calculated to generate a candidate path set, and the paths in the candidate path set are recorded in the central monitoring system, including:

[0142] According to the latest status information, the location of emergency needs and the location of all currently available emergency supplies, relevant information is collected and integrated to obtain accurate basic data D;

[0143] D={p s , P d , {P i}}

[0144] Among them, P s is the location of the emergency supplies storage location, Pd is the location of the emergency need location, {P i} is the location set of all currently available first aid supplies;

[0145] Based on the accurate basic data D, define the population size N and select the crossover probability p c , mutation probability p m The basic parameters required by the genetic algorithm are initialized, and an initial population containing randomly generated potential delivery routes is initialized;

[0146] Each individual s in the initial population i Represents a potential delivery route, consisting of a series of nodes;

[0147] According to the basic data D, a complex fitness function f(s) is designed. i ), used to evaluate each potential delivery route s i The fitness function considers the factors including the path length L(s i ), estimated transportation time T(s i ), traffic condition prediction result C(s i ) and road construction conditions that affect transportation efficiency E(s i ), and obtain the fitness evaluation standard;

[0148] The fitness evaluation standard f(s) is calculated by the following formula: i ):

[0149]

[0150] Among them, w L , w T , w C , w E They are the impact weights of path length, estimated transportation time, traffic condition prediction results and road construction conditions; δ L , δ T , δ C , δ E is the corresponding exponential factor, which is used to adjust the influence of each factor; f(s i ) is the fitness function used to evaluate each potential delivery route s i The advantages and disadvantages of L(s i ) is the path length; T(s i ) is the estimated transportation time; C(s i ) is the traffic condition prediction result; E(s i ) is the road construction situation; i is an index variable used to identify each individual in the population;

[0151] Based on the fitness evaluation standard f(si ), using the selection, crossover and mutation operations of the genetic algorithm, the potential delivery routes in the initial population S0 are iteratively optimized to generate an optimized population S opt ;

[0152] According to the fitness value f(s i ), using the roulette wheel selection method to select the better individuals to enter the next generation population S t+1 ;

[0153] The selection probability p is calculated by the following formula: select (s i ):

[0154]

[0155] Where λ is the sensitivity coefficient, which is used to adjust the selection pressure; f(s j ) is the fitness value of other individuals; p select (s i ) is the selection probability, which is used to determine the probability of each individual being selected to enter the next generation population; e is the base of the natural logarithm;

[0156] With crossover probability p c For two selected individuals s a and b Perform crossover to generate new individuals s a' ,s b' ;

[0157] The intersection point is selected using the following formula:

[0158] if rand(0,1) <p c then cross s a ands b to generate s a' ,s b'

[0159] Among them, rand(0,1) is a random number uniformly distributed in the interval [0,1];

[0160] With mutation probability p m For some individuals i Perform mutations to introduce diversity and prevent the algorithm from converging prematurely;

[0161] The mutation operation is performed using the following formula:

[0162] if rand(0,1) <p m then mutate s i to generate s'i

[0163] After multiple rounds of iterations, the optimized population S is finally obtained. opt ;

[0164] According to the optimized population S opt , filter out multiple potential delivery routes that meet the preset conditions and form a candidate route set P candidate and recording the paths in the candidate path set in a central monitoring system;

[0165] P candidate ={s i ∈S opt |f(s i )≤θ}

[0166] Among them, θ is the pre-set fitness threshold, which is used to screen the optimal potential delivery route; S opt is the optimized population; P candidate is the set of candidate paths;

[0167] Finally, an additional scoring mechanism is introduced to further optimize the selection of candidate paths;

[0168] The comprehensive benefit score B(s) is calculated by the following formula: i ):

[0169]

[0170] Where η is the balance weight, μ and ν are sensitivity coefficients, and f ideal is the ideal fitness value, E threshold is the threshold value of road construction; E(s i ) represents the impact value of the road construction condition on the ith route.

[0171] The following is a detailed explanation of each parameter:

[0172] P s : The location of the first aid supplies storage location, indicating the starting point of the supplies.

[0173] P d : The location of the emergency need location, indicating the destination of the supplies.

[0174] {P i}: The location set of all currently available first aid supplies, indicating the specific storage location of each supply.

[0175] N: is the population size, the number of individuals in the initial population of the genetic algorithm. A larger population can increase diversity, but the computational cost will also increase accordingly; a smaller population may lead to premature convergence.

[0176] p c : is the probability of crossover, the probability of two selected individuals undergoing crossover operations. A higher crossover probability helps generate new combinations and explore more solution spaces; a lower probability may limit the generation of new solutions.

[0177] p m : is the probability of mutation, the probability of a certain individual mutating. Introducing random changes prevents the algorithm from converging to the local optimal solution too early and maintains the diversity of the population.

[0178] w L : The influence weight of path length.

[0179] w T : The impact weight of the estimated shipping time.

[0180] w C : The impact weight of traffic condition prediction results.

[0181] w E : Impact weight of road construction conditions.

[0182] δ L : Exponential factor of path length, used to adjust its influence.

[0183] δ T : Exponential factor for estimated shipping time, used to adjust its impact.

[0184] δ C : Exponential factor of traffic condition prediction results, used to adjust its impact.

[0185] δ E : An exponential factor for road construction conditions, used to adjust their impact.

[0186] L(s i ): Path length of the ith potential delivery route.

[0187] T(s i ): Estimated transportation time of the ith potential delivery route.

[0188] C(s i ): Traffic condition prediction result of the ith potential delivery route.

[0189] E(s i ): Impact value of road construction conditions on the ith potential delivery route.

[0190] s i : Represents a potential delivery route, consisting of a series of nodes.

[0191] λ: Sensitivity coefficient, used to adjust the selection pressure. A higher λ value makes individuals with high fitness more likely to be selected.

[0192] f(s j ): The fitness values ​​of other individuals.

[0193] e: natural logarithm base.

[0194] rand(0, 1): A random number uniformly distributed in the interval [0, 1].

[0195] η: Balance weight, used to adjust the relative importance between environmental prediction and material characteristics impact.

[0196] μ and ν: sensitivity coefficients used to adjust for environmental conditions that deviate from the ideal value f ideal And the impact index deviates from the threshold E threshold degree of impact.

[0197] f ideal : Ideal fitness value, indicating the desired optimal fitness standard.

[0198] E threshold : Threshold value of road construction conditions, indicating the acceptable range of road construction impact.

[0199] E(s i ): Impact value of road construction conditions on the ith route.

[0200] The following is a brief introduction to the design reasons of each sub-item:

[0201] : Path length is an important component of distribution cost. A shorter path means lower fuel consumption and less time wasted. Introducing exponential factor δ L Penalties for long paths can be strengthened to ensure that the system prefers shorter paths.

[0202] :The estimated transportation time directly affects the distribution efficiency. Shorter transportation time can deliver emergency supplies to the destination faster. Introducing the exponential factor δ T Penalties for long transport times can be strengthened to ensure that the system prioritizes faster routes.

[0203] :The traffic condition prediction results can help the system avoid possible congested sections in advance. Introducing the exponential factor δ C It can increase attention to future changes in traffic conditions and ensure that the system chooses a path with smoother current and future traffic conditions.

[0204] :Road construction may cause traffic disruption or delay. Introducing exponential factor δ E Avoidance of construction sections can be strengthened to ensure that the system avoids areas under construction as much as possible.

[0205] The reason why this formula adds up the sub-items is that the impact of each factor on fitness is independent and important. By adding them together, all factors can be considered comprehensively to ensure that the final route is the best result in all aspects. i ) and estimated transportation time T(s) i ) is the direct physical and time cost and needs to be given priority. Traffic condition prediction result C(s i ) and road construction conditions E(s i ) is a dynamic factor that will affect future transportation efficiency and also needs to be taken into consideration. Through the weighted summation method, the system can flexibly adjust the importance of each factor according to the actual situation, so as to find a delivery route with the highest comprehensive benefit.

[0206] Fitness function f(s i ) is designed to comprehensively consider four important factors: route length, estimated transportation time, traffic condition prediction results, and road construction conditions. Each item has its own unique importance. Through the weighted summation method, it can ensure that the system can quickly and accurately select the optimal distribution route in a complex and changing traffic environment, thereby improving the efficiency and reliability of emergency material distribution. This design not only improves the accuracy of path planning, but also enhances the flexibility and adaptability of the system, ensuring that emergency materials can reach their destination in the shortest time and successfully complete the rescue mission.

[0207] This part measures the current fitness f(s i ) and the ideal fitness f ideal The difference between the two. Using the exponential function It can smoothly reflect the impact of the gap on the score. When the gap is large, the score will be significantly reduced; when the gap is small, the score is close to 1. By multiplying the weight η, the importance of environmental prediction (fitness deviation) in the total score can be adjusted.

[0208] This part measures the road construction situation E(s i ) and the acceptable threshold E threshold The difference between the two. Also using the exponential function To smoothly reflect the impact of the gap on the score. When the gap is large, the score will be significantly reduced; when the gap is small, the score is close to 1. By multiplying the weight 1-η, the importance of the material characteristics effect (road construction deviation) in the total score can be adjusted.

[0209] The reason why this formula adds up the sub-items is that the impact of environmental prediction (fitness deviation) and material characteristics (road construction deviation) on the comprehensive benefit score are independent but equally important. By adding them together, these two factors can be comprehensively considered to ensure that the final score can comprehensively evaluate the pros and cons of each route. Environmental prediction (fitness deviation) reflects the gap between the current fitness and the ideal state, which directly affects the distribution efficiency. The impact of material characteristics (road construction deviation) reflects the impact of road construction on distribution, especially in the distribution of emergency materials, where road construction may cause delays or interruptions, so special attention needs to be paid. Through the weighted summation method, the system can flexibly adjust the importance of the two factors according to the actual situation, so as to find a distribution route with the highest comprehensive benefit.

[0210] Comprehensive benefit score B(s i ) is designed to further optimize the selection of candidate routes. By introducing an additional scoring mechanism, the fitness deviation and road construction deviation are comprehensively considered to ensure that the final selected route is not only highly fit, but also meets various constraints in actual operation. By adjusting the weight η, the impact of environmental prediction and material characteristics can be flexibly weighed in different situations. The use of an exponential function to smoothly reflect the impact of the gap on the score makes the score more accurate and reasonable. Comprehensive consideration of multiple factors ensures that the selected route is optimal in all aspects, thereby improving the efficiency and reliability of emergency material distribution. Through such a design, the system can quickly and accurately select the optimal distribution route in a complex and changeable traffic environment, thereby improving the efficiency and success rate of emergency material distribution.

[0211] Here is a specific example:

[0212] Suppose a major traffic accident occurs in a city and a batch of emergency supplies need to be urgently deployed to the accident site. The system activates the intelligent path planning function, collects and integrates relevant information based on the latest status information, the location of emergency needs, and the location of all currently available emergency supplies, and obtains accurate basic data D.

[0213] Basic data definition:

[0214] D={P s , P d , {P i}}

[0215] Among them, P s It is the location of the emergency supplies storage place; d is the location of the emergency need location; i} is the location set of all currently available first aid supplies.

[0216] Based on accurate basic data D, define the population size N = 50 and select the crossover probability pc =0.8, mutation probability p m =0.1, and initialize an initial population S0 containing randomly generated potential delivery routes.

[0217] According to the basic data D, a complex fitness function f(s i ), used to evaluate each potential delivery route s i The fitness function considers the factors including the path length L(s i ), estimated transportation time T(s i ), traffic condition prediction result C(s i ) and road construction conditions that affect transportation efficiency E(s i ), and get the fitness evaluation standard:

[0218]

[0219] Assume that the influence weights and index factors of each factor are:

[0220] w L =0.4,δ L =1;

[0221] w T =0.3,δ T =1.2;

[0222] w C =0.2,δ C =1.5;

[0223] w E =0.1,δ E =1;

[0224] Based on the fitness evaluation criterion f(s i ), using the selection, crossover and mutation operations of the genetic algorithm, the potential delivery routes in the initial population S0 are iteratively optimized to generate the optimized population S opt .

[0225] The roulette wheel selection method is used to select the better individuals to enter the next generation population S t+1 .

[0226] Calculate the selection probability p select (s i ):

[0227]

[0228] Assuming the sensitivity coefficient λ = 0.5, calculate the selection probability of each individual.

[0229] With crossover probability pc = 0.8 for two selected individuals s a and b Perform crossover to generate new individuals s a' and b' .

[0230] With mutation probability p m = 0.1 for some individuals s i Perform mutations to introduce diversity and prevent the algorithm from converging prematurely.

[0231] After multiple rounds of iterations, the optimized population S is finally obtained. opt According to the optimized population S opt , filter out multiple potential delivery routes that meet the preset conditions and form a candidate route set P candidate , and record the paths in the candidate path set in the central monitoring system:

[0232] P candidate ={s i ∈S opt |f(s i )≤θ}

[0233] Assuming that the preset fitness threshold θ=100, potential delivery routes whose fitness values ​​do not exceed θ are screened out.

[0234] In order to further optimize the selection of candidate paths, an additional scoring mechanism is introduced to calculate the comprehensive benefit score B(s i ):

[0235]

[0236] Assuming the balance weight η = 0.7, the sensitivity coefficient μ = 0.5, ν = 0.3, the ideal fitness value f ideal =90, threshold E for road construction conditions threshold =2, calculate the comprehensive benefit score of each candidate path.

[0237] Assume that after genetic algorithm optimization, the following potential delivery routes and their fitness values ​​are obtained:

[0238] s1: f(s1) = 85;

[0239] s2: f(s2) = 95;

[0240] s3: f(s3) = 105;

[0241] Screen out potential delivery routes s1 and s2 whose fitness values ​​do not exceed θ = 100, and calculate their comprehensive benefit scores:

[0242] For s1:

[0243]

[0244] Assume E(s1)=1:

[0245] B(s1)=0.7·(1-e -0.5·5 )+0.3·(1-e -0.3·1 )

[0246] B(s1)=0.7203

[0247] For s2:

[0248]

[0249] Assume E(s2) = 2:

[0250] B(s2)=0.7·(1-e -0.5·5 )+0.3·(s1-e -0.3·0 )

[0251] B(s2)=0.6425

[0252] According to the calculation results, the comprehensive benefit score of candidate route s1 B(s1) = 0.7203 is higher than the comprehensive benefit score of s2 B(s2) = 0.6425. Therefore, the system finally selected s1 as the optimal delivery route to ensure that emergency supplies can reach the accident site in the shortest time.

[0253] In this way, the system not only achieves accurate management and real-time monitoring of emergency supplies, but also significantly improves the efficiency and accuracy of distribution, ensuring that emergency supplies can reach their destination in the shortest time possible and successfully complete the rescue mission. In addition, the system's prediction model is constantly learning and optimizing, which improves the accuracy of future predictions and further enhances the system's emergency response capabilities.

[0254] This application takes into account that in the management and storage of emergency supplies, it is crucial to ensure that the supplies are always in the best state of preservation during transportation and storage. Traditional environmental monitoring methods can usually only provide simple information on the location of supplies, and lack the ability to monitor the surrounding environmental parameters in real time and predict future change trends. This may cause supplies to be damaged due to unsuitable environmental conditions, especially in emergency situations, where the quality of supplies is directly related to the rescue effect.

[0255] In order to improve the intelligence level and emergency response capabilities of the emergency material management system, a method is needed to monitor environmental parameters in real time, predict future environmental change trends, and evaluate the impact of environmental conditions on material preservation in combination with material characteristics. This method can identify potential risks in advance, ensure that emergency materials are always in the best state of preservation, and improve rescue efficiency and success rate. Therefore, a new optional solution is proposed, which includes:

[0256] According to the material information file, the location information and surrounding environmental parameters of the emergency materials are collected in real time, and the environmental change trend in the future is predicted. The impact of environmental conditions on material preservation is evaluated in combination with material characteristics to obtain environmental adaptability analysis results, including:

[0257] According to the material information file, the location information and surrounding environmental parameters of the first aid materials are collected in real time by using sensor nodes deployed at the storage location of the first aid materials, and the collected data is transmitted to the central monitoring system through a low-power wide area network to obtain the latest location and environmental parameter data;

[0258] Based on the latest location and environmental parameter data E current , combined with historical environmental data E history And weather forecast information forecast , using the environmental prediction model, predicting the environmental change trend of the area where the emergency supplies are located in the future;

[0259] The predicted value of environmental conditions at future time t is predicted by the following formula:

[0260] E future (t) = α·E current +β·E history +γ·M forecast

[0261] Among them, α, β, and γ are weight coefficients, which respectively represent the relative importance of the latest environmental parameter data, historical environmental data, and meteorological forecast information in the prediction; E future (t) is a comprehensive prediction result, reflecting the environmental conditions that the area where the emergency supplies are located may face in the future time t; E current is the environmental parameter data; E history is historical environmental data; M forecast It is weather forecast information;

[0262] Based on the characteristics of the emergency supplies recorded in the material information file, assess the impact of different environmental conditions on the preservation of the emergency supplies;

[0263] The impact index I of environmental conditions on the preservation of emergency supplies is evaluated by the following formula: impact :

[0264]

[0265] Among them, w T , w H , w L , w S are the influence weights of temperature, humidity, light and shelf life; δ T , δ H , δ L , δ S are the corresponding exponential factors, which are used to adjust the influence of various environmental factors; T is the temperature value of the environment surrounding the emergency supplies; H is the relative humidity value of the environment surrounding the emergency supplies; L is the light intensity value of the environment surrounding the emergency supplies; S is the shelf life of the emergency supplies; I impact It comprehensively considers multiple environmental factors and material characteristics to assess the impact of these factors on the preservation of emergency materials;

[0266] Combined with the environmental change trend prediction results E future (t) and material characteristics assessment results I impact , using environmental adaptability analysis algorithms to assess whether current and future environmental conditions meet the storage requirements for emergency supplies;

[0267] The environmental adaptability analysis results A are evaluated by the following formula adaptability :

[0268]

[0269] Where η is the balance weight between environmental prediction and material characteristics; λ and μ are sensitivity coefficients used to adjust the deviation of environmental conditions from the ideal value E ideal And the impact index deviates from the threshold I threshold The degree of influence; e represents the base of natural logarithm; A adaptability It is a comprehensive consideration of the prediction results of environmental change trends E future (t) and material characteristics assessment results I impact , assess whether current and future environmental conditions are suitable for the storage of emergency supplies.

[0270] The following is a detailed explanation of each parameter:

[0271] α: Weight coefficient of the latest environmental parameter data. Determined through experiments and parameter adjustment, usually a positive value to reflect the importance of the current environmental conditions. The optimal value can be obtained based on historical data analysis.

[0272] β: Weight coefficient of historical environmental data. Determined through historical data analysis and expert experience, usually takes a positive value to reflect the impact of past environmental conditions on the forecast. Can be set through long-term monitoring data.

[0273] γ: Weight coefficient of weather forecast information. It is determined based on the historical accuracy and importance assessment of the weather forecast model. It is usually positive and reflects the impact of future weather changes on the environment. It can be obtained from the forecast information released by the meteorological department.

[0274] E current :The latest location and environmental parameter data are collected in real time by sensor nodes deployed at emergency material storage locations and transmitted to the central monitoring system via a low-power wide area network.

[0275] E history :Historical environmental data. Extracted from the historical database, it records the changes in environmental parameters over a period of time.

[0276] M forecast :Weather forecast information. Obtained from the forecast information released by the meteorological department, it reflects the weather change trend in the future.

[0277] w T :The weight of temperature influence. It is determined based on the material property archive and historical data analysis. It is usually a positive value, reflecting the influence of temperature on material preservation.

[0278] T: The temperature value of the environment surrounding the emergency supplies. Collected in real time through sensor nodes.

[0279] δ T : Exponential factor of temperature, used to adjust the degree of temperature influence. Determined by experiments and parameter adjustment, usually takes a positive value to increase the penalty for extreme temperatures.

[0280] w H :The weight of humidity. It is determined based on the material property archive and historical data analysis. It is usually a positive value, reflecting the degree of influence of humidity on material preservation.

[0281] H: Relative humidity value of the environment around the emergency supplies. Collected in real time through sensor nodes.

[0282] δ H : Exponential factor of humidity, used to adjust the degree of humidity influence. Determined by experiments and parameter adjustment, usually takes a positive value to increase the penalty for high humidity.

[0283] w L : The weight of the impact of light. It is determined based on the material property archives and historical data analysis. It is usually a positive value, reflecting the degree of influence of light on the preservation of materials.

[0284] L: Light intensity value of the environment surrounding the emergency supplies. Collected in real time through sensor nodes.

[0285] δ L: Exponential factor of illumination, used to adjust the degree of illumination influence. Determined by experiments and parameter adjustment, usually takes a positive value to increase the penalty for strong light exposure.

[0286] w S :The weight of the impact of the shelf life. It is determined based on the material characteristics archive and historical data analysis. It is usually a positive value, reflecting the impact of the shelf life on the preservation of the material.

[0287] S: Shelf life of emergency supplies. Extracted from the supplies information file.

[0288] δ S : Exponential factor of shelf life, used to adjust the degree of shelf life impact. Determined through experiments and parameter adjustment, usually takes a positive value to increase attention to materials that are about to expire

[0289] η: Balance weight, used to adjust the relative importance between environmental prediction (environmental change trend) and material characteristics. It is set according to actual conditions and needs, and usually takes a value between [0, 1], indicating the importance ratio of the two. The optimal value can be determined through historical data analysis and expert experience.

[0290] λ and μ: sensitivity coefficients, used to adjust for environmental conditions that deviate from the ideal value E ideal And the impact index deviates from the threshold I threshold The degree of influence. Determined through experiments and parameter adjustment, usually a positive value is taken to enhance the sensitivity to deviation values. It can be optimized according to actual test results to ensure that the model has good generalization ability. It is determined based on material property archives and historical data analysis. It is usually an empirical value that represents the standard of the optimal solution. It can be set based on past successful storage environment data.

[0291] I threshold :The threshold of the impact index, indicating the acceptable impact range. It is determined based on the material characteristic archive and historical data analysis, usually an empirical value, indicating the maximum acceptable impact value. Relevant information can be extracted from historical successful storage cases.

[0292] E future (t): The predicted value of environmental conditions in the future time t. Calculated by the environmental prediction model, it reflects the changing trend of future environmental conditions.

[0293] I impact :The impact index of environmental conditions on the preservation of emergency supplies. Calculated by the impact index formula, it reflects the impact of current environmental conditions on the preservation of supplies.

[0294] The following is a brief introduction to the design reasons of each sub-item:

[0295] α·E current: This part measures the importance of the current environmental conditions. The latest environmental parameters directly reflect the current actual situation, so they have a higher weight when predicting future environmental conditions. Using multiplication operations can flexibly adjust the influence of current environmental conditions to ensure that the prediction results can respond to the latest environmental changes in a timely manner.

[0296] β·E history : This section measures the trend of historical environmental conditions. Historical data provides context for environmental changes and helps predict future trends. Using multiplication operations allows flexibility in adjusting the impact of historical environmental conditions to ensure that the forecast results take into account long-term trends.

[0297] γ·M forecast : This part measures the impact of future weather changes. Weather forecast information provides weather trends over a period of time in the future, which is crucial for predicting environmental conditions. Using multiplication operations can flexibly adjust the impact of weather forecast information to ensure that the forecast results can take into account the impact of future weather changes.

[0298] The reason why this formula adds up the sub-items is that the importance of each factor to the environmental condition prediction is independent and complementary. By adding them together, all factors can be taken into account to ensure that the final prediction result is more accurate and comprehensive. Specifically: the current environmental condition E current It reflects the latest actual situation and is particularly important for short-term forecasts. history It provides background information on long-term trends and is helpful for medium-term forecasts. forecast It provides the trend of future weather changes, which is crucial for long-term forecasting. Through the weighted summation method, the system can flexibly adjust the weight of each factor according to the actual situation, so as to find the best forecast result that comprehensively considers current, historical and future factors.

[0299] This formula is designed to predict the environmental change trend in the area where the emergency supplies are located in the future. By comprehensively considering the latest environmental parameters, historical environmental data and weather forecast information, the formula ensures the accuracy, reliability and flexibility of the prediction results. The specific advantages are as follows: Combining the latest environmental parameters, historical data and weather forecasts, the prediction results are closer to the actual situation. Through multi-source data fusion, the uncertainty brought by a single data source is reduced and the stability of the prediction is improved. By adjusting the weight coefficients α, β and γ, different environmental changes can be flexibly responded to in different situations to ensure that the prediction results are adapted to various scenarios. This design enables the system to quickly and accurately predict future environmental conditions in a complex and changing environment, providing strong support for the storage and management of emergency supplies, and ensuring that the supplies are always in the best state of preservation.

[0300] :This part measures the impact of temperature on the preservation of emergency supplies. Temperature is one of the important factors affecting the preservation of supplies, especially for supplies such as medicines that need to be stored at low temperatures. The multiplication operation can flexibly adjust the degree of temperature influence, and the exponential factor δ is introduced T Penalties for extreme temperatures can be increased to ensure more accurate forecasts.

[0301] :This part measures the effect of humidity on the preservation of emergency supplies. Humidity is also an important environmental factor, especially for supplies that are easily affected by moisture. The multiplication operation can flexibly adjust the degree of humidity, and the exponential factor δ is introduced H The penalty for high humidity can be increased to ensure more accurate prediction results.

[0302] This section measures the effect of light on the preservation of emergency supplies. Light intensity may affect the stability of some supplies, especially light-sensitive medicines. The multiplication operation can flexibly adjust the degree of light influence, and introduce an exponential factor δ L The penalty for strong light exposure can be increased to ensure more accurate prediction results.

[0303] :This part measures the impact of shelf life on the preservation of emergency supplies. The shelf life is directly related to the effectiveness and safety of the supplies. The multiplication operation can flexibly adjust the impact of the shelf life, and the exponential factor δ is introduced S It can increase attention to materials that are about to expire and ensure more accurate forecast results.

[0304] The reason why this formula adds up the sub-items is that the impact of each environmental factor on the preservation of first aid supplies is independent and complementary. By adding them together, all factors can be taken into account to ensure that the final evaluation result is more comprehensive and accurate. Specifically: Temperature T directly affects the chemical stability of materials, especially in high or low temperature environments. Humidity H affects the physical and chemical properties of materials, especially materials that are easily hygroscopic or damp. Light L affects the stability of light-sensitive materials, such as certain medicines and biological products. The shelf life S is directly related to the effectiveness and safety of materials, especially for first aid supplies with strict expiration requirements. Through the weighted summation method, the system can flexibly adjust the weight of each factor according to the actual situation, so as to find the best evaluation result that comprehensively considers multiple environmental factors.

[0305] This formula is designed to evaluate the impact of environmental conditions on the preservation of emergency supplies. By comprehensively considering the four important factors of temperature, humidity, light and shelf life, the formula ensures the accuracy, reliability and flexibility of the evaluation results. The specific advantages are as follows: Combining the four important factors of temperature, humidity, light and shelf life makes the evaluation results closer to the actual situation. By fusing multi-source data, the uncertainty caused by a single factor is reduced and the stability of the evaluation is improved. By adjusting the weight coefficient w T , w H , w L , w S and the exponential factor δ T , δ H , δ L , δ S It can flexibly respond to different environmental changes in different situations to ensure that the evaluation results are suitable for various scenarios. This design enables the system to quickly and accurately evaluate the storage conditions of emergency supplies in complex and changing environments, providing strong support for material management and emergency response, and ensuring that the materials are always in the best state of preservation.

[0306] :This part measures the predicted value of future environmental conditions E future (t) and ideal environmental conditions E ideal The difference between the two. Using the exponential function The effect of the gap on the score can be smoothly reflected. When the gap is large, the score will be significantly reduced; when the gap is small, the score is close to 1. By multiplying the weight η, the importance of environmental prediction (environmental change trend) in the total score can be adjusted.

[0307] :This part measures the impact index I impact and the acceptable threshold I threshold The difference between the two. Also using the exponential function To smoothly reflect the impact of the gap on the score. When the gap is large, the score will be significantly reduced; when the gap is small, the score is close to 1. By multiplying the weight 1-η, the importance of the material characteristics in the total score can be adjusted.

[0308] The reason why this formula adds up the sub-items is that the impact of environmental forecasts (environmental change trends) and material characteristics on the comprehensive benefit score are independent but equally important. By adding them together, these two factors can be comprehensively considered to ensure that the final score can comprehensively evaluate the pros and cons of each route. Specifically, environmental forecasts (environmental change trends) reflect the changing trends of future environmental conditions, which directly affect the safety and effectiveness of material preservation. The impact of material characteristics reflects the specific impact of current environmental conditions on material preservation, especially in the preservation of emergency materials, where environmental conditions are directly related to the quality and validity period of the materials. Through weighted summation, the system can flexibly adjust the importance of the two factors according to actual conditions, so as to find a storage plan with the highest comprehensive benefit.

[0309] This formula is designed to evaluate whether the current and future environmental conditions meet the storage requirements of emergency supplies. By introducing an additional scoring mechanism, the predicted results of environmental change trends are comprehensively considered. future (t) and material characteristics assessment results I impact , ensuring that the storage conditions finally selected are not only highly adaptable, but also meet various constraints in actual operations. By adjusting the weight ηη, the impact of environmental prediction and material characteristics can be flexibly weighed in different situations. The use of exponential functions to smoothly reflect the impact of the gap on the score makes the score more accurate and reasonable. Taking multiple factors into consideration, it ensures that the selected storage conditions are optimal in all aspects, improving the safety and reliability of emergency material storage. Through such a design, the system can quickly and accurately evaluate storage conditions in complex and changing environments, improve the intelligence level of emergency material management and emergency response capabilities, and ensure that the materials are always in the best preservation state.

[0310] Here is a specific example:

[0311] Suppose a city hospital needs to ensure that its emergency medicines and equipment are always kept in the best condition during storage. The system activates the intelligent environmental monitoring function, collects the location information and surrounding environmental parameters of emergency materials in real time according to the records in the material information file, predicts the environmental change trend in the future, and evaluates the impact of environmental conditions on material preservation based on the characteristics of the materials.

[0312] Data definition: E current is the latest location and environmental parameter data; E history is historical environmental data; M forecast It is weather forecast information.

[0313] According to the material information archive, the sensor nodes (such as temperature and humidity sensors, light intensity meters, etc.) deployed at the storage location of emergency materials are used to collect the location information and surrounding environmental parameters (such as temperature, humidity, and light intensity) of the emergency materials in real time, and the collected data is transmitted to the central monitoring system through the low-power wide area network to obtain the latest location and environmental parameter data E current .

[0314] Environmental change trend prediction type, predicting the environmental change trend of the area where emergency supplies are located in the future:

[0315] E future (t) = α·E current +β·E history +γ·M forecast

[0316] Assume that the weight coefficients are: α = 0.5; β = 0.3; γ = 0.2;

[0317] Assuming the current time is t0, predict the environmental condition prediction value E within the future time t future (t). For example, to predict the temperature trend in the next 24 hours:

[0318] E future (t) = 0.5·E current +0.3·E history +0.2·M forecast

[0319] Assumption E current =25℃, E history =23℃,M forecast =27℃:

[0320] E future (t) = 0.5·25 + 0.3·23 + 0.2·27

[0321] E future (t) = 12.5 + 6.9 + 5.4

[0322] E future (t)=24.8℃

[0323] According to the characteristics of emergency supplies recorded in the material information file, the impact of different environmental conditions on the preservation of emergency supplies is evaluated:

[0324]

[0325] Assume that the influence weights and index factors of each factor are:

[0326] w T =0.4,δ T=1.2; w H =0.3,δ H =1.5; w L =0.2,δ L =1.0; w S =0.1,δ S =1.0;

[0327] Assume the current environmental conditions are:

[0328] Temperature T = 25°C; humidity H = 60%; light intensity L = 500 lux; shelf life S = 12 months;

[0329] I impact =0.4·25 1.2 +0.3 60 1.5 +0.2 500 1.0 +0.1 12 1.0

[0330] I impact =0.4·70.71+0.3·226.27+0.2·500+0.1·12

[0331] I impact =28.28+67.88+100+1.2

[0332] I impact =197.36

[0333] Combined with the prediction results of environmental change trend E future (t) and material characteristics assessment results I impact , using the environmental adaptability analysis algorithm to evaluate whether the current and future environmental conditions meet the storage requirements of emergency supplies:

[0334]

[0335] Assume that the balance weight η = 0.7, the sensitivity coefficient λ = 0.5, μ = 0.3, and the ideal environmental conditions E ideal =20℃, impact index threshold I threshold =150;

[0336] A adaptability =0.7·(1-e -0.5·|24.8-20| )+0.3·(1-e -0.3·|197.36-150| )

[0337] A adaptability =0.9365

[0338] According to the calculation results, the environmental adaptability analysis results A adaptability=0.9365, indicating that the current and future environmental conditions are basically suitable for the storage requirements of emergency supplies. Although the temperature is expected to reach 24.8℃ in the next 24 hours, slightly higher than the ideal temperature of 20℃, it is still within the acceptable range. Taking into account factors such as temperature, humidity, light intensity and shelf life, the evaluation results show that the impact index of current environmental conditions on the preservation of emergency supplies is 197.36, slightly higher than the set threshold of 150, but generally still within a safe range.

[0339] Therefore, the system confirms that the current environmental conditions basically meet the storage requirements of emergency supplies, and no additional measures are needed immediately. However, it is recommended to continue to closely monitor environmental changes, especially in terms of temperature and humidity, to ensure that emergency supplies are always in the best state of preservation. This intelligent environmental monitoring and prediction mechanism significantly improves the intelligence level and emergency response capabilities of the emergency supplies management system, ensures that the quality of supplies is not affected, and ensures the smooth progress of rescue work.

[0340] Figure 2 The present application provides a schematic diagram of a first aid material tracking system based on the Internet of Things, such as Figure 2 As shown, the system includes:

[0341] The allocation and binding module 21 is used to allocate a unique electronic tag identifier to each first aid material, and securely bind it with the specific information of the first aid material to generate a material information file;

[0342] The collection prediction module 22 is used to collect the location information and surrounding environmental parameters of the emergency supplies in real time according to the supply information file, and predict the environmental change trend in the future, and evaluate the impact of environmental conditions on the storage of supplies in combination with the characteristics of the supplies to obtain the environmental adaptability analysis results;

[0343] The detection and identification module 23 is used to set the safety threshold range suitable for different types of emergency supplies based on the results of the environmental adaptability analysis. When the detected environmental parameters exceed the set safety threshold or the supplies are moved without authorization, the abnormal event is identified by using an abnormal detection algorithm, and the triggering situation of the early warning mechanism is recorded and updated in the supplies information file to obtain the latest status information;

[0344] The simulation selection module 24 is used to calculate multiple potential optimal delivery routes based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies using a genetic algorithm, and simulate the transportation time and cost under different routes in combination with a real-time traffic condition prediction model and traffic flow simulation technology, select the plan with the highest comprehensive benefit, and continuously adjust the path planning strategy based on a reinforcement learning algorithm to obtain an optimized delivery route;

[0345] Construction module 25 is used to build a resource allocation visualization management platform based on the material information file, environmental adaptability analysis results, early warning mechanism triggering conditions and the optimized distribution route. The resource allocation visualization management platform allows managers to intuitively view the distribution, status and transportation progress of each emergency material through a map view, and supports the immediate issuance and adjustment of material dispatch instructions.

[0346] Figure 2 The IoT-based emergency supplies tracking system can perform Figure 1 The implementation principle and technical effect of the first aid material tracking method based on the Internet of Things described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the first aid material tracking system based on the Internet of Things in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0347] In one possible design, Figure 2 The IoT-based emergency supplies tracking system of the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0348] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0349] The processing component 32 is used to: assign a unique electronic tag identifier to each first aid material, and securely bind it with the specific information of the first aid material to generate a material information file; based on the material information file, collect the location information and surrounding environmental parameters of the first aid material in real time, predict the environmental change trend in the future, and evaluate the impact of environmental conditions on material preservation in combination with material characteristics to obtain environmental adaptability analysis results; based on the results of the environmental adaptability analysis, set a safety threshold range suitable for different types of first aid materials. When the detected environmental parameters exceed the set safety threshold or the material is unauthorizedly moved, use the anomaly detection algorithm to identify abnormal events, record and update the triggering situation of the early warning mechanism in the material information file, and obtain to the latest status information; based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal distribution routes, and the transportation time and cost under different routes are simulated in combination with the real-time traffic condition prediction model and traffic flow simulation technology, the highest comprehensive benefit plan is selected, and the path planning strategy is continuously adjusted based on the reinforcement learning algorithm to obtain the optimized distribution route; based on the material information archive, the environmental adaptability analysis results, the triggering of the early warning mechanism and the optimized distribution route, a resource allocation visualization management platform is constructed, and the resource allocation visualization management platform allows managers to intuitively view the distribution, status and transportation progress of each emergency material through a map view, and supports the immediate issuance and adjustment of material dispatch instructions.

[0350] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0351] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component 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 disk.

[0352] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0353] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0354] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0355] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0356] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a method for tracking emergency supplies based on the Internet of Things.

[0357] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0358] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0359] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0360] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for tracking emergency supplies based on the Internet of Things, characterized in that: include: Assign a unique electronic tag identifier to each emergency material, and securely bind it with the specific information of the emergency material to generate a material information file; According to the material information file, the location information and surrounding environmental parameters of the emergency materials are collected in real time, and the environmental change trend in the future is predicted. The impact of environmental conditions on the preservation of materials is evaluated in combination with the material characteristics to obtain environmental adaptability analysis results; Based on the results of the environmental adaptability analysis, a safety threshold range suitable for different types of emergency supplies is set. When the detected environmental parameters exceed the set safety threshold or unauthorized movement of supplies occurs, an abnormal event is identified using an anomaly detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the supply information file to obtain the latest status information; Based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal delivery routes, and the transportation time and cost under different routes are simulated by combining the real-time traffic condition prediction model and traffic flow simulation technology, and the plan with the highest comprehensive benefit is selected. The path planning strategy is continuously adjusted based on the reinforcement learning algorithm to obtain the optimized delivery route; Based on the material information archive, environmental adaptability analysis results, early warning mechanism triggering conditions and the optimized distribution routes, a resource allocation visualization management platform is constructed. The resource allocation visualization management platform allows managers to intuitively view the distribution, status and transportation progress of each emergency material through a map view, and supports the immediate issuance and adjustment of material dispatch instructions.

2. The method according to claim 1, characterized in that Based on the result of the environmental adaptability analysis, the safety threshold range adapted to different types of emergency supplies is set. When the detected environmental parameters exceed the set safety threshold or unauthorized movement of supplies occurs, an abnormal event is identified using an abnormality detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the supply information file to obtain the latest status information, including: Based on the results of the environmental adaptability analysis, the environmental parameters are evaluated according to the storage requirements of different types of first aid supplies to obtain the safety threshold ranges suitable for the different types of first aid supplies, and the safety threshold ranges are stored in the central monitoring system; Using sensor nodes deployed in the emergency material storage environment, the environmental parameters are collected in real time, and the data is transmitted to a central monitoring system. The central monitoring system monitors the changes in environmental parameters in real time based on the stored safety threshold range. When it is detected that the environmental parameters exceed the set safety threshold or the materials are moved without authorization, the current situation is evaluated based on the environmental parameters and the material location information using an anomaly detection algorithm to identify whether it is an abnormal event, generate an abnormal event identification result, and record the abnormal event identification result in the central monitoring system; Based on the abnormal event identification result, when it is confirmed as an abnormal event, the early warning mechanism is immediately triggered, a notification is immediately sent to the preset contact, and an early warning report containing the nature, time, location and information of emergency supplies involved in the abnormal event is generated, and the early warning report is also stored in the central monitoring system; According to the early warning report, the central monitoring system records the triggering of the early warning mechanism and updates it to the material information file to obtain the latest status information.

3. The method according to claim 2, characterized in that The sensor nodes deployed in the emergency material storage environment are used to collect the environmental parameters in real time and transmit the data to the central monitoring system. The central monitoring system monitors the changes of the environmental parameters in real time based on the stored safety threshold range. When it is detected that the environmental parameters exceed the set safety threshold or the materials are moved without authorization, the abnormality detection algorithm is used to evaluate the current situation according to the environmental parameters and the material location information, identify whether it is an abnormal event, generate an abnormal event identification result, and record the abnormal event identification result in the central monitoring system, including: The sensor nodes deployed in the emergency material storage environment are used to collect the environmental parameters in real time, and the data is transmitted to the central monitoring system through a low-power wide area network to obtain the latest environmental parameter data; Based on the latest environmental parameter data, the central monitoring system monitors the environmental parameter changes in real time according to the stored safety threshold range, and generates an environmental exceeding signal when it is detected that the environmental parameter exceeds the set safety threshold; In addition to the environmental parameters, the sensor node also monitors the location information of the emergency supplies. When unauthorized movement of the supplies is detected, a corresponding alarm signal is immediately generated, and the alarm signal and the location information are transmitted to the central monitoring system to obtain unauthorized movement event data; Based on the environmental excess signal and the unauthorized movement event data, the central monitoring system uses an anomaly detection algorithm to evaluate the current situation, identify whether it is an abnormal event, and generate an abnormal event evaluation result.

4. The method according to claim 3, characterized in that Based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies, a genetic algorithm is used to calculate multiple potential optimal delivery routes, and the transportation time and cost under different routes are simulated by combining the real-time traffic condition prediction model and traffic flow simulation technology, and the plan with the highest comprehensive benefit is selected. The path planning strategy is continuously adjusted based on the reinforcement learning algorithm to obtain the optimized delivery route, including: Based on the latest status information, the location of emergency needs, and the location of all currently available emergency supplies, relevant information is collected and integrated to obtain accurate basic data; Using a genetic algorithm, based on the accurate basic data, multiple potential delivery routes from the emergency material storage location to the emergency demand location are calculated to generate a candidate path set, and the paths in the candidate path set are recorded in the central monitoring system; Based on the candidate path set and in combination with the real-time traffic condition prediction model, the traffic flow on each path is predicted, and based on the historical traffic data and the real-time traffic information, the traffic change trend in different time periods is predicted to obtain the traffic condition prediction result, and the traffic condition prediction result is stored in the central monitoring system; According to the traffic condition prediction results, using traffic flow simulation technology, for each path in the candidate path set, simulating transportation time and cost, considering factors affecting transportation efficiency, generating a detailed transportation evaluation report for each route, and recording the detailed transportation evaluation report in the central monitoring system; Based on the transport evaluation report, select the delivery route with the highest comprehensive benefit from the candidate route set, generate an optimal route selection result, and record the optimal route selection result in a central monitoring system; Based on the optimal path selection results and implementation status, the reinforcement learning algorithm is used to continuously adjust the path planning strategy to generate an optimized delivery route.

5. The method according to claim 4, characterized in that The method of using a genetic algorithm to calculate multiple potential delivery routes from a first aid material storage location to a first aid demand location based on the accurate basic data, generating a candidate path set, and recording the paths in the candidate path set in the central monitoring system includes: Collect and integrate relevant information based on the latest status information, the location of emergency needs, and the location of all currently available emergency supplies to obtain accurate basic data; Based on the accurate basic data, using a genetic algorithm, the distribution routes from the emergency material storage location to the emergency demand location are initialized, the basic parameters required by the genetic algorithm such as population size, selection crossover probability, and mutation probability are defined, and an initial population including randomly generated potential distribution routes is initialized to obtain an initial population; Based on the basic data, a fitness function is designed to evaluate the pros and cons of each potential delivery route, wherein the fitness function considers factors including path length, estimated transportation time, traffic condition prediction results, and road construction conditions, and obtains a fitness evaluation standard; Based on the fitness evaluation criteria, the potential delivery routes in the initial population are iteratively optimized using the selection, crossover and mutation operations of the genetic algorithm to generate an optimized population; Based on the optimized population, multiple potential delivery routes that meet preset conditions are screened to form a candidate path set, and the paths in the candidate path set are recorded in a central monitoring system.

6. The method according to claim 4, characterized in that The method predicts the traffic flow on each path based on the candidate path set and in combination with the real-time traffic condition prediction model, predicts the traffic change trend in different time periods based on historical traffic data and real-time traffic information, obtains traffic condition prediction results, and stores the traffic condition prediction results in the central monitoring system, including: Based on the candidate path set, extract key section information of each path, organize the key section information, and obtain basic data for traffic flow prediction; Based on the basic data, sensor nodes and traffic cameras are used to collect data on key sections in combination with historical traffic data and real-time road condition information to obtain comprehensive traffic data; Based on the comprehensive traffic data, a real-time traffic condition prediction model is used to predict the traffic flow on each path, taking time factors and special events into consideration, predicting traffic change trends in different time periods, generating traffic condition prediction results, and recording the traffic condition prediction results in a central monitoring system.

7. The method according to claim 1, characterized in that According to the material information file, the location information and surrounding environmental parameters of the emergency materials are collected in real time, and the environmental change trend in the future is predicted. The impact of environmental conditions on material preservation is evaluated in combination with material characteristics to obtain environmental adaptability analysis results, including: According to the material information file, the location information and surrounding environmental parameters of the first aid materials are collected in real time by using sensor nodes deployed at the storage location of the first aid materials, and the collected data is transmitted to the central monitoring system through a low-power wide area network to obtain the latest location and environmental parameter data; Based on the latest location and environmental parameter data, combined with historical environmental data and weather forecast information, using an environmental prediction model, predict the environmental change trend of the area where the emergency supplies are located in the future, generate environmental change trend prediction results, and store the environmental change trend prediction results in a central monitoring system; According to the characteristics of the emergency materials recorded in the material information file, the influence of different environmental conditions on the preservation of the emergency materials is evaluated to obtain a material characteristic evaluation result, and the material characteristic evaluation result is updated in the material information file; In combination with the environmental change trend prediction results and the material characteristics assessment results, an environmental adaptability analysis algorithm is used to evaluate whether current and future environmental conditions meet the storage requirements for emergency supplies, obtain environmental adaptability analysis results, and update the environmental adaptability analysis results to the material information file.

8. An emergency supplies tracking system based on the Internet of Things, characterized in that: include: An allocation and binding module is used to allocate a unique electronic tag identifier to each first aid material, and securely bind it with the specific information of the first aid material to generate a material information file; The collection and prediction module is used to collect the location information and surrounding environmental parameters of the emergency supplies in real time according to the material information file, and predict the environmental change trend in the future, and evaluate the impact of environmental conditions on the preservation of materials in combination with the material characteristics to obtain environmental adaptability analysis results; A detection and identification module is used to set a safety threshold range suitable for different types of emergency supplies based on the results of the environmental adaptability analysis. When the detected environmental parameters exceed the set safety threshold or unauthorized movement of supplies occurs, an abnormal event is identified using an abnormal detection algorithm, and the triggering of the early warning mechanism is recorded and updated in the supply information file to obtain the latest status information; A simulation selection module is used to calculate multiple potential optimal delivery routes based on the latest status information, the location of emergency needs and the location of all currently available emergency supplies using a genetic algorithm, and to simulate the transportation time and cost under different routes by combining a real-time traffic condition prediction model and traffic flow simulation technology, and select the plan with the highest comprehensive benefit, and to continuously adjust the path planning strategy based on a reinforcement learning algorithm to obtain an optimized delivery route; A construction module is used to build a resource allocation visualization management platform based on the material information archive, environmental adaptability analysis results, early warning mechanism triggering conditions and the optimized distribution routes. The resource allocation visualization management platform allows managers to intuitively view the distribution, status and transportation progress of various emergency materials through a map view, and supports the immediate issuance and adjustment of material dispatch instructions.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a first aid material tracking method based on the Internet of Things as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an emergency material tracking method based on the Internet of Things as described in any one of claims 1 to 7 is implemented.

Images