Basic human error probability evaluation method and apparatus, device, medium and product

Abstract

The present application relates to the technical field of data analysis, in particular to a basic human error probability evaluation method and apparatus, a device, a medium and a product. The method comprises: acquiring target case information that needs to be analyzed; inputting the target case information into a pre-constructed multi-agent analysis framework, the multi-agent analysis framework outputting a multi-agent analysis result of the target case information; and, on the basis of a pre-constructed knowledge graph database and the multi-agent analysis result, generating values of a plurality of indicator parameters of a basic human error probability, and, on the basis of the knowledge graph database and the values of the plurality of indicator parameters, evaluating the basic human error probability for the target case information. Thus, the present application solves the problems of high dependence on expert knowledge, long evaluation time, low evaluation efficiency, etc. in the prior art.

Description

Basic methods, devices, equipment, media and products for assessing the probability of human error.

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411917310.X, filed on December 24, 2024, entitled “Method, Apparatus, Device, Medium and Product for Evaluating Basic Human Error Probability”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of data analysis technology, and in particular to a method, apparatus, equipment, medium and product for assessing the probability of human error. Background Technology

[0004] In safety management and risk assessment across numerous industries, accidents are often closely linked to human factors. This is particularly true in high-risk sectors such as nuclear power, aviation, and transportation, where the vast majority of accidents can be traced back to human error. Human error not only causes direct property damage and personal injury but also has long-term negative impacts on society and the environment. Therefore, assessing and reducing the probability of human error has become a crucial issue in improving safety.

[0005] Existing basic methods for assessing the probability of human error generally rely on expert knowledge and empirical judgment to determine the probability of human error. The main problem with these methods is their heavy dependence on expert experience. The assessment process is often cumbersome and time-consuming, especially in complex systems and multi-factor scenarios, where the assessment difficulty increases, leading to low assessment efficiency. Summary of the Invention

[0006] This application provides a basic method, apparatus, equipment, medium, and product for assessing the probability of human error, in order to solve the problems of existing technologies that rely heavily on expert knowledge, have long assessment times, and low assessment efficiency.

[0007] The first aspect of this application provides a method for assessing the probability of basic human error, comprising the following steps: obtaining target case information to be analyzed; inputting the target case information into a pre-constructed multi-agent analysis framework, the multi-agent analysis framework outputting multi-agent analysis results of the target case information; generating values ​​of multiple indicator parameters for the probability of basic human error based on a pre-constructed knowledge graph database and the multi-agent analysis results; and assessing the probability of basic human error of the target case information based on the knowledge graph database and the values ​​of the multiple indicator parameters.

[0008] Optionally, before generating the values ​​of multiple indicator parameters of the basic human error probability based on the pre-built knowledge graph database and multi-agent analysis results, the method further includes: identifying the user's analysis needs; determining the type of basic human error probability analysis based on the analysis needs; determining the target knowledge graph of the knowledge graph database based on the type; and generating the values ​​of multiple indicator parameters of the basic human error probability based on the target knowledge graph and multi-agent analysis results.

[0009] Optionally, the multi-agent analysis framework includes first to fourth agents, wherein the first agent is used to perform task analysis on the target case information; the second agent is used to perform context analysis on the target case information; the third agent is used to perform cognitive activity analysis on the target case information; and the fourth agent is used to perform time constraint analysis on the target case information.

[0010] Optionally, before generating the values ​​of multiple indicator parameters of the basic human error probability based on the pre-built knowledge graph database and multi-agent analysis results, the method further includes: acquiring data related to the basic human error probability from the target database; and constructing a knowledge graph database using the target graph database management system and related data.

[0011] Optionally, the multi-agent analysis results include task analysis results, context analysis results, cognitive activity analysis results, and time constraint analysis results. The indicator parameters include human factors affecting performance, cognitive error patterns, tasks, performance influencing factor variables, and other performance influencing factors. The knowledge graph database includes a scene familiarity knowledge graph, an information availability and reliability knowledge graph, and a task complexity knowledge graph.

[0012] Optionally, the task analysis process includes at least one of the following: task overview, task classification, analysis of task objectives, checking error types and impacts, and determining task complexity; the context analysis process includes at least one of the following: identifying the background conditions in which the task occurs, analyzing the support required to perform the task, clarifying the initial conditions and requirements for task initiation, and checking error measurement data; the cognitive activity analysis process includes at least one of the following: checking the cognitive needs required to perform the task and understanding the psychological processes behind task performance; and the time constraint analysis process includes at least one of the following: analyzing data sources and analyzing time constraints.

[0013] A second aspect of this application provides a basic human error probability assessment device, comprising: an acquisition module for acquiring target case information to be analyzed; an input module for inputting the target case information into a pre-constructed multi-agent analysis framework, wherein the multi-agent analysis framework outputs multi-agent analysis results of the target case information; and an evaluation module for generating values ​​of multiple index parameters of the basic human error probability based on a pre-constructed knowledge graph database and the multi-agent analysis results, and evaluating the basic human error probability of the target case information based on the knowledge graph database and the values ​​of the multiple index parameters.

[0014] Optionally, it also includes: an identification module, used to identify the user's analysis needs before generating the values ​​of multiple indicator parameters of the basic human error probability based on the pre-built knowledge graph database and multi-agent analysis results; determine the type of basic human error probability analysis based on the analysis needs; determine the target knowledge graph of the knowledge graph database based on the type; and generate the values ​​of multiple indicator parameters of the basic human error probability based on the target knowledge graph and multi-agent analysis results.

[0015] Optionally, the multi-agent analysis framework includes first to fourth agents, wherein the first agent is used to perform task analysis on the target case information; the second agent is used to perform context analysis on the target case information; the third agent is used to perform cognitive activity analysis on the target case information; and the fourth agent is used to perform time constraint analysis on the target case information.

[0016] Optionally, it also includes: a construction module, used to acquire data related to the basic human error probability in the target database before generating values ​​for multiple indicator parameters of the basic human error probability based on the pre-built knowledge graph database and multi-agent analysis results; and to construct the knowledge graph database using the target graph database management system and related data.

[0017] Optionally, the multi-agent analysis results include task analysis results, context analysis results, cognitive activity analysis results, and time constraint analysis results. The indicator parameters include human factors affecting performance, cognitive error patterns, tasks, performance influencing factor variables, and other performance influencing factors. The knowledge graph database includes a scene familiarity knowledge graph, an information availability and reliability knowledge graph, and a task complexity knowledge graph.

[0018] Optionally, the task analysis process includes at least one of the following: task overview, task classification, analysis of task objectives, checking error types and impacts, and determining task complexity; the context analysis process includes at least one of the following: identifying the background conditions in which the task occurs, analyzing the support required to perform the task, clarifying the initial conditions and requirements for task initiation, and checking error measurement data; the cognitive activity analysis process includes at least one of the following: checking the cognitive needs required to perform the task and understanding the psychological processes behind task performance; and the time constraint analysis process includes at least one of the following: analyzing data sources and analyzing time constraints.

[0019] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to perform the basic human error probability assessment method as described in the above embodiments.

[0020] A fourth aspect of this application provides a computer-readable storage medium having a computer program or instructions stored thereon, which are executed by a processor to perform the basic human error probability assessment method as described above.

[0021] The fifth aspect of this application provides a computer program product, including a computer program or instructions, which, when executed, implement the basic human error probability assessment method as described in the above embodiments.

[0022] Therefore, this application has at least the following beneficial effects:

[0023] This application embodiment allows the target case information to be analyzed to be input into a pre-built multi-agent analysis framework. The multi-agent analysis framework then analyzes the target case information and combines the results with a pre-built knowledge graph database to generate values ​​for multiple indicator parameters of the basic human error probability. Based on the knowledge graph database and the values ​​of these indicator parameters, the basic human error probability of the target case information is evaluated. This helps industry personnel more efficiently quantify and assess the probability of human error, thereby improving the efficiency of safety risk assessment and providing strong decision support for improving human factor reliability. Furthermore, it does not rely excessively on expert knowledge; the basic human error probability is quickly generated through simple text descriptions, reducing assessment time and improving efficiency. Therefore, it solves the technical problems of existing technologies, such as high reliance on expert knowledge, long assessment times, and low assessment efficiency.

[0024] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0025] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0026] Figure 1 is a flowchart of a basic human error probability assessment method provided according to an embodiment of this application;

[0027] Figure 2 is an example diagram of a basic human error probability assessment device provided according to an embodiment of this application;

[0028] Figure 3 is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0029] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0030] The following description, with reference to the accompanying drawings, outlines a method, apparatus, device, medium, and product for assessing the probability of human error based on embodiments of this application. Existing methods for assessing the probability of human error, as mentioned in the background section, generally rely on expert knowledge and employ empirical judgment to determine the probability of human error. The main problems with such methods are: firstly, they heavily rely on expert experience, lacking sufficient objectivity and comprehensiveness; secondly, the evaluation process is often cumbersome and time-consuming, especially in complex systems and multi-factor situations, increasing the difficulty of accurate and efficient evaluation. This application provides a basic human error probability assessment method. In this method, the target case information to be analyzed can be input into a pre-built multi-agent analysis framework. The multi-agent analysis results of the target case information are then combined with a pre-built knowledge graph database to generate values ​​of multiple indicator parameters for the basic human error probability. Based on the knowledge graph database and the values ​​of these indicator parameters, the basic human error probability of the target case information is assessed. This helps industry personnel to more efficiently quantify and assess the probability of human error, thereby improving the efficiency of safety risk assessment and providing strong decision support for improving human reliability. Furthermore, it does not rely excessively on expert knowledge; the basic human error probability is quickly generated through simple text descriptions, reducing evaluation time and improving efficiency. Thus, it solves the problems of existing technologies that heavily rely on expert knowledge, have long evaluation times, and low evaluation efficiency.

[0031] Specifically, Figure 1 is a flowchart illustrating a basic human error probability assessment method provided in an embodiment of this application.

[0032] As shown in Figure 1, this basic human error probability assessment method includes the following steps:

[0033] In step S101, the target case information to be analyzed is obtained.

[0034] In step S102, the target case information is input into the pre-built multi-agent analysis framework, and the multi-agent analysis framework outputs the multi-agent analysis results of the target case information.

[0035] The results of multi-agent analysis include task analysis results, context analysis results, cognitive activity analysis results, and time constraint analysis results.

[0036] It is understood that, in the embodiments of this application, target case information can be input into a pre-built multi-agent analysis framework, and the multi-agent analysis framework can output the multi-agent analysis results of the target case information.

[0037] In this embodiment of the application, the multi-agent analysis framework includes a first to a fourth agent, wherein the first agent is used to perform task analysis on the target case information; the second agent is used to perform context analysis on the target case information; the third agent is used to perform cognitive activity analysis on the target case information; and the fourth agent is used to perform time constraint analysis on the target case information.

[0038] It is understood that the multi-agent analysis framework in this application includes first to fourth agents, that is, the multi-agent analysis framework deploys four agents driven by a large language model, including a first agent, a second agent, a third agent, and a fourth agent. These agents are designed to further refine and analyze the target case information provided by the user, and to more comprehensively reflect the human error process in the case.

[0039] The first agent is used to perform task analysis on the target case information; the second agent is used to perform contextual analysis on the target case information; the third agent is used to perform cognitive activity analysis on the target case information; and the fourth agent is used to perform time constraint analysis on the target case information.

[0040] Specifically:

[0041] The primary task of the first intelligent agent is to analyze data sources and identify tasks related to reported human error information. This task analysis comprises several key components. First, a task overview is provided, outlining the general process of the task. Second, task classification is performed, categorizing tasks according to their function or type to gain a clearer understanding of their nature and context. Third, the task objectives are analyzed, clarifying the specific goals of each task. Fourth, typical error types and their impacts are examined, identifying common errors in the task and assessing their potential consequences. Finally, the task complexity is determined, providing in-depth insights into the task difficulty, covering tasks from simple to highly complex. Specific hints and engineering content are shown below:

[0042] Analyze data sources to identify tasks involving reports of human error. Here are specific guidelines:

[0043] 1. Overview of the task process.

[0044] 2. Categorizing tasks by function or type helps in understanding their nature and context. For example:

[0045] Operational task: For example, "Use a fuel engine to transport fuel components".

[0046] Monitoring tasks: such as "indicator checks".

[0047] Diagnostic tasks: For example, "diagnostics that require interpreting a large number of instructions and alarms".

[0048] Decision-making task: For example, "choosing the wrong strategy".

[0049] Communication tasks: such as "pilot reiteration communications" and "nuclear facility operation communications".

[0050] Training task: For example, "Students take a test on relational working memory."

[0051] 3. Analyze the specific objectives of the task, such as:

[0052] Operational task: The goal is to complete a certain physical or logical action (such as transportation or program execution).

[0053] Monitoring task: The goal is to correctly identify signals or states (such as alarm detection and indicator checks).

[0054] Diagnostic task: The goal is to correctly understand complex or ambiguous information (such as interpreting alarms and indications).

[0055] Decision-making task: The goal is to select the correct strategy or solution.

[0056] Communication task: The goal is to accurately transmit or receive information.

[0057] Training objectives: The goal is to improve capabilities or assess performance.

[0058] 4. Analyze typical error types in the task and their impact, such as:

[0059] Omission error: For example, "Nuclear power plant maintenance (omitted instruction)".

[0060] Error identification: For example, "highly experienced driver simulation driving (miss rate of peripheral detection task)".

[0061] Execution error: For example, "Delayed execution (incorrect assessment of margin)".

[0062] Communication errors: For example, "pilot repeats communication (error rate of incorrect repeating messages)".

[0063] 5. Determine the complexity level of the task, including:

[0064] Simple tasks: such as "reading a table" and "signal detection".

[0065] Complex tasks: such as "diagnostics that require interpreting a large number of instructions and alarms" and "controlled operations that require monitoring the results of actions and adjusting actions accordingly".

[0066] Please answer my question in Chinese. The content to be analyzed is: {data_scource}, where data_scource represents the case information to be analyzed.

[0067] II. The core task of the second intelligent agent is to analyze the data source and the context related to task execution. Specifically, this includes four key tasks: First, identifying the background conditions under which the task occurs; second, analyzing the support required to execute the task; third, clarifying the initial conditions and requirements for task initiation; and finally, examining error metric data and evaluating task-related performance and results. The specific hints and engineering content are shown below:

[0068] Analyze the data source and the context. Here are specific guidelines:

[0069] 1. Identify the background conditions in which the task occurs, such as:

[0070] Whether it is done in a simulation environment (e.g., "Nuclear power plant operator performs emergency operating procedures (EOPs) on simulator").

[0071] Does it involve dynamic changes or complex situations (e.g., "operating the controller while monitoring a dynamic display")?

[0072] Is it an emergency mission under special circumstances (e.g., a series of missions such as "Nuclear power plant workers performing steam generator tube rupture (SGTR) incidents").

[0073] 2. Analyze the support required for task execution:

[0074] Tools and equipment: such as whether instruments, control panels or simulators are needed.

[0075] Procedures and instructions: Are there clear operating procedures or scripts?

[0076] Teamwork: such as whether it is necessary to communicate with others or coordinate tasks.

[0077] 3. Clarify the context and requirements for starting the task:

[0078] Regular triggers: such as periodic tasks or routine maintenance tasks.

[0079] Abnormal triggers: such as emergency tasks when a fault occurs (e.g., the "Nuclear power plant workers perform steam generator tube rupture (SGTR) events" series).

[0080] Context-dependent: For example, tasks in dynamic displays or multitasking environments.

[0081] 4. Analyze erroneous metrics, for example:

[0082] Error rate range: The error rate is explicitly stated for some tasks (e.g., 5% to 50% in "pilot repeat communication").

[0083] Severity of errors: Some errors may lead to system failure or catastrophic consequences.

[0084] Please answer my question in Chinese. The content to be analyzed is: {data_scource}.

[0085] Third, the primary task of the third agent is to analyze data sources and describe the task, identifying the specific cognitive activities involved. This includes examining the cognitive requirements for task execution and understanding the psychological processes behind task performance. Specific hinting engineering content is shown below:

[0086] Analyze data sources and describe the task to identify the cognitive activities involved. For example:

[0087] 1. Experience: Does the task require skilled operators (e.g., "military operator reading the table")?

[0088] 2. Cognitive abilities: such as memory ability (e.g., “students take a test on relational working memory”) or perceptual ability (e.g., “detecting signals during nuclear facility operation”).

[0089] 3. Decision-making ability: such as the need to assess ambiguous information (e.g., "diagnostics that require interpreting a large number of instructions and alarms").

[0090] The content to be analyzed is: {data_scource}.

[0091] Fourth, the primary task of the fourth agent is to analyze data sources and evaluate time constraints related to task execution. This involves identifying time limits, deadlines, or time-sensitive conditions that affect task execution and results. Specific hints for the project are shown below:

[0092] Analyze the data source and time constraints. The content to be analyzed is: {data_scource}.

[0093] In this application embodiment, the task analysis process includes at least one of the following: task overview, task classification, analyzing the task objectives, checking error types and their impacts, and determining the task complexity; the context analysis process includes at least one of the following: identifying the background conditions in which the task occurs, analyzing the support required to execute the task, clarifying the initial conditions and requirements for task initiation, and checking error measurement data; the cognitive activity analysis process includes at least one of the following: checking the cognitive needs required to execute the task and understanding the psychological processes behind task performance; the time constraint analysis process includes at least one of the following: analyzing data sources and analyzing time constraints.

[0094] It is understood that the process by which the four intelligent agents in this application embodiment analyze the target case information is as follows: The process of the first intelligent agent performing task analysis includes at least one of the following: task overview, task classification, analysis of task objectives, checking error types and impacts, and determining task complexity; The process of the second intelligent agent performing context analysis includes at least one of the following: identifying the background conditions of the task occurrence, analyzing the support required to execute the task, clarifying the initial conditions and requirements for task initiation, and checking at least one of the following: error measurement data; The process of the third intelligent agent performing cognitive activity analysis includes at least one of the following: checking the cognitive needs required for task execution and understanding the psychological processes behind task performance; The process of the fourth intelligent agent performing time constraint analysis includes at least one of the following: analyzing data sources and analyzing time constraints.

[0095] The following example illustrates the process and results of analysis performed by the multi-agent analysis framework.

[0096] The existing case information is as follows: This task requires the pilot to listen to and repeat the instructions of the air traffic controller. The pilot stores the information in memory, repeats it at the end of the transmission, and inputs the above content into a pre-built multi-agent analysis framework.

[0097] I. For the first agent, the output of the task analysis is as follows:

[0098] 1. Task Overview

[0099] This task requires pilots to heed instructions from air traffic controllers and accurately repeat those instructions after the information has been transmitted. This involves storing information in memory and ensuring the accurate reproduction of critical information.

[0100] 2. Task Classification

[0101] This task can be divided into two categories: communication tasks, which involve repeating the controller's instructions; and memory tasks, which require information to be transmitted from short-term memory. The main objectives of the task are to ensure the accuracy of communication—to deliver key information without omission or misunderstanding; and to ensure the reliability of memory—to ensure that no information is lost before repetition.

[0102] 3. Common Errors and Their Impact

[0103] Two common error types have been identified: communication errors, where critical information is incorrectly repeated or omitted; and memory errors, where pilots fail to recall all critical information. Both types of errors can affect flight safety, leading to incorrect operational instructions or incomplete actions.

[0104] 4. Task complexity

[0105] The task is classified as medium complexity.

[0106] 5. Difficulty of the task

[0107] It is mainly affected by the amount of key information and the transmission method (listening, memorizing, and repetition). As the complexity of the information increases, the difficulty of the task also increases.

[0108] II. For the second agent, the output of the context analysis is as follows:

[0109] 1. Task Background

[0110] This mission is conducted in a real operational environment, not a simulation. The mission takes place in a static context, meaning it does not involve dynamic changes. However, the complexity and amount of information may vary. There is no time limit for the mission, allowing pilots ample time to accurately relay the information.

[0111] 2. Support conditions required for task execution

[0112] The equipment required for this mission is extremely simple, relying solely on wireless communication devices. No other additional instruments or tools are mentioned. Since the relay of instructions depends primarily on the pilot's experience, there are no specific operating procedures or guidelines. The mission is conducted independently, without the need for teamwork or external verification.

[0113] 3. Task Triggering Conditions

[0114] This mission is typically triggered by a communication request from air traffic controllers and is part of routine flight operations. The execution of the mission is influenced by the complexity of the communication instructions and the methods of information transmission.

[0115] 4. Error measurement data

[0116] Error rates are not explicitly reported, but paraphrasing errors can occur under varying levels of information complexity. While the severity of these errors is not quantified, they can affect the accuracy of flight commands and pose a potential risk to operational safety.

[0117] III. For the third agent, the output results of cognitive activity analysis are as follows:

[0118] 1. Perception ability

[0119] It requires the ability to listen to and identify key information. One must understand the logical relationships within the information and the intent behind it.

[0120] 2. Memory capacity

[0121] The ability to retain multiple instructions in short-term memory is crucial. Information must be repeated without omission or distortion.

[0122] 3. Communication skills

[0123] The ability to accurately paraphrase information is crucial. The integrity and accuracy of key information must be maintained.

[0124] 4. Cognitive load

[0125] Cognitive load may increase when information complexity is high. This phenomenon is particularly pronounced in multitasking scenarios.

[0126] IV. For the fourth agent, the output of the time constraint analysis is as follows:

[0127] 1. Time constraints

[0128] The task has no time limit, allowing pilots ample time to complete the retelling. The time factor does not directly affect the error rate.

[0129] 2. Potential impact

[0130] Despite having ample time, the high complexity of the information may indirectly increase the difficulty of the task.

[0131] In this embodiment of the application, the multi-agent analysis results include the following: the indicator parameters include human factors affecting performance, cognitive error patterns, tasks, performance influencing factor variables, and other performance influencing factors; and the knowledge graph database includes a scene familiarity knowledge graph, an information availability and reliability knowledge graph, and a task complexity knowledge graph.

[0132] In step S103, the values ​​of multiple indicator parameters of the basic human error probability are generated based on the pre-constructed knowledge graph database and the multi-agent analysis results. The basic human error probability of the target case information is evaluated based on the knowledge graph database and the values ​​of the multiple indicator parameters.

[0133] The indicator parameters include PIF (Performance Influencing Factors), CFM (Cognitive Failure Mode), Task (and error measure), Performance Influencing Factor Variable (PIF Measure), and Other Performance Influencing Factors (and Uncertainty).

[0134] It is understood that the embodiments of this application can generate values ​​of multiple indicator parameters for the basic human error probability based on the pre-built knowledge graph database and multi-agent analysis results, and evaluate the basic human error probability of the target case information based on the knowledge graph database and the values ​​of multiple indicator parameters, so as to help industry personnel quantify and evaluate the probability of human error more efficiently, thereby improving the efficiency of safety risk assessment and providing strong decision support for improving human reliability.

[0135] In this embodiment of the application, before generating the values ​​of multiple index parameters of the basic human error probability based on the pre-constructed knowledge graph database and the multi-agent analysis results, the method further includes: acquiring data related to the basic human error probability in the target database; and constructing a knowledge graph database using the target graph database management system and the related data.

[0136] The target database consists of publicly available human factors reliability databases, such as the Integrated Human Event Analysis System for Human Reliability Data (IDHEAS-DATA) released in the United States in 2021; the target graphical data management system can be selected based on specific circumstances, such as Neo4j.

[0137] It is understood that the embodiments of this application can obtain data related to the basic human error probability in the target database, and then use the target graph database management system and related data to construct a knowledge graph database.

[0138] The following example uses a knowledge graph database built on Neo4j and IDHEAS-DATA.

[0139] The data on basic human factor reliability is divided into three categories: scenario familiarity (specific content in Tables 1 and 2), information availability and reliability (specific content in Tables 3 and 4), and task complexity (specific content in Tables 5 and 6). The specific type of analysis of basic human factor error probability is specified by the user. Table 1 shows the attribute identifiers and descriptions for the performance influencing factor - scenario familiarity; Table 2 shows the basic human factor error probability for the performance influencing factor - scenario familiarity; Table 3 shows the attribute identifiers and descriptions for the performance influencing factor - information availability and reliability; Table 4 shows the basic human error probability for information availability and reliability; Table 5 shows the attribute identifiers and descriptions for the performance influencing factor - task complexity; and Table 6 shows the basic human error probability for task complexity.

[0140] Table 1

[0141] Table 2

[0142] Table 3

[0143] Table 4

[0144] Table 5

[0145] Table 6

[0146] In this embodiment of the application, before generating the values ​​of multiple index parameters of the basic human error probability based on the pre-constructed knowledge graph database and the multi-agent analysis results, the method further includes: identifying the user's analysis needs; determining the type of basic human error probability analysis based on the analysis needs; determining the target knowledge graph of the knowledge graph database based on the type; and generating the values ​​of multiple index parameters of the basic human error probability based on the target knowledge graph and the multi-agent analysis results.

[0147] The analysis types include scene familiarity, information availability and reliability, and task complexity, while the knowledge graph database includes scene familiarity knowledge graph, information availability and reliability knowledge graph, and task complexity knowledge graph.

[0148] It is understood that the embodiments of this application can identify the user's analysis needs, determine the type of basic human error probability analysis based on the analysis needs, and then determine the target knowledge graph of the knowledge graph database based on the type. Based on the target knowledge graph and the multi-agent analysis results, the values ​​of multiple index parameters of basic human error probability are generated.

[0149] For example, if the user selects "Scene Database" as the type of basic human error probability analysis, the knowledge graph database will automatically switch to the nodes and information corresponding to scene familiarity, i.e., scene familiarity knowledge graph.

[0150] Specifically, this embodiment of the application, based on the analysis results output by the aforementioned knowledge graph data path and multi-agent analysis framework, generates the values ​​of various parameters of the basic human error probability based on the prompting engineering output of the large language model. Specifically, the user needs to select the type of basic human error probability analysis; assuming the user selects "task complexity" from three options: scene familiarity, information availability and reliability, and task complexity. Thus, the knowledge graph automatically switches to the nodes and information corresponding to "task complexity". Next, combining the knowledge from the knowledge graph and the output results of the aforementioned multi-agent analysis framework, the prompting engineering of the large language model generates the values ​​of various parameters of the basic human error probability. These parameters include Performance Influencing Factors (PIF), Cognitive Failure Mode (CFM), Task (and error measure), Performance Influencing Factor Measure (PIF Measure), and Other Performance Influencing Factors (and Uncertainty).

[0151] I. The following are the project prompts for Task (and error measure):

[0152] Please analyze the human error rates for these tasks, which are reported in the data source, along with definitions of the human errors measured in these tasks. The following is reference information for the analysis.

[0153] knowledge base:

[0154] Task information: scen_task;

[0155] Task context information: scen_context;

[0156] Information about cognitive activities involved in the task: scen_cog;

[0157] Task time limit information: scen_time;

[0158] Please write an analysis process for the Task (and error measure) output from {task_lib}, selecting the most suitable output from the list. The final output should be between <>. Please answer my question in English and strictly follow the required format.

[0159] Here, scen_task, scen_context, scen_cog, and scen_time are the output results of the agents for task analysis, context analysis, cognitive activity analysis, and time constraint analysis, respectively, while task_lib is the Task (and error measure) attribute information of the knowledge graph corresponding to "task complexity". After extraction, the Task (and error measure) is obtained as "Pilots listen to and read back key messages".

[0160] II. The prompts for Cognitive Failure Mode (CFM) are as follows:

[0161] Now please analyze the CFMs (Cognitive Failure Modes). CFMs are labeled D, U, DM, E, and T, representing Detection Failure, Understanding Failure, Decisionmaking Failure, Action Execution Failure, and Interteam Coordination Failure, respectively. Note that the task may involve multiple applicable CFMs.

[0162] D (Detection): Failed to correctly detect or identify the required information (such as alarms, instrument readings).

[0163] U (Understanding): Failure to correctly understand or interpret information (e.g., misunderstanding procedures, misinterpreting system status).

[0164] DM (Decisionmaking): Failure to make the right decision (e.g., choosing an inappropriate strategy).

[0165] E (Action Execution): Failed to execute the required action correctly (e.g., pressing the wrong button, operation delay).

[0166] T (Interteam Coordination): Failure of interteam communication or collaboration (such as incorrect information transmission or poor coordination).

[0167] If indistinguishable CFMs are reported in the task completion time, the output is "Unsp", indicating that no CFMs were specified. If the procedure involves multiple CFMs, output according to the logic: "&" for logical AND and " / " for logical OR. For example, if the procedure contains both D and U, the output is "<D&U> ".

[0168] The following is reference information used for analysis.

[0169] knowledge base:

[0170] Task information: scen_task;

[0171] Task context information: scen_context;

[0172] Information about cognitive activities involved in the task: scen_cog;

[0173] Task time limit information: scen_time;

[0174] Task (and error measure): Pilots listen to and read back key messages.

[0175] Please select the most suitable CFMs from {CFMs_lib}, output the analysis process, and output the final results between <>. Please answer my question in English and strictly follow the required format.

[0176] Here, scen_task, scen_context, scen_cog, and scen_time are the output results of the agents for task analysis, context analysis, cognitive activity analysis, and time constraint analysis, respectively. The "Task (and error measure): Pilots listen to and read back key messages" part contains the Task (and error measure) information already determined in the previous step. CFMs_lib is the CFMs attribute information of the knowledge graph corresponding to the Task (and error measure) "Pilots listen to and read back key messages" in "Task Complexity". After extraction, the CFMs result is "U".

[0177] III. The following are the project details regarding the factors affecting human factors in performance:

[0178] Now please analyze the basic PIF attributes. The following is reference information for the analysis.

[0179] Task information: scen_task;

[0180] Task context information: scen_context;

[0181] Information about cognitive activities involved in the task: scen_cog;

[0182] Task time limit information: scen_time;

[0183] Task (and error measure): Pilots listen to and read back key messages;

[0184] CFMs: U (Understanding).

[0185] Please select the most suitable PIF attribute from PIF_Attribute_lib, output the analysis process, and output the final result between <>. Please answer my question in English and strictly follow the required format.

[0186] Among them, scen_task, scen_context, scen_cog, and scen_time are the output results of the agents for task analysis, context analysis, cognitive activity analysis, and time constraint analysis, respectively. The Task (and error measure): Pilots listen to and read back key messages and CFMs: U (Understanding) are the already determined Task (and error measure). PIF_Attribute_lib is the PIF attribute information of the knowledge graph corresponding to the Task (and error measure) of "Pilots listen to and read back key messages" and CFMs of "U (Understanding)" in the "Task Complexity" section. After extraction, the PIF is "C11".

[0187] IV. The following are the suggested engineering contents for the Performance Influence Factor Measure (PIF Measure):

[0188] Now please analyze the PIF attribute metric—a task-specific factor or variable in the data source used to describe the process of task execution, which is related to a measurement of the human error rate. The following is reference information for the analysis.

[0189] Task information: scen_task;

[0190] Task context information: scen_context;

[0191] Information about cognitive activities involved in the task: scen_cog;

[0192] Task time limit information: scen_time;

[0193] Task (and error measure): Pilots listen to and read back key messages;

[0194] CFMs: U (Understanding);

[0195] PIF: C11.

[0196] Please select the most suitable PIF attribute measure from {PIF_Measure_lib}, output the analysis process, and output the final result between <>. Please answer my question in English and strictly follow the required format.

[0197] The components are: Task (and error measure): Pilots listen to and read back key messages; CFMs: U (Understanding); and PIF: C11. These are the already defined Task (and error measure). The CFMs information, PIF_Attribute_lib, represents the PIF Measure attribute information for the knowledge graph corresponding to the Task (and error measure) of "Pilots listen to and read back key messages," CFMs of "U (Understanding)," and PIF of "C11" in the "Task Complexity" section. After extraction, the output result is PIF measure: "Message complexity of key messages in one transmission."

[0198] V. Regarding other performance influencing factors (and uncertainties), the following are the project-related tips:

[0199] Now please analyze other PIFs (and uncertainties). Besides the PIF attributes in the study, the task context in the data source may contain other PIF attributes that may exist during task execution and therefore affect the reported human error rate. This section documents other existing PIF attributes, specifically whether the task was executed under time constraints. Information about time availability is crucial for inferring the underlying HEP (probability of Human Error) from the reported human error data. If time is insufficient, the reported human error rate corresponds to the sum of the underlying HEP and the probability of errors due to time constraints (P). It also documents uncertainties in the data source, as well as those mapped to CFM and PIF attributes. These uncertainties will affect how the reported error rate is integrated to inform the underlying HEP.

[0200] There are uncertainties in the data source and mapping to IDHEAS-G CFM, especially if the number of task executions is not large enough, the reported error rate may not represent the lowest HEP.

[0201] Task information: scen_task;

[0202] Task context information: scen_context;

[0203] Information about cognitive activities involved in the task: scen_cog;

[0204] Task time limit information: scen_time;

[0205] Task (and error measure): Pilots listen to and read back key messages;

[0206] CFMs: U (Understanding);

[0207] PIF: C11;

[0208] PIF Measure: Message complexity of key messages in one transmission.

[0209] Please write your answer with the following information requirements: Please select the most suitable output Other PIFs (and Uncertainty) from {Other_pif_lib}, where the content in parentheses represents the uncertainties. Output the analysis process and the final result between <>. Answer my question in English and strictly follow the required format.

[0210] The components are: Task (and error measure): Pilots listen to and read back key messages; CFMs: U (Understanding); PIF: C11; and PIF Measure: Message complexity of key messages in one transmission. These are the already determined Task (and error measure) components. The CFMs information, PIF_Attribute_lib, corresponds to the PIF Measure attribute information of the knowledge graph in the "Task Complexity" section, where the Task (and error measure) is "Pilots listen to and read back key messages," the CFMs are "U (Understanding)," the PIF is "C11," and the PIF Measure is "Message complexity of key messages in one transmission." After extraction, the output results show Other PlFs (and Uncertainty) as (Mixture of normal and emergent operations other PlF attributes may exist).

[0211] After obtaining the values ​​of each indicator parameter, the values ​​were entered into the knowledge graph database for searching. The search revealed that there was only one node in the knowledge graph. After querying with Neo4j, the Error Rate attribute of this node was found to be "M5=0.036, M8=0.05, M11=0.11, M15=0.23, M17=0.32, M>20=0.5". Thus, the basic human error probability of this case was obtained.

[0212] The basic human error probability assessment method of this application is described below through an embodiment, including:

[0213] 1. Construct a multi-agent analysis framework.

[0214] A multi-agent analysis framework is constructed to decompose case information and more comprehensively reflect the process of human error in the cases. This method deploys four agents driven by a large language model, each performing different tasks: task analysis, context analysis, cognitive activity analysis, and time constraint analysis. These agents aim to further refine and analyze the case information provided by the user.

[0215] 2. Construct a knowledge graph database for basic human error probability analysis.

[0216] Data on basic human error probabilities were collected from the Integrated Human Event Analysis System for Human Reliability Data (IDHEAS-DATA) released in the United States in 2021, and a knowledge graph database of basic human error probabilities was built using Neo4j.

[0217] 3. Input information and generate multi-agent analysis results for the described case.

[0218] Users input the case information to be analyzed into the multi-agent framework, which outputs task-related analysis, context analysis, cognitive activity analysis, and time constraint analysis results.

[0219] 4. Combining the results output of knowledge graphs and multi-agent systems, the values ​​of various parameters of the basic human error probability are generated based on the large language model.

[0220] Combining the knowledge graph database from step 2 and the output of the multi-agent framework from step 3, the values ​​of various parameters of the basic human error probability are generated based on the large language model output. Specifically, these parameters include performance influencing factors (PIF), cognitive failure mode (CFM), task (and error measure), performance influencing factor measure (PIF Measure), and other performance influencing factors (and uncertainty).

[0221] 5. Combine knowledge graph search to output the final basic human error probability value.

[0222] The values ​​of each parameter obtained in step 4 are input into the knowledge graph database for searching to obtain the final basic human-caused failure probability and to conduct a quantitative risk assessment of the described case.

[0223] In summary, this application's embodiment of a method for assessing the probability of basic human error based on a multi-agent framework and knowledge graph combines large language model technology, knowledge graph technology, and a multi-agent framework. First, a multi-agent analysis framework is constructed. By decomposing case information through a multi-agent system, the process of human error in the case can be more comprehensively reflected. Next, a knowledge graph database for basic human error probability analysis is constructed. The knowledge graph can systematically store the experience of domain experts, relevant data, and standard specifications, providing structured knowledge support for analysis. Then, the user inputs the corresponding case information, and an automated process generates the multi-agent analysis results for the described case. Next, the knowledge graph and large language model are combined to generate values ​​for various parameters of the basic human error probability. Finally, by combining the search function of the knowledge graph, the final basic human error probability value is output, thus providing efficient and accurate quantitative results for human factor reliability assessment.

[0224] According to the basic human error probability assessment method proposed in this application, the target case information to be analyzed can be input into a pre-constructed multi-agent analysis framework. The multi-agent analysis framework inputs the multi-agent analysis results of the target case information and combines them with a pre-constructed knowledge graph database to generate the values ​​of multiple indicator parameters of the basic human error probability. Then, the basic human error probability of the target case information is assessed based on the knowledge graph database and the values ​​of multiple indicator parameters. This helps industry personnel to quantify and assess the probability of human error more efficiently, thereby improving the efficiency of safety risk assessment and providing strong decision support for improving human factor reliability. Moreover, it does not rely too much on expert knowledge, and the basic human error probability is quickly generated through simple text description, reducing the assessment time and improving the assessment efficiency.

[0225] Next, referring to the accompanying drawings, a basic human error probability assessment device proposed according to an embodiment of this application is described.

[0226] Figure 2 is a block diagram of a basic human error probability assessment device according to an embodiment of this application.

[0227] As shown in Figure 2, the basic human error probability assessment device 10 includes: an acquisition module 100, an input module 200, and an assessment module 300.

[0228] The acquisition module 100 is used to acquire the target case information to be analyzed; the input module 200 is used to input the target case information into a pre-built multi-agent analysis framework, and the multi-agent analysis framework outputs the multi-agent analysis results of the target case information; the evaluation module 300 is used to generate the values ​​of multiple indicator parameters of the basic human error probability based on the pre-built knowledge graph database and the multi-agent analysis results, and evaluate the basic human error probability of the target case information based on the knowledge graph database and the values ​​of the multiple indicator parameters.

[0229] In this embodiment of the application, the device 10 further includes an identification module.

[0230] The identification module is used to identify the user's analysis needs before generating the values ​​of multiple indicator parameters of the basic human error probability based on the pre-built knowledge graph database and multi-agent analysis results; determine the type of basic human error probability analysis based on the analysis needs; determine the target knowledge graph of the knowledge graph database based on the type; and generate the values ​​of multiple indicator parameters of the basic human error probability based on the target knowledge graph and multi-agent analysis results.

[0231] In this embodiment of the application, the multi-agent analysis framework includes a first to a fourth agent, wherein the first agent is used to perform task analysis on the target case information; the second agent is used to perform context analysis on the target case information; the third agent is used to perform cognitive activity analysis on the target case information; and the fourth agent is used to perform time constraint analysis on the target case information.

[0232] In this embodiment of the application, the apparatus 10 further includes a construction module.

[0233] The construction module is used to acquire data related to the basic human error probability in the target database before generating values ​​for multiple indicator parameters of the basic human error probability based on the pre-built knowledge graph database and multi-agent analysis results; and to construct the knowledge graph database using the target graph database management system and related data.

[0234] In this embodiment, the multi-agent analysis results include task analysis results, context analysis results, cognitive activity analysis results, and time constraint analysis results. The indicator parameters include human performance influencing factors, cognitive error patterns, tasks, performance influencing factor variables, and other performance influencing factors. The knowledge graph database includes scene familiarity knowledge graph, information availability and reliability knowledge graph, and task complexity knowledge graph.

[0235] In this application embodiment, the task analysis process includes at least one of the following: task overview, task classification, analyzing the task objectives, checking error types and their impacts, and determining the task complexity; the context analysis process includes at least one of the following: identifying the background conditions in which the task occurs, analyzing the support required to execute the task, clarifying the initial conditions and requirements for task initiation, and checking error measurement data; the cognitive activity analysis process includes at least one of the following: checking the cognitive needs required to execute the task and understanding the psychological processes behind task performance; the time constraint analysis process includes at least one of the following: analyzing data sources and analyzing time constraints.

[0236] It should be noted that the foregoing explanation of the basic human error probability assessment method embodiment also applies to the basic human error probability assessment device of this embodiment, and will not be repeated here.

[0237] The basic human error probability assessment device proposed in this application can input the target case information to be analyzed into a pre-constructed multi-agent analysis framework. The multi-agent analysis framework inputs the multi-agent analysis results of the target case information and combines them with a pre-constructed knowledge graph database to generate the values ​​of multiple indicator parameters of the basic human error probability. Then, based on the knowledge graph database and the values ​​of multiple indicator parameters, the basic human error probability of the target case information is assessed. This helps industry personnel to quantify and assess the probability of human error more efficiently, thereby improving the efficiency of safety risk assessment and providing strong decision support for improving human reliability. Moreover, it does not rely too much on expert knowledge, but can quickly generate the basic human error probability through simple text description, reducing the assessment time and improving the assessment efficiency.

[0238] Figure 3 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0239] The memory 301, the processor 302, and the computer program stored on the memory 301 and capable of running on the processor 302.

[0240] When the processor 302 executes the program, it implements the basic human error probability assessment method provided in the above embodiments.

[0241] Furthermore, electronic devices also include:

[0242] Communication interface 303 is used for communication between memory 301 and processor 302.

[0243] The memory 301 is used to store computer programs that can run on the processor 302.

[0244] The memory 301 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0245] If the memory 301, processor 302, and communication interface 303 are implemented independently, they can be interconnected via a bus to communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in Figure 3, but this does not imply that there is only one bus or one type of bus.

[0246] Optionally, in a specific implementation, if the memory 301, processor 302, and communication interface 303 are integrated on a single chip, then the memory 301, processor 302, and communication interface 303 can communicate with each other through an internal interface.

[0247] Processor 302 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0248] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed by a processor, implements the above-described basic human error probability assessment method.

[0249] This application also provides a computer program product, including a computer program or instructions, which, when executed, implement the above-described basic human error probability assessment method.

[0250] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0251] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0252] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0253] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0254] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

Claims

1. A basic method for assessing the probability of human error, characterized in that, Includes the following steps: Obtain the target case information that needs to be analyzed; The target case information is input into a pre-built multi-agent analysis framework, and the multi-agent analysis framework outputs the multi-agent analysis results of the target case information. Based on the pre-constructed knowledge graph database and the multi-agent analysis results, the values ​​of multiple indicator parameters for the basic human error probability are generated, and the basic human error probability of the target case information is evaluated based on the knowledge graph database and the values ​​of the multiple indicator parameters.

2. The basic human error probability assessment method according to claim 1, characterized in that, Before generating values ​​for multiple indicators of the basic human error probability based on the pre-constructed knowledge graph database and the multi-agent analysis results, the process also includes: Identify users' analytical needs; Based on the aforementioned analytical requirements, determine the type of the basic human error probability analysis; The target knowledge graph of the knowledge graph database is determined based on the type; Based on the target knowledge graph and the results of the multi-agent analysis, values ​​for multiple index parameters of the basic human error probability are generated.

3. The basic human error probability assessment method according to claim 1, characterized in that, The multi-agent analysis framework includes first to fourth agents, wherein... The first intelligent agent is used to perform task analysis on the target case information; The second intelligent agent is used to perform contextual analysis on the target case information; A third intelligent agent is used to perform cognitive activity analysis on the target case information; The fourth agent is used to perform time-constrained analysis on the target case information.

4. The basic human error probability assessment method according to claim 1, characterized in that, Before generating values ​​for multiple indicators of the basic human error probability based on the pre-constructed knowledge graph database and the multi-agent analysis results, the process also includes: Obtain data from the target database related to the baseline human error probability; The knowledge graph database is constructed using the target graph database management system and the related data.

5. The basic human error probability assessment method according to claim 1, characterized in that, The multi-agent analysis results include task analysis results, context analysis results, cognitive activity analysis results, and time constraint analysis results. The indicator parameters include human factors affecting performance, cognitive error patterns, tasks, performance influencing factor variables, and other performance influencing factors. The knowledge graph database includes scene familiarity knowledge graph, information availability and reliability knowledge graph, and task complexity knowledge graph.

6. The basic human error probability assessment method according to claim 3, characterized in that, The task analysis process includes at least one of the following: task overview, task classification, analysis of task objectives, checking error types and their impact, and determination of task complexity. The context analysis process includes: identifying the background conditions in which the task occurs, analyzing the support required to execute the task, clarifying the initial conditions and requirements for task initiation, and checking at least one of the error measurement data; The cognitive activity analysis process includes: examining the cognitive needs required for task performance and understanding at least one of the psychological processes behind task performance; The time constraint analysis process includes: analyzing the data source and analyzing at least one of the time constraints.

7. A basic human error probability assessment device, characterized in that, include: The acquisition module is used to acquire information about the target case to be analyzed. The input module is used to input the target case information into a pre-built multi-agent analysis framework, and the multi-agent analysis framework outputs the multi-agent analysis results of the target case information. The evaluation module is used to generate values ​​of multiple indicator parameters for the basic human error probability based on the pre-built knowledge graph database and the multi-agent analysis results, and to evaluate the basic human error probability of the target case information based on the knowledge graph database and the values ​​of the multiple indicator parameters.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the basic human error probability assessment method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, The computer program or instructions are executed by a processor to implement the basic human error probability assessment method as described in any one of claims 1-6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed, they implement the basic human error probability assessment method as described in any one of claims 1-6.

Images