Method, device and computer equipment for matching data of emergency plan for sudden incidents

Abstract

The present application relates to a method, device and computer equipment for matching emergency plan data for emergencies. The method of the present application includes obtaining a data set; processing the data set to establish an emergency plan generation model; using the emergency plan generation model to process the current emergency event and generate the current emergency plan data; reading the current execution subject in the current emergency plan data, sending the current emergency plan data to the terminal device corresponding to the current execution subject, and starting the timing; sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data; and displaying the current emergency event, the current emergency plan data and the evaluation information in association. The method realizes the establishment of an emergency plan generation model using historical quantities, and then uses the emergency plan generation model to analyze the emergency events that are occurring and generate emergency plan data, thereby solving the problem of low efficiency in the traditional manual formulation of emergency plan data.

Description

Technical Field

[0001] The present application relates to the field of intelligent data processing technology, and in particular to a method, device and computer equipment for matching data of emergency response plans for emergencies. Background Art

[0002] With the continuous development and progress of society, emergency management plays a vital role in ensuring the safety of people's lives and property and social stability. In the current era, the complexity and diversity of emergency events are becoming more and more significant, and the traditional emergency management model is facing severe challenges.

[0003] The rise of big data technology has brought new development opportunities to the field of emergency management. By collecting, organizing and analyzing massive amounts of data, detailed information about emergencies can be quickly obtained, including the location, time, scale and scope of impact of the incident. These data help emergency management departments to more accurately assess the situation of the incident and formulate more scientific and reasonable emergency strategies. For example, before a natural disaster occurs, early prediction of the disaster can be achieved by analyzing meteorological and geological data, thereby gaining valuable time for evacuating people and allocating materials. The application of artificial intelligence technology has further improved the efficiency and level of emergency management. Artificial intelligence can quickly process and analyze large amounts of data and automatically identify the type and severity of emergency events. For example, when a fire occurs, artificial intelligence can use image recognition technology to quickly determine the location of the fire source and the intensity of the fire, and provide accurate information to the fire department so that effective firefighting actions can be taken in a timely manner. However, the existing technology still needs to be improved in terms of response efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device and computer equipment that can quickly generate emergency plan data and quickly distribute and execute emergency plan data matching for emergencies in response to the above technical problems.

[0005] A method for matching emergency response plan data, comprising the following steps:

[0006] Obtain a data set including historical emergency event data and historical emergency plan data corresponding to the historical emergency event data; the historical emergency event data at least includes public health safety events, natural disaster events, traffic accident events and social security events; the historical emergency plan data at least includes execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle;

[0007] Process the data set and establish an emergency plan generation model;

[0008] Use the emergency plan generation model to handle current emergencies and generate current emergency plan data;

[0009] Read the current execution subject in the current emergency plan data, send the current emergency plan data to the terminal device corresponding to the current execution subject, and start timing;

[0010] When the timing duration is equal to the current execution cycle in the current emergency plan data, an evaluation request is sent to the terminal device to obtain evaluation information for the current emergency plan data;

[0011] After obtaining the evaluation information, the current emergency event, current emergency plan data and evaluation information are displayed in association.

[0012] In one embodiment, the evaluation information includes text feedback, completion score, accuracy score, and rationality score;

[0013] When the timing duration is equal to the current execution cycle in the current emergency plan data, after the step of sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data, the method further includes the steps of:

[0014] Update the current emergency plan data based on text feedback, completion score, accuracy score and rationality score;

[0015] Update the emergency plan generation model based on current emergencies and updated current emergency plan data.

[0016] In one embodiment, when the timing duration is equal to the current execution cycle in the current emergency plan data, after the step of sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data, the step further includes:

[0017] Based on the evaluation information, obtain the current execution efficiency score of the current execution subject;

[0018] The final execution efficiency score of the current execution entity is updated based on the previous execution efficiency score and the current execution efficiency score of the current execution entity; the final execution efficiency score is used as a consideration factor in selecting the execution entity during the process of generating emergency plan data.

[0019] In one embodiment, in the step of obtaining the current execution efficiency score of the current execution subject based on the evaluation information, the current execution efficiency score is obtained based on the following formula:

[0020]

[0021] in, Indicates the current execution efficiency score; Indicates the completion score; represents the accuracy score; represents the plausibility score;

[0022] In the step of updating the final execution efficiency score of the current execution subject according to the previous execution efficiency score and the current execution efficiency score of the current execution subject, the final execution efficiency score is obtained based on the following formula:

[0023]

[0024] in, Indicates the final execution efficiency score; Indicates the last execution efficiency score.

[0025] In one embodiment, the step of processing the data set to establish an emergency plan generation model includes the steps of:

[0026] The word frequency-inverse document frequency algorithm is used to extract data features in the data set to obtain a data feature set;

[0027] Use named entity recognition algorithm to extract specific attributes in the data set and obtain a specific attribute set;

[0028] The cosine similarity algorithm is used to classify the objects in the data feature set and the specific attribute set to obtain the object classification results;

[0029] The naive Bayes classification algorithm is used to process the object classification results to obtain the category information of historical emergency data;

[0030] The tensor flow algorithm is used to process data feature sets, specific attribute sets, category information and model parameters to build an emergency plan generation model;

[0031] Among them, in the process of building the emergency plan generation model, the stochastic gradient descent algorithm is used to update the model parameters.

[0032] In one embodiment, the step of using the emergency plan generation model to process the current emergency event and generate the current emergency plan data further includes the steps of:

[0033] Use the emergency plan generation model to analyze the characteristic information of the current emergency;

[0034] Based on the feature information and the final execution efficiency score of the execution subject in the current emergency plan data, the execution subject in the current emergency plan data is assigned; the execution subject is one of the following: composed of N equal units, composed of the nearest delegable unit, or composed of a command unit and N equal units.

[0035] In one embodiment, in a mode where the execution body is composed of N equal units, the equal units are obtained based on the following formula:

[0036]

[0037] in, represents equal units; represents a positive integer; represents the emergency plan generation model; Represents feature information;

[0038] In a manner where the execution subject is composed of the nearest delegable unit, the nearest delegable unit is obtained based on the following formula:

[0039]

[0040] in, It indicates that the unit can be assigned recently; Indicates the closest distance; Indicates the unit address; Indicates the minimum number of personnel required; Indicates the place of execution; Indicates the unit type; represents the minimum execution efficiency score; represents a positive integer;

[0041] In the manner where the execution subject is composed of a command unit and N equal units, the command unit is obtained based on the following formula:

[0042]

[0043] in, Indicates the command unit; Indicates the time-to-reach score; Representative execution experience rating; represents equal units; I represents event categories.

[0044] A device for matching data of emergency response plans for emergencies, the device comprising:

[0045] A data acquisition module is used to acquire a data set including historical emergency event data and historical emergency plan data corresponding to the historical emergency event data; the historical emergency event data at least includes public health safety events, natural disaster events, traffic accidents and social security events; the historical emergency plan data at least includes execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle;

[0046] The model building module is used to process the data set and build an emergency plan generation model;

[0047] The emergency plan data generation module is used to use the emergency plan generation model to handle the current emergency event and generate the current emergency plan data;

[0048] The plan allocation module is used to read the current execution subject in the current emergency plan data, send the current emergency plan data to the terminal device corresponding to the current execution subject, and start timing;

[0049] An evaluation acquisition module, used to send an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data when the timing duration is equal to the current execution cycle in the current emergency plan data;

[0050] The information display module is used to display the current emergency event, the current emergency plan data and the evaluation information in association with each other after obtaining the evaluation information.

[0051] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0052] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0053] One of the above technical solutions has the following advantages and beneficial effects:

[0054] The method for matching emergency plan data for sudden events in the present application includes the following steps: obtaining a data set including historical sudden event data and historical emergency plan data corresponding to the historical sudden event data; processing the data set to establish an emergency plan generation model; using the emergency plan generation model to process the current sudden event to generate current emergency plan data; reading the current execution subject in the current emergency plan data, sending the current emergency plan data to the terminal device corresponding to the current execution subject, and starting timing; when the timing duration is equal to the current execution period in the current emergency plan data, sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data; after obtaining the evaluation information, displaying the current sudden event, the current emergency plan data, and the evaluation information in association with each other. It is possible to use historical quantities to establish an emergency plan generation model, and then use the emergency plan generation model to analyze the emergencies that are occurring and generate emergency plan data, which solves the problem of low efficiency in traditional manual preparation of emergency plan data. After generating the emergency plan data, the application can also automatically allocate the emergency plan data to the corresponding execution entity, thereby improving the efficiency of emergency plan data transmission. Finally, after the emergency plan data is executed, the emergency plan data will be scored to further optimize the emergency plan generation model so that better emergency plan data can be generated next time. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is an application environment diagram of the emergency response plan data matching method for sudden incidents in an embodiment of the present application.

[0056] Figure 2 Schematic diagram of the process of matching emergency response plan data for emergencies in an embodiment of the present application.

[0057] Figure 3 A flowchart of the steps for constructing an emergency plan generation model in an embodiment of the present application.

[0058] Figure 4 A flowchart for obtaining the execution main steps in the embodiments of the present application.

[0059] Figure 5 A flowchart of the step of updating the final execution efficiency score in an embodiment of the present application.

[0060] Figure 6 It is a structural block diagram of the emergency response plan data device in the embodiment of the present application.

[0061] Figure 7 Schematic diagram of the internal structure of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application 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 application and are not used to limit the present application.

[0063] The emergency response plan data matching method provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 and the display device 106 communicate with the server 104 through the network. The server 104 obtains a data set containing historical emergency data and historical emergency plan data corresponding to the historical emergency data, establishes an emergency plan generation model based on the data set, and the emergency plan generation model processes the current emergency to generate current emergency plan data, and dispatches the current emergency plan data to the corresponding terminal 102 so that the corresponding execution subject executes the current emergency plan data, obtains evaluation information through the terminal 102, and finally displays the evaluation information using the display device 106. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented with an independent server or a server cluster composed of multiple servers. The display device 106 can be a liquid crystal display device or an LED display device.

[0064] In one embodiment, Figure 2 As shown, a method for matching emergency response plan data is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0065] Step S210, obtain a data set containing historical emergency data and historical emergency plan data corresponding to the historical emergency data. Historical emergency refers to an emergency that occurred in the past. In one example, historical emergency includes at least public health safety events, natural disaster events, traffic accident events, and social security events. The historical emergency data includes the time of occurrence, the location of occurrence, the nature of the event (four levels: particularly serious, serious, large, and general), the on-site conditions, the event category (public health safety events, natural disaster events, traffic accident events, and social security events), etc. The historical emergency plan data refers to the plan formulated to deal with the historical emergency data. In one example, the historical emergency plan data includes at least the execution time, execution location, execution subject, number of execution personnel, execution plan, and execution cycle. The historical emergency data and the historical emergency plan data can be stored in the server's memory, or in an external memory, or in the cloud. When needed, the historical emergency data and the historical emergency data can be directly called.

[0066] Step S220, process the data set and establish an emergency plan generation model. By analyzing the historical data, the basic logic of taking countermeasures for different types of emergencies can be learned, so that when the current emergency occurs, an emergency plan can be formulated with reference to the historical data. In one example, after obtaining the data set, a convolutional neural network model is built through the tensor flow algorithm (TensorFlow) to construct a plan generation model.

[0067] In one example, a feasible method for establishing an emergency plan generation model is provided. Specifically,

[0068] like Figure 3 As shown, the steps of processing the data set and establishing the emergency plan generation model include the following steps:

[0069] Step S310, using the term frequency-inverse document frequency algorithm to extract data features in the data set, and obtain a data feature set. The term frequency-inverse document frequency algorithm (TF-IDF) is a feature vectorization method used for text mining, which is used to evaluate the importance of a word to a document set or a document in a corpus. The TF-IDF algorithm consists of two parts: term frequency (TF) and inverse document frequency (IDF).

[0070] In one example, the specific algorithm is as follows:

[0071] , where TF stands for term frequency, which indicates how often a word appears in a particular document, and IDF stands for inverse document frequency, which indicates how common a word appears in a corpus. Indicative words, Represents a document.

[0072] Based on word frequency and inverse document frequency, the data features in the data set are obtained to form a data feature set. The data features include event nature, on-site conditions, event category, execution subject, number of execution personnel, execution plan and execution cycle.

[0073] Step S320, using a named entity recognition algorithm to extract specific attributes from the data set and obtain a specific attribute set. Among them, the named entity recognition (NER) algorithm is an important task in natural language processing. Its main goal is to identify specific entities in the text. These entities usually include names of people, places, organizations, time, etc. The dictionary matching method in the named entity recognition algorithm can be used to extract specific attributes from the data set, such as time, place, and other data with low word frequency but very important. The principle is: to extract specific attributes such as time and place in the text through predefined time vocabulary lists and place vocabulary lists. The specific algorithm is as follows:

[0074] ,in represents a specific set of attributes extracted; Indicates a specific attribute; Text data representing the incident, Represents a predefined vocabulary, Represents a dictionary matching method.

[0075] Step S330, using the cosine similarity algorithm to classify the objects in the data feature set and the specific attribute set, and obtaining the object classification result. The cosine similarity algorithm is a measurement method for measuring the similarity between two vectors. It evaluates their similarity by calculating the cosine value of the angle between the two vectors. The closer the cosine similarity value is to 1, the more similar the two vectors are; the closer it is to 0, the less similar the two vectors are.

[0076] The cosine similarity algorithm is used to calculate the features with high similarity and classify the features. Each class of features with high similarity can represent an event category, and the event category can be calculated based on this. The object classification result is the classification result of the features corresponding to different event categories.

[0077] The cosine similarity algorithm evaluates the similarity between two text vectors by calculating the cosine value of the angle between them. The cosine similarity algorithm is as follows: ,in Represents the cosine of the angle between two vectors, represents the dot product of vector A and vector B, that is, the sum of the products of the corresponding elements, and are the magnitudes of vectors A and B respectively.

[0078] Step S340: Process the object classification result using a naive Bayes classification algorithm to obtain category information of historical emergency event data.

[0079] Different emergencies have different categories and features. The Naive Bayesian classification algorithm is used to classify features of emergencies of different categories. The Naive Bayesian classification algorithm is a classification method based on the feature conditional independence assumption of the Bayesian theorem. Its basic principle is to calculate the posterior probability of each category in a specific text, and at the same time calculate the feature probability distribution under a given category. Then, the product of the conditional probabilities of each feature of each category in the specific text is used to select the category with the maximum probability. This category and its features are the category and features of the emergency. The specific algorithm is as follows:

[0080] Bayes’ Theorem: , represents the posterior probability of each category A under sample B, represents the probability of sample B appearing given classification A, represents the probability of parameter A before observing any data, is the marginal probability of data B.

[0081] , In the case of category A, the product of the conditional probabilities of each feature of sample B is represented. In the case of category A, the feature The probability distribution of occurrence.

[0082] Finally, the category with the maximum posterior probability is taken as the final classification result (category information, that is, event category), and the features of the text represent the features under this category.

[0083] Maximum a posteriori probability formula: ,in Indicates maximum value calculation.

[0084] Step S350, using the tensor flow algorithm to process the data feature set, specific attribute set, category information and model parameters to build an emergency plan generation model.

[0085] Use TensorFlow to build a convolutional neural network model and construct a plan generation model.

[0086] Plan generation model: .in Indicates the generated plan; The input features (including data feature set, specific attribute set, and category information) reflect various data information in the emergency; represents the model parameters; Represents the emergency plan generation model.

[0087] Step S360, in the process of constructing the emergency plan generation model, the model parameters are updated using the stochastic gradient descent algorithm.

[0088] The model is trained using the data set, and the gradient descent method is used to optimize the model parameters. The core idea of ​​the gradient descent method is to iterate along the negative gradient direction of the loss function. Through repeated iterations, the local minimum of the loss function can be gradually approached, thereby realizing model training and optimization.

[0089] Stochastic Gradient Descent Algorithm: . Indicates The model parameters after iterations are represents the learning rate, Indicates that the loss function is at point In each iteration, the stochastic gradient descent method randomly selects a sample and uses the gradient of the sample to update the model parameters.

[0090] Step S230, the emergency plan generation model is used to process the current emergency event and generate the current emergency plan data. It should be noted that the current emergency plan data includes the execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle. Among them, the determination of the execution subject is related to whether the emergency plan can be successfully completed. Based on the historical emergency plan, the basic elements of the current plan (location of the incident, required personnel, etc.) can be obtained, and the required unit type can be obtained in combination with these basic elements. The units that can be delegated and meet the required unit type are calculated based on the location of the incident, the number of required personnel, etc. For events that require a command unit on site, a field command unit is established by statistically calculating the time when the unit arrives at the location of the incident and the number of times it has on-site command experience. All units participating in the execution of this plan are issued the plan content they are responsible for, and the overall plan is notified to each unit, which is conducive to the linkage between multiple units.

[0091] In order to determine the optimal execution subject, in an example, Figure 4 As shown, the step of using the emergency plan generation model to process the current emergency event and generate the current emergency plan data also includes the following steps:

[0092] Step S410: Analyze the characteristic information of the current emergency event using the emergency plan generation model. It should be noted that the characteristic information includes execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle.

[0093] Step S420, based on the characteristic information and the final execution efficiency score of the execution subject in the current emergency plan data, the execution subject in the current emergency plan data is assigned; the execution subject is one of the following: composed of N equal units, composed of the nearest delegable unit, or composed of a command unit and N equal units. It should be noted that equal units refer to units of the same level. The level of the command unit is higher than that of the equal unit. The final execution efficiency score of the execution subject in the current emergency plan data is a score of the efficiency of the execution subject in executing the plan in the past.

[0094] In one example, an emergency event is complex and requires multiple units. Usually, many units cooperate with each other to implement the plan to solve the emergency event. All the required unit types are analyzed based on the event characteristics. In the case where the execution subject is composed of N equal units, the equal units are obtained based on the following formula:

[0095]

[0096] in, represents equal units; represents a positive integer; represents the emergency plan generation model; Represents feature information;

[0097] In a manner where the execution subject is composed of the nearest delegable unit, the nearest delegable unit is obtained based on the following formula:

[0098]

[0099] in, It indicates that the unit can be assigned recently; Indicates the closest distance; Indicates the address of the unit; Indicates the minimum number of personnel required; Indicates the place of execution; Indicates the unit type; represents the minimum execution efficiency score; represents a positive integer;

[0100] For an emergency, the situation at the scene may be very complicated, so it is necessary to set up a unified command unit on the scene to coordinate the execution of the entire scene. The selection principle is: first, according to the type of event, we get the type of unit needed, and then select the unit that can arrive at the scene as soon as possible and has on-site command experience from this type of unit. We calculate the scores for time and command experience respectively, and the unit with the largest sum of the two scores is the on-site command unit. In the method where the execution subject is composed of a command unit and N equal units, the command unit is obtained based on the following formula:

[0101]

[0102] in, Indicates the command unit; Indicates the time-to-reach score; Representative execution experience rating; represents equal units; I represents event categories.

[0103] Among them, the time score calculation formula is: ,in Indicates the time (minutes) the unit arrived at the scene of the incident, Represents time fraction.

[0104] Experience score calculation formula: ,in Indicates the number of times the unit took on on-site command. Represents experience score.

[0105] Step S240, read the current execution subject in the current emergency plan data, send the current emergency plan data to the terminal device corresponding to the current execution subject, and start timing. After generating the current emergency plan data, the current emergency plan data is distributed to each current execution subject based on the wireless communication technology according to the current execution subject. Among them, when the current emergency plan data arrives at the terminal device, the timing starts. The timing is used to monitor the time for the current execution subject to complete the current emergency plan and ensure that the current execution subject can execute the current emergency plan on time.

[0106] Step S250, when the timing duration is equal to the current execution cycle in the current emergency plan data, an evaluation request is sent to the terminal device to obtain evaluation information for the current emergency plan data. It should be noted that when the timing duration is equal to the current execution cycle in the current emergency plan data, it is assumed that the current execution subject has completed the current emergency plan. In order to know the effect of the current emergency plan, the evaluation information is obtained from the execution subject of the current emergency plan. Therefore, an evaluation request is sent to the terminal device of the execution subject, and the execution subject opens the evaluation link and enters the evaluation information.

[0107] In one example, the evaluation information includes text feedback, a completion score, an accuracy score, and a rationality score.

[0108] Completion score calculation formula: ,in Represents the final calculated completion score, Represents the average of all unit completion scores.

[0109] Accuracy score calculation formula: ,in represents the final calculated accuracy score, Represents the average of all unit accuracy scores.

[0110] Reasonableness score calculation formula: ,in represents the final calculated rationality score, Represents the average of all unit plausibility scores.

[0111] Text feedback is used to describe some evaluation content that cannot be quantified.

[0112] In one example, when the timing duration is equal to the current execution cycle in the current emergency plan data, after the step of sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data, the steps also include: updating the current emergency plan data based on text feedback, completion score, accuracy score and rationality score; updating the emergency plan generation model based on the current emergency event and the updated current emergency plan data. It should be noted that the aforementioned model training method can be used to update the emergency plan generation model.

[0113] In one example, if Figure 5 As shown, when the timing duration is equal to the current execution cycle in the current emergency plan data, after the step of sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data, the step further includes:

[0114] Step S510, based on the evaluation information, obtain the current execution efficiency score of the current execution subject.

[0115] In the step of obtaining the current execution efficiency score of the current execution subject based on the evaluation information, the current execution efficiency score is obtained based on the following formula:

[0116]

[0117] in, Indicates the current execution efficiency score; Indicates the completion score; represents the accuracy score; represents the plausibility score;

[0118] Step S520, updating the final execution efficiency score of the current execution subject according to the previous execution efficiency score and the current execution efficiency score of the current execution subject; the final execution efficiency score is used as a consideration factor for selecting the execution subject in the process of generating emergency plan data.

[0119] In one example, in the step of updating the final execution efficiency score of the current execution subject according to the previous execution efficiency score and the current execution efficiency score of the current execution subject, the final execution efficiency score is obtained based on the following formula:

[0120]

[0121] in, Indicates the final execution efficiency score; Indicates the last execution efficiency score.

[0122] Step S260, after obtaining the evaluation information, the current emergency event, the current emergency plan data and the evaluation information are displayed in association. The current emergency event, the current emergency plan data and the evaluation information are displayed using a display device, for example, three display areas are divided on the display interface of the display device, and the current emergency event, the current emergency plan data and the evaluation information are displayed respectively.

[0123] The method for matching emergency plan data for sudden events in the present application includes the following steps: obtaining a data set including historical sudden event data and historical emergency plan data corresponding to the historical sudden event data; processing the data set to establish an emergency plan generation model; using the emergency plan generation model to process the current sudden event to generate current emergency plan data; reading the current execution subject in the current emergency plan data, sending the current emergency plan data to the terminal device corresponding to the current execution subject, and starting timing; when the timing duration is equal to the current execution period in the current emergency plan data, sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data; after obtaining the evaluation information, displaying the current sudden event, the current emergency plan data, and the evaluation information in association with each other. It is possible to use historical quantities to establish an emergency plan generation model, and then use the emergency plan generation model to analyze the emergencies that are occurring and generate emergency plan data, which solves the problem of low efficiency in the traditional manual formulation of emergency plan data. After generating the emergency plan data, this application can also automatically distribute the emergency plan data to the corresponding execution entity, thereby improving the efficiency of emergency plan data transmission. Finally, after the emergency plan data is executed, the emergency plan data will be scored to further optimize the emergency plan generation model so that better emergency plan data can be generated next time. This application uses emergency plan generation technology to analyze emergencies and generate emergency plans. Through automatic circulation and execution technology, it is possible to automatically distribute and automatically implement and track plans. Through execution result analysis and matching analysis technology, it is possible to analyze the results of plan implementation and strengthen subsequent plan generation strategies.

[0124] It should be understood that although Figure 2-Figure 5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-Figure 5 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0125] In one embodiment, Figure 6 As shown, a device for matching emergency plan data is provided, comprising:

[0126] The data acquisition module 610 is used to acquire a data set including historical emergency event data and historical emergency plan data corresponding to the historical emergency event data; the historical emergency event data at least includes public health safety events, natural disaster events, traffic accidents and social security events; the historical emergency plan data at least includes execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle;

[0127] Model building module 620, used to process the data set and build an emergency plan generation model;

[0128] The emergency plan data generation module 630 is used to process the current emergency event using the emergency plan generation model and generate the current emergency plan data;

[0129] The plan allocation module 640 is used to read the current execution subject in the current emergency plan data, send the current emergency plan data to the terminal device corresponding to the current execution subject, and start timing;

[0130] Evaluation acquisition module 650, used to send an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data when the timing duration is equal to the current execution cycle in the current emergency plan data;

[0131] The information display module 660 is used to display the current emergency event, the current emergency plan data and the evaluation information in association with each other after obtaining the evaluation information.

[0132] For the specific definition of the emergency plan data matching device for emergencies, please refer to the definition of the emergency plan data matching method for emergencies in the above text, which will not be repeated here. Each module in the above emergency plan data matching device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0133] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The library of the computer device is used to store historical emergency event data and historical emergency plan data corresponding to the historical emergency event data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for matching emergency plan data for emergencies is implemented.

[0134] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0135] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0136] Obtain a data set including historical emergency event data and historical emergency plan data corresponding to the historical emergency event data; the historical emergency event data at least includes public health safety events, natural disaster events, traffic accident events and social security events; the historical emergency plan data at least includes execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle;

[0137] Process the data set and establish an emergency plan generation model;

[0138] Use the emergency plan generation model to handle current emergencies and generate current emergency plan data;

[0139] Read the current execution subject in the current emergency plan data, send the current emergency plan data to the terminal device corresponding to the current execution subject, and start timing;

[0140] When the timing duration is equal to the current execution cycle in the current emergency plan data, an evaluation request is sent to the terminal device to obtain evaluation information for the current emergency plan data;

[0141] After obtaining the evaluation information, the current emergency event, current emergency plan data and evaluation information are displayed in association.

[0142] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0143] Obtain a data set including historical emergency event data and historical emergency plan data corresponding to the historical emergency event data; the historical emergency event data at least includes public health safety events, natural disaster events, traffic accident events and social security events; the historical emergency plan data at least includes execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle;

[0144] Process the data set and establish an emergency plan generation model;

[0145] Use the emergency plan generation model to handle current emergencies and generate current emergency plan data;

[0146] Read the current execution subject in the current emergency plan data, send the current emergency plan data to the terminal device corresponding to the current execution subject, and start timing;

[0147] When the timing duration is equal to the current execution cycle in the current emergency plan data, an evaluation request is sent to the terminal device to obtain evaluation information for the current emergency plan data;

[0148] After obtaining the evaluation information, the current emergency event, current emergency plan data and evaluation information are displayed in association.

[0149] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, library or other medium used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0150] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0151] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A method for matching emergency response plan data, characterized in that: The following steps are involved: Acquire a data set including historical emergency event data and historical emergency plan data corresponding to the historical emergency event data; the historical emergency event data at least includes public health and safety events, natural disaster events, traffic accidents and social security events; The historical emergency plan data at least includes the execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle; Processing the data set to establish an emergency plan generation model; The emergency plan generation model is used to process the current emergency event and generate current emergency plan data; Read the current execution subject in the current emergency plan data, send the current emergency plan data to the terminal device corresponding to the current execution subject, and start timing; When the timing duration is equal to the current execution cycle in the current emergency plan data, sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data; After obtaining the evaluation information, the current emergency event, the current emergency plan data and the evaluation information are displayed in association; The step of processing the data set to establish an emergency plan generation model includes the following steps: Using a word frequency-inverse document frequency algorithm to extract data features in the data set to obtain a data feature set; A named entity recognition algorithm is used to extract specific attributes in the data set to obtain a specific attribute set; the specific attributes are important data with low word frequency; Using a cosine similarity algorithm to classify the objects in the data feature set and the specific attribute set to obtain an object classification result; Using a naive Bayesian classification algorithm to process the object classification result to obtain category information of the historical emergency event data; Using a tensor flow algorithm to process the data feature set, the specific attribute set, the category information and the model parameters, and constructing the emergency plan generation model; In the process of constructing the emergency plan generation model, a stochastic gradient descent algorithm is used to update the model parameters.

2. The method for matching emergency response plan data according to claim 1, characterized in that: The evaluation information includes text feedback, completion score, accuracy score and rationality score; When the timing duration is equal to the current execution cycle in the current emergency plan data, after the step of sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data, the method further includes the steps of: Based on the text feedback, the completion score, the accuracy score, and the rationality score, updating the current emergency plan data; Based on the current emergency event and the updated current emergency plan data, the emergency plan generation model is updated.

3. The method for matching emergency response plan data according to claim 1, characterized in that: When the timing duration is equal to the current execution cycle in the current emergency plan data, after the step of sending an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data, the method further includes the steps of: Based on the evaluation information, obtaining a current execution efficiency score of the current execution subject; According to the last execution efficiency score and the current execution efficiency score of the current execution subject, the final execution efficiency score of the current execution subject is updated; The final execution efficiency score is used as a consideration factor in selecting the execution entity during the process of generating emergency plan data.

4. The method for matching emergency response plan data according to claim 3, characterized in that: In the step of obtaining the current execution efficiency score of the current execution subject based on the evaluation information, the current execution efficiency score is obtained based on the following formula: in, represents the current execution efficiency score; Indicates the completion score; represents the accuracy score; represents the plausibility score; In the step of updating the final execution efficiency score of the current execution subject according to the last execution efficiency score and the current execution efficiency score of the current execution subject, the final execution efficiency score is obtained based on the following formula: in, Indicates the final execution efficiency score; Indicates the last execution efficiency score.

5. The method for matching emergency response plan data according to any one of claims 1 to 4, characterized in that: The step of using the emergency plan generation model to process the current emergency event and generate the current emergency plan data also includes the following steps: Using the emergency plan generation model to analyze the characteristic information of the current emergency; Based on the characteristic information and the final execution efficiency score of the execution subject in the current emergency plan data, the execution subject in the current emergency plan data is assigned; the execution subject is one of the following: composed of N equal units, composed of the nearest delegable unit, or composed of a command unit and N equal units.

6. The method for matching emergency response plan data according to claim 5, characterized in that: In the manner in which the execution subject is composed of N equal units, the equal units are obtained based on the following formula: in, represents said equal unit; represents a positive integer; represents the emergency plan generation model; Indicates the characteristic information; In the manner in which the execution subject is composed of the nearest delegable unit, the nearest delegable unit is obtained based on the following formula: in, Indicates the nearest assignable unit; Indicates the closest distance; Indicates the address of the unit; Indicates the minimum number of personnel required; Indicates the place of execution; Indicates the unit type; represents the minimum execution efficiency score; represents a positive integer; In the manner in which the execution subject is composed of a command unit and N equal units, the command unit is obtained based on the following formula: in, indicates said command unit; Indicates the time-to-reach score; Representative execution experience rating; represents equal units; I represents event categories.

7. A data matching device for emergency response plan, characterized in that: The device comprises: A data acquisition module, used to acquire a data set including historical emergency event data and historical emergency plan data corresponding to the historical emergency event data; the historical emergency event data at least includes public health and safety events, natural disaster events, traffic accidents and social security events; the historical emergency plan data at least includes execution time, execution location, execution subject, number of execution personnel, execution plan and execution cycle; A model building module, used to process the data set and build an emergency plan generation model; An emergency plan data generation module, used to use the emergency plan generation model to process the current emergency event and generate current emergency plan data; A plan allocation module, used to read the current execution subject in the current emergency plan data, send the current emergency plan data to the terminal device corresponding to the current execution subject, and start timing; An evaluation acquisition module, configured to send an evaluation request to the terminal device to obtain evaluation information for the current emergency plan data when the timing duration is equal to the current execution cycle in the current emergency plan data; An information display module, used to display the current emergency event, the current emergency plan data and the evaluation information in association with each other after obtaining the evaluation information; Wherein, the model building module is also used to perform the following steps: Using a word frequency-inverse document frequency algorithm to extract data features in the data set to obtain a data feature set; A named entity recognition algorithm is used to extract specific attributes in the data set to obtain a specific attribute set; the specific attributes are important data with low word frequency; Using a cosine similarity algorithm to classify the objects in the data feature set and the specific attribute set to obtain an object classification result; Using a naive Bayesian classification algorithm to process the object classification result to obtain category information of the historical emergency event data; Using a tensor flow algorithm to process the data feature set, the specific attribute set, the category information and the model parameters, and constructing the emergency plan generation model; In the process of constructing the emergency plan generation model, a stochastic gradient descent algorithm is used to update the model parameters.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images