Emergency rescue and disaster relief plan generation method and device

Abstract

The invention relates to the technical field of emergency rescue, in particular to an emergency rescue and disaster relief plan generation method and device, more comprehensive information support is provided for generation of an emergency rescue and disaster relief plan by fusing data of multiple professional fields to form spatial data, and the comprehensive data processing mode has the advantage that the emergency rescue and disaster relief plan generation efficiency is improved. The emergency rescue and disaster relief plan better conforms to the actual situation, and the practicability and operability of the emergency rescue and disaster relief plan are improved; the emergency rescue and disaster relief plan can be automatically generated according to the acquired spatial data in combination with the characteristics of the current disaster, so that the efficiency and accuracy of generating the emergency rescue and disaster relief plan are improved; and the generated initial plan is continuously and dynamically adjusted and optimized according to the updated spatial data, so that the method can adapt to continuously changing disaster situations and disaster relief requirements.

Description

Technical Field

[0001] The present invention relates to the field of emergency rescue technology, and in particular to a method and device for generating an emergency rescue plan. Background Art

[0002] Large-scale geological disasters such as earthquakes, landslides and mud-rock flows frequently occur in southwest my country. The northwest region is dry and rainless, and there are many mountainous areas, which makes it prone to natural disasters such as mountain torrents and mud-rock flows. In addition, Tibet, Qinghai and Yunnan-Guizhou regions are at high altitudes and often face disastrous weather such as strong winds, heavy snow and low temperatures.

[0003] In the face of extreme meteorological and geological disasters, emergency rescue and relief efforts are needed for all types of disasters. However, given the large differences in characteristics of the disaster-stricken areas, the prominent seasonal characteristics of the disasters, and the orderly and mobile organization of disaster relief forces, how to assist the emergency management departments in effectively deploying and mobilizing government units and emergency rescue and relief forces from all walks of life, and how to rationally allocate rescue supplies has become a major problem.

[0004] The existing emergency rescue and disaster relief plans use ontology editing tools to construct the relevant instance information extracted from the network into a conceptual hierarchical relationship to form a disaster event knowledge graph, and at the same time introduce external structured knowledge such as fire protection and medical care to form their knowledge graphs respectively; then use graph neural network technology to merge the knowledge graphs in the above fields into a disaster event emergency response knowledge graph, realize multi-field emergency resource coordination based on disaster events, and provide support for the accurate generation of emergency plans. However, the existing technology does not take into account that the impact of existing disasters will continue to change. The emergency rescue and disaster relief plans that simply rely on historical cases will lead to the efficiency and accuracy of plan generation, and cannot adapt to the changing disaster situation and rescue needs.

[0005] In view of this, overcoming the defects of the prior art is an urgent problem to be solved in the field of this technology. Summary of the invention

[0006] The technical problem to be solved by the present invention is how to quickly and accurately generate an effective disaster relief plan to adapt to the ever-changing disaster situation and rescue needs.

[0007] The present invention adopts the following technical solution:

[0008] In a first aspect, a method for generating an emergency rescue plan is provided, comprising:

[0009] Get initial spatial data;

[0010] Generate an initial emergency plan based on the initial spatial data and in combination with the characteristics of the current disaster;

[0011] Updating the initial spatial data to obtain target spatial data;

[0012] The generated initial plan is dynamically adjusted and optimized according to the target spatial data to obtain a disaster relief plan corresponding to the current disaster.

[0013] Preferably, updating the initial spatial data to obtain target spatial data includes:

[0014] Converting the initial spatial data, loading the converted initial spatial data into the WebGIS platform, and displaying them visually;

[0015] Establish a regular or real-time initial spatial data update mechanism, update the initial spatial data according to the initial spatial data update mechanism, and ensure that the initial spatial data on the WebGIS platform remains up to date to obtain the target spatial data.

[0016] Preferably, generating an initial plan based on the initial spatial data and in combination with the characteristics of the current disaster includes:

[0017] Determining whether the characteristics of the current disaster are similar to those of historical cases based on the initial spatial data;

[0018] When the characteristics of the current disaster are similar to those of historical cases, the corresponding solutions are obtained and the initial plan is generated through the cycle of case retrieval, case reuse, case correction and case storage;

[0019] When the characteristics of the current disaster have no obvious correlation with historical cases, the best matching case is determined through the classification algorithm, and an initial plan is generated based on the best matching case.

[0020] Preferably, when the characteristics of the current disaster are similar to those of historical cases, obtaining a corresponding solution and generating an initial plan through a cycle of case retrieval, case reuse, case correction and case storage includes:

[0021] According to the initial spatial data, the current disaster characteristics are expressed in the form of cases to obtain target cases;

[0022] Input the target case into the case library through the case description, and search the case library to find the matching case that best matches the target case;

[0023] If a matching case is found in the case library, extracting the emergency rescue plan corresponding to the matching case as the initial plan;

[0024] If no matching case is found in the case library, the cases similar to the target case are modified according to the actual situation of the target case, and the emergency rescue and disaster relief plans corresponding to the cases similar to the target case are continuously adjusted and improved until an initial plan that satisfies the user is generated.

[0025] Preferably, when the characteristics of the current disaster have no obvious correlation with the historical cases, determining the best matching case by a classification algorithm, and generating an initial plan according to the best matching case includes:

[0026] According to the classification requirements of emergencies, the events in the case library are classified to obtain classification results, and the accident type corresponding to the current disaster is determined according to the classification results and the characteristics of the current disaster;

[0027] The posterior probability is calculated according to the accident type corresponding to the current disaster, and the best matching case of the current disaster is obtained according to the posterior probability, and the emergency rescue plan corresponding to the best matching case of the current disaster is used as the initial plan.

[0028] Preferably, the calculating of the posterior probability according to the accident type corresponding to the current disaster, and obtaining the best matching case of the current disaster according to the posterior probability comprises:

[0029] The posterior probability P(c ij ) is calculated as:

[0030]

[0031] Among them, X is the event, C is the event classification, m is the number of representative cases under the corresponding event type, and n ij is the number of cases with the highest similarity in the case database, and N is the total number of disaster cases, then:

[0032]

[0033]

[0034] Among them, x z is the attribute of event X; n ij (x z ) is when c ij When it is the best matching case, the event type has the same sample size as the number of typical accident cases under its type; z is the Cartesian product starting from z = 1, and q is the Cartesian product q times;

[0035] The best matching case for the current disaster is calculated as:

[0036]

[0037] Among them, argmax is a function that finds the parameter of a function.

[0038] Preferably, dynamically adjusting and optimizing the generated initial plan according to the target spatial data to obtain a disaster relief plan corresponding to the current disaster includes:

[0039] Constructing a rule knowledge base, an emergency rescue resource configuration knowledge base, an emergency disposal knowledge base and a knowledge graph according to the target space data, and combining the rule knowledge base, the emergency rescue resource configuration knowledge base and the emergency disposal knowledge base with the knowledge graph to obtain an inference resource base;

[0040] Putting the inference resource library into the inference engine, and performing semantic inference on the characteristics of the current disaster through the inference engine to obtain the inference result;

[0041] The rule knowledge base, the emergency rescue resource configuration knowledge base and the emergency response knowledge base are updated according to the reasoning results, and the initial plan is optimized according to the updated rule knowledge base, the updated emergency rescue resource configuration knowledge base and the updated emergency response knowledge base to obtain a disaster relief plan corresponding to the current disaster.

[0042] Preferably, the placing of the reasoning resource library into a reasoning engine, and obtaining a reasoning result by performing semantic reasoning on the characteristics of the current disaster through the reasoning engine comprises:

[0043] The rules corresponding to the rule knowledge base are converted into instance and rule forms that can be recognized by the reasoning engine through the semantic rule conversion bridge;

[0044] The reasoning engine is called to perform semantic reasoning, and the reasoning engine performs reasoning according to the input characteristics of the current disaster and the converted instance and rule form to obtain the reasoning result.

[0045] In a second aspect, a device for generating an emergency rescue and disaster relief plan is provided, the device comprising: a processor and a memory for storing instructions executable by the processor;

[0046] Wherein, the processor is configured to execute the method for generating an emergency rescue plan as described in the first aspect.

[0047] In a third aspect, a non-volatile computer storage medium is provided, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are executed by one or more processors to complete the method for generating emergency rescue plans as described in the first aspect.

[0048] In a fourth aspect, a chip is provided, comprising: a processor and an interface, for calling and running a computer program stored in the memory from a memory, and executing the method for generating an emergency rescue plan as described in the first aspect.

[0049] In a fifth aspect, a computer program product comprising instructions is provided. When the instructions are executed on a computer or a processor, the computer or the processor executes the method for generating an emergency rescue plan as described in the first to fourth aspects and any one of the aspects.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The present invention forms spatial data by integrating data from multiple professional fields, thereby providing more comprehensive information support for the generation of emergency rescue and disaster relief plans. This comprehensive data processing method makes the emergency rescue and disaster relief plans more in line with the actual situation and improves the practicality and operability of the emergency rescue and disaster relief plans. It can automatically generate emergency rescue and disaster relief plans based on the acquired spatial data and in combination with the characteristics of the current disaster, thereby improving the efficiency and accuracy of the generation of emergency rescue and disaster relief plans. It can dynamically adjust and optimize the generated initial plan based on the updated spatial data, thereby adapting to the ever-changing disaster situation and disaster relief needs.

[0052] In summary, the present invention can provide scientific, efficient and accurate plan support for emergency rescue and disaster relief work, improve the efficiency and success rate of emergency rescue and disaster relief work, and reduce the losses caused by disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 It is a schematic diagram of a method for generating an emergency rescue plan provided by an embodiment of the present invention;

[0055] Figure 2 It is a specific flow chart of a method for generating an emergency rescue plan provided by an embodiment of the present invention;

[0056] Figure 3 It is a schematic diagram of a process for generating an initial plan provided by an embodiment of the present invention;

[0057] Figure 4 It is a flowchart of a case-based reasoning provided by an embodiment of the present invention;

[0058] Figure 5 It is a schematic diagram of a process of updating initial spatial data provided by an embodiment of the present invention;

[0059] Figure 6 It is a schematic diagram of a JESS reasoning process provided by an embodiment of the present invention;

[0060] Figure 7 It is a schematic diagram of a process of obtaining a disaster relief plan corresponding to a current disaster provided by an embodiment of the present invention;

[0061] Figure 8 It is a structural schematic diagram of an emergency rescue and disaster relief plan generating device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] Unless the context requires otherwise, throughout the specification and claims, the term "including" is to be interpreted as open inclusion, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples" or "some examples" and the like are intended to indicate that specific features, structures, materials or characteristics associated with the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representation of the above terms does not necessarily refer to the same embodiment or example. In addition, the specific features, structures, materials or characteristics may be included in any one or more embodiments or examples in any appropriate manner, that is, although they may be carried in the embodiments or examples of the above terms due to reasons such as the order and position of appearance, it is not limited to that they can be carried in combination by one embodiment or example.

[0064] In the description of the present invention, the terms "first" and "second" are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "multiple" is two or more. In addition, for example, the same type of nouns may be described as two independent individuals by adding "A" and "B" at the end. In this case, the corresponding features defined as "A" and "B" are only used to distinguish the same type of individuals for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features.

[0065] When describing some embodiments, the expressions "coupling", "coupling" and "connection" and their derivatives may be used. For example, when describing some embodiments, the term "connection" may be used to indicate that two or more components are in direct physical or electrical contact with each other. For another example, when describing some embodiments, the term "coupling" may be used to indicate that two or more components are in direct physical or electrical contact. However, the terms "connection" or "coupling" may also refer to two or more components that are not in direct contact with each other, but still cooperate or interact with each other, such as "optical path coupling", "wireless connection", etc. The embodiments disclosed herein are not necessarily limited to the contents of the present invention.

[0066] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0067] Embodiment 1:

[0068] The present embodiment provides a method for generating an emergency rescue plan, including: acquiring initial spatial data; generating an initial plan based on the initial spatial data and in combination with characteristics of a current disaster; updating the initial spatial data to obtain target spatial data; and dynamically adjusting and optimizing the generated initial plan based on the target spatial data to obtain a disaster relief plan corresponding to the current disaster.

[0069] In one embodiment, Figure 1 As shown in the figure, the method for generating emergency rescue and relief plans includes comprehensive monitoring of the disaster area, including meteorological and hydrological monitoring, to predict the development trend of the disaster and formulate corresponding rescue measures. For example, heavy rain may cause floods to rise further, and flood prevention preparations need to be made in advance. Disaster situation analysis can grasp the scope, degree and development direction of the disaster in real time, and help rescuers determine key rescue areas and priority rescue targets. Civil society analysis focuses on the living conditions, needs and social order of the people in the disaster area to ensure that the rescue work can meet the actual needs of the people while maintaining social stability. The analysis and judgment stage comprehensively considers policy and regulatory analysis and public opinion dynamic analysis to ensure that emergency rescue and relief work is carried out within the framework of legality and compliance, while actively responding to social concerns and creating a good rescue atmosphere.

[0070] After fully analyzing the situation in the disaster area, the emergency plan template is retrieved. The emergency plan template is formulated based on previous emergency rescue and disaster relief experience and relevant policies and regulations, and provides a basic framework for generating specific emergency rescue and disaster relief plans. According to the emergency plan template and the actual situation in the disaster area, personnel and resource grouping are carried out. Personnel grouping includes arranging various types of rescue teams to ensure that the forces in various professional fields can work together; resource grouping is to reasonably allocate resources such as rescue materials, equipment and funds to ensure that resources can be efficiently invested in emergency rescue and disaster relief work. On the basis of personnel grouping and resource grouping, a specific emergency rescue and disaster relief plan is generated. The emergency rescue and disaster relief plan includes specific contents such as rescue routes, rescue methods, and personnel placement, providing detailed guidance for rescue work. At the same time, a task list is formulated to clarify the specific tasks and responsibilities of each rescue team and department to ensure that the rescue work is carried out in an orderly manner.

[0071] As the situation in the disaster area may change at any time, the emergency rescue plan needs to be dynamically adjusted and optimized. According to the new meteorological and hydrological information, changes in the disaster situation, feedback from the public and social conditions, and public opinion trends, the rescue strategy and resource allocation should be adjusted in a timely manner to ensure that the plan always adapts to the actual situation and improves the efficiency and effectiveness of the rescue.

[0072] Combined with the acquired spatial data and the characteristics of the current disaster (such as disaster type, geographical location), etc., the analogy reasoning algorithm is used to retrieve the closest case for modification as the initial plan; or the classification algorithm is used to determine the type of the current disaster according to the event feature attributes and calculate the posterior probability to generate an initial plan. Finally, based on the continuously updated spatial data, rule reasoning based on the knowledge graph can be used to build a rule knowledge base and emergency rescue resource allocation, emergency response knowledge base, etc. The initial plan is adjusted and optimized using the reasoning engine combined with the rules satisfied by the rule knowledge base, so that the disaster relief plan is more in line with the actual disaster rescue situation.

[0073] The specific steps of the method for generating the emergency rescue plan will be described in detail below.

[0074] In one embodiment, Figure 2 As shown, the method for generating an emergency rescue plan includes:

[0075] Step 101: Acquire initial spatial data.

[0076] In one embodiment, the initial spatial data includes information such as geographic elements, meteorological data, and disaster relief resources, providing basic data support for the generation of emergency plans. Geographic elements include topography, landforms, roads, etc.; meteorological data include temperature, rainfall, wind direction, etc.; disaster relief resources include the distribution of medical facilities, the location of fire stations, and the location of rescue teams. The initial spatial data can come from various map service providers, government agencies, etc., and is authoritative, accurate, and real-time. Through operations such as data format conversion, loading and display, establishment of update mechanisms, and quality control, the availability of spatial data is ensured.

[0077] Step 102: Generate an initial emergency plan based on the initial spatial data and the characteristics of the current disaster

[0078] In this embodiment, the calculation method to be used to obtain the initial plan can be determined based on whether the characteristics of the current disaster are similar to historical cases.

[0079] Step 103: Update the initial spatial data to obtain target spatial data.

[0080] In this embodiment, the degree, scope, and impact of the disaster are constantly changing. The spatial data is updated according to the actual situation to obtain the target spatial data, so that the initial plan can be revised according to the target spatial data.

[0081] Step 104: dynamically adjust and optimize the generated initial plan according to the target spatial data to obtain a disaster relief plan corresponding to the current disaster.

[0082] In this embodiment, a reasoning mechanism may be used to dynamically adjust and optimize the initial plan to obtain a disaster relief plan that is more compatible with the current disaster.

[0083] This embodiment forms spatial data by integrating data from multiple professional fields, thereby providing more comprehensive information support for the generation of emergency rescue and disaster relief plans. This comprehensive data processing method makes the emergency rescue and disaster relief plans more in line with actual conditions and improves the practicality and operability of the emergency rescue and disaster relief plans. It can automatically generate emergency rescue and disaster relief plans based on the acquired spatial data and in combination with the characteristics of the current disaster, thereby improving the efficiency and accuracy of the generation of emergency rescue and disaster relief plans. It can dynamically adjust and optimize the generated initial plan based on the updated spatial data, thereby adapting to the ever-changing disaster situation and disaster relief needs.

[0084] In one embodiment, Figure 3 As shown, step 102 includes: judging whether the characteristics of the current disaster are similar to the historical cases according to the initial spatial data, and if so, executing step 1021; if not, executing step 1022.

[0085] Step 1021: When the characteristics of the current disaster are similar to those of historical cases, the corresponding solution is obtained and the initial prediction is generated through the cycle of case retrieval, case reuse, case correction and case storage.

[0086] In one embodiment, the current disaster characteristics are expressed in the form of cases according to the initial spatial data to obtain a target case; the target case is input into a case library through a case description, and is searched in the case library to find a matching case that best matches the target case; if a matching case is found in the case library, the emergency rescue and disaster relief plan corresponding to the matching case is extracted as the initial plan; if no matching case is found in the case library, the case similar to the target case is corrected according to the actual situation of the target case, and the emergency rescue and disaster relief plan corresponding to the case similar to the target case is continuously adjusted and improved until an initial plan that satisfies the user is generated.

[0087] like Figure 4 As shown in the figure, the flowchart shows the process of case-based reasoning method in handling emergencies. Through the steps of retrieval, reuse, correction and storage, a decision-making plan is provided for new emergencies. The specific steps include: when an emergency occurs, first describe the target case and clarify the key characteristics and problems of the emergency. Then retrieve historical similar cases in the case library. The case library is a database that stores various event cases handled in the past. By matching the characteristics of the target case with the cases in the case library, historical similar cases are found. Then the retrieved historical similar cases are evaluated to determine whether they meet the current emergency situation. If they meet, the decision-making plan in the historical case can be directly reused to provide a solution for the current emergency. If the retrieved historical case does not meet the current emergency situation, or although there are similarities, it cannot fully meet the needs, the historical case needs to be corrected. The correction process may involve the adjustment and improvement of the decision-making plan. Combined with the specific situation of the current emergency, the plan is optimized to make it more suitable for the current problem. When a decision-making plan suitable for the current emergency is obtained after correction, or new valuable experience and cases are generated during the processing process, it is stored in the case library. This step can continuously enrich the case library and improve the efficiency and accuracy of handling similar emergencies in the future. Among them, the above-mentioned case-based reasoning method can be used to handle sudden disasters, and the sudden event is the current disaster.

[0088] Step 1022: When the characteristics of the current disaster have no obvious correlation with the historical cases, the best matching case is determined through a classification algorithm, and an initial plan is generated based on the best matching case.

[0089] In one embodiment, the events in the case library are classified according to the classification requirements of the emergency events to obtain the classification results, and the accident type corresponding to the current disaster is determined according to the classification results and the characteristics of the current disaster; the posterior probability is calculated according to the accident type corresponding to the current disaster, and the best matching case of the current disaster is obtained according to the posterior probability, and the emergency rescue plan corresponding to the best matching case of the current disaster is used as the initial plan.

[0090] First, the events in the case library are classified according to the classification requirements of emergencies. The classification requirements can be formulated by relevant departments or professional institutions, aiming to systematically classify and manage different types of emergencies. For example, the classification may be based on factors such as the nature of the disaster (such as earthquakes, floods, fires, etc.), scale (small, medium, large, etc.), and scope of impact (local, regional, national, etc.).

[0091] Then, the accident type corresponding to the current disaster is determined based on the characteristics of the current disaster. A detailed analysis of the current disaster is required, including but not limited to the location, time, intensity, and impact range of the disaster. By comparing the location, time, intensity, and impact range of the disaster with the classification standards in the case library, the accident type closest to the current disaster can be determined. For example, if the current disaster is an earthquake in a specific area with a high magnitude and a large impact range, it can be classified as a "large earthquake disaster" accident type based on the corresponding characteristics.

[0092] The posterior probability is calculated based on the accident type corresponding to the current disaster. The probability estimate of the event can be updated through the known prior probability and new evidence (characteristics of the current disaster) to calculate the posterior probability. In the calculation process, it is necessary to consider the number and characteristics of cases in the case library that are similar to the current disaster, as well as the degree of similarity between the current disaster and the cases similar to the current disaster. For example, if there are multiple historical cases similar to the current earthquake disaster in the case library, the posterior probability of the current disaster can be calculated by counting the number of cases with the same characteristics as the current disaster in historical cases similar to the current earthquake disaster, and the success probability of the corresponding emergency rescue plan.

[0093] The best matching case for the current disaster is obtained based on the posterior probability, which is usually determined by comparing the posterior probabilities of different cases. The case with the highest posterior probability is considered to be the most similar to the current disaster and the most likely to provide an effective emergency rescue plan. For example, if after calculating the posterior probability, it is found that a historical earthquake case has the highest posterior probability, then the corresponding case is determined to be the best matching case for the current disaster.

[0094] In one embodiment, suppose a disaster event X occurs, and the event attributes collected at the early stage of the accident are X = {x1, x2, ... xn}, the attribute value is {k1,k2,…k n To determine the type of accident to which this disaster event belongs, first, according to the classification requirements of the Ministry of Emergency Management, the events in the case library are divided into {C1, C2, …C n There are several categories, and under them there are several representative cases, such as C i ={C i1 ,C i2 ,…C im}(m>0), then the corresponding accident type is determined according to the key attributes of the event. Then the posterior probability P(c ij ) is calculated as:

[0095]

[0096] Among them, X is the event, C is the event classification, m is the number of representative cases under the corresponding event type, and n ij is the number of cases with the highest similarity in the case database, and N is the total number of disaster cases, then:

[0097]

[0098] Among them, x z is the attribute of event X; n ij (x z ) is when c ij When it is the best matching case, the event type has the same sample size as the number of typical accident cases under its type; z is the Cartesian product starting from z = 1, and q is the Cartesian product q times;

[0099] The best matching case for the current disaster is calculated as:

[0100]

[0101] Among them, argmax is a function that finds the parameter of a function.

[0102] Generate an initial plan based on the emergency rescue plan answer corresponding to the best matching case of the current disaster. Once the best matching case is determined, the emergency rescue plan corresponding to the case can be directly adopted as the initial plan, or appropriate adjustments and optimizations can be made on its basis to better adapt to the specific situation of the current disaster. For example, if the best matching case is a case of successful response to a similar earthquake disaster, then the experience of rescue team deployment, material allocation, personnel evacuation, etc. in the case can be used to formulate an initial plan for the current disaster.

[0103] In one embodiment, Figure 5 As shown, the step 103 specifically includes:

[0104] Step 1031: convert the initial spatial data, load the converted initial spatial data into the WebGIS platform, and display it visually.

[0105] Since the formats of the initial spatial data provided by different data sources may be different, such as Shapefile, GeoJSON (full name: Geographic JavaScript Object Notation), etc., a unified data format conversion is required so that the initial spatial data can be used smoothly in subsequent processing and analysis to ensure the compatibility and operability of the spatial data. The converted spatial data is then loaded into the WebGIS platform for visual display. Rendering and layer overlay can be performed on the map, allowing decision makers to intuitively understand the distribution of disasters and rescue resources.

[0106] Step 1032: Establish a regular or real-time initial spatial data update mechanism, and update the initial spatial data according to the initial spatial data update mechanism to ensure that the initial spatial data on the WebGIS platform remains up to date to obtain the target spatial data.

[0107] Establish a regular or real-time data update mechanism to ensure that spatial data is always up to date. You can set up a data update interface to regularly obtain new data from the data source; you can also use scheduled tasks or monitor data source changes to promptly discover data updates and handle them accordingly. For example, during a disaster, meteorological data may change constantly, and the location and availability of rescue resources may also change. Timely updating of this data is crucial to generating accurate plans.

[0108] In order to ensure the accuracy and reliability of spatial data, data quality control is required, including evaluating and screening data sources to remove unreliable data sources; preprocessing and cleaning spatial data to remove erroneous, duplicated or incomplete spatial data; setting spatial data verification rules to verify spatial data and ensure that spatial data meets certain standards and specifications.

[0109] In one embodiment, Figure 6 As shown: This flowchart shows the process of using the JESS inference engine combined with the knowledge graph and the custom rule base to analyze and respond to disaster events. The specific steps include:

[0110] Disaster events are the starting point of the entire process, indicating that a disaster event has occurred, such as an earthquake, flood, fire, etc. The specific information of the disaster event includes the location, time, scale, and scope of impact. Once a disaster event occurs, the emergency response mechanism needs to be activated. Emergency response includes a series of actions, such as organizing rescue teams, deploying rescue resources, and issuing alarms.

[0111] The knowledge graph plays a key role in this process, integrating various information about disaster events, including the type of disaster, the surrounding environment of the disaster area, and the distribution of rescue resources. The knowledge graph graphically represents information such as the type of disaster, the surrounding environment of the disaster area, and the distribution of rescue resources, making the relationship between information more intuitive and easy to understand. For example, the knowledge graph can show the location of rescue resources such as hospitals, fire brigades, and police stations near the disaster area, as well as geographic information such as roads and rivers. For a specific disaster event A, detailed information needs to be collected and organized, which may include the specific type of disaster (such as the magnitude of an earthquake, the water level of a flood, etc.), the population density of the affected area, the damage to buildings, etc. Detailed information will provide an important basis for subsequent reasoning.

[0112] The JESS inference engine uses the information in the knowledge graph and the custom rule base to reason and analyze disaster events. The JESS inference engine can automatically deduce the best strategy for responding to disasters based on the input disaster event information and rules. For example, based on the population density and building damage in the disaster area, the inference engine can determine how many rescue personnel and materials need to be deployed; based on the road congestion, the inference engine can plan the best rescue route. The relevant emergency resource information around the disaster area includes various emergency resources around the disaster area, such as hospitals, fire brigades, police stations, and rescue material storage points. Information such as the location, quantity, and availability of emergency resources is very important for formulating emergency response strategies. The custom rule base is a series of rules formulated by experts based on previous experience and knowledge. The rules cover response strategies and resource allocation principles in various disaster situations. For example, the rule base may contain rules such as "If the magnitude of the earthquake is greater than a certain level, then large rescue equipment should be deployed first." The JESS inference engine will reason based on the corresponding rules and information in the knowledge graph to determine the best emergency response strategy.

[0113] In summary, the JESS reasoning flowchart provides a scientific and systematic method for emergency response to disaster events. By integrating technologies such as knowledge graph, JESS reasoning engine and custom rule base, effective emergency response strategies can be formulated quickly and accurately to improve the efficiency and effectiveness of disaster response.

[0114] Based on the above JESS reasoning process principle, in one embodiment, Figure 7 As shown, the step 104 specifically includes:

[0115] Step 1041: construct a rule knowledge base, an emergency rescue resource configuration knowledge base, an emergency response knowledge base and a knowledge graph based on the target space data, and combine the rule knowledge base, the emergency rescue resource configuration knowledge base and the emergency response knowledge base with the knowledge graph to obtain an inference resource library.

[0116] Among them, the SWRL rule knowledge base, the emergency rescue resource configuration knowledge base and the emergency disposal knowledge base correspond to the above-mentioned custom rule base. The rule knowledge base can be a SWRL rule knowledge base.

[0117] In one embodiment, a series of rules are determined based on the target spatial data and expressed in the form of SWRL. For example, if the spatial data shows that a certain area is severely affected by a disaster and has inconvenient transportation, a rule may be formulated that "if the disaster area has inconvenient transportation and the disaster is serious, helicopter rescue resources should be deployed first." The above rules cover the response strategies and resource allocation principles under various disaster situations. The corresponding rules are sorted and stored to form a SWRL rule knowledge base, which provides a rule basis for subsequent reasoning.

[0118] Based on the target spatial data, the types, quantities, distribution and other information of various rescue resources are clarified. For example, the location of hospitals, the number of medical personnel, the location of fire brigades, the configuration of fire trucks, etc. in different regions are determined based on the target spatial data. This information is sorted and stored to form a knowledge base for emergency rescue resource allocation, so that rescue resources can be reasonably arranged in the plan adjustment.

[0119] Considering the casualties and property losses caused by the disaster, the emergency response knowledge base is constructed in combination with the target spatial data. For example, the distribution of people and the damage to buildings in the disaster-stricken area are determined based on the target spatial data, and then the rescue measures for different degrees of casualties (such as first aid, surgery, and post-disaster treatment for minor injuries, serious injuries, and deaths) and the disposal strategies for property losses (such as the reconstruction and repair of collapsed houses and damaged infrastructure) are determined. This information is organized and stored to form an emergency response knowledge base.

[0120] Construct a disaster-related knowledge graph to visualize and structure the various entities in the disaster event (such as disaster type, rescue resources, disaster-stricken areas, etc.) and the relationships between them (such as the distance relationship between the disaster site and rescue resources, the association relationship between the disaster-stricken areas and emergency response measures, etc.). Combine the SWRL rule knowledge base, emergency rescue resource configuration knowledge base, and emergency response knowledge base with the knowledge graph. For example, in the knowledge graph, the emergency rescue resources corresponding to a disaster-stricken area can be found through the relationship between entities, and then the actual deployment plan of these resources can be determined in combination with the specific information in the emergency rescue resource configuration knowledge base; or the specific disposal measures for casualties and property losses in the area can be determined through the connection between the disaster-stricken area and the relevant content in the emergency response knowledge base. Finally, a reasoning resource library is formed to provide comprehensive information support for subsequent reasoning.

[0121] Step 1042: Put the reasoning resource library into the reasoning engine, and use the reasoning engine to perform semantic reasoning on the characteristics of the current disaster to obtain a reasoning result.

[0122] In one embodiment, the reasoning resource library is placed in the JESS reasoning engine, the current disaster information is input to perform semantic reasoning of SWRL rules, and reasoning is performed based on the logical relationship between the SWRL rules and the current disaster information to obtain the reasoning result.

[0123] In one embodiment, the rules corresponding to the rule knowledge base are converted into instances and rule forms that can be recognized by the reasoning engine through a semantic rule conversion bridge; the reasoning engine is called to perform semantic reasoning, and the reasoning engine performs reasoning based on the input characteristics of the current disaster and the converted instances and rule forms to obtain the reasoning results.

[0124] The SWRL rules are converted into instances and rule forms that can be recognized by the JESS reasoning engine through the semantic rule conversion bridge; the JESS reasoning engine is called to perform semantic reasoning of the SWRL rules, and the JESS reasoning engine performs reasoning based on the input current disaster information and the converted instance and rule form to obtain the reasoning result. More specifically, the constructed reasoning resource library (including the SWRL rule knowledge base, the emergency rescue resource configuration knowledge base, the emergency disposal knowledge base, and the combined knowledge graph) is placed in the reasoning engine. Input the current disaster information, such as the geographical location of the disaster-stricken area, the type of disaster, the degree of disaster, etc. The reasoning engine performs semantic reasoning of the SWRL rules based on the input information and the content in the reasoning resource library. For example, if the input information shows that an earthquake has occurred in a certain area and the disaster is serious, the reasoning engine will reason based on the rules in the SWRL rule knowledge base (such as "If the magnitude of the earthquake is greater than a certain degree and the population in the disaster-stricken area is dense, then large-scale rescue equipment and medical teams will be deployed first") and the entity relationships in the knowledge graph.

[0125] Based on the logical relationship between SWRL rules and current disaster information, a series of relevant conclusions about emergency plan optimization are obtained. For example, it is inferred which rescue resources need to be deployed, which emergency response measures need to be taken, the deployment direction and quantity of rescue resources, etc. The conclusions obtained serve as the reasoning results and provide a basis for subsequent plan adjustments.

[0126] Step 1043: Update the rule knowledge base, the emergency rescue resource configuration knowledge base and the emergency response knowledge base according to the reasoning results, and optimize the initial plan according to the updated rule knowledge base, the updated emergency rescue resource configuration knowledge base and the updated emergency response knowledge base to obtain a disaster relief plan corresponding to the current disaster.

[0127] According to the inference results, the contents of the SWRL rule knowledge base, the emergency rescue resource configuration knowledge base, and the emergency disposal knowledge base are updated synchronously. For example, if the inference results show that a certain area needs more medical resources, then the number of medical resources in the area is updated in the emergency rescue resource configuration knowledge base; if the inference results require adjustment of a rescue rule, then the corresponding rule is modified in the SWRL rule knowledge base.

[0128] Since the content in the knowledge base is closely related to the generation of the plan, when the knowledge base is updated, the initial plan is adjusted and optimized according to the updated SWRL rule knowledge base, emergency rescue resource configuration knowledge base, and emergency disposal knowledge base. For example, as the number of medical resources in the emergency rescue resource configuration knowledge base is updated, the content of the plan regarding the allocation of medical resources in the area will also be adjusted, which may increase the number of medical personnel deployed or change the distribution method of medical supplies. By continuously updating the knowledge base and adjusting and optimizing the plan, the final emergency rescue plan can better adapt to the changing disaster situation and rescue needs, and obtain a disaster relief plan corresponding to the current disaster.

[0129] To sum up, this embodiment forms spatial data by integrating data from multiple professional fields, thereby providing more comprehensive information support for the generation of emergency rescue and disaster relief plans. This comprehensive data processing method makes the emergency rescue and disaster relief plans more in line with the actual situation and improves the practicality and operability of the emergency rescue and disaster relief plans. It can automatically generate emergency rescue and disaster relief plans based on the acquired spatial data and in combination with the characteristics of the current disaster, thereby improving the efficiency and accuracy of the generation of emergency rescue and disaster relief plans. It can dynamically adjust and optimize the generated initial plan based on the updated spatial data, so as to adapt to the ever-changing disaster situation and disaster relief needs.

[0130] This embodiment can provide scientific, efficient and accurate plan support for emergency rescue and disaster relief work, improve the efficiency and success rate of emergency rescue and disaster relief work, reduce the losses caused by disasters, and protect people's lives and property.

[0131] Embodiment 2:

[0132] In Example 1, a method for generating an emergency rescue and disaster relief plan is provided. In this embodiment, a device for generating an emergency rescue and disaster relief plan is proposed. The device for generating an emergency rescue and disaster relief plan includes: a processor and a memory for storing processor executable instructions; wherein the processor is configured to execute the method for generating an emergency rescue and disaster relief plan described in Example 1.

[0133] like Figure 8 As shown, the emergency rescue plan generation device includes a processor 21 and a memory 22, wherein the processor 21 and the memory 22 can be connected via a bus or other means.

[0134] The processor 21 may be a central processing unit (CPU). The processor 21 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0135] The memory 22, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the method for generating a disaster rescue plan in Embodiment 1 of the present invention. The processor executes various functional applications and training processes of the processor by running the non-transitory software programs, instructions and modules stored in the memory.

[0136] The memory 22 may include a program storage area and a training storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the training storage area may store training created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 22 may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The one or more modules are stored in the memory 22, and when executed by the processor 21, execution such as Figure 1 The method for generating a disaster rescue plan in the embodiment 1 is shown. The specific details of the above-mentioned method for generating a disaster rescue plan can be found in Figure 1 , Figure 2 and Figure 3 The corresponding descriptions and effects in the embodiments shown in the figure can be understood and will not be repeated here.

[0137] This embodiment further provides a computer storage medium, which stores a computer program. The computer program can be executed by a processor to complete the method for generating an emergency rescue plan described in Embodiment 1.

[0138] The computer storage medium stores computer executable instructions, and the computer executable instructions can execute the emergency rescue plan generation method in any of the above method embodiments. The storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); the storage medium can also include a combination of the above types of memory.

[0139] The specific steps of the method for generating the emergency rescue plan are shown in Example 1 and will not be repeated in this example.

[0140] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating an emergency rescue plan, characterized in that: include: Get initial spatial data; Generate an initial emergency plan based on the initial spatial data and in combination with the characteristics of the current disaster; Updating the initial spatial data to obtain target spatial data; The generated initial plan is dynamically adjusted and optimized according to the target spatial data to obtain a disaster relief plan corresponding to the current disaster.

2. The method for generating a disaster rescue plan according to claim 1, characterized in that: The updating of the initial spatial data to obtain the target spatial data includes: Converting the initial spatial data, loading the converted initial spatial data into the WebGIS platform, and displaying them visually; Establish a regular or real-time initial spatial data update mechanism, update the initial spatial data according to the initial spatial data update mechanism, and ensure that the initial spatial data on the WebGIS platform remains up to date to obtain the target spatial data.

3. The method for generating emergency rescue plan according to claim 1, characterized in that: The generating of the initial plan according to the initial spatial data and in combination with the characteristics of the current disaster includes: Determining whether the characteristics of the current disaster are similar to those of historical cases based on the initial spatial data; When the characteristics of the current disaster are similar to those of historical cases, the corresponding solutions are obtained and the initial plan is generated through the cycle of case retrieval, case reuse, case correction and case storage; When the characteristics of the current disaster have no obvious correlation with historical cases, the best matching case is determined through the classification algorithm, and an initial plan is generated based on the best matching case.

4. The method for generating a disaster rescue plan according to claim 3, characterized in that: When the characteristics of the current disaster are similar to those of historical cases, the corresponding solutions are obtained and the initial plan is generated through the cycle of case retrieval, case reuse, case correction and case storage, including: According to the initial spatial data, the current disaster characteristics are expressed in the form of cases to obtain target cases; Input the target case into the case library through the case description, and search the case library to find the matching case that best matches the target case; If a matching case is found in the case library, extracting the emergency rescue plan corresponding to the matching case as the initial plan; If no matching case is found in the case library, the cases similar to the target case are modified according to the actual situation of the target case, and the emergency rescue and disaster relief plans corresponding to the cases similar to the target case are continuously adjusted and improved until an initial plan that satisfies the user is generated.

5. The method for generating emergency rescue plan according to claim 3, characterized in that: When the characteristics of the current disaster have no obvious correlation with the historical cases, the best matching case is determined by the classification algorithm, and the initial plan is generated according to the best matching case, including: According to the classification requirements of emergencies, the events in the case library are classified to obtain classification results, and the accident type corresponding to the current disaster is determined according to the classification results and the characteristics of the current disaster; The posterior probability is calculated according to the accident type corresponding to the current disaster, and the best matching case of the current disaster is obtained according to the posterior probability, and the emergency rescue plan corresponding to the best matching case of the current disaster is used as the initial plan.

6. The method for generating emergency rescue plan according to claim 5, characterized in that: The calculating of the posterior probability according to the accident type corresponding to the current disaster and obtaining the best matching case of the current disaster according to the posterior probability includes: The posterior probability P(c ij ) is calculated as: Among them, X is the event, C is the event classification, m is the number of representative cases under the corresponding event type, and n ij is the number of cases with the highest similarity in the case database, and N is the total number of disaster cases, then: Among them, x z is the attribute of event X; n ij (x z ) is when c ij When it is the best matching case, the event type has the same sample size as the number of typical accident cases under its type; z is the Cartesian product starting from z = 1, and q is the Cartesian product q times; The best matching case for the current disaster is calculated as: Among them, argmax is a function that finds the parameter of a function.

7. The method for generating emergency rescue plan according to claim 1, characterized in that: The dynamically adjusting and optimizing the generated initial plan according to the target spatial data to obtain a disaster relief plan corresponding to the current disaster includes: Constructing a rule knowledge base, an emergency rescue resource configuration knowledge base, an emergency disposal knowledge base and a knowledge graph according to the target space data, and combining the rule knowledge base, the emergency rescue resource configuration knowledge base and the emergency disposal knowledge base with the knowledge graph to obtain an inference resource base; Putting the inference resource library into the inference engine, and performing semantic inference on the characteristics of the current disaster through the inference engine to obtain the inference result; The rule knowledge base, the emergency rescue resource configuration knowledge base and the emergency response knowledge base are updated according to the reasoning results, and the initial plan is optimized according to the updated rule knowledge base, the updated emergency rescue resource configuration knowledge base and the updated emergency response knowledge base to obtain a disaster relief plan corresponding to the current disaster.

8. The method for generating a disaster rescue plan according to claim 7, characterized in that: The placing of the inference resource library into an inference engine and performing semantic inference on the characteristics of the current disaster through the inference engine to obtain an inference result includes: The rules corresponding to the rule knowledge base are converted into instance and rule forms that can be recognized by the reasoning engine through the semantic rule conversion bridge; The reasoning engine is called to perform semantic reasoning, and the reasoning engine performs reasoning according to the input characteristics of the current disaster and the converted instance and rule form to obtain the reasoning result.

9. A device for generating emergency rescue plans, characterized in that: The emergency rescue plan generating device comprises: a processor and a memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the emergency rescue plan generation method as described in any one of claims 1-8.

10. A non-volatile computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, and the computer executable instructions are executed by one or more processors to complete the emergency rescue and disaster relief plan generation method as described in any one of claims 1-8.

Images