Risk assessment method, device and equipment, readable storage medium and program product
Through the automated evaluation of the target accident tree model and current indicator data, the problem of low accuracy in traditional risk assessment methods is solved, and a high accuracy risk assessment before the accident occurs is achieved.
Patent Information
- Application Number
- CN202510311254.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-17
- Publication Date
- 2025-08-01
AI Technical Summary
Traditional risk assessment methods are analyzed after an accident, resulting in low evaluation accuracy and it is difficult to scientifically and systematically evaluate the potential risks of personal safety accidents.
By obtaining the target accident tree model and current indicator data of the target event, using the pre-trained target accident tree model for risk assessment, and automatically assessing the risk of the target event, including iteratively training the initial accident tree model to adjust the event weight and indicator weight to ensure the accuracy of the evaluation results.
It realizes automated and accurate risk assessment before accidents, improves the accuracy of risk assessment, and avoids the low accuracy problems caused by manual analysis in traditional methods.
Smart Images
Figure CN120410177A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of personal safety management, and particularly to a risk assessment method, apparatus, device, readable storage medium, and program product. Background Art
[0002] In the field of personal safety management, it is very important to analyze the risk of accidents.
[0003] Traditional risk analysis methods usually analyze the causes of accidents manually after the accidents occur, so as to evaluate the risk of subsequent accidents.
[0004] However, the above risk assessment method has the problem of low assessment accuracy. Summary of the Invention
[0005] Based on this, it is necessary to provide a risk assessment method, apparatus, device, readable storage medium, and program product that can improve the assessment accuracy for the above technical problems.
[0006] In a first aspect, this application provides a risk assessment method, including:
[0007] Obtain the target fault tree model corresponding to the target event and multiple current index data of the target event. The index items corresponding to each current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item;
[0008] According to each current index data, each index weight, and the target fault tree model, obtain the risk assessment result of the target event.
[0009] In one embodiment, the method further includes:
[0010] Obtain the initial fault tree model, multiple historical event data of the target event, and multiple historical index data corresponding to each historical event data;
[0011] Iteratively train the initial fault tree model according to each historical index data and each historical event data to obtain the target fault tree model.
[0012] In one embodiment, iteratively training the initial fault tree model according to each historical index data and each historical event data to obtain the target fault tree model includes:
[0013] For each iterative training process, determine the sample index data corresponding to the iterative training process from each historical index data, and obtain the historical risk assessment result corresponding to the sample index data according to the sample index data and the intermediate fault tree model;
[0014] Compare the actual risk data in the sample event data corresponding to the historical risk assessment results with the sample indicator data to obtain a comparison result;
[0015] If the comparison result does not meet the preset conditions, adjust the current event weights of each basic event in the intermediate fault tree model according to the comparison result until the comparison result meets the preset conditions to obtain the target fault tree model.
[0016] In one embodiment, the method further includes:
[0017] Obtain the intermediate events and basic events corresponding to the target event;
[0018] Obtain the initial fault tree model according to the association relationship between the target event, intermediate events and basic events, and obtain the event weights corresponding to each basic event according to the occurrence probability corresponding to each basic event.
[0019] In one embodiment, obtaining the event weights corresponding to each basic event according to the occurrence probability corresponding to each basic event includes:
[0020] Determine the occurrence probability corresponding to the target event according to the occurrence probability corresponding to each basic event;
[0021] Determine the event weights corresponding to each basic event according to the occurrence probability corresponding to each basic event and the occurrence probability corresponding to the target event.
[0022] In one embodiment, the method further includes:
[0023] Calculate the correlation parameters between each basic event and each index item in the initial fault tree model according to each historical event data and each historical index data;
[0024] Determine the index item corresponding to each basic event according to each correlation parameter.
[0025] In a second aspect, the present application further provides a risk assessment device, including:
[0026] An acquisition module, configured to acquire the target fault tree model corresponding to the target event and multiple current index data of the target event, the index items corresponding to each current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item;
[0027] An evaluation module, configured to obtain a risk assessment result of the target event according to each current index data, each index weight and the target fault tree model.
[0028] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method in the first aspect as described above are implemented.
[0029] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the first aspect as described above are implemented.
[0030] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method in the first aspect as described above are implemented.
[0031] For the above risk assessment method, device, equipment, readable storage medium and program product, by obtaining the target fault tree model corresponding to the target event and multiple current index data of the target event, the risk assessment result of the target event can be obtained according to each current index data, each index weight and the target fault tree model. Among them, the index items corresponding to each current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item. In this way, the risk of the target event occurring can be evaluated through the pre-trained target fault tree model and the current index data, so as to obtain the risk assessment result of the target event, avoiding the problem of low assessment accuracy in the traditional technology of analyzing the cause of the accident manually after the accident occurs and then evaluating the risk of subsequent accidents. The technical solution provided by the present application automatically evaluates the risk of the target event occurring before the target event occurs through the target fault tree model and multiple current index data of the target event, and the assessment accuracy is higher. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.
[0033] Figure 1 It is an application environment diagram of the risk assessment method in an embodiment;
[0034] Figure 2 It is a flowchart of the risk assessment method in an embodiment;
[0035] Figure 3It is a schematic flowchart of the training process of the initial accident tree model in another embodiment;
[0036] Figure 4 It is a schematic flowchart of the establishment process of the initial accident tree model in another embodiment;
[0037] Figure 5 It is a schematic structural diagram of an exemplary initial accident tree model in another embodiment;
[0038] Figure 6 It is a schematic flowchart of an exemplary risk assessment in another embodiment;
[0039] Figure 7 It is a structural block diagram of a risk assessment device in one embodiment;
[0040] Figure 8 It is an internal structural diagram of a computer device in one embodiment. Detailed implementation manners
[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to 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.
[0042] In the field of personal safety management, it is very important to analyze the risk of accidents occurring.
[0043] In related technologies, the analysis of the risk of an event occurring often relies on experience summary and post-event analysis, lacking systematicness and quantification, and it is difficult to comprehensively and accurately reveal the deep causes and potential risks of accidents. Especially when dealing with complex personal safety accidents, how to scientifically and systematically evaluate risks and formulate effective preventive measures has become an urgent problem to be solved.
[0044] Traditional risk analysis methods usually analyze the causes of accidents manually after the accidents occur, so as to evaluate the risks of subsequent accidents. Therefore, the above risk assessment methods have the problem of low assessment accuracy.
[0045] In view of this, the present application provides a risk assessment method, apparatus, device, readable storage medium and program product. By obtaining the target fault tree model corresponding to the target event and multiple current index data of the target event, the risk assessment result of the target event can be obtained according to each current index data, each index weight and the target fault tree model. Among them, the index items corresponding to each current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item. In this way, the risk of the target event occurring can be evaluated through the pre-trained target fault tree model and the current index data, so as to obtain the risk assessment result of the target event, avoiding the problem of low evaluation accuracy in the traditional technology where the cause of the accident is analyzed manually after the accident occurs, and then the risk of subsequent accidents occurring is evaluated. The technical solution provided by the present application automatically evaluates the risk of the target event occurring before the target event occurs through the target fault tree model and multiple current index data of the target event, and the evaluation accuracy is higher.
[0046] The risk assessment method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the data storage system can store the data that the server 101 needs to process. The data storage system can be integrated on the server 101, or can be placed in the cloud or other network servers. The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.
[0047] In an exemplary embodiment, as Figure 2 shown, a risk assessment method is provided. Taking the method applied to the Figure 1 server 101 as an example for description, it includes the following steps 201 and 202. Among them:
[0048] Step 201, obtain the target fault tree model corresponding to the target event and multiple current index data of the target event.
[0049] Among them, the index items corresponding to each current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item.
[0050] In the embodiments of the present application, the target event can be a specific occurrence or phenomenon that requires risk assessment, such as a failure in a specific production process, an abnormality that occurs during the operation of a certain type of system, etc. In the field of personal safety, the target event can be a personal accident; the index item can be a dimension representing the occurrence of a personal accident, such as an operation risk distribution index, etc.; and the index data corresponds to the index item and can be data information reflecting the relevant status of the target event, while the current index data can be real-time or current-stage data information, and these data have a corresponding relationship with the basic events in the target accident tree model and are used to measure the specific state of the basic events at the current moment.
[0051] Optionally, the server can obtain multiple pieces of current index data of the target event input by the user through an external input device; optionally, the server area can obtain multiple pieces of current index data of the target event from the local database.
[0052] The target accident tree model corresponding to the target event can be a pre-trained model, and its basic model can be an accident tree model. In the embodiments of the present application, the accident tree model can be a logical model for analyzing accident causal relationships.
[0053] Optionally, the server can directly obtain the pre-trained target accident tree model from the target storage address; optionally, the server can establish an initial accident tree model for the target event and train the initial accident tree model to obtain the target accident tree model.
[0054] Step 202: Obtain the risk assessment result of the target event according to each piece of current index data, each index weight, and the target accident tree model.
[0055] In a possible implementation manner, the server can input each piece of current index data and each index weight into the target accident tree model to obtain the risk assessment result. Optionally, the server can determine the tree-shaped path diagram of the risk occurrence from the target accident tree model according to each piece of current index data and each index weight. For example, the server can determine the index data corresponding to each index item according to the current index data. Based on this, the server can determine the currently occurring basic events, and the server can calculate the risk probability of the occurrence of the target event according to the basic events that currently occur, each index weight, and the target accident tree model, and use this risk probability as the risk assessment result.
[0056] In another possible implementation manner, after obtaining the risk assessment result, the server can also output the risk assessment result to prompt the user of the risk of the occurrence of the target accident.
[0057] In this way, in the above embodiments, the risk of the target event occurring can be evaluated through the pre-trained target fault tree model and the current index data, so as to obtain the risk assessment result of the target event, avoiding the problem of low assessment accuracy in the traditional technology where the cause of the accident is analyzed manually after the accident occurs, and then the risk of subsequent accidents occurring is evaluated. The technical solution provided by this application automatically evaluates the risk of the target event occurring before the target event occurs through the target fault tree model and multiple current index data of the target event, and the assessment accuracy is higher.
[0058] In one embodiment, based on the above Figure 2 illustrated embodiment, refer to Figure 3 , this embodiment relates to the process of training the initial fault tree model. As Figure 3 shown, this process may include step 301 and step 302.
[0059] Step 301, obtain the initial fault tree model, multiple historical event data of the target event, and multiple historical index data corresponding to each historical event data.
[0060] The initial fault tree model can be an initially constructed logical framework model for analyzing accident causal relationships. In the embodiments of this application, the initial fault tree model may include the target event, intermediate events that cause the target event to occur, basic events, and the logical relationships between these events.
[0061] In one possible implementation manner, the server can directly obtain the initial fault tree model. In another possible implementation manner, the server can first determine the target event, and obtain the intermediate events and basic events corresponding to the target event according to the target event.
[0062] In the embodiments of this application, the server will also obtain multiple historical event data corresponding to the target event and multiple historical index data corresponding to each historical event data. Among them, the historical event data can be event records that occurred at historical times and are the same as or of the same type as the target event. The historical event data may include the event occurrence time, event type, actual risk data, etc. The actual risk data can characterize the cause of the event occurrence; while the historical index data can correspond to each piece of historical event data and reflect the specific data of each measurement dimension when each historical event occurs.
[0063] Optionally, the server can obtain multiple historical event data input by the user and multiple historical index data corresponding to each historical event data through an external input device; optionally, the server can directly obtain multiple historical event data stored in the database and multiple historical index data corresponding to each historical event data from the database.
[0064] Step 302: Iteratively train the initial fault tree model based on the historical indicator data and historical event data to obtain the target fault tree model.
[0065] In the embodiment of the present application, the server can preprocess the collected historical indicator data and historical event data. The data preprocessing includes operations such as data cleaning (removing duplicate, incorrect, and data records with excessive missing values) and data standardization (unifying indicator data of different magnitudes and ranges into a specific standard range for subsequent calculation and comparison).
[0066] Based on the preprocessed historical indicator data and historical event data, the server can iteratively train the initial fault tree model to obtain the target fault tree model.
[0067] For each iterative training process, the server can determine the sample indicator data corresponding to the iterative training process from the historical indicator data, and obtain the historical risk assessment result corresponding to the sample indicator data based on the sample indicator data and the intermediate fault tree model; compare the historical risk assessment result with the actual risk data in the sample event data corresponding to the sample indicator data to obtain a comparison result; if the comparison result does not meet the preset condition, adjust the current event weights of each basic event in the intermediate fault tree model according to the comparison result until the comparison result meets the preset condition to obtain the target fault tree model.
[0068] The preset condition can be that the historical risk assessment result matches the actual risk data. Optionally, if the historical risk assessment result does not match the actual risk data, the server can determine the difference between the risk assessment result output by the current intermediate fault tree model and the actual risk data according to the comparison result, and adjust the current event weights of each basic event in the intermediate fault tree model according to the difference. Exemplarily, for a basic event not reflected in the historical risk assessment result, its corresponding weight is increased by 10%; optionally, if the historical risk assessment result matches the actual risk data, the server can use the intermediate fault tree model in the current iteration process as the target fault tree model.
[0069] In one embodiment, based on the above Figure 3 illustrated embodiment, refer to Figure 4 , this embodiment relates to the process of establishing the initial fault tree model. As Figure 4 shown, this process may include Step 401 and Step 402.
[0070] Step 401: Obtain the intermediate events and basic events corresponding to the target event.
[0071] In the embodiments of the present application, the server may first determine a target event. Optionally, the server may obtain the target event manually input by a staff member through an external input device; alternatively, the server may obtain a specified target event through other relevant business systems, so as to clarify the specific object to be analyzed by the initial fault tree model to be constructed, such as "personal injury accident" or "electric shock accident", etc.
[0072] After determining the target event, the server may, based on the relevant information of the target event, analyze and obtain intermediate events and basic events corresponding to the target event. The intermediate event may be an indirect cause leading to the occurrence of the target event, while the basic event may be a direct cause leading to the occurrence of the intermediate event. For example, when the intermediate event is equipment failure, the basic events may include equipment aging, non-standard operating procedures of staff members, etc.
[0073] Step 402: Obtain an initial fault tree model based on the association relationships among the target event, intermediate events, and basic events, and obtain the event weights corresponding to each basic event according to the occurrence probabilities corresponding to each basic event.
[0074] After obtaining the intermediate events and basic events corresponding to the target event, the server obtains the association relationships among the target event, intermediate events, and basic events. In the embodiments of the present application, the server may use the target event as the top event of the fault tree and place it at the topmost layer of the tree. Then, according to the causal relationships between the analyzed intermediate events and basic events, the intermediate events are arranged in layers below the target event, and the basic events are placed at the bottom layer. The server may convert the association relationships between the events into different logic gates, such as "AND gate", "OR gate", etc., and connect the events according to different logic gates, so as to obtain an initial fault tree model. The initial fault tree model may refer to Figure 5 , Exemplarily, T is the target event, A1~A4 are intermediate events, and x1~x6 are basic events.
[0075] Exemplarily, taking the target event as a personal accident as an example, the corresponding intermediate events, extrusion time, and the association relationships between the events may refer to Table 1:
[0076]
[0077] Table 1
[0078] The occurrence probabilities corresponding to each basic event may represent the occurrence frequencies corresponding to each basic event. After obtaining the initial fault tree model, the server may calculate the event probabilities corresponding to each basic event. In the embodiments of the present application, the server may count the frequencies of each basic event appearing in each historical event data, so as to obtain the occurrence probabilities corresponding to each basic event.
[0079] In the embodiments of the present application, the server may obtain the event weights corresponding to each basic event according to the occurrence probabilities corresponding to each basic event. In one possible implementation, the server may determine the occurrence probability corresponding to the target event according to the occurrence probabilities corresponding to each basic event, and then determine the event weights corresponding to each basic event according to the occurrence probabilities corresponding to each basic event and the occurrence probability corresponding to the target event.
[0080] Regarding the process of the server determining the occurrence probability corresponding to the target event according to the occurrence probabilities corresponding to each basic event, the server may adopt one of the state enumeration method, the minimum cut set method, and the leading term approximation method.
[0081] Taking the state enumeration method as an example, the server may calculate the occurrence probability corresponding to the target event by the following steps:
[0082] Step 1: List the state value table corresponding to the basic events, and calculate the structure function φ p (X) according to the structure corresponding to the initial fault tree model, where φ p (X) is a function with variables being basic events X = {X1, X2, …, X n}, and φ p (X) is a binary variable representing the state of the target event. φ p (X) = 1 indicates that the top event occurs, and vice versa, indicating that the target event does not occur.
[0083] Step 2: Obtain the algebraic sum of the probability products of the states corresponding to each basic event that makes φ p (X) = 1.
[0084] (1)
[0085] Among them, T is the target event, p is the serial number of the state combination of each basic event, φ p (X)= is the structure function value of the p-th combination, and q i is the probability of the i-th basic event occurring.
[0086] Taking the minimum cut set method as an example, the server may calculate the occurrence probability corresponding to the target event by the following steps:
[0087] First, the server may first calculate the minimum cut sets corresponding to the initial fault tree model. The steps for obtaining the minimum cut sets of the target event may include establishing the Boolean expression of the fault tree and simplifying it to the simplest standard form by using Boolean algebra rules, etc.
[0088] Taking Figure 5 the initial fault tree model shown as an example, the server may obtain the Boolean expression of its target event T as:
[0089] (2)
[0090] Therefore, the simplest standard form of the minimal cut sets is E1 = {X1, X2}, E2 = {X4, X5}, E3 = {X4, X6}
[0091] Then, the server can substitute the minimal cut sets into the following formula to obtain the occurrence probability corresponding to the target event:
[0092] (3)
[0093] where r and s are the ordinal numbers of the minimal cut sets, k is the number of minimal cut sets, and X i ∈E r represents the i-th basic event belonging to the r-th minimal cut set, and X i ∈E r ∪E s represents the i-th basic event belonging to the r-th or s-th minimal cut set
[0094] Taking the first-term approximation method as an example, the server can calculate the occurrence probability corresponding to the target event by the following steps:
[0095] When the initial accident tree model is large and the number of basic events and minimal cut sets is large, the server can use the following formula to calculate the occurrence probability corresponding to the target event:
[0096] (4)
[0097] where r and s are the ordinal numbers of the minimal cut sets, k is the number of minimal cut sets, X i ∈E r represents the i-th basic event belonging to the r-th minimal cut set, P(T) is the occurrence probability of the top event, and q i is the occurrence probability of the i-th basic event
[0098] After obtaining the occurrence probabilities corresponding to the target event and each basic event, the server can determine the event weights corresponding to each basic event according to the occurrence probabilities corresponding to each basic event and the occurrence probability corresponding to the target event. In the embodiments of the present application, the event weights can represent the key importance coefficients corresponding to each basic event, and the key importance coefficients can represent the importance degrees of each basic event in the target event. Regarding the key importance coefficients, they can be calculated by the following formula:
[0099] (5)
[0100] where I c (i) is the key importance coefficient of the i-th basic event, and I q(i) is the probability importance coefficient of the i-th basic event, P(T) is the occurrence probability of the target event, and q i is the occurrence probability of the i-th basic event.
[0101] Regarding the calculation formula of the probability importance coefficient, the following formula can be referred to:
[0102] (6)
[0103] where P(T) is the occurrence probability of the top event, and q i is the occurrence probability of the i-th basic event. In the embodiment of the present application, the probability importance coefficient can characterize the degree of change in the occurrence probability of the target event caused by the change in the occurrence probability of the i-th basic event.
[0104] Through the above method, the server can obtain the initial accident tree model. In the related art, the index items corresponding to each basic event are usually determined manually. In order to improve the accuracy of the risk assessment corresponding to the target accident tree model, in the embodiment of the present application, the server can determine the index items corresponding to each basic event through an automated method: the server can calculate the correlation parameters between each basic event and each index in the initial accident tree model according to each historical event data and each historical index data, and determine the index items corresponding to each basic event according to each correlation.
[0105] In the embodiment of the present application, the server can obtain multiple index items, each historical event data, and the historical index data corresponding to different index items. These historical event data and historical index data can be the data used for the training of the initial accident tree model in the above text, or the data newly obtained by the server.
[0106] For these historical event data and historical index data, the server can perform data preprocessing on them, including missing value processing, outlier processing, etc.
[0107] For the processed historical event data and historical index data, the server can calculate the correlation parameters between each index item and each basic event by using statistical methods such as the Pearson correlation coefficient or the Spearman rank correlation coefficient. For each basic event, the server can use the index item with a higher correlation parameter as the index item corresponding to the basic event.
[0108] In one embodiment, referring to Figure 6 , an exemplary risk assessment method is provided, and this method can be applied to Figure 1 the implementation environment shown.
[0109] Step 601, obtain the intermediate events and basic events corresponding to the target event.
[0110] Step 602: Obtain the initial fault tree model according to the correlation relationships among the target event, intermediate events, and basic events.
[0111] Step 603: Determine the occurrence probability corresponding to the target event according to the occurrence probabilities corresponding to each basic event.
[0112] Step 604: Determine the event weights corresponding to each basic event according to the occurrence probabilities corresponding to each basic event and the occurrence probability corresponding to the target event.
[0113] Step 605: Calculate the correlation parameters between each basic event and each index item in the initial fault tree model according to each historical event data and each historical index data.
[0114] Step 606: Determine the index item corresponding to each basic event according to each correlation parameter.
[0115] Step 607: Obtain the initial fault tree model, multiple historical event data of the target event, and multiple historical index data corresponding to each historical event data.
[0116] Step 608: For each iterative training process, determine the sample index data corresponding to the iterative training process from each historical index data, and obtain the historical risk assessment result corresponding to the sample index data according to the sample index data and the intermediate fault tree model.
[0117] Step 609: Compare the historical risk assessment result with the actual risk data in the sample event data corresponding to the sample index data to obtain a comparison result.
[0118] Step 610: If the comparison result does not meet the preset condition, adjust the current event weights of each basic event in the intermediate fault tree model according to the comparison result until the comparison result meets the preset condition to obtain the target fault tree model.
[0119] Step 611: Obtain the target fault tree model corresponding to the target event and multiple current index data of the target event.
[0120] Among them, the index items corresponding to each current index data correspond to the basic events included in the target fault tree model respectively; among them, the index weight of the index item is the same as the event weight of the basic event corresponding to the index item.
[0121] Step 612: Obtain the risk assessment result of the target event according to each current index data, each index weight, and the target fault tree model.
[0122] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.
[0123] Based on the same inventive concept, an embodiment of the present application further provides a risk assessment device for implementing the above-mentioned risk assessment method. The implementation solution provided by this device to solve problems is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the risk assessment device provided below can refer to the limitations on the risk assessment method in the above text, and will not be repeated here.
[0124] In an exemplary embodiment, as Figure 7 shown, a risk assessment device is provided, including: an acquisition module 701 and an evaluation module 702, where:
[0125] The acquisition module 701 is used to acquire the target fault tree model corresponding to the target event and multiple current index data of the target event. The index items corresponding to each current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item;
[0126] The evaluation module 702 is used to obtain the risk assessment result of the target event according to each current index data, each index weight, and the target fault tree model.
[0127] In one embodiment, the device further includes:
[0128] A data acquisition module, which is used to acquire an initial fault tree model, multiple historical event data of the target event, and multiple historical index data corresponding to each historical event data;
[0129] A training module, which is used to iteratively train the initial fault tree model according to each historical index data and each historical event data to obtain the target fault tree model.
[0130] In one embodiment, the training module includes:
[0131] A training and evaluation unit, configured to, for each iterative training process, determine sample index data corresponding to the iterative training process from the respective historical index data, and obtain a historical risk assessment result corresponding to the sample index data according to the sample index data and an intermediate fault tree model;
[0132] A comparison unit, configured to compare the historical risk assessment result with actual risk data in sample event data corresponding to the sample index data to obtain a comparison result;
[0133] An adjustment unit, configured to, if the comparison result does not meet a preset condition, adjust current event weights of the respective basic events in the intermediate fault tree model according to the comparison result until the comparison result meets the preset condition, so as to obtain the target fault tree model.
[0134] In one embodiment, the apparatus further includes:
[0135] An initial model establishment module, configured to obtain intermediate events and the basic events corresponding to the target event; obtain the initial fault tree model according to the association relationship between the target event, the intermediate events, and the basic events, and obtain event weights corresponding to the respective basic events according to occurrence probabilities corresponding to the respective basic events.
[0136] In one embodiment, the initial model establishment module includes:
[0137] A basic event occurrence probability calculation unit, configured to determine the occurrence probability corresponding to the target event according to occurrence probabilities corresponding to the respective basic events;
[0138] A weight determination unit, configured to determine event weights corresponding to the respective basic events according to occurrence probabilities corresponding to the respective basic events and the occurrence probability corresponding to the target event.
[0139] In one embodiment, the initial model establishment module includes:
[0140] A relevant parameter calculation unit, configured to calculate relevant parameters between the respective basic events and respective index items in the initial fault tree model according to the respective historical event data and the respective historical index data;
[0141] An index determination unit, configured to determine the index items corresponding to the respective basic events according to the respective relevant parameters.
[0142] Each module in the above risk assessment apparatus can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent thereof, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.
[0143] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 database of the computer device is used to store risk assessment data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a risk assessment method.
[0144] Those skilled in the art can understand that Figure 8 the structure shown in
[0145] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.
[0146] Obtain the target fault tree model corresponding to the target event and multiple current index data of the target event. The index items corresponding to each of the current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item;
[0147] According to each of the current index data, each of the index weights, and the target fault tree model, obtain the risk assessment result of the target event.
[0148] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0149] Obtain an initial fault tree model, a plurality of historical event data of the target event, and a plurality of historical index data corresponding to each of the historical event data;
[0150] Iteratively train the initial fault tree model according to each of the historical index data and each of the historical event data to obtain the target fault tree model.
[0151] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0152] For each iterative training process, determine the sample index data corresponding to the iterative training process from each of the historical index data, and obtain the historical risk assessment result corresponding to the sample index data according to the sample index data and the intermediate fault tree model;
[0153] Compare the historical risk assessment result with the actual risk data in the sample event data corresponding to the sample index data to obtain a comparison result;
[0154] If the comparison result does not meet the preset condition, adjust the current event weights of each of the basic events in the intermediate fault tree model according to the comparison result until the comparison result meets the preset condition to obtain the target fault tree model.
[0155] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0156] Obtain the intermediate events and the basic events corresponding to the target event;
[0157] Obtain the initial fault tree model according to the correlation relationship between the target event, the intermediate events, and the basic events, and obtain the event weights corresponding to each of the basic events according to the occurrence probabilities corresponding to each of the basic events.
[0158] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0159] Determine the occurrence probability corresponding to the target event according to the occurrence probabilities corresponding to each of the basic events;
[0160] Determine the event weights corresponding to each of the basic events according to the occurrence probabilities corresponding to each of the basic events and the occurrence probability corresponding to the target event.
[0161] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0162] Calculate the correlation parameters between each of the basic events and each of the index items in the initial fault tree model according to the respective historical event data and the respective historical index data;
[0163] Determine the index items corresponding to each of the basic events according to the respective correlation parameters.
[0164] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:
[0165] Obtain a target fault tree model corresponding to a target event and multiple current index data of the target event. The index items corresponding to the respective current index data correspond to the basic events included in the target fault tree model respectively, and the index weights of the index items are the same as the event weights of the basic events corresponding to the index items;
[0166] Obtain a risk assessment result of the target event according to the respective current index data, the respective index weights, and the target fault tree model.
[0167] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0168] Obtain an initial fault tree model, multiple historical event data of the target event, and multiple historical index data corresponding to the respective historical event data;
[0169] Iteratively train the initial fault tree model according to the respective historical index data and the respective historical event data to obtain the target fault tree model.
[0170] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0171] For each iterative training process, determine sample index data corresponding to the iterative training process from the respective historical index data, and obtain a historical risk assessment result corresponding to the sample index data according to the sample index data and an intermediate fault tree model;
[0172] Compare the historical risk assessment result with the actual risk data in the sample event data corresponding to the sample index data to obtain a comparison result;
[0173] If the comparison result does not meet a preset condition, adjust the current event weights of each of the basic events in the intermediate fault tree model according to the comparison result until the comparison result meets the preset condition to obtain the target fault tree model.
[0174] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0175] Obtain the intermediate event and the basic event corresponding to the target event;
[0176] Obtain the initial fault tree model according to the correlation relationship among the target event, the intermediate event, and the basic event, and obtain the event weight corresponding to each basic event according to the occurrence probability corresponding to each basic event.
[0177] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0178] Determine the occurrence probability corresponding to the target event according to the occurrence probability corresponding to each basic event;
[0179] Determine the event weight corresponding to each basic event according to the occurrence probability corresponding to each basic event and the occurrence probability corresponding to the target event.
[0180] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0181] Calculate the correlation parameters between each basic event and each index item in the initial fault tree model according to each historical event data and each historical index data;
[0182] Determine the index item corresponding to each basic event according to each correlation parameter.
[0183] In one embodiment, a computer program product is provided, including a computer program, which when executed by a processor, implements the following steps:
[0184] Obtain the target fault tree model corresponding to the target event and multiple current index data of the target event, the index item corresponding to each current index data corresponds to the basic event included in the target fault tree model respectively, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item;
[0185] Obtain the risk assessment result of the target event according to each current index data, each index weight, and the target fault tree model.
[0186] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0187] Obtain the initial fault tree model, multiple historical event data of the target event, and multiple historical index data corresponding to each historical event data;
[0188] Iteratively train the initial accident tree model according to the historical indicator data and the historical event data to obtain the target accident tree model.
[0189] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0190] For each iterative training process, determine the sample indicator data corresponding to the iterative training process from the historical indicator data, and obtain the historical risk assessment result corresponding to the sample indicator data according to the sample indicator data and the intermediate accident tree model;
[0191] Compare the historical risk assessment result with the actual risk data in the sample event data corresponding to the sample indicator data to obtain a comparison result;
[0192] If the comparison result does not meet the preset condition, adjust the current event weights of the basic events in the intermediate accident tree model according to the comparison result until the comparison result meets the preset condition to obtain the target accident tree model.
[0193] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0194] Obtain the intermediate events and the basic events corresponding to the target event;
[0195] Obtain the initial accident tree model according to the association relationship between the target event, the intermediate events and the basic events, and obtain the event weights corresponding to the basic events according to the occurrence probabilities corresponding to the basic events.
[0196] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0197] Determine the occurrence probability corresponding to the target event according to the occurrence probabilities corresponding to the basic events;
[0198] Determine the event weights corresponding to the basic events according to the occurrence probabilities corresponding to the basic events and the occurrence probability corresponding to the target event.
[0199] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0200] Calculate the correlation parameters between the basic events and the index items in the initial accident tree model according to the historical event data and the historical indicator data;
[0201] Determine the index items corresponding to the basic events according to the correlation parameters.
[0202] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.
[0203] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory 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), magnetoresistive 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 be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.
[0204] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, 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, it should be considered as the scope recorded in this application.
[0205] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several deformations and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.
Claims
1. A risk assessment method, characterized in that The method includes: Obtaining a target fault tree model corresponding to a target event and multiple current index data of the target event, where the index items corresponding to the current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item; Obtaining a risk assessment result of the target event according to the current index data, the index weights, and the target fault tree model.
2. The method according to claim 1, wherein The method further includes: Obtaining an initial fault tree model, multiple historical event data of the target event, and multiple historical index data corresponding to the historical event data; Iteratively training the initial fault tree model according to the historical index data and the historical event data to obtain the target fault tree model.
3. The method according to claim 2, wherein The iteratively training the initial fault tree model according to the historical index data and the historical event data to obtain the target fault tree model includes: For each iterative training process, determining sample index data corresponding to the iterative training process from the historical index data, and obtaining a historical risk assessment result corresponding to the sample index data according to the sample index data and an intermediate fault tree model; Comparing the historical risk assessment result with the actual risk data in the sample event data corresponding to the sample index data to obtain a comparison result; If the comparison result does not meet a preset condition, adjusting the current event weights of the basic events in the intermediate fault tree model according to the comparison result until the comparison result meets the preset condition to obtain the target fault tree model.
4. The method according to claim 3, wherein The method further includes: Obtaining intermediate events and the basic events corresponding to the target event; Obtaining the initial fault tree model according to the association relationship between the target event, the intermediate events, and the basic events, and obtaining the event weights corresponding to the basic events according to the occurrence probabilities corresponding to the basic events.
5. The method according to claim 4, characterized in that The obtaining the event weights corresponding to the basic events according to the occurrence probabilities corresponding to the basic events includes: Determining the occurrence probability corresponding to the target event according to the occurrence probabilities corresponding to the basic events; Determining the event weights corresponding to the basic events according to the occurrence probabilities corresponding to the basic events and the occurrence probability corresponding to the target event.
6. The method according to claim 4, wherein The method further includes: Calculating correlation parameters between the basic events and the index items in the initial fault tree model according to the historical event data and the historical index data; Determining the index items corresponding to the basic events according to the correlation parameters.
7. A risk assessment device, characterized in that The device includes: An obtaining module, configured to obtain a target fault tree model corresponding to a target event and multiple current index data of the target event, where the index items corresponding to the current index data respectively correspond to the basic events included in the target fault tree model, and the index weight of the index item is the same as the event weight of the basic event corresponding to the index item; An evaluation module, configured to obtain a risk assessment result of the target event according to each of the current index data, each of the index weights, and the target accident tree model.
8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, 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.
10. A computer program product, comprising a computer program, 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.