Method and device for dynamic decision support for human error in emergency response in high-risk industries

Abstract

The application relates to a dynamic decision support method and device for human error in emergency response of high-risk industries, wherein the method comprises the following steps: identifying and classifying human errors in the execution process of emergency operation regulations; obtaining probabilities of different types of human errors; establishing a dynamic Bayesian network model of human factors in the emergency response process; obtaining a case database of human errors in the emergency response process according to the human error probabilities; and learning and updating parameters of the established dynamic Bayesian network model of human factors in the emergency response process. Thus, decision support is provided for preventing and controlling the skipping and execution errors of operators.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer software, in particular to a dynamic decision support method and device for human error in emergency response of high-risk industries. BACKGROUND

[0002] After an accident occurs, the on-site personnel often follow the corresponding emergency plan to take accident mitigation measures, and the emergency operation procedure is often an operation list, and the operator needs to execute the corresponding steps in turn;

[0003] However, in an emergency situation, the operator is prone to cognitive load and is prone to skipping steps and making execution errors, but the on-site personnel cannot know whether their behavior is wrong or not, which is not conducive to the subsequent operation, and needs to be solved urgently. SUMMARY

[0004] The present application provides a dynamic decision support method and device for human error in emergency response of high-risk industries to reduce the skipping steps and execution errors of operators in an emergency situation.

[0005] The first aspect of the present application provides a dynamic decision support method for human error in emergency response of high-risk industries, comprising the following steps: collecting human error data in the execution process of the emergency operation procedure in the target risk industry, and classifying the human error data to obtain a failure classification result, and calculating the human error probability of each failure type in the failure classification result; constructing a human dynamic Bayesian network model corresponding to the emergency response process in the target risk industry, and generating a human error case database in the emergency response process according to the human error probability and the human dynamic Bayesian network model; based on the human error case database, the human dynamic Bayesian network model is parameterized and updated, so that the human dynamic Bayesian network model after parameterization and updating and the preset environmental conditions are used to make dynamic decisions for the emergency response process in the target risk industry.

[0006] Optionally, in an embodiment of the present application, the human error data is classified to obtain a failure classification result, and the human error probability of each failure type in the failure classification result is calculated, comprising: classifying the human error data to obtain the failure classification result, wherein the failure classification result includes a diagnostic error type and an operation error type; based on a preset cognitive reliability model and a human behavior error definition, the human error probability corresponding to the diagnostic error type and the operation error type is calculated respectively.

[0007] Optionally, in an embodiment of the present application, the constructing the human factor dynamic Bayesian network model corresponding to the emergency response process in the target risk industry, and generating a human factor error case database in the emergency response process according to the human factor error probability and the human factor dynamic Bayesian network model, comprises: determining a plurality of link nodes corresponding to the emergency response process in the target risk industry based on the error classification result, and constructing the human factor dynamic Bayesian network model according to the plurality of link nodes, wherein the plurality of link nodes comprise an emergency plan execution node, an emergency action node, an action diagnosis error node, an action response error node, a recovery factor error node with, and a no-recovery factor error and accident node; and constructing a success criterion corresponding to the emergency response process based on the human factor error probability of the diagnosis error type and the operation error type, and generating the human factor error case database according to the human factor error probability and the success criterion by using a preset Monte Carlo algorithm.

[0008] Optionally, in an embodiment of the present application, the parameter learning and updating of the human factor dynamic Bayesian network model based on the human factor error case database is used to dynamically determine the emergency response process in the target risk industry by using the human factor dynamic Bayesian network model after the parameter learning and updating and a preset environmental condition, which comprises: learning the human factor error probability of each link node in the human factor error case database by using the human factor dynamic Bayesian network model and a preset MAP algorithm to obtain an accident occurrence probability; dynamically determining a plurality of error classification results of the each link node, and calculating a dynamic value of the accident occurrence probability according to the plurality of error classification results, so as to provide dynamic decision support for the emergency response process in the target risk industry by using the dynamic value.

[0009] The second aspect embodiment of the present application provides a dynamic decision support device for human factor errors in emergency response in a high-risk industry, which comprises: a classification module configured to collect human factor error data in an emergency operation procedure execution process in a target risk industry, and classify the human factor error data to obtain an error classification result, and calculate a human factor error probability of each error type in the error classification result; a modeling module configured to construct a human factor dynamic Bayesian network model corresponding to an emergency response process in the target risk industry, and generate a human factor error case database in the emergency response process according to the human factor error probability and the human factor dynamic Bayesian network model; and a dynamic decision support module configured to perform parameter learning and updating of the human factor dynamic Bayesian network model based on the human factor error case database, so as to dynamically determine the emergency response process in the target risk industry by using the human factor dynamic Bayesian network model after the parameter learning and updating and a preset environmental condition.

[0010] Optionally, in an embodiment of the present application, the classification module comprises: an acquisition unit configured to classify the human error data to obtain the error classification result, wherein the error classification result comprises a diagnosis error type and an operation error type; and a calculation unit configured to calculate human error probabilities corresponding to the diagnosis error type and the operation error type respectively based on a preset cognitive reliability model and a human error behavior definition.

[0011] Optionally, in an embodiment of the present application, the modeling module comprises: a first determination unit configured to determine a plurality of link nodes corresponding to an emergency response process in the target risk industry based on the error classification result, and construct the human dynamic Bayesian network model according to the plurality of link nodes, wherein the plurality of link nodes comprise an emergency plan execution node, an emergency action node, an action diagnosis error node, an action response error node, a recovery factor error node, and a non-recovery factor error and accident node; and a construction unit configured to construct a success criterion corresponding to the emergency response process based on the human error probabilities of the diagnosis error type and the operation error type, and generate the human error case database according to the human error probabilities and the success criterion by using a preset Monte Carlo algorithm.

[0012] Optionally, in an embodiment of the present application, the dynamic decision support module comprises: a learning unit configured to learn human error probabilities corresponding to each link node in the human error case database by using the human dynamic Bayesian network model and a preset MAP algorithm to obtain an accident occurrence probability; and a second determination unit configured to dynamically determine a plurality of error classification results of the each link node, and calculate a dynamic value of the accident occurrence probability according to the plurality of error classification results, so as to provide dynamic decision support for the emergency response process in the target risk industry through the dynamic value.

[0013] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the dynamic decision support method for human error in emergency response of high-risk industry as described in the above embodiments.

[0014] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the dynamic decision support method for human error in emergency response of high-risk industry as described above.

[0015] The fifth aspect of the present application provides a computer program product, comprising a computer program, which is executed to implement the dynamic decision support method for human error in emergency response of high-risk industry as described above.

[0016] Thus, embodiments of the present application have the following beneficial effects:

[0017] Embodiments of the present application can collect human error data in the execution process of emergency operation procedures in the target risk industry, classify the human error data to obtain error classification results, and calculate the human error probability of each error type in the error classification results; construct a human dynamic Bayesian network model corresponding to the emergency response process in the target risk industry, and generate a human error case database in the emergency response process according to the human error probability and the human dynamic Bayesian network model; based on the human error case database, perform parameter learning and updating on the human dynamic Bayesian network model, so as to make dynamic decisions on the emergency response process in the target risk industry through the human dynamic Bayesian network model after parameter learning and updating and the preset environmental conditions, thereby providing reference and guidance for the emergency response process in the high-risk industry to a certain extent, and providing decision support for scientific emergency. Thus, decision support is provided for the prevention and control of operation personnel skipping and execution errors.

[0018] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0019] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, wherein:

[0020] Figure 1 A flowchart of a dynamic decision support method for human error in emergency response in a high-risk industry according to an embodiment of the present application;

[0021] Figure 2 A logic architecture schematic diagram of a dynamic decision support method for human error in emergency response in a high-risk industry according to an embodiment of the present application;

[0022] Figure 3 An execution logic schematic diagram of a dynamic decision support method for human error in emergency response in a high-risk industry according to an embodiment of the present application;

[0023] Figure 4 A human dynamic Bayesian network model schematic diagram according to an embodiment of the present application;

[0024] Figure 5 An emergency response process human dynamic risk spectrum diagram under multiple conditions according to an embodiment of the present application;

[0025] Figure 6An example diagram of a high-risk industry emergency response human error dynamic decision support device according to an embodiment of the present application;

[0026] Figure 7 A structural schematic diagram of an electronic device provided by an embodiment of the present application.

[0027] Among them, 10-high risk industry emergency response human error dynamic decision support device; 100-classification module, 200-modeling module, 300-dynamic decision support module; 701-memory, 702-processor, 703-communication interface. DETAILED DESCRIPTION

[0028] The embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar notations represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0029] The high-risk industry emergency response human error dynamic decision support method and device of the embodiments of the present application are described below with reference to the accompanying drawings. In view of the problems mentioned in the above background art, the present application provides a high-risk industry emergency response human error dynamic decision support method, in which human error data in the execution process of emergency operation procedures in a target risk industry is collected, and the human error data is classified to obtain an error classification result, and the human error probability of each error type in the error classification result is calculated; a human error dynamic Bayesian network model corresponding to the emergency response process in the target risk industry is constructed, and a human error case database in the emergency response process is generated according to the human error probability and the human error dynamic Bayesian network model; based on the human error case database, the human error dynamic Bayesian network model is parameterized and updated, so that the emergency response process in the target risk industry is dynamically decided by the human error dynamic Bayesian network model after parameterization and updating and the preset environmental conditions, thereby providing reference and guidance for the high-risk industry emergency response process to a certain extent, and providing decision support for scientific emergency. Thus, the skip and execution error of the operator can be prevented and controlled to a certain extent.

[0030] Specifically, Figure 1 A flowchart of a high-risk industry emergency response human error dynamic decision support method provided by an embodiment of the present application.

[0031] As Figure 1 shown, the high-risk industry emergency response human error dynamic decision support method includes the following steps:

[0032] In step S101, human error data in an emergency operation procedure execution process in a target risk industry is collected, and the human error data is classified to obtain an error classification result, and a human error probability of each error type in the error classification result is calculated.

[0033] Embodiments of the present application can first classify errors that can occur in the emergency operation procedure of the target risk industry into diagnostic errors and operational errors, wherein the diagnostic errors include deciding whether to enter the decision at the beginning and judging whether to execute the steps when executing each operation content; and the operational errors are whether each operation procedure content is successfully executed; then, embodiments of the present application can calculate the human error probability of each link according to the human cognitive reliability model and the definition of human error behavior in the national standard.

[0034] Optionally, in an embodiment of the present application, the human error data is classified to obtain an error classification result, and a human error probability of each error type in the error classification result is calculated, comprising: classifying the human error data to obtain an error classification result, wherein the error classification result includes diagnostic error types and operational error types; and calculating the human error probability of the diagnostic error types and the operational error types respectively based on a preset cognitive reliability model and a human error behavior definition.

[0035] It should be noted that for diagnostic errors, the HCR analysis method assumes that when the first explicit alarm is triggered after an accident occurs, the probability that the operation team does not respond to the alarm is related to the ratio of the available response time to the team median response time. In order to evaluate the reaction of the operation team under the accident condition, extensive simulator tests are carried out in the prior art, and the test results show that the relationship between the non-response probability and the time ratio can be appropriately modeled by a Weibull distribution. Specifically, assuming that P represents the probability that the operation team does not respond, the human diagnostic error probability is calculated using formula (1):

[0036]

[0037] Further analysis of the simulator test results confirms that when the response behavior of the operator is classified into different types, the non-response probabilities of different types follow different Weibull distributions, that is, the parameters a, β and γ in the probability calculation formula are different. In the HCR (Human Cognitive Reliability) method, human response behavior is divided into three categories based on skills, rules and knowledge, wherein the skill-based behavior refers to the behavior that the operator can perform skillfully without referring to the program; the rule-based behavior refers to the behavior that the operator needs to follow a specific program due to not being familiar with the operation; and the knowledge-based behavior refers to the behavior that there is no explicit program to rely on, and the operator needs to rely on personal understanding and judgment to perform.

[0038] The HCR model provides Weibull distribution parameters of the three behavior types based on the simulator test results, as shown in Table 1:

[0039] Table 1

[0040]

[0041]

[0042] Using the parameters described in Table 1, the embodiments of the present application can calculate the non-response probability of a specific type of operator response behavior.

[0043] For action errors, the embodiments of the present application refer to existing authoritative research and divide human action errors into cases with and without recovery factors, as shown in Table 2.

[0044] Table 2

[0045]

[0046] Therefore, the embodiments of the present application identify and classify human errors in the emergency operation procedure execution process, and obtain different types of human error probabilities, thereby providing reliable data support for constructing a human dynamic Bayesian network model and a human error case database.

[0047] In step S102, a human dynamic Bayesian network model corresponding to the emergency response process in the target risk industry is constructed, and a human error case database in the emergency response process is generated according to the human error probability and the human dynamic Bayesian network model.

[0048] Further, as shown in Table 2, the embodiments of the present application also need to establish a human dynamic Bayesian network model in the emergency response process, and obtain a human error case database in the emergency response process according to the human error probability. Figure 2

[0049] ​Optionally, in an embodiment of the present application, a human factor dynamic Bayesian network model corresponding to an emergency response process in a target risk industry is constructed, and a human factor error case database in the emergency response process is generated according to a human factor error probability and the human factor dynamic Bayesian network model, including: based on the error classification result, a plurality of link nodes corresponding to the emergency response process in the target risk industry are determined, and a human factor dynamic Bayesian network model is constructed according to the plurality of link nodes, wherein the plurality of link nodes include an emergency plan execution node, an emergency action node, an action diagnosis error node, an action response error node, an error node with recovery factors, and an error node without recovery factors and an accident node; based on the human factor error probability of the diagnosis error type and the operation error type, a success criterion corresponding to the emergency response process is constructed, and a human factor error case database is generated according to the human factor error probability and the success criterion by using a preset Monte Carlo algorithm.

[0050] It should be noted that the node state division and allocation in the human factor dynamic Bayesian network model in the emergency response process are as shown in Table 3:

[0051] Table 3

[0052]

[0053]

[0054] In an embodiment of the present application, the implementation state of the emergency plan (IEP) is divided into two: state 1 (S1) indicates that the emergency plan measures are implemented, and state 2 (S2) indicates that they are not implemented. Since the emergency plan contains a plurality of actions, the number of emergency actions (EAs) can be set to be from 1 to N in the present embodiment, wherein N corresponds to the number of actions related to the initial event in the emergency plan. The result state also has two: state 1 (S1) indicates that the result is successful, and state 2 (S2) indicates that the result is unsuccessful.

[0055] As described above, human errors are divided into two categories: action diagnosis errors (ADEs) and action response errors (AREs), and the node states of each error type have been defined. Among them, for action diagnosis errors, the states are classified as no error, skill-based error, rule-based error, and knowledge-based error; for action response errors, the states are classified as no error, error with recovery factors, and error without recovery factors; for accidents, the state is simply set to occur or not occur.

[0056] After obtaining the occurrence probability of human factor diagnosis and action errors, an embodiment of the present application can then construct a success criterion, and use a Monte Carlo algorithm to generate a corresponding human factor error case database in the corresponding emergency response link according to the corresponding probability.

[0057] In step S103, based on the human error case database, the human error dynamic Bayesian network model is learned and updated in parameters, so as to make dynamic decisions on the emergency response process in the target risk industry through the human error dynamic Bayesian network model learned and updated in parameters and preset environmental conditions.

[0058] Further, the embodiments of the present application also need to learn and update the parameters of the human error dynamic Bayesian network model constructed in the emergency response process, to provide dynamic decision support for the operators in the emergency response process.

[0059] Optionally, in an embodiment of the present application, based on the human error case database, the human error dynamic Bayesian network model is learned and updated in parameters, so as to make dynamic decisions on the emergency response process in the target risk industry through the human error dynamic Bayesian network model learned and updated in parameters and preset environmental conditions, including: learning the human error probability corresponding to each link node in the human error case database through the human error dynamic Bayesian network model and the preset MAP algorithm, to obtain the accident occurrence probability; dynamically determining a plurality of error classification results of each link node, and calculating a dynamic value of the accident occurrence probability according to the plurality of error classification results, to provide dynamic decision support for the emergency response process in the target risk industry through the dynamic value.

[0060] It should be noted that after data collection, the embodiments of the present application can learn the probability of each node by using the MAP algorithm provided by the GeNIe 2.0 software, and then obtain the probability of accident occurrence, and at the same time, the different states of each step can be dynamically set to obtain the dynamic value of the final occurrence probability, so as to realize the learning and updating of the parameters of the Bayesian network model; then, a series of environmental conditions can be set to dynamically display the influence of human error on the consequences of the emergency response process.

[0061] The execution logic of the dynamic decision support method for human error in high-risk industry emergency response of the present application is described below through a specific embodiment and in conjunction with the accompanying drawings.

[0062] Figure 3 The execution logic diagram of the dynamic decision support method for human error in high-risk industry emergency response of the present application is shown in FIG. 1. Figure 3 As shown in FIG. 1, the execution process of the dynamic decision support method for human error in high-risk industry emergency response of the present application is described as follows:

[0063] S301: Collect emergency operation procedure data and classify them:

[0064] As an implementable way, taking the pipe rupture before the initial event water flow meter as an example, the specific embodiments of the present application refer to the corresponding emergency response plan, and determine the key measures, as shown in Table 4:

[0065] Table 4

[0066]

[0067] It should be noted that the nuclear power plant operators have received comprehensive training, and all procedures are recorded in detail in the emergency manual, in which the specific emergency actions for the pipe rupture in front of the feedwater flow meter are shown in Table 5:

[0068] Table 5

[0069]

[0070] It should be noted that all the actions listed in Table 5 are rule-based behaviors.

[0071] S302: Determine the human error probability of each link in the emergency plan execution process:

[0072] Further, the embodiments of the present application can also be based on expert knowledge, assuming the allowed time of each step and corresponding to the time listed in Table 4; based on formula (1) and Table 1, the embodiments of the present application can determine the human error probability (HEPs) of each action, as shown in Table 4; after receiving the abnormal event signal, the available time for the embodiments of the present application to decide to execute the emergency plan (IEP) is generally assumed to be 5 minutes; for the action error probability, the embodiments of the present application use the values provided in Table 2, i.e. 0.025 for each key step with a recovery factor, and 0.05 for each key step without a recovery factor.

[0073] S303: Generate sample data according to the success criteria using the human error probability:

[0074] After that, the specific embodiments of the present application refer to the Monte Carlo method, and generate 2000 samples using the human error probability (HEPs) listed in Table 4; the data generation logic is as follows:

[0075] (1) If an error without a recovery factor (ERF) occurs, the corresponding action response error (ARE) will also occur;

[0076] (2) If an action response error (ARE) occurs, the corresponding emergency action (EA) will also fail;

[0077] (3) Considering the priority of the action, if EA1 fails, then EA2, EA3, EA4 and EA5 will also fail; if EA2 fails, then EA3, EA4 and EA5 will also fail, and so on;

[0078] (4) In addition, the impact of the incident emergency plan (IEP) must also be considered: if the IEP fails, EA1 also fails, and in turn, EA2 to EA5 also fail;

[0079] (5) The occurrence condition of the accident is: if the IEP, EA1 or any subsequent emergency action (up to EA5) fails, the accident will occur;

[0080] (6) If an action diagnosis error (ADE) occurs, it is considered that there is a skip phenomenon, which may lead to the occurrence of the event.

[0081] Based on the above logic, the specific embodiments of the present application generate 2000 data points to support subsequent Bayesian dynamic analysis, and Table 6 shows some Bayesian data samples:

[0082] Table 6

[0083]

[0084] S304: Parameter learning and implementation of dynamic emergency response human error risk spectrum calculation.

[0085] The generated data and constructed Bayesian network used in the specific embodiments of the present application are as shown in Figure 4 In addition, parameter learning is used to determine the probability distribution of each factor, and based on the Bayesian network structure and training data, the MAP algorithm provided by the GeNIe2.0 software can be used to learn the probability of each node, for example, the probability of an accident occurring in the S1 state is 46%, and the probability in the S2 state is 54%.

[0086] In addition, the specific embodiments of the present application analyze the risk spectrum under four operating states, as shown in Figure 5 The change in the probability of an accident occurring with the progress of the operation is observed; in the normal execution of each step, when each step is correctly and completely executed, the probability of an accident steadily decreases. However, in the second case, when a skip occurs at EA2, the probability of an accident sharply rises to 93%, and even if EA3, EA4 and EA5 are executed correctly, the probability of an accident continues to rise. Similarly, when the operator takes a wrong operation, the trend of the probability of an accident is similar to that of the skip operation, which sharply rises to 97% at EA3, and then remains at a high level. For the two-step skip case: if a skip occurs at EA2 and EA3 is skipped again, the probability of an accident decreases, mainly because the skip of EA3 may correct the error of EA2 to some extent; however, with the execution of EA4 and EA5, the probability of an accident rises again.

[0087] The above results demonstrate that the specific embodiments of this application can effectively and dynamically identify skipped errors and erroneous operations, thereby providing decision support for operators and reducing the possibility of human error in emergency situations.

[0088] The dynamic decision support method for human error in emergency response in high-risk industries proposed in this application collects human error data during the execution of emergency operating procedures in the target risk industry, classifies the human error data to obtain error classification results, and calculates the probability of human error for each error type in the error classification results; constructs a human error dynamic Bayesian network model corresponding to the emergency response process in the target risk industry, and generates a human error case database in the emergency response process based on the human error probability and the human error dynamic Bayesian network model; based on the human error case database, the human error dynamic Bayesian network model is subjected to parameter learning and updating, so as to make dynamic decisions on the emergency response process in the target risk industry through the parameter learning and updated human error dynamic Bayesian network model and preset environmental conditions, thereby providing reference and guidance for the emergency response process in high-risk industries to a certain extent, and providing decision support for scientific emergency response.

[0089] Secondly, with reference to the accompanying drawings, a dynamic decision support device for human error in emergency response in high-risk industries, based on an embodiment of this application, is described.

[0090] Figure 6 This is a block diagram of a dynamic decision support device for human error emergency response in high-risk industries, according to an embodiment of this application.

[0091] like Figure 6 As shown, the dynamic decision support device 10 for human error emergency response in high-risk industries includes: a classification module 100, a modeling module 200, and a dynamic decision support module 300.

[0092] The classification module 100 is used to collect human error data during the execution of emergency operating procedures in the target risk industry, classify the human error data to obtain error classification results, and calculate the probability of human error for each error type in the error classification results.

[0093] Modeling module 200 is used to construct a human factor dynamic Bayesian network model corresponding to the emergency response process in the target risk industry, and generate a database of human factor error cases in the emergency response process based on the probability of human factor errors and the human factor dynamic Bayesian network model.

[0094] The dynamic decision support module 300 is used to learn and update the parameters of the human factors dynamic Bayesian network model based on the human factors error case database, so as to make dynamic decisions on the emergency response process in the target risk industry through the human factors dynamic Bayesian network model after parameter learning and update and the preset environmental conditions.

[0095] Optionally, in an embodiment of the present application, the classification module 100 comprises an acquisition unit and a calculation unit.

[0096] The acquisition unit is configured to classify the human error data to obtain an error classification result, wherein the error classification result comprises a diagnosis error type and an operation error type.

[0097] The calculation unit is configured to calculate human error probabilities of the diagnosis error type and the operation error type respectively based on a preset cognitive reliability model and a human error behavior definition.

[0098] Optionally, in an embodiment of the present application, the modeling module 200 comprises a first determination unit and a construction unit.

[0099] The first determination unit is configured to determine a plurality of link nodes corresponding to an emergency response process in a target risk industry based on the error classification result, and construct a human error dynamic Bayesian network model according to the plurality of link nodes, wherein the plurality of link nodes comprise an emergency plan execution node, an emergency action node, an action diagnosis error node, an action response error node, a recovery factor error node with error, and a recovery factor error and accident node without error.

[0100] The construction unit is configured to construct a success criterion corresponding to the emergency response process based on the human error probabilities of the diagnosis error type and the operation error type, and generate a human error case database according to the human error probabilities and the success criterion by using a preset Monte Carlo algorithm.

[0101] Optionally, in an embodiment of the present application, the dynamic decision support module 300 comprises a learning unit and a second determination unit.

[0102] The learning unit is configured to learn human error probabilities of each link node in the human error case database by using the human error dynamic Bayesian network model and a preset MAP algorithm, to obtain an accident occurrence probability.

[0103] The second determination unit is configured to dynamically determine a plurality of error classification results of each link node, and calculate a dynamic value of the accident occurrence probability according to the plurality of error classification results, to provide dynamic decision support for the emergency response process in the target risk industry through the dynamic value.

[0104] It should be noted that the foregoing explanation and description of the embodiment of the dynamic decision support method for human error in emergency response of high-risk industries is also applicable to the embodiment of the dynamic decision support device for human error in emergency response of high-risk industries, which will not be described here again.

[0105] The high-risk industry emergency response human error dynamic decision support device provided by the embodiment of the application comprises a classification module, which is used to collect human error data in an emergency operation procedure execution process in a target risk industry, and classifies the human error data to obtain an error classification result, and calculates a human error probability of each error type in the error classification result; a modeling module, which is used to construct a human dynamic Bayesian network model corresponding to an emergency response process in the target risk industry, and generate a human error case database in the emergency response process according to the human error probability and the human dynamic Bayesian network model; and a dynamic decision support module, which is used to perform parameter learning and updating on the human dynamic Bayesian network model based on the human error case database, so as to perform dynamic decision on the emergency response process in the target risk industry through the human dynamic Bayesian network model after the parameter learning and updating and a preset environment condition, thereby providing reference and guidance for the emergency response process in the high-risk industry to a certain extent, and providing decision support for scientific emergency.

[0106] Figure 7 The structure schematic diagram of the electronic device provided by the embodiment of the application is provided. The electronic device can comprise:

[0107] The memory 701, the processor 702 and the computer program stored in the memory 701 and executable on the processor 702.

[0108] The processor 702 implements the high-risk industry emergency response human error dynamic decision support method provided in the above embodiment when executing the program.

[0109] Further, the electronic device further comprises:

[0110] The communication interface 703 is used for communication between the memory 701 and the processor 702.

[0111] The memory 701 is used to store the computer program executable on the processor 702.

[0112] The memory 701 can contain a high-speed RAM memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0113] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 7 Only one thick line is used in the figure to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0114] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can complete communication between each other through an internal interface.

[0115] The processor 702 can be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0116] The embodiments of the present application also provide a computer readable storage medium, having stored thereon a computer program, which is executed by a processor to implement the above-mentioned method for dynamic decision support for human error in emergency response of high-risk industries.

[0117] The embodiments of the present application also provide a computer program product, comprising a computer program, which is executed to implement the above-mentioned method for dynamic decision support for human error in emergency response of high-risk industries.

[0118] In the description of the application, reference to "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that a particular feature, structure, material, or characteristic being described is included in at least one embodiment or example of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment or example. Furthermore, the described specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. In addition, the usage of "N" means at least two, for example, two, three or the like, unless explicitly stated otherwise.

[0119] Furthermore, the terms "first", "second", or the like, are used merely as a designation of certain elements or features of the application, and do not imply or connote relative importance or a specific order of precedence. Thus, features defined with "first", "second", etc. can include at least one of the features, either explicitly or implicitly.

[0120] Any process or method descriptions or blocks in flow charts or otherwise described herein represent embodiments which can be managed as one or more modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions or steps, and alternate implementations are possible. In some embodiments, the processes and methods described can be executably encoded on a machine- readable medium in a data signal embodied in an electromagnetic signal, a wireless signal, or a propagated signal.

[0121] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of instructions to implement logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, processor- based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a computer- readable storage medium or a computer-readable signal medium. The computer- readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include the following: an electrical connection having one or more wires (electrical connections), a portable computer diskette (a magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via, for example, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

[0122] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware and in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0123] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiments can be completed by programs instructing related hardware, and the programs can be stored in a computer-readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0124] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0125] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A dynamic decision support method for human error in emergency response in high-risk industries, characterized by, The method comprises the following steps: Collecting human error data in the execution process of emergency operation procedures in a target risk industry, and classifying the human error data to obtain error classification results, and calculating human error probability of each error type in the error classification results according to a human cognitive reliability model; Building a human dynamic Bayesian network model corresponding to the emergency response process in the target risk industry, and generating a human error case database in the emergency response process according to the human error probability and the human dynamic Bayesian network model; Based on the human error case database, the human dynamic Bayesian network model is parameterized and updated, and the emergency response process in the target risk industry is dynamically decided by the human dynamic Bayesian network model after parameterization and updating and the preset environmental conditions. The method comprises the following steps: Based on the error classification results, a plurality of link nodes corresponding to the emergency response process in the target risk industry are determined, and the human dynamic Bayesian network model is built according to the plurality of link nodes, wherein the plurality of link nodes include an emergency plan execution node, an emergency action node, an action diagnosis error node, an action response error node, a recovery factor error node with error and an accident node without recovery factor error. Based on the human error probability of each error type, a success criterion corresponding to the emergency response process is built, and the human error case database is generated according to the human error probability and the success criterion by using a preset Monte Carlo algorithm.

2. The method of claim 1, wherein, The method comprises the following steps: The human error data is classified to obtain the error classification results, wherein the error classification results include diagnosis error types and operation error types. Based on a preset cognitive reliability model and human behavior error definition, the human error probability corresponding to the diagnosis error types and the operation error types is calculated respectively.

3. The method of claim 1, wherein, The method comprises the following steps: The human error probability corresponding to each link node in the human error case database is learned by the human dynamic Bayesian network model and a preset MAP algorithm to obtain an accident occurrence probability. The plurality of error classification results of each link node are dynamically determined, and the dynamic value of the accident occurrence probability is calculated according to the plurality of error classification results, so as to provide dynamic decision support for the emergency response process in the target risk industry by the dynamic value.

4. A dynamic decision support device for human error in emergency response in high-risk industries, characterized by, The method comprises the following steps: The classification module is configured to collect human error data in the execution of the emergency operation procedure in the target risk industry, and classify the human error data to obtain an error classification result, and calculate a human error probability of each error type in the error classification result according to a human cognitive reliability model. The modeling module is configured to construct a human dynamic Bayesian network model corresponding to the emergency response process in the target risk industry, and generate a human error case database in the emergency response process according to the human error probability and the human dynamic Bayesian network model. The dynamic decision support module is configured to perform parameter learning and updating on the human dynamic Bayesian network model based on the human error case database, so as to make a dynamic decision on the emergency response process in the target risk industry by using the human dynamic Bayesian network model after the parameter learning and updating and a preset environmental condition. The modeling module comprises: The first determination unit is configured to determine a plurality of link nodes corresponding to the emergency response process in the target risk industry based on the error classification result, and construct the human dynamic Bayesian network model according to the plurality of link nodes, wherein the plurality of link nodes comprise an emergency plan execution node, an emergency action node, an action diagnosis error node, an action response error node, a recovery factor error node with recovery factor, and a recovery factor error and accident node without recovery factor. The construction unit is configured to construct a success criterion corresponding to the emergency response process based on the human error probability of each error type, and generate the human error case database according to the human error probability and the success criterion by using a preset Monte Carlo algorithm.

5. The apparatus of claim 4, wherein, The classification module comprises: The acquisition unit is configured to classify the human error data to obtain the error classification result, wherein the error classification result comprises a diagnosis error type and an operation error type. The calculation unit is configured to calculate the human error probability of the diagnosis error type and the operation error type respectively based on a preset cognitive reliability model and a human behavior error definition.

6. An electronic device, comprising: The computer program is executed by the processor to implement the dynamic decision support method for human error in emergency response in a high-risk industry according to any one of claims 1-3. The computer program is executed by the processor to implement the dynamic decision support method for human error in emergency response in a high-risk industry according to any one of claims 1-3.

7. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed to implement the dynamic decision support method for human error in emergency response in a high-risk industry according to any one of claims 1-3.

8. A computer program product comprising a computer program, characterized in that, ​

Images