Emergency plan determination method and device, computer device, and storage medium

Abstract

This application relates to a method, apparatus, computer equipment, and storage medium for determining emergency response plans. The method includes: extracting event elements and plan elements from event information of a current production event and plan information of candidate emergency response plans; determining a first correspondence between the current production event and the plan categories of the candidate emergency response plans, and a second correspondence between the current production event and the plan scenarios of the candidate emergency response plans, based on the event elements and plan elements; and determining the target emergency response plan corresponding to the current production event from the candidate emergency response plans using an emergency response plan prediction model, based on the first and second correspondences. This method makes the determined first and second correspondences more accurate, further improving the accuracy of the target emergency response plan determined based on the first and second correspondences, reducing problems such as incorrect selection, omissions, and time-consuming processes caused by manual selection of emergency response plans, and improving work efficiency.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, computer equipment, and storage medium for determining emergency response plans. Background Technology

[0002] With the development of artificial intelligence technology, the application of automated equipment or systems is becoming more and more widespread.

[0003] Currently, when automated equipment or systems generate production events during operation, the data center typically sends the event information to production operation personnel through designated channels. These personnel, based on their experience and by reviewing historical emergency response plans for different production events, manually select the appropriate emergency response plan from a pool of pre-defined candidate plans, according to the event information.

[0004] However, this method may have problems such as incorrect or missing emergency plans, resulting in inaccurate emergency plan determination, and is time-consuming and inefficient, which urgently need to be improved. Summary of the Invention

[0005] Therefore, it is necessary to provide an emergency plan determination method, device, computer equipment, computer-readable storage medium, and computer program product that can accurately and efficiently determine the target emergency plan corresponding to the current production event in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for determining an emergency response plan. The method includes:

[0007] Extract event elements and contingency plan elements from the event information of current production events and the contingency plan information of candidate emergency plans;

[0008] Based on the event elements and contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and the second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan;

[0009] By using the emergency response plan prediction model, and based on the first and second correspondence relationships, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans.

[0010] In one embodiment, the step of determining a first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and a second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan, based on the event element and the contingency plan element, includes:

[0011] Based on the event source, event level, urgency, event response channel, monitoring source, and event area in the event elements, and the contingency plan category in the contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan;

[0012] Based on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, and the contingency scenario in the contingency plan elements, determine the second correspondence between the current production event and the contingency scenario of the candidate emergency plan.

[0013] In one embodiment, the method is characterized by determining a first correspondence between the current production event and the candidate emergency response plan categories based on the event source, event level, urgency, event reporting channel, monitoring source, and event area in the event elements, and the plan category in the plan elements, including:

[0014] Using a Naive Bayes classifier, linear regression analysis is performed on the event source, event level, urgency, event response channel, monitoring source, and event domain of the event elements, as well as the contingency plan category of the contingency plan elements, to obtain the first prior probability and the first conditional probability.

[0015] Based on the first prior probability and the first conditional probability, determine the first correspondence between the current production event and the plan category of the candidate emergency response plan.

[0016] In one embodiment, the method is characterized by determining a second correspondence between the current production event and the candidate emergency response scenario based on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, and the contingency scenario in the contingency plan elements, including:

[0017] Using a Naive Bayes classifier, linear regression analysis is performed on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, as well as the contingency scenario in the contingency plan elements, to obtain the second prior probability and the second conditional probability.

[0018] Based on the second prior probability and the second conditional probability, a second correspondence is determined between the current production event and the candidate emergency response scenarios.

[0019] In one embodiment, the method is characterized by extracting event elements and contingency plan elements from the event information of the current production event and the contingency plan information of candidate contingency plans, including:

[0020] Extract target data from the event information of the current production event;

[0021] By analyzing the model, event elements of the current production event are extracted from the target data;

[0022] By analyzing the model, the plan elements of the candidate emergency response plans are extracted from the plan information of the candidate emergency response plans.

[0023] In one embodiment, the method further includes:

[0024] Obtain the feedback results of the contingency plan within a preset time period; wherein, the feedback results of the contingency plan are determined based on the target emergency plan and expected emergency effects determined by the emergency plan prediction model within the preset time period;

[0025] Based on the feedback results of the emergency plan and the target emergency plan within the preset time period, the emergency plan prediction model is optimized and adjusted.

[0026] In one embodiment, the feature is that, based on the feedback results of the contingency plan within a preset time period and the target emergency plan, the emergency plan prediction model is optimized and adjusted, including:

[0027] Based on the plan elements and plan feedback results corresponding to the target emergency plans within the preset time period, the target emergency plans within the preset time period are sorted.

[0028] Based on the ranking results, optimize the emergency response plan from the target emergency response plan;

[0029] Based on the optimized emergency response plan, the prediction model of the emergency response plan was optimized and adjusted.

[0030] Secondly, this application also provides an emergency response plan determination device. The device includes:

[0031] The element extraction module is used to extract event elements and plan elements from the event information of the current production event and the plan information of the candidate emergency plan;

[0032] The relationship determination module is used to determine the first correspondence between the current production event and the plan category of the candidate emergency plan, and the second correspondence between the current production event and the plan scenario of the candidate emergency plan, based on the event elements and plan elements.

[0033] The contingency plan determination module is used to determine the target contingency plan corresponding to the current production event from the candidate contingency plans based on the first and second correspondence relationships using the contingency plan prediction model.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0035] Extract event elements and contingency plan elements from the event information of current production events and the contingency plan information of candidate emergency plans;

[0036] Based on the event elements and contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and the second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan;

[0037] By using the emergency response plan prediction model, and based on the first and second correspondence relationships, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans.

[0038] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0039] Extract event elements and contingency plan elements from the event information of current production events and the contingency plan information of candidate emergency plans;

[0040] Based on the event elements and contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and the second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan;

[0041] By using the emergency response plan prediction model, and based on the first and second correspondence relationships, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans.

[0042] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0043] Extract event elements and contingency plan elements from the event information of current production events and the contingency plan information of candidate emergency plans;

[0044] Based on the event elements and contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and the second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan;

[0045] By using the emergency response plan prediction model, and based on the first and second correspondence relationships, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans.

[0046] The aforementioned emergency response plan determination method, device, computer equipment, and storage medium extract event elements and plan elements from the event information of the current production event and the plan information of candidate emergency response plans. Based on the event elements and plan elements, a first correspondence relationship is determined between the current production event and the plan categories of the candidate emergency response plans, and a second correspondence relationship is determined between the current production event and the plan scenarios of the candidate emergency response plans. Using an emergency response plan prediction model, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans based on the first and second correspondence relationships. This solution extracts elements based on event information and plan information, and determines the first and second correspondence relationships based on the extracted event elements and plan elements, making the determined first and second correspondence relationships more accurate. Furthermore, by determining the target emergency response plan from the candidate emergency response plans based on the correspondence relationships of the two dimensions, namely the first and second correspondence relationships, the accuracy of the determined target emergency response plan is ensured. The entire process of determining the target emergency response plan corresponding to the current production event in this solution requires no manual assistance, reducing problems such as incorrect selection, omission, and time consumption caused by manual selection of emergency response plans, and improving work efficiency. Attached Figure Description

[0047] Figure 1 This embodiment provides an application environment diagram for an emergency response plan determination method.

[0048] Figure 2 A flowchart illustrating the first emergency response plan determination method provided in this embodiment;

[0049] Figure 3 A flowchart illustrating the training principle of an emergency response plan prediction model provided in this embodiment;

[0050] Figure 4 This is a schematic diagram of a process for determining a first correspondence in this embodiment;

[0051] Figure 5 This is a schematic diagram of a process for determining a second correspondence in this embodiment;

[0052] Figure 6 A schematic diagram illustrating the process of optimizing and adjusting the first type of emergency response plan prediction model provided in this embodiment;

[0053] Figure 7 A flowchart illustrating the optimization and adjustment process of the second emergency response plan prediction model provided in this embodiment;

[0054] Figure 8 This is a flowchart illustrating the second emergency response plan determination method provided in this embodiment;

[0055] Figure 9A flowchart illustrating a method for determining an emergency response plan provided in this embodiment;

[0056] Figure 10 This is a structural block diagram of the first type of emergency response plan determination device provided in this embodiment;

[0057] Figure 11 This is a structural block diagram of the second type of emergency response plan determination device provided in this embodiment;

[0058] Figure 12 This is a structural block diagram of the third type of emergency response plan determination device provided in this embodiment;

[0059] Figure 13 This is a structural block diagram of the fourth type of emergency response plan determination device provided in this embodiment;

[0060] Figure 14 This is a structural block diagram of the fifth type of emergency response plan determination device provided in this embodiment;

[0061] Figure 15 This is an internal structural diagram of a computer device provided in this embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] The emergency response plan determination method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, in one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows. Figure 1 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores event information and contingency plan information. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a contingency plan determination method.

[0064] This embodiment discloses an emergency response plan determination method, apparatus, computer equipment, and storage medium. It extracts event elements and plan elements from event information of the current production event and plan information of candidate emergency response plans. Based on the event elements and plan elements, it determines a first correspondence between the plan categories of the current production event and the candidate emergency response plans, and a second correspondence between the plan scenarios of the current production event and the candidate emergency response plans. Using an emergency response plan prediction model, based on the first and second correspondences, it determines the target emergency response plan corresponding to the current production event from the candidate emergency response plans.

[0065] In one embodiment, such as Figure 2 As shown, an emergency response plan determination method is provided, which can be applied to... Figure 1 Taking the server in the example, the following steps are included:

[0066] S201 extracts event elements and contingency plan elements from the event information of the current production event and the contingency plan information of the candidate emergency response plan.

[0067] Production events can be unexpected events occurring in the production environment due to hardware or software issues. For example, this could include errors, crashes, or system malfunctions in the production environment. Event information can be relevant information describing the content of the production event.

[0068] The emergency response plan can be an emergency preparedness plan for handling sudden events. Optionally, the candidate emergency response plan can be all the selectable emergency response plans pre-defined for various types of production events in the production environment. In this embodiment, the number of candidate emergency response plans is usually multiple. The plan information can be relevant information describing the plan content corresponding to the candidate emergency response plan.

[0069] The event elements can be the element information corresponding to the event information. Optionally, these event elements may include, but are not limited to, the following: event source, event level, urgency level, event reporting channel, monitoring source, event description information, event domain, impact data, alarm location, alarm level, system name, server identifier, and event type. The event source can be the location where the production event occurred. The event level can be the level at which the production event occurred. The urgency level can be the requirement for handling the production event. The event reporting channel can be the channel through which the production event was obtained. The monitoring source can be the source monitoring the production event. The event domain can be the domain to which the production event belongs. The alarm location can be the location where the warning information for the production event was generated. The alarm level can be the level of the warning information generated by the production event. The system name can be the name of the system that generated the production event. The server identifier can be the identifier of the server that generated the production event. The event description information can be information describing the content of the production event. The event type can be the type of production event. Furthermore, after acquiring the event elements, the event elements can be stored in data with granularity of year, month, and day.

[0070] The contingency plan elements can be information corresponding to candidate emergency plans. Optionally, these elements may include, but are not limited to, information such as plan category and plan scenario. The plan category can be different categories of candidate emergency plans. The warning scenario can be production event scenario information corresponding to the candidate emergency plan. Optionally, the warning scenario may include the corresponding handling plan, verification plan, fault phenomenon, and production event number.

[0071] Optionally, the event information of the current production event is obtained, and the event elements corresponding to the event information are extracted using the event information through a pre-set event element template; the contingency plan information of the candidate emergency plan is obtained, and the contingency plan elements corresponding to the contingency plan information are extracted using the contingency plan information through a pre-set contingency plan element template.

[0072] S202 determines the first correspondence between the current production event and the candidate emergency response plan categories, and the second correspondence between the current production event and the candidate emergency response plan scenarios, based on the event elements and plan elements.

[0073] Optionally, there are multiple ways to determine the first correspondence between the current production event and the plan category of the candidate emergency plan, and the second correspondence between the current production event and the plan scenario of the candidate emergency plan, based on the event elements and the plan elements. This application does not limit the methods in this regard.

[0074] One possible implementation is to input the event elements and contingency plan elements into a pre-trained first relationship prediction model. The first relationship prediction model analyzes the input event elements and contingency plan elements and outputs a first correspondence between the current production event and the contingency plan category of the candidate emergency plan. At the same time, the event elements and contingency plan elements are input into a pre-set second relationship prediction model. The second relationship prediction model analyzes the input event elements and contingency plan elements and outputs a second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan.

[0075] Another optional implementation method is to pre-set different combinations of event elements and contingency plan elements, and corresponding first and second correspondence lookup lists. In this case, based on the obtained event elements and contingency plan elements, the first and second correspondences corresponding to the event elements of the current production event and the contingency plan elements of each candidate emergency plan can be found from the first and second correspondence lookup lists.

[0076] Optionally, in this embodiment, another possible implementation of determining the first and second correspondences based on event elements and contingency plan elements can be to determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan based on the event source, event level, urgency, event reporting channel, monitoring source, and event domain in the event elements, and the contingency plan category in the contingency plan elements; and to determine the second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan based on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, and the contingency plan scenario in the contingency plan elements.

[0077] Specifically, when determining the first correspondence, based on the event source, event level, urgency, event reporting channel, monitoring source, and event domain in the event elements, and the contingency plan category in the contingency plan elements, a pre-set Naive Bayes classifier is used to perform linear analysis to determine the first correspondence between the current production event and the contingency plan category of the candidate emergency response plan. When determining the second correspondence, based on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, and the contingency plan scenario in the contingency plan elements, a pre-set Naive Bayes classifier is used to perform linear analysis to determine the second correspondence between the current production event and the contingency plan scenario of the candidate emergency response plan.

[0078] S203 uses an emergency response prediction model to determine the target emergency response plan corresponding to the current production event from candidate emergency response plans based on the first and second correspondence relationships.

[0079] The emergency response plan prediction model can be a model that selects the optimal emergency response plan corresponding to a production event from candidate emergency response plans based on the first and second correspondence relationships. Optionally, the emergency response plan prediction model can be a Long Short-Term Memory (LSTM) network.

[0080] Among them, the target emergency plan can be the optimal emergency plan corresponding to the production event.

[0081] Optionally, the first and second correspondences are input into a pre-trained emergency response prediction model. The emergency response prediction model makes predictions based on the input first and second correspondences, selects the optimal emergency response plan corresponding to the production event from the candidate emergency response plans, and uses the emergency response plan as the output of the model, thereby determining the target emergency response plan corresponding to the current production event.

[0082] Optionally, during the training of the emergency response plan prediction model in this embodiment, multiple prediction models can be trained based on multiple sets of training samples over a continuous period. Then, based on a long short-term memory network, nonlinear analysis is performed on the multiple prediction models to obtain the final emergency response plan prediction model. For example, as shown... Figure 3As shown, the training method for the emergency response plan model in this embodiment can be as follows: Obtain event information corresponding to various production events within a historical time period, extract event elements from each event information, and extract plan elements from candidate emergency response plans. Divide the event information into four groups at preset time intervals (e.g., one year). For each group of event information, construct a training set by combining its event elements and the plan elements of the candidate emergency response plans. This results in four training sets corresponding to the four time periods. For each training set corresponding to a time period, input the event elements and plan elements into the corresponding Naive Bayes classifier for linear analysis. For example, taking the first training set corresponding to the first time period as an example, the first Naive Bayes classifier is used to analyze the first training set... Linear analysis is performed on the time period categories (i.e., event source, event level, urgency, event response channel, monitoring source, and event domain in event elements, and contingency plan category in contingency plan elements) to generate a first correspondence between production events in the first training set and contingency plan categories of candidate emergency plans. A second Naive Bayes classifier is then used to perform linear analysis on the first time period subcategories (i.e., alarm location, alarm level, system name, server identifier, event description information, and event type in event elements, and contingency plan scenario in contingency plan elements) in the first training set to generate a second correspondence between production events in the first training set and contingency plan scenarios of candidate emergency plans. A first prediction model is constructed based on the first and second emergency relationships. Similarly, a second, third, and fourth prediction model are constructed. Then, the first and second prediction models are fused and input into the Long Short-Term Memory (LSTM) network for nonlinear analysis; the second and third prediction models are fused and input into the LTM network for nonlinear analysis; the third and fourth prediction models are fused and input into the LTM network for nonlinear analysis. Based on the final analysis results, the LTM network outputs the fused prediction model, and then the output fused prediction model is subjected to regression verification. If it passes, the fused prediction model is used as the final emergency response plan prediction model.

[0083] The aforementioned emergency response plan determination method extracts event elements and plan elements from the event information of the current production event and the plan information of candidate emergency response plans. Based on these elements, it determines a first correspondence between the current production event and the plan categories of the candidate emergency response plans, and a second correspondence between the current production event and the plan scenarios of the candidate emergency response plans. Using an emergency response plan prediction model, it determines the target emergency response plan corresponding to the current production event from the candidate emergency response plans based on these first and second correspondences. This solution extracts elements based on event information and plan information, and determines the first and second correspondences based on the extracted event elements and plan elements, making the determined first and second correspondences more accurate. Furthermore, by determining the target emergency response plan from the candidate emergency response plans based on the correspondences of both dimensions, the accuracy of the determined target emergency response plan is ensured. This solution requires no manual intervention throughout the entire process of determining the target emergency response plan corresponding to the current production event, reducing problems such as incorrect selection, omissions, and time-consuming processes caused by manual emergency response plan selection, thus improving work efficiency.

[0084] Optionally, target data is extracted from the event information of the current production event. Through an analysis model, event elements of the current production event are extracted from the target data. Similarly, through the analysis model, plan elements of candidate emergency plans are extracted from the plan information of candidate emergency plans. The target data can be data extracted from the event information after data processing, playing a crucial role in determining the target emergency plan. The analysis model can be a model for extracting elements from the target data. Optionally, the analysis model can be a snowflake-shaped analysis model or a star-shaped analysis model; this application does not limit this. Specifically, the event information of the current production event is obtained, and the event information is processed using data warehouse technology (Extract-Transform-Load, ETL) to extract and separate the target data from the event information. The extracted and separated target data and the plan information of candidate emergency plans are input into a pre-set analysis model. The analysis model will extract elements based on the input target data, extracting event elements. Similarly, the analysis model will extract elements based on the input plan information, extracting plan elements.

[0085] Optionally, after extracting event elements and contingency plan elements through the analysis model, this embodiment can display the extracted event elements and contingency plan elements in the form of fact tables and dimension tables. Specifically, in the fact table and dimension table for production events, the fact table records the event name and specific content of the production event, while the dimension table records the event element names and their corresponding specific event element content. Similarly, in the fact table and dimension table for emergency plans, the fact table records the emergency plan name and its specific content, while the dimension table records the contingency plan element names and their corresponding specific contingency plan element content.

[0086] Figure 4 This is a flowchart illustrating the process of determining the first correspondence in one embodiment. The accuracy of the confirmed first correspondence directly affects the accuracy of the subsequent target emergency plan. Therefore, to ensure the accuracy of the generated target emergency plan, this embodiment provides an optional method for determining the first correspondence, including the following steps:

[0087] S401 uses a Naive Bayes classifier to perform linear regression analysis on the event source, event level, urgency, event response channel, monitoring source, and event domain in the event elements, as well as the contingency plan category in the contingency plan elements, to obtain the first prior probability and the first conditional probability.

[0088] The first prior probability can be an estimate based on the likelihood of selecting a certain contingency plan category when all production events occur in the future.

[0089] Among them, the first conditional probability can be an estimate of the probability of selecting a certain emergency plan category given that a certain factor corresponds to a production event.

[0090] Optionally, the event source, event level, urgency, event response channel, monitoring source, and event domain in the event elements, as well as the contingency plan category in the contingency plan elements, are input into a pre-set Naive Bayes classifier. The Naive Bayes classifier performs linear regression analysis on the input elements to obtain the first prior probability and the first conditional probability.

[0091] For example, suppose there are a total of m events, of which s1 originate from Xisanqi and s2 from Waigaoqiao, and the event levels are level 1 (l1) and level 2 (l2). The number of contingency plans of type I and type II are x1 and x2 respectively, then:

[0092] The first prior probability corresponding to contingency plan category I: The first prior probability corresponding to contingency plan category II:

[0093] The first conditional probability of the event originating in Xisanqi and corresponding to contingency plan category I: The first conditional probability corresponding to the event originating in Xisanqi and contingency plan category II: The first conditional probability corresponding to the event source Waigaoqiao and contingency plan category I: The first conditional probability corresponding to the event source Waigaoqiao and contingency plan category II:

[0094] The first conditional probability corresponding to event level 1 and contingency plan category I: The first conditional probability corresponding to event level one and contingency plan category two: The first conditional probability corresponding to event level two and contingency plan category I: The first conditional probability corresponding to event level 2 and contingency plan category II:

[0095] S402 determines the first correspondence between the current production event and the candidate emergency response plan categories based on the first prior probability and the first conditional probability.

[0096] Optionally, based on the first prior probability and the first conditional probability, a first correspondence between the current production event and the plan category of the candidate emergency plan is calculated through a pre-set calculation logic (such as multiplying the first prior probability and the first conditional probability).

[0097] For example, suppose there are a total of m events, of which s1 are from Xisanqi and s2 are from Waigaoqiao, l1 are at level 1, and x1 are the number of contingency plan categories I. Then:

[0098] The first correspondence between the incident originating in Xisanqi, the incident level 1, and the contingency plan category I: The first correspondence between the incident source (Waigaoqiao), incident level 1, and contingency plan category I:

[0099] The method described above for determining the first correspondence uses a Naive Bayes classifier to perform linear regression analysis on the event source, event level, urgency, event response channel, monitoring source, and event domain among the event elements, and the contingency plan category among the contingency plan elements, to obtain a first prior probability and a first conditional probability, thus determining the first correspondence between the current production event and the contingency plan category of the candidate emergency response plan. This method, based on a Naive Bayes classifier and a linear regression model, considers the influence of different event elements on the selected contingency plan category, increasing the comprehensiveness and accuracy of determining the first correspondence.

[0100] Figure 5 This is a flowchart illustrating the process of determining the second correspondence in one embodiment. The accuracy of the confirmed second correspondence directly affects the accuracy of the subsequent target emergency plan. Therefore, to ensure the accuracy of the generated target emergency plan, this embodiment provides an optional method for determining the second correspondence, including the following steps:

[0101] S501 uses a Naive Bayes classifier to perform linear regression analysis on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, as well as the contingency scenario in the contingency plan elements, to obtain the second prior probability and the second conditional probability.

[0102] The second prior probability can be an estimate of the likelihood of choosing a particular contingency scenario based on all future production events.

[0103] The second conditional probability can be an estimate of the likelihood of selecting a specific emergency plan for a given production event, given that a certain factor corresponds to the occurrence of such an event.

[0104] Optionally, the alarm location, alarm level, system name, server identifier, event description information and event type in the event elements, as well as the contingency scenario in the contingency plan elements, are input into a pre-set Naive Bayes classifier. The Naive Bayes classifier performs linear regression analysis on the input elements to obtain the second prior probability and the second conditional probability.

[0105] For example, suppose there are a total of n events, including alarm locations SiteA and SiteB (totaling Site1 and Site2); alarm levels Ala and Alb (totaling Al1 and Al2); system names SysA and SysB (totaling Sys1 and Sys2); and contingency scenario E. no1 E no2 If the frequency of occurrence is o1 and o2 respectively, then:

[0106] Contingency Plan Scenario E no1 The corresponding second prior probability: Contingency Plan Scenario E no2 The corresponding second prior probability:

[0107] Alarm location Site A and contingency scenario E no1 The corresponding second conditional probability: Alarm location Site B and contingency scenario E no1 The corresponding second conditional probability: Alarm level Ala and contingency scenario E no1 The corresponding second conditional probability: Alarm Level Alb and Contingency Scenario E no1 The corresponding second conditional probability: System name SysA and contingency scenario E no1 The corresponding second conditional probability: System name SysB and contingency scenario E no1 The corresponding second conditional probability:

[0108] S502 determines the second correspondence between the current production event and the candidate emergency response scenario based on the second prior probability and the second conditional probability.

[0109] Optionally, based on the second prior probability and the second conditional probability, a second correspondence between the current production event and the candidate emergency response scenario is calculated through pre-set calculation logic (such as multiplying the first prior probability and the second conditional probability).

[0110] For example, suppose there are a total of n events, including alarm locations SiteA and SiteB (totaling Site1 and Site2); alarm levels Ala and Alb (totaling Al1 and Al2); system names SysA and SysB (totaling Sys1 and Sys2); and contingency scenario E. no1 If the number of occurrences is o1, then:

[0111] Alarm location SiteA, alarm level Ala, system name SysA, and contingency scenario E no1 The first correspondence:

[0112]

[0113] Alarm location SiteB, alarm level Alb, system name SysB, and contingency scenario E no1 The first correspondence:

[0114]

[0115] The method described above for determining the second correspondence uses a Naive Bayes classifier to perform linear regression analysis on the alarm location, alarm level, system name, server identifier, event description information, and event type among the event elements, as well as the contingency plan scenarios among the contingency plan elements, to obtain a second prior probability and a second conditional probability. Based on the second prior probability and the second conditional probability, the second correspondence between the current production event and the contingency plan scenarios of the candidate emergency response plan is determined. This method uses a linear regression model based on a Naive Bayes classifier and takes into account the influence of different event elements on the selected contingency plan scenarios, thus increasing the comprehensiveness and accuracy of determining the second correspondence.

[0116] Figure 6This is a flowchart illustrating the optimization and adjustment process of an emergency response plan prediction model in one embodiment. The accuracy of the emergency response plan prediction model directly affects the accuracy of the output target emergency response plan. Therefore, to improve the accuracy of the emergency response plan prediction model, this embodiment provides an optional method for optimizing and adjusting the emergency response plan prediction model, including the following steps:

[0117] S601 obtains the feedback results of the contingency plan within a preset time period.

[0118] The feedback results of the emergency plan are determined based on the target emergency plan and expected emergency effects determined by the emergency plan prediction model within the preset time period.

[0119] Optionally, based on the production events that the target emergency plan needs to address within a preset time period, and obtaining the actual emergency effect of the target emergency plan, the actual emergency effect is analyzed based on the expected emergency effect to obtain the plan feedback results.

[0120] S602 optimizes and adjusts the emergency response plan prediction model based on the feedback results of the plan within the preset time period and the target emergency response plan.

[0121] Optionally, based on the feedback results of the emergency plan and the target emergency plan obtained within the preset time period, the emergency plan prediction model parameters corresponding to the emergency plan prediction model are calculated through the pre-set model optimization logic, and the emergency plan prediction model is optimized and adjusted based on the emergency plan prediction model parameters.

[0122] The optimization and adjustment process of the aforementioned emergency response plan prediction model involves obtaining the plan feedback results within a preset time period, and then optimizing and adjusting the model based on these feedback results and the target emergency response plan. This method optimizes and adjusts the emergency response plan prediction model by using the feedback results of the target emergency response plan output by the model and the reverse process of the target emergency response plan, thereby continuously improving the accuracy of the model during its use.

[0123] Figure 7 This is a flowchart illustrating the optimization and adjustment process of an emergency response plan prediction model in one embodiment. The accuracy of the emergency response plan prediction model directly affects the accuracy of the output target emergency response plan. Therefore, to improve the accuracy of the emergency response plan prediction model, this embodiment provides an optional method for optimizing and adjusting the emergency response plan prediction model, including the following steps:

[0124] S701 sorts the target emergency plans within the preset time period based on the plan elements and plan feedback results corresponding to the target emergency plans within the preset time period.

[0125] Optionally, based on the obtained plan elements and feedback results of the target emergency plans within a preset time period, and considering the effectiveness of the feedback results while also taking into account the plan elements, a pre-set scoring logic is used to comprehensively score the target emergency plans, and the target emergency plans within the preset time period are ranked based on this comprehensive score. It should be noted that this ranking order can be from highest to lowest comprehensive score or from lowest to highest comprehensive score.

[0126] Based on the ranking results, S702 determines the optimized emergency response plan from the target emergency response plan.

[0127] Optionally, if the target emergency plans are ranked from high to low based on the comprehensive score, then the target emergency plan with the preset ranking (e.g., the last 1-10) in the ranking results is selected as the optimized emergency plan; if the target emergency plans are ranked from low to high based on the comprehensive score, then the target emergency plan with the preset ranking (e.g., the last 1-10) in the ranking results is selected as the optimized emergency plan.

[0128] S703 optimizes and adjusts the emergency response plan prediction model based on the optimized emergency response plan.

[0129] Optionally, based on the obtained optimized emergency plan, the parameters of the emergency plan prediction model corresponding to the optimized emergency plan are calculated through a pre-set model optimization logic, and the emergency plan prediction model is optimized and adjusted based on the emergency plan prediction model parameters.

[0130] The optimization and adjustment process of the aforementioned emergency response plan prediction model is based on ranking the target emergency response plans within a preset time period according to the plan elements and feedback results. Based on the ranking, optimized emergency response plans are selected from the target plans, and the prediction model is then optimized and adjusted according to these optimized plans. This method ranks the target emergency response plans and selects optimized plans to adjust the prediction model, increasing the rationality of the adjustments and further improving the accuracy of the emergency response plan prediction model.

[0131] In one embodiment, this embodiment provides an optional method for determining an emergency response plan, using the application of this method to a server as an example for illustration. For example... Figure 8 As shown, the method includes the following steps:

[0132] S801 extracts target data from the event information of the current production event.

[0133] S802 extracts event elements of the current production event from the target data through analysis models.

[0134] S803 uses an analysis model to extract the plan elements of candidate emergency plans from the plan information of candidate emergency plans.

[0135] S804 uses a Naive Bayes classifier to perform linear regression analysis on the event source, event level, urgency, event response channel, monitoring source, and event domain in the event elements, as well as the contingency plan category in the contingency plan elements, to obtain the first prior probability and the first conditional probability.

[0136] S805 determines the first correspondence between the current production event and the candidate emergency response plan categories based on the first prior probability and the first conditional probability.

[0137] The S806 uses a Naive Bayes classifier to perform linear regression analysis on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, as well as the contingency scenario in the contingency plan elements, to obtain the second prior probability and the second conditional probability.

[0138] S807 determines the second correspondence between the current production event and the candidate emergency response scenario based on the second prior probability and the second conditional probability.

[0139] S808 uses an emergency response prediction model to determine the target emergency response plan corresponding to the current production event from candidate emergency response plans based on the first and second correspondence relationships.

[0140] S809 obtains the feedback results of the contingency plan within a preset time period.

[0141] S810 sorts the target emergency plans within a preset time period based on the plan elements and plan feedback results corresponding to the target emergency plans within the preset time period.

[0142] Based on the ranking results, S811 determines the optimized emergency response plan from the target emergency response plans.

[0143] S812 optimizes and adjusts the emergency response plan prediction model based on the optimized emergency response plan.

[0144] Combination Figure 9 As shown, the data processing module processes event information to obtain target data, then extracts event elements from the target data. The calculation and analysis module uses a Naive Bayes classifier to perform linear analysis on the plan elements and event elements obtained from the data processing module, resulting in several correlation tables (i.e., tables corresponding to the plan elements and event elements). Figure 9 (Relation tables 1 to n in the table)

[0145] The relevant table records the correspondence between event-plan categories and event-plan scenarios. Based on this correspondence, the data is input into a pre-set Long Short-Term Memory (LSTM) network. The LSM network outputs the target emergency plans corresponding to the generated events. Simultaneously, the model optimization module filters the output target emergency plans, removing those whose feedback results exceed a preset threshold. For the remaining target emergency plans, the module sorts them based on plan elements and feedback results, analyzes the sorted plans, and finally optimizes and adjusts the LSM network based on the analysis results.

[0146] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise expressly stated herein, the execution of these steps does not necessarily follow the order indicated by the arrows.

[0147] Strict sequence restrictions apply; these steps can be performed in other orders. Moreover, at least some steps in the flowcharts involved in the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0148] 5. Based on the same inventive concept, embodiments of this application also provide an emergency response method for implementing the above-mentioned emergency plan determination method.

[0149] Emergency plan determination device. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more emergency plan determination device embodiments provided below can be found in the limitations of the emergency plan determination method above, and will not be repeated here.

[0150] In one embodiment, such as Figure 10 As shown, an emergency response plan determination device 1 is provided, comprising: an element extraction module 10, a relationship determination module 11, and a plan determination module 12, wherein:

[0151] The element extraction module 10 is used to extract event elements and plan elements from the event information of the current production event and the plan information of the candidate emergency plan;

[0152] The relationship determination module 11 is used to determine the relationship between the current production event and the candidate emergency response plan categories based on event elements and plan elements.

[0153] The first correspondence, and the second correspondence between the current production event and the contingency scenarios of the candidate emergency response plan;

[0154] 5. Emergency Plan Determination Module 12 is used to determine candidate emergency plans based on the first and second correspondence relationships using the emergency plan prediction model.

[0155] The target emergency response plan corresponding to the current production event is determined.

[0156] In one embodiment, such as Figure 11 As shown, Figure 10 The relationship determination module 11 in the middle includes:

[0157] The first correspondence confirmation unit 110 is used to determine the first correspondence between the current production event and the candidate emergency response plan category based on the event source, event level, urgency, event response channel, monitoring source and event area in the event elements, and the plan category in the plan elements.

[0158] The second correspondence confirmation unit 111 is used to determine the second correspondence between the current production event and the contingency scenario of the candidate emergency plan based on the alarm location, alarm level, system name, server identifier, event description information and event type in the event elements, and the contingency scenario in the contingency plan elements.

[0159] In one embodiment, Figure 11 The first correspondence confirmation unit 110 in the middle includes:

[0160] The first probability prediction subunit is used to perform linear regression analysis on the event source, event level, urgency, event response channel, monitoring source and event domain in the event elements and the contingency plan category in the contingency plan elements through a Naive Bayes classifier to obtain the first prior probability and the first conditional probability.

[0161] The first relationship confirmation subunit is used to determine the first correspondence between the current production event and the plan category of the candidate emergency plan based on the first prior probability and the first conditional probability.

[0162] In one embodiment, Figure 11 The second correspondence confirmation unit 111 includes:

[0163] The second probability prediction subunit is used to perform linear regression analysis on the alarm location, alarm level, system name, server identifier, event description information and event type in the event elements and the contingency scenario in the contingency plan elements through the Naive Bayes classifier to obtain the second prior probability and the second conditional probability.

[0164] The second relationship confirmation subunit is used to determine the second correspondence between the current production event and the candidate emergency response scenario based on the second prior probability and the second conditional probability.

[0165] In one embodiment, such as Figure 12 As shown, Figure 10 The feature extraction module 10 includes:

[0166] The data extraction unit 100 is used to extract target data from the event information of the current production event;

[0167] Event element extraction unit 101 is used to extract event elements of the current production event from the target data through an analysis model;

[0168] The contingency plan element extraction unit 102 is used to extract contingency plan elements from the contingency plan information of candidate emergency plans through an analysis model.

[0169] In one embodiment, such as Figure 13 As shown, Figure 10 The emergency response plan determination device 1 also includes:

[0170] The feedback acquisition module 13 is used to acquire the emergency plan feedback results within a preset time period; wherein, the emergency plan feedback results are determined based on the target emergency plan and expected emergency effect determined by the emergency plan prediction model within the preset time period;

[0171] The optimization and adjustment module 14 is used to optimize and adjust the emergency plan prediction model based on the feedback results of the plan and the target emergency plan within a preset time period.

[0172] In one embodiment, such as Figure 14 As shown, Figure 13 The optimization and adjustment module 14 also includes:

[0173] The sorting unit 140 is used to sort the target emergency plans within the preset time period based on the plan elements and plan feedback results corresponding to the target emergency plans within the preset time period.

[0174] The emergency plan determination unit 141 is used to determine the optimized emergency plan from the target emergency plans based on the ranking results;

[0175] The optimization and adjustment unit 142 is used to optimize and adjust the emergency plan prediction model according to the optimized emergency plan.

[0176] The various modules in the aforementioned emergency response plan determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0177] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 15 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements an emergency response plan determination method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0178] Those skilled in the art will understand that Figure 15 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0179] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0180] Extract event elements and contingency plan elements from the event information of current production events and the contingency plan information of candidate emergency plans;

[0181] Based on the event elements and contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and the second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan;

[0182] By using the emergency response plan prediction model, and based on the first and second correspondence relationships, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans.

[0183] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0184] Based on the event source, event level, urgency, event response channel, monitoring source, and event area in the event elements, and the contingency plan category in the contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan;

[0185] Based on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, and the contingency scenario in the contingency plan elements, determine the second correspondence between the current production event and the contingency scenario of the candidate emergency plan.

[0186] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0187] Using a Naive Bayes classifier, linear regression analysis is performed on the event source, event level, urgency, event response channel, monitoring source, and event domain in the event elements, as well as the contingency plan category in the contingency plan elements, to obtain the first prior probability and the first conditional probability.

[0188] Based on the first prior probability and the first conditional probability, determine the first correspondence between the current production event and the plan category of the candidate emergency response plan.

[0189] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0190] Using a Naive Bayes classifier, linear regression analysis is performed on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, as well as the contingency scenario in the contingency plan elements, to obtain the second prior probability and the second conditional probability.

[0191] Based on the second prior probability and the second conditional probability, a second correspondence is determined between the current production event and the candidate emergency response scenarios.

[0192] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0193] Extract target data from the event information of the current production event;

[0194] By analyzing the model, event elements of the current production event are extracted from the target data;

[0195] By analyzing the model, the plan elements of the candidate emergency response plans are extracted from the plan information of the candidate emergency response plans.

[0196] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0197] Obtain the feedback results of the contingency plan within a preset time period; wherein, the feedback results of the contingency plan are determined based on the target emergency plan and expected emergency effects determined by the emergency plan prediction model within the preset time period;

[0198] Based on the feedback results of the emergency plan and the target emergency plan within the preset time period, the emergency plan prediction model is optimized and adjusted.

[0199] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0200] Based on the plan elements and plan feedback results corresponding to the target emergency plans within the preset time period, the target emergency plans within the preset time period are sorted.

[0201] Based on the ranking results, optimize the emergency response plan from the target emergency response plan;

[0202] Based on the optimized emergency response plan, the prediction model of the emergency response plan was optimized and adjusted.

[0203] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0204] Extract event elements and contingency plan elements from the event information of current production events and the contingency plan information of candidate emergency plans;

[0205] Based on the event elements and contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and the second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan;

[0206] By using the emergency response plan prediction model, and based on the first and second correspondence relationships, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans.

[0207] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0208] Extract event elements and contingency plan elements from the event information of current production events and the contingency plan information of candidate emergency plans;

[0209] Based on the event elements and contingency plan elements, determine the first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and the second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan;

[0210] By using the emergency response plan prediction model, and based on the first and second correspondence relationships, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans.

[0211] It should be noted that the data involved in this application (including but not limited to event information of production incidents and emergency plan information) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0212] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0213] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0214] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining an emergency response plan, characterized in that, The method includes: Extract event elements and contingency plan elements from the event information of current production events and the contingency plan information of candidate emergency plans; Based on the event elements and the contingency plan elements, a first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and a second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan are determined. Using the emergency response plan prediction model, the target emergency response plan corresponding to the current production event is determined from the candidate emergency response plans based on the first correspondence and the second correspondence. The step of determining a first correspondence between the current production event and the contingency plan category of the candidate emergency response plan, and a second correspondence between the current production event and the contingency plan scenario of the candidate emergency response plan, based on the event elements and the contingency plan elements, includes: Using a Naive Bayes classifier, linear regression analysis is performed on the event source, event level, urgency, event response channel, monitoring source, and event domain in the event elements, as well as the contingency plan category in the contingency plan elements, to obtain the first prior probability and the first conditional probability. Based on the first prior probability and the first conditional probability, a first correspondence is determined between the current production event and the plan category of the candidate emergency plan; Based on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, and the contingency scenario in the contingency plan elements, a second correspondence is determined between the current production event and the contingency scenario of the candidate emergency plan.

2. The method according to claim 1, characterized in that, The step of determining the second correspondence between the current production event and the candidate emergency response scenario based on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, and the contingency scenario in the contingency plan elements, includes: Using a Naive Bayes classifier, linear regression analysis is performed on the alarm location, alarm level, system name, server identifier, event description information, and event type in the event elements, as well as the contingency scenario in the contingency plan elements, to obtain the second prior probability and the second conditional probability. Based on the second prior probability and the second conditional probability, a second correspondence is determined between the current production event and the contingency scenario of the candidate emergency plan.

3. The method according to claim 1, characterized in that, The step of extracting event elements and contingency plan elements from the event information of the current production event and the contingency plan information of the candidate emergency response plan includes: Extract target data from the event information of the current production event; By analyzing the model, the event elements of the current production event are extracted from the target data; By analyzing the model, the plan elements of the candidate emergency response plan are extracted from the plan information of the candidate emergency response plan.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Obtain the feedback results of the contingency plan within a preset time period; wherein, the feedback results of the contingency plan are determined based on the target emergency plan and expected emergency effect determined by the emergency plan prediction model within the preset time period; Based on the feedback results of the contingency plan and the target emergency plan within the preset time period, the emergency plan prediction model is optimized and adjusted.

5. The method according to claim 4, characterized in that, The step of optimizing and adjusting the emergency plan prediction model based on the feedback results of the plan and the target emergency plan within the preset time period includes: Based on the plan elements and plan feedback results corresponding to the target emergency plans within the preset time period, the target emergency plans within the preset time period are sorted. Based on the ranking results, an optimized emergency response plan is determined from the target emergency response plans. Based on the optimized emergency response plan, the prediction model of the emergency response plan is optimized and adjusted.

6. An emergency response plan determination device, characterized in that, The device includes: The element extraction module is used to extract event elements and plan elements from the event information of the current production event and the plan information of the candidate emergency plan; The relationship determination module is used to determine, based on the event elements and the contingency plan elements, a first correspondence between the current production event and the contingency plan category of the candidate emergency plan, and a second correspondence between the current production event and the contingency plan scenario of the candidate emergency plan; The contingency plan determination module is used to determine the target contingency plan corresponding to the current production event from the candidate contingency plans based on the first correspondence relationship and the second correspondence relationship through the contingency plan prediction model. The relationship determination module includes a first correspondence relationship confirmation unit and a second correspondence relationship confirmation unit. The first correspondence relationship confirmation unit includes a first probability prediction subunit and a first relationship confirmation subunit. The first probability prediction subunit is used to perform linear regression analysis on the event source, event level, urgency, event response channel, monitoring source and event domain in the event elements and the contingency plan category in the contingency plan elements through a Naive Bayes classifier to obtain the first prior probability and the first conditional probability. The first relationship confirmation subunit is used to determine a first correspondence between the current production event and the plan category of the candidate emergency plan based on the first prior probability and the first conditional probability; The second correspondence confirmation unit is used to determine the second correspondence between the current production event and the contingency scenario of the candidate emergency plan based on the alarm location, alarm level, system name, server identifier, event description information and event type in the event elements, and the contingency scenario in the contingency plan elements.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images