Emergency service resource determination method and equipment based on sensing network model

Abstract

The invention provides an emergency service resource determination method and device based on a sensing network model, and relates to the technical field of emergency management.The method comprises the steps that a resource data set of a to-be-detected disaster environment is obtained, then the resource data set is preprocessed, and a sensing result data set is obtained; and inputting the perception result data set into the trained perception network model to obtain resource demand data of the current to-be-detected disaster environment, so as to perform emergency service evaluation through the resource demand data. On the basis, the disaster situation can be accurately analyzed, and the required emergency resources are intelligently analyzed and accurately estimated, so that the problems of information fragmentation, non-uniform resource allocation, low matching efficiency and the like existing in management and allocation of the current emergency service resources are solved, and the accuracy of disaster site situation measurement is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency management, and more particularly, to a method and device for determining emergency service resources based on a perception network model. Background Art

[0002] Under normal circumstances, when dealing with emergencies such as natural disasters and accident disasters, emergency management personnel are required to quickly and accurately allocate emergency service resources. However, in the prior art, the management of emergency service resources mainly relies on manual statistics and traditional paper file records. This method has problems such as lagging information update and difficult data sharing, resulting in the difficulty for emergency management personnel to quickly obtain comprehensive and accurate resource information when facing emergencies, thereby affecting the speed and effectiveness of emergency response.

[0003] At the same time, in terms of resource allocation, traditional scheduling methods are mostly based on empirical judgment, lacking scientific and systematic analysis means, and prone to the phenomenon of unbalanced resource allocation. In addition, there are also large uncertainties in the perception of the disaster scene situation and the demand assessment of rescue capabilities, which further exacerbates the difficulty of resource allocation.

[0004] Based on this, there is an urgent need for an emergency management system that can monitor the resource status in real time and dynamically, quickly summarize resource requirements, accurately evaluate the disaster scene situation, and scientifically predict the demand for rescue capabilities. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method and device for determining emergency service resources based on a perception network model, which can accurately analyze and evaluate the disaster situation, and perform intelligent analysis and accurate estimation on the required emergency resources, overcome the problems of fragmented information, uneven resource allocation, and low matching efficiency in the management and allocation of current emergency service resources, and improve the accuracy of measuring the disaster scene situation.

[0006] To achieve the above purpose, the technical solutions adopted in the embodiments of the present invention are as follows:

[0007] In a first aspect, the present invention provides a method for determining emergency service resources based on a perception network model, including the following steps:

[0008] Obtain a resource data set of the disaster environment to be measured; wherein, the resource data set includes various types of disaster characteristic data;

[0009] Preprocess the resource data set to obtain a perception result data set;

[0010] Input the perception result data set into the trained perception network model to obtain the resource requirement data of the current disaster environment to be measured, so as to perform emergency service evaluation through the resource requirement data;

[0011] The resource demand data includes multiple resource demand categories and the quantity of resources matching each resource demand category.

[0012] Optionally, the step of preprocessing the resource dataset to obtain the perception result data includes:

[0013] Eliminate noise in each disaster characteristic data under the resource dataset;

[0014] Normalizing the characteristic data of each disaster after noise elimination to obtain normalized characteristic data of each disaster;

[0015] The target features of the normalized disaster characteristic data are extracted and labeled to obtain the feature labels related to the disaster environment to be measured and the perception result data set.

[0016] Optionally, the step of inputting the perception result data set into the trained perception network model to obtain resource demand data of the current disaster environment to be tested includes:

[0017] Matching resources corresponding to each target feature under the current disaster type based on the knowledge graph matching perception results dataset;

[0018] Determine the similarity score between each target feature and the corresponding matching resource;

[0019] The number of emergency resources corresponding to each target feature is calculated based on the similarity score.

[0020] Optionally, the step of matching resources corresponding to each target feature in the perception achievement dataset under the current disaster type based on the knowledge graph matching includes:

[0021] Based on the knowledge graph matching perception results dataset, the initial matching resource category corresponding to each target feature under the current disaster type;

[0022] Calculate the matching degree between each target feature and the corresponding initial matching resource category;

[0023] According to the matching degree, the matching resource categories that meet the preset matching value are selected from the corresponding initial matching resource categories as the final matching resources.

[0024] Optionally, the calculation formula of the matching degree satisfies:

[0025]

[0026] Among them, MD is the matching degree, n is the total number of target features in the perception result dataset, and w j is the weight of the j-th target feature, x j is the value of the jth target feature in the perception result dataset, y jis the reference value of the j-th target feature in the domain knowledge graph, sin(x j , y j ) is the similarity function value of the j-th target feature.

[0027] Optionally, the steps of determining the similarity score between each target feature and the corresponding resource requirement category include:

[0028] Calculate the similarity between each target feature and the corresponding matching resource;

[0029] Determine the similarity score between the corresponding matching resources according to the similarity.

[0030] Optionally, the steps of calculating the emergency resource quantity corresponding to each target feature according to the similarity score include:

[0031] Determine the initial emergency resource quantity based on the similarity score and the preset resource quantity;

[0032] Determine the dynamic adjustment coefficient based on the dynamic parameters in the perception result dataset;

[0033] Determine the emergency resource quantity corresponding to each target feature based on the initial emergency resource quantity and the dynamic adjustment coefficient.

[0034] Optionally, the determination formula of the emergency resource quantity satisfies:

[0035]

[0036] In the formula, Q is the emergency resource quantity; s i is the similarity score between the i-th target feature and the corresponding matching resource category; d i is the preset resource quantity corresponding to the i-th target feature; c m is the meteorological condition adjustment coefficient; c i is the light condition adjustment coefficient; c t is the traffic condition adjustment coefficient.

[0037] Optionally, the steps of inputting the perception result dataset into the trained perception network model to obtain the resource requirement data of the current disaster environment to be measured further include:

[0038] Judge whether the difference between each emergency resource quantity and the corresponding preset resource quantity is equal to the threshold range; if it is equal, take the emergency resource quantity as the emergency resource quantity corresponding to the current target feature, obtain the emergency resource quantities corresponding to multiple target features and each target feature, and determine the resource requirement data of the current disaster environment to be measured;

[0039] And update the corresponding preset resource quantity according to the emergency resource quantity corresponding to the current target feature.

[0040] In a second aspect, the present invention provides an electronic device, including a processor and a memory. The memory stores machine-executable instructions that can be executed by the processor, and the processor can execute the machine-executable instructions to implement the emergency service resource determination method described in any one of the above first aspects.

[0041] An emergency service resource determination method and device based on a perception network model provided by an embodiment of the present invention. The determination method obtains a resource data set of a to-be-detected disaster environment, then preprocesses the resource data set to obtain a perception result data set; subsequently, inputs the perception result data set into a trained perception network model to obtain resource demand data of the current to-be-detected disaster environment, so as to perform emergency service evaluation through the resource demand data; wherein, the resource demand data includes multiple resource demand categories and the resource quantities matching each of the resource demand categories. Based on this, the present invention can accurately analyze and evaluate the disaster situation, and perform intelligent analysis and accurate estimation on the required emergency resources, overcoming problems such as information fragmentation, uneven resource allocation, and low matching efficiency in the current management and allocation of emergency service resources, and improving the accuracy of disaster site situation measurement.

[0042] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0044] Figure 1 Shows a flowchart of the steps of the emergency service resource determination method provided by an embodiment of the present invention;

[0045] Figure 2 Shows a sub-step flowchart of step 100 in an embodiment of the present invention;

[0046] Figure 3 Shows a sub-step flowchart of step 200 in an embodiment of the present invention;

[0047] Figure 4 Shows a processing flowchart of step 200 in an embodiment of the present invention;

[0048] Figure 5 Shows one of the sub-step flowcharts of step 300 in an embodiment of the present invention;

[0049] Figure 6Shows the sub-step flowchart of step 301 in the embodiment of the present invention;

[0050] Figure 7 Shows the sub-step flowchart of step 302 in the embodiment of the present invention;

[0051] Figure 8 Shows the processing flowchart of step 303 in the embodiment of the present invention;

[0052] Figure 9 Shows the second sub-step flowchart of step 300 in the embodiment of the present invention;

[0053] Figure 10 Shows the structural schematic diagram of the server in the embodiment of the present invention.

[0054] Icon: 10 - Server. Detailed implementation manners

[0055] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Usually, the components of the embodiments of the present invention described and shown in the accompanying drawings here can be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0057] It should be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including the said element.

[0058] As described in the background art, there are problems such as information fragmentation, uneven resource distribution, and low matching efficiency in the management and allocation of current emergency service resources.

[0059] Based on the above problems, this application provides a method that can accurately analyze and evaluate the disaster situation, and intelligently analyze and accurately estimate the required emergency resources, providing intelligent services for the rapid decision-making and dispatching of emergency service resources.

[0060] The following will introduce in detail the emergency service resource determination method and device provided by this application based on the perception network model.

[0061] Please refer to Figure 1 , Figure 1 , which shows the step flowchart of an emergency service resource determination method provided by the present invention. The emergency service resource determination method in this application includes steps 100 to 300.

[0062] Step 100: Obtain the resource data set of the disaster environment to be measured.

[0063] Among them, the resource data set includes various types of disaster feature data.

[0064] Step 200: Preprocess the resource data set to obtain the perception result data set;

[0065] Step 300: Input the perception result data set into the trained perception network model to obtain the resource requirement data of the current disaster environment to be measured, so as to conduct emergency service evaluation through the resource requirement data.

[0066] Among them, the resource requirement data includes multiple resource requirement categories and the resource quantities matching each resource requirement category.

[0067] Based on the perception network theory, the present invention constructs an emergency service resource determination method based on the perception network model. This method uses the perception modeling theory to conduct capacity evaluation and analysis modeling of emergency service resources. It can, on the basis of comprehensively obtaining various data and information at the event site and judging the situation, uniformly manage various resource requirements at the event site, quantitatively calculate specific requirements, and then obtain the resource requirement data of the current disaster environment to be measured, so that emergency service management personnel can quickly determine the decision of emergency service resources based on this resource requirement data to ensure personnel safety.

[0068] It should be noted that in this embodiment, the resource requirement data includes multiple resource requirement categories and the resource quantities matching each resource requirement category. The above resource requirement categories can be respectively the types (or attributes) of rescue teams and rescue materials, and the resource quantity is the number of rescue teams corresponding to the corresponding rescue team types, the quantities corresponding to various rescue materials, etc.

[0069] To ensure the diversity of data indicators and improve the accuracy of the emergency service resource determination method in this application, please, on the basis of Figure 1 , refer to Figure 2 , Figure 2 , which shows the sub-step flowchart of step 100 in this embodiment. Among them, step 100 in this embodiment includes step 101 and step 102.

[0070] Step 101: Construct a disaster perception network.

[0071] Step 102: Obtain the real-time data of the disaster environment to be measured and the data parameters related to the current disaster environment to be measured through the disaster perception network, and obtain a resource dataset.

[0072] Among them, the resource dataset at least includes environmental monitoring data, personnel distribution data, and traffic condition data.

[0073] In this embodiment, the specific implementation manner of obtaining the resource dataset of the disaster environment to be measured can rely on the disaster perception network to collect the data at the scene of sudden events in real time.

[0074] In a possible implementation manner, the construction method of the above-mentioned disaster perception network can be: deploy various physical sensors in key urban areas, such as commercial areas, residential areas, traffic arteries, etc. The various physical sensors monitor the environmental parameters indoors and outdoors in real time, so as to obtain the real-time data corresponding to the exact disaster environment to be measured when a disaster occurs. In addition, the disaster perception network can also integrate and develop a data interface program to dock with mainstream social media platforms to obtain disaster-related information published by the public, including text, pictures, and videos.

[0075] In this embodiment, the disaster perception network can also integrate and process the above-mentioned multi-type and multi-source data, and use the integrated dataset as the final resource dataset. In a possible implementation manner, the resource dataset at least includes key information such as the address information of the disaster environment to be measured, the time of disaster occurrence, the affected range, and the disaster event. The multi-type disaster characteristic data described in this application is the above-mentioned different key information related to the disaster environment to be measured.

[0076] In addition, this application also provides an implementation manner for obtaining the resource dataset of the disaster environment to be measured. It should be noted that this manner can supplement the implementation manner of the previous embodiment to improve the richness of the disaster characteristic data and the accuracy of the emergency service resource determination method.

[0077] [[ID=2,2]]The supplementary implementation manner described in this embodiment may include: drone patrol and manual information collection. Among them, drone patrol means: install a high-precision radiation detector, a high-definition camera, and an infrared thermal imager on the drone, and then after the disaster occurs, use the above-mentioned modified drone to monitor the radiation dose rate in the air in real time, and at the same time use the high-definition camera and the infrared thermal imager to take on-site images and videos to identify the location of the disaster source, the direction and range of disaster spread, and the situation of affected buildings and trapped people. Manual information collection means: rescue personnel conduct manual information collection at the disaster scene; record the needs of the affected people and count the number of damaged infrastructure.

[0078] Based on the above implementation method, after obtaining the resource data set, the disaster characteristic data of multiple types can be further preprocessed. Please Figure 1 on the basis of Figure 3 , Figure 3 shows a step-by-step flowchart of step 200, and this step 200 includes steps 201 to 203.

[0079] Step 201: Eliminate the noise of each disaster characteristic data in the resource data set.

[0080] Step 202: Normalize each disaster characteristic data after eliminating the noise to obtain the normalized disaster characteristic data.

[0081] Step 203: Extract the target features of the normalized disaster characteristic data, and label the target features to obtain the feature labels related to the disaster environment to be measured for each disaster characteristic data, which are used as the perception result data set.

[0082] In this embodiment, before extracting the target features of each disaster characteristic data, it is necessary to first perform a data cleaning and format standardization operation process on the resource data set to improve the accuracy of the data.

[0083] In a possible implementation manner, the implementation manner of eliminating the noise of each disaster characteristic data in the resource data set in step 201 and performing data cleaning is as follows: using statistical analysis methods, identifying and removing abnormal data points caused by equipment failures or signal interferences to obtain the disaster characteristic data with abnormal values removed; then using techniques such as interpolation and regression analysis to reasonably fill in the missing data points to ensure the integrity of the data; finally, duplicate data entries can also be identified and deleted by comparing data records to eliminate redundant parameters, thereby obtaining the disaster characteristic data after eliminating the noise.

[0084] It should be noted that the present application does not limit the operation sequence or specific implementation manner of the above data cleaning, as long as the integrity and accuracy of the data can be ensured. The above implementation manner is only a simple exemplary illustration and should not be regarded as a limitation of the data cleaning step.

[0085] In a possible implementation manner, the normalization operation in step 202 is to uniformly convert the data from different channels and formats into a structured format acceptable to the analysis model to obtain the normalized disaster characteristic data.

[0086] To improve the convenience of the emergency service resource determination method, after normalizing the resource dataset, it is also possible to extract target features from the disaster characteristic data of different types in the resource dataset, label the extracted target features, and further determine the precise location and scope of influence of the disaster as well as the time when the disaster occurred, so as to facilitate the subsequent determination of resource demand data using the perception network model.

[0087] In this embodiment, the implementation manner of step 203 can be:

[0088] Perform feature extraction on different types of data in each normalized disaster characteristic data respectively.

[0089] Taking the processing of sound data as an example, first, speech recognition technology can be applied to convert the sound signal into text data, and then natural language processing technology can be used to extract the keywords describing the nature and urgency of the disaster from the text data.

[0090] Taking the processing of video data as an example, if the dynamic image processing method is adopted, motion detection and behavior recognition technologies can be used to extract the dynamic information in the video, such as crowd flow and vehicle movement, so as to further evaluate the impact of the disaster on traffic and personnel distribution; if the static image processing method is adopted, video frame extraction technology can be used to capture the static images of the disaster scene to further analyze the impact of the disaster on buildings and other infrastructure.

[0091] Taking the processing of text data as an example, keyword extraction and context recognition can be directly performed. For example, natural language processing technology can be used to extract keywords from the text and recognize the context to understand the description information of the disaster scene.

[0092] Furthermore, after obtaining the features corresponding to the above different data samples, the integrated data can be classified according to the features and uses of the data. In this embodiment, the data types are divided into: environmental monitoring category, including the distribution range, density and harmful degree of harmful radiation and harmful gases; personnel distribution category, including population density, personnel movement trajectory, etc.; traffic condition category, such as urban road density, road traffic flow, road congestion situation, and peak traffic flow time of the road, etc.

[0093] Finally, to ensure the consistency and comparability of the data, Sensor-ML language can be used to perform normalized description on the extracted features. Based on this, the present invention can summarize different categories of resource data in this way and perform numerical description to realize the quantitative management of various perception resources in the disaster environment and obtain the final perception result dataset.

[0094] Among them, reference can be made to Figure 4 , Figure 4The processing flow chart of step 200 in this embodiment is shown. The perceived result data set may include data such as time, wind force, wind direction, disaster type, disaster level, population, disaster situation, roads, and facilities.

[0095] For the convenience of reference by emergency management service personnel, the present application also discloses a data preprocessing method. After obtaining the final perceived result data set, data fusion technologies such as data association and data fusion algorithms can be used to integrate relevant information scattered in different data sources to form a complete data view of the disaster event.

[0096] Before obtaining the resource requirement data of the current disaster environment to be measured by using the trained perception network model, the present application can also first screen each data in the perceived result data set to screen out target features that better meet the evaluation indicators.

[0097] In this embodiment, an efficiency evaluation model can be first constructed. The efficiency evaluation model can use linear regression analysis to determine the linear relationship between target features. The calculation formula can be expressed as:

[0098] Y = Xβ + ε;

[0099] In the formula, Y is the dependent variable, representing the evaluation result of emergency service efficiency; X is the independent variable matrix, representing the target features of disaster data; β is the regression coefficient vector, representing the influence degree of each feature on the efficiency evaluation; ε is the error term, representing the random error of the model.

[0100] Among them, the regression coefficient β can be estimated by the least squares method to minimize the sum of squared residuals. That is, the calculation formula of the regression coefficient vector can be expressed as: β^ = argmin β ||Y - Xβ|| 2 , where argmin β ||.|| 2 is the calculation function of the least squares method.

[0101] Furthermore, by comparing the evaluation results corresponding to each target feature, target features with better evaluation results can be screened out from each target feature. For example, target features below the preset evaluation value are excluded from each target feature, and then the disaster feature data corresponding to the final target features is obtained, constituting the perceived result data set.

[0102] Based on this, the present application can further screen out target features that better meet the evaluation indicators through the evaluation result of emergency service efficiency.

[0103] Please, on the basis of Figure 1 , refer to Figure 5 , Figure 5 The sub-step flow chart of step 300 is shown. This step 300 includes steps 301 to 303.

[0104] Step 301: Based on the knowledge graph, match the corresponding matching resources of each target feature in the current disaster type under the perception result data set.

[0105] Step 302: Determine the similarity score between each target feature and the corresponding matching resources.

[0106] Step 303: Calculate the number of emergency resources corresponding to each target feature according to the similarity score.

[0107] In this embodiment, the construction and training of the perception network model can be as follows: Based on historical disaster data and machine learning algorithms, a radioactive accident emergency service effectiveness evaluation model is trained. This perception network model can evaluate the types and quantities of emergency resources required according to factors such as the scale, intensity, and impact range of the disaster. In a possible implementation manner, the machine learning algorithm may include a decision tree algorithm and a knowledge graph model. Based on this, the perception network model can predict the effectiveness of resources such as vehicles, equipment, and rescue personnel according to characteristics such as the type of disaster, affected area, spread speed, and population density in the affected area. At the same time, the knowledge graph model is used to match the resource demand categories with the corresponding resource quantities. For example, according to the radiation type, coverage range, and radiation diffusion speed, a corresponding rescue plan is intelligently matched, and the rescue plan includes the required resource demand categories and the corresponding resource quantities.

[0108] In this embodiment, a domain knowledge graph can be constructed by collecting and organizing professional knowledge in the field of emergency rescue, including disaster types, emergency resources, rescue processes, disposal methods, etc.

[0109] After obtaining the perception network model, the resource demand data of the current disaster environment to be measured can be obtained by using the perception network model. Please refer to Figure 5 on the basis of Figure 6 , Figure 6 The sub-step flowchart showing Step 301 is shown, and Step 301 includes Step 3011 to Step 3013.

[0110] Step 3011: Based on the knowledge graph, match the corresponding initial matching resource categories of each target feature in the current disaster type under the perception result data set.

[0111] Step 3012: Calculate the matching degree between each target feature and the corresponding initial matching resource category.

[0112] Step 3013: Screen the matching resource categories that meet the preset matching value from the corresponding initial matching resource categories as the final matching resources.

[0113] In this embodiment, the calculation formula of the matching degree in Step 3012 satisfies:

[0114]

[0115] Among them, MD is the matching degree, n is the total number of target features in the perception result dataset, w j is the weight of the j-th target feature, x j is the value of the j-th target feature in the perception result dataset, y j is the reference value of the j-th target feature in the knowledge graph, sin(x j , y j ) is the similarity function value of the j-th target feature.

[0116] In this embodiment, the function of the knowledge graph model is to obtain disaster feature information. For example, after information such as the above-mentioned time, wind speed, and wind force, it can be retrieved in the knowledge graph through semantic understanding to obtain the corresponding entities and relationships, that is, the resource requirements such as rescue teams, rescue capabilities, and equipment types corresponding to information such as time, wind speed, and wind force, and obtain the initial matching resource categories.

[0117] It should be noted that the data information sources in the initial matching resource categories come from the above-mentioned collection and collation of professional knowledge in the field of emergency rescue.

[0118] In this embodiment, the graph traversal algorithm is also used to traverse the path information corresponding to the type information in the initial matching resource categories in the knowledge graph, and perform a similarity evaluation on the path information, that is, calculate the matching degree between each target feature and the corresponding initial matching resource category in step 3012, so as to infer the types of rescue materials required for different perception elements (the annotations corresponding to the above target features).

[0119] Furthermore, in this embodiment, the final matching resources matching any perception element can be screened through a preset matching degree value. For example, if the matching degree MD is greater than the preset value T, it is considered that the current perception element matches the reference value in the knowledge graph, and then the type of rescue materials required is obtained.

[0120] After obtaining the screened and final matching resources, determine the similarity score between each target feature and the corresponding matching resource, and then use the similarity score to obtain the quantity of emergency resources corresponding to each target feature.

[0121] Please, on the basis of Figure 5 , refer to Figure 7 , Figure 7 which shows the sub-step flowchart of step 302. In this embodiment, step 302 includes steps 3021 to 3022.

[0122] Step 3021: Calculate the similarity between each target feature and the corresponding matching resource.

[0123] Step 3022: Determine the similarity score between the corresponding matching resources according to the similarity.

[0124] It should be noted that this embodiment does not limit the calculation method of similarity. In a possible implementation manner, the calculation formula of the similarity S can be expressed as:

[0125]

[0126] In the formula, w i is the weight of the i-th target feature, and m i is the matching degree of the i-th target feature, and the value is 0 or 1.

[0127] Subsequently, according to the similarity value, a matching degree score can be generated for the matching resources corresponding to each target feature, and the range of the matching degree score is [0, 1].

[0128] Based on this, please, on the basis of Figure 5 , refer to Figure 8 , Figure 8 shows the sub-step flowchart of step 303. In this embodiment, step 303 includes steps 3031 to 3033.

[0129] Step 3031: Determine the initial emergency resource quantity based on the similarity score and the preset resource quantity.

[0130] Step 3032: Determine the dynamic adjustment coefficient based on the dynamic parameters in the perception result dataset.

[0131] Step 3033: Determine the emergency resource quantity corresponding to each target feature based on the initial emergency resource quantity and the dynamic adjustment coefficient.

[0132] In this embodiment, the determination formula of the emergency resource quantity satisfies:

[0133]

[0134] In the formula, Q is the emergency resource quantity; s i is the similarity score between the i-th target feature and the corresponding matching resource category; d i is the preset resource quantity corresponding to the i-th target feature; c m is the meteorological condition adjustment coefficient; c i is the illumination condition adjustment coefficient; c t is the traffic condition adjustment coefficient.

[0135] In this embodiment, the initial emergency resource quantity can be determined first based on the similarity score and the preset resource quantity through calculation methods such as linear interpolation or weighted average. The calculation method of the initial emergency resource quantity can be expressed as: In the formula, Q is the emergency resource quantity; si is the similarity score between the i-th target feature and the corresponding matching resource category; d i is the preset resource quantity corresponding to the i-th target feature.

[0136] To further simulate the possible paths of disaster development and predict secondary disasters and long-term impacts, the perception network model in this application further includes a time series analysis model or a numerical simulation model. Then, through this perception network model, the development trend of the disaster is predicted to obtain the disaster state at a future moment, including possible paths, changes in the affected range, the occurrence probability of secondary disasters, etc.

[0137] In a possible implementation manner, the perception network model in this application can monitor and predict dynamic elements such as meteorological changes, lighting environment changes, and traffic environment changes in real time, and determine a dynamic adjustment coefficient based on these dynamic elements to optimize the initial emergency resource quantity.

[0138] When the dynamic adjustment coefficient includes a meteorological condition adjustment coefficient c m , a lighting condition adjustment coefficient c l , and a traffic condition adjustment coefficient c t , in this embodiment, the formula for determining the emergency resource quantity satisfies:

[0139]

[0140] It should be noted that this embodiment does not limit the process of the time series analysis model to determine the dynamic adjustment coefficient based on dynamic elements.

[0141] Furthermore, this application can also utilize the analysis and deduction ability of the knowledge graph in the field of disaster chains to interpret and identify the future environmental situation in the disaster occurrence area. According to the dynamic change process of various target features, such as environmental changes, the occurrence of potential secondary disasters, environmental data conditions, etc., the risk factors affecting rescue are interpreted and identified, and then the possible new resource requirements are calculated. Among them, the calculation formula for the new resource requirements can satisfy: RD = f(E, SD, PD);

[0142] In the formula, RD represents the newly added resource demand, E represents the environmental change parameter, SD represents the occurrence probability of secondary disasters, PD represents the main risk factor parameter, and f is a function used to calculate the resource demand based on these parameters.

[0143] Further, the present application can further calculate based on the above resource demand data in combination with specific disaster parameters to determine the specific quantity requirements of each resource. For example, according to factors such as radiation level, affected area, population density, etc., calculate the quantities of resources such as protective clothing, decontamination equipment, medical supplies, etc.; the specific quantity requirements are presented in the form of data values, directly reflecting the required resource quantities, facilitating decision-makers to allocate and make decisions on resources.

[0144] In a possible implementation manner, the calculation process of the above specific resource demand values can be understood as follows: The required number of rescue personnel P can be determined according to the affected area A (unit: square kilometers) and the number of rescue personnel required per capita r (unit: person / square kilometer). The calculation formula for the required number of rescue personnel P satisfies: P = A × r; after determining the required number of rescue personnel P, in combination with the number of equipment required per rescue personnel e (unit: equipment / person), calculate the required number of rescue equipment D, and the calculation formula satisfies: D = P × e; in addition, the total amount of materials M can be calculated based on the affected population N (unit: person) and the per capita material demand s (unit: unit material / person), and the calculation formula satisfies: M = N × s.

[0145] The present application can obtain the final resource demand data based on the above two determination methods and generate a resource demand list, which details the scale of the rescue team, the level of rescue capabilities, the types of equipment, and the types and quantities of rescue materials, providing clear guidance for resource allocation.

[0146] In summary, the present invention can achieve accurate estimation of emergency service capabilities, improve the estimation accuracy, and provide a scientific basis for emergency decision-making by integrating multiple data sources and intelligent analysis technologies.

[0147] To further improve the sustainability of the perception network model in the present application, please Figure 5 on the basis of Figure 9 and refer to Figure 9 There is also shown a step-by-step flowchart of step 300, where step 300 further includes step 304.

[0148] Step 304: Determine whether the difference between the quantity of each emergency resource and the corresponding preset resource quantity is equal to the threshold range;

[0149] If it is equal, use the quantity of the emergency resource as the quantity of the emergency resource corresponding to the current target feature, obtain the emergency resource quantities corresponding to multiple target features and each target feature, and determine the resource demand data of the current disaster environment to be measured; and return to step 303 to update the corresponding preset resource quantity according to the quantity of the emergency resource corresponding to the current target feature.

[0150] Otherwise, use the corresponding preset resource quantity as the resource demand data of the current disaster environment to be measured.

[0151] In this embodiment, the quantity range corresponding to the preset resource type in the existing resource demand template can be matched with the characteristics of the current disaster environment to be measured. When the actual demand value (the quantity of emergency resources corresponding to the current target feature) falls within the preset quantity range in the resource demand template, it is considered a successful match. Among them, the construction method of the existing resource demand template is as follows: the influence range, affected groups, influence time, possibility of secondary disasters, professional requirements for emergency services, etc. of different disaster levels are preset.

[0152] At the same time, the corresponding preset resource quantity is updated using the quantity of emergency resources corresponding to the current target feature to improve the effectiveness of the emergency service resource determination method in the present invention.

[0153] Based on this, emergency management personnel can put forward targeted resource allocation suggestions according to the above resource demand data, improve the utilization efficiency of emergency resources, and adjust the resource configuration plan in real-time feedback to enhance the response speed and handling ability of emergency services.

[0154] Following a similar idea to the previous embodiment, the present invention also provides an electronic device, which includes a processor and a memory. The memory stores machine-executable instructions that can be executed by the processor, and the processor can execute the machine-executable instructions to implement the steps of the above emergency service resource determination method.

[0155] Following a similar idea to the previous embodiment, please refer to Figure 10 , Figure 10 to provide a block diagram of a server. The server 10 includes a memory, a processor, and a communication module. Each element of the memory, the processor, and the communication module is directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines.

[0156] Among them, the memory is used to store programs or data. The memory can be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0157] The processor is used to read / write the data or programs stored in the memory and execute corresponding functions.

[0158] The communication module is used to establish a communication connection between the server and other communication terminals through the network, and is used to transmit and receive data through the network.

[0159] It should be understood that Figure 10 the structure shown is only a schematic diagram of the server structure, and the server may further include more or fewer components than those shown in Figure 10 or different configurations from those shown in Figure 10 shown. Figure 10 Each component shown in can be implemented by hardware, software or a combination thereof.

[0160] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0161] In addition, in each embodiment of the present invention, the functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0162] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0163] The foregoing are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining emergency service resources based on a perception network model, characterized in that It includes the following steps: Obtain a resource dataset of the disaster environment to be measured; wherein, the resource dataset includes various types of disaster feature data; Preprocess the resource dataset to obtain a perception result dataset; Input the perception result dataset into a trained perception network model to obtain the resource demand data of the current disaster environment to be measured, so as to conduct an emergency service assessment through the resource demand data; Wherein, the resource demand data includes multiple resource demand categories and the resource quantities matching each of the resource demand categories.

2. The method for determining emergency service resources according to claim 1, wherein The step of preprocessing the resource dataset to obtain perception result data includes: Eliminate the noise of each of the disaster feature data in the resource dataset; Normalize each of the disaster feature data after noise elimination to obtain each of the normalized disaster feature data; Extract the target features of each of the normalized disaster feature data, and label the target features to obtain the feature labels of each of the disaster feature data related to the disaster environment to be measured, so as to obtain a perception result dataset.

3. The emergency service resource determination method according to claim 1, characterized in that The step of inputting the perception result dataset into a trained perception network model to obtain the resource demand data of the current disaster environment to be measured includes: Match the target features in the perception result dataset with the corresponding matching resources under the current disaster type based on a knowledge graph; Determine the similarity score between each target feature and the corresponding matching resource; Calculate the emergency resource quantity corresponding to each target feature according to the similarity score.

4. The emergency service resource determination method according to claim 3, wherein The step of matching the target features in the perception result dataset with the corresponding matching resources under the current disaster type based on a knowledge graph includes: Match the target features in the perception result dataset with the corresponding initial matching resource categories under the current disaster type based on a knowledge graph; Calculate the matching degree between each target feature and the corresponding initial matching resource category; Screen the matching resource categories that meet the preset matching value from the corresponding initial matching resource categories according to the matching degree as the final matching resources.

5. The emergency service resource determination method according to claim 4, wherein The calculation formula of the matching degree satisfies: Among them, MD is the matching degree, n is the total number of target features in the perceived result dataset, w j is the weight of the j-th target feature, x j is the value of the j-th target feature in the perceived result dataset, y j is the reference value of the j-th target feature in the domain knowledge graph, sin(x j ,y j ) is the similarity function value of the j-th target feature.

6. The emergency service resource determination method according to claim 3, wherein The step of determining the similarity score between each target feature and the corresponding resource demand category includes: Calculate the similarity between each target feature and the corresponding matching resource; Determine the similarity score between the corresponding matching resources according to the similarity.

7. The emergency service resource determination method according to claim 3, wherein The step of calculating the emergency resource quantity corresponding to each target feature according to the similarity score includes: Determine the initial emergency resource quantity based on the similarity score and the preset resource quantity; Determine the dynamic adjustment coefficient based on the dynamic parameters in the perception result dataset; Determine the emergency resource quantity corresponding to each target feature based on the initial emergency resource quantity and the dynamic adjustment coefficient.

8. The method for determining emergency service resources according to claim 7, wherein The determination formula of the emergency resource quantity satisfies: Where Q is the quantity of emergency resources; s i is the similarity score between the i-th target feature and the corresponding matching resource category; d i is the preset resource quantity corresponding to the i-th target feature; c m is the meteorological condition adjustment coefficient; c i is the lighting condition adjustment coefficient; c t is the traffic condition adjustment coefficient.

9. The emergency service resource determination method according to claim 7, wherein The step of inputting the perception result dataset into a trained perception network model to obtain the resource demand data of the current disaster environment to be measured further includes: Determine whether the difference between the quantity of each of the emergency resources and the corresponding preset resource quantity is equal to the threshold range; if it is equal, use the quantity of the emergency resources as the quantity of the emergency resources corresponding to the current target feature, obtain a plurality of target features and the quantity of the emergency resources corresponding to each target feature, and determine the resource demand data of the current disaster environment to be measured; And update the corresponding preset resource quantity according to the quantity of the emergency resources corresponding to the current target feature.

10. An electronic device, characterized in that, It includes a processor and a memory, the memory stores machine-executable instructions that can be executed by the processor, and the processor can execute the machine-executable instructions to implement the emergency service resource determination method according to any one of claims 1-9.

Images