Human-computer interaction public place biological terrorism risk whole process assessment method

Through the full-process evaluation method of bioterrorism risk in public places with human-computer interaction, combined with the Fp-growth algorithm and Bayesian network model, the problem of insufficient correlation of indicators in traditional evaluation methods is solved, and the full-process risk assessment of bioterror events is realized , improves the accuracy and comprehensiveness of the assessment and provides more effective support for risk prevention and control in public places.

CN118966511APending Publication Date: 2024-11-15TIANJIN UNIV +1
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202410877548.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-02
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Traditional bioterrorist risk assessment methods are difficult to comprehensively evaluate the complexity of risk factors, and lack indicator correlation, resulting in inaccurate evaluation results.

Method used

The full-process evaluation method of bioterrorist risk in public places using human-computer interaction is used to achieve the correlation between risk factors by obtaining a list of risk factors, expert scoring, Fp-growth algorithm data mining, Bayesian network model construction and conditional probability table calculation. Relationship and dynamic assessment.

Benefits of technology

The full-process risk assessment of bioterrorist incidents has been realized, the accuracy and comprehensiveness of the assessment have been improved, and more effective support for the risk prevention and control work in important public places.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966511A_ABST
    Figure CN118966511A_ABST
Patent Text Reader

Abstract

The invention discloses a human-computer interaction public place biological terrorism risk whole process assessment method, and belongs to the technical field of biological terrorism risk assessment. Acquiring a risk factor list of the bioterrorism event of the target place; performing expert scoring on the risk factor list to obtain scoring data, and constructing a risk assessment index system of the bioterrorism event of the target site according to the scoring data; performing data mining on each risk factor, the score data and the event historical data to obtain a mutual association relationship among the risk assessment indexes; constructing a Bayesian network structure of the Bayesian network model according to the correlation relationship; calculating a conditional probability table of a Bayesian network model according to the Bayesian network structure and the score data; and inputting real-time data into the Bayesian network model to update the probability of each node, and performing risk level evaluation. The method has the advantages that the influence of lack of consideration of index relevance in a traditional assessment method is eliminated, and the risk assessment result is more accurate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of bioterrorism risk assessment, and in particular relates to a human-computer interactive public place bioterrorism risk full-process assessment method. Background Art

[0002] Traditional bioterrorism risk assessment research often focuses on single aspects such as bioterrorism monitoring, casualty assessment, and economic loss at a site, or only involves single-dimensional environmental risk factors, making it difficult to conduct a comprehensive assessment of bioterrorism incidents with highly complex risk factors.

[0003] In order to smoothly carry out risk prevention and control work for bioterrorism incidents in important public places, it is necessary to evaluate various risk events in order to understand the possible harm caused by the incidents, which is of great significance for ensuring the health of people in important public places and social security.

[0004] The risk of bioterrorism incidents includes both static risks inherent in local facilities and dynamic risks such as crowd behavior. The former represents the specific conditions of various risk factors such as the site environment that increase the risk of the incident, while the latter reflects the real-time risk evolution of the incident in combination with crowd behavior, emergency response, etc. in the event of an incident. It is necessary to combine dynamic risk assessment with local static risk analysis to obtain the most accurate results of risk assessment. Therefore, it is urgent to develop a human-computer interactive full-process assessment method for bioterrorism risk in public places to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to meet practical needs and provide a human-computer interactive full-process assessment method for bioterrorism risks in public places, which eliminates the influence of traditional assessment methods that lack consideration of indicator correlation, so that risk assessment can obtain more accurate results.

[0006] To achieve the above-mentioned purpose, the present invention aims to provide a human-computer interactive method for assessing the whole process of bioterrorism risk in public places, comprising the following steps:

[0007] S1. Obtain a list of risk factors for bioterrorism incidents at target locations;

[0008] S2. Experts score the risk factor list to obtain scoring data, and construct a risk assessment index system for bioterrorism incidents at target sites based on the scoring data; the risk assessment index system includes several risk factors, scoring data for each risk factor, and scoring data and event history data corresponding to the event history data;

[0009] S3, using the Fp-growth algorithm to perform data mining on various risk factors, scoring data, and event history data to obtain the correlation between risk assessment indicators;

[0010] S4, constructing a Bayesian network structure of a Bayesian network model according to the mutual correlation relationship;

[0011] S5, calculating the conditional probability table of the Bayesian network model according to the Bayesian network structure and the scoring data;

[0012] S6. Input real-time data into the Bayesian network model to update the probability of each node and conduct risk level assessment.

[0013] Furthermore, the risk factor list includes ex ante risk factors, in-process risk factors and ex post risk factors; wherein: the ex ante risk factors include monitoring and detection indicators, emergency support indicators; the in-process risk factors include risk diffusion indicators, emergency response indicators; the ex post risk factors include safety indicators, event spillover risk indicators.

[0014] Further, S2 includes: S21, collecting scoring data of the importance of each risk factor in the risk factor list provided by experts in multiple rounds; S22, performing statistical analysis on the scoring data to obtain the weight of each risk factor, that is, obtaining a risk assessment index system for bioterrorism incidents in important places.

[0015] Further, the S3 includes the following steps: S31, create an item header table: count the historical data of each risk factor to obtain the frequency, and arrange them in descending order of frequency; S32, build an initial FP tree: traverse the historical data of the risk factor and create a tree structure; S33, extract frequent item sets from the FP tree: for the items in the item header table, create a conditional pattern base for each item; the conditional pattern base is a set of paths ending with the corresponding item; S34, build a conditional FP tree: use the conditional pattern base to build an FP tree to reflect the situation of frequent item sets containing corresponding items; S35, recursive mining: recursively execute S31 to S34 for each conditional FP tree until the FP tree contains a single path or is empty; S36, output: a frequent item set list, which contains all item sets that meet the minimum support requirements and support counts.

[0016] Furthermore, in the Fp-growth algorithm, the support is not less than 0.6, the confidence is not less than 0.75, and the lift is not less than 1.

[0017] Furthermore, the conditional probability table is obtained by maximum likelihood estimation method.

[0018] Further, S61, the real-time data is input into the Bayesian network model to calculate the risk value; the calculation formula of the risk value is:

[0019]

[0020] Among them, P(B|e) is the posterior probability after real-time evidence e is given, P(B) is the prior probability of event B, P(e|B) is the probability of evidence given event B, and P(e) is the predefined posterior probability of evidence. is the joint distribution of e;

[0021] S62. Obtain the corresponding risk level according to the risk value.

[0022] Further, S62 also includes: calculating a risk threshold to obtain a corresponding risk level;

[0023] The risk threshold is determined by the following formula:

[0024]

[0025] Where N is the number of risk levels, Threshold i Represents the lower limit of the threshold range corresponding to the i-th risk level, 1≤i≤N, R max is the maximum risk value, R min is the minimum risk value.

[0026] The advantages and positive effects of this application are:

[0027] Based on the above technical solution, the present invention quantifies the risk factors by dividing them into pre-, mid- and post-event risk factors, dynamically assesses the probability and threat level of a bioterrorism incident, and realizes risk assessment of the entire bioterrorism incident process;

[0028] The present invention eliminates the impact of traditional assessment methods that lack consideration of indicator correlation, so that risk assessment can obtain more accurate results, helps to improve the accuracy and comprehensiveness of bioterrorism risk assessment, and provides more effective support for risk prevention and control work in important public places. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 The method for assessing the risk of bioterrorism incidents in a target public place provided by an embodiment of the present invention is shown;

[0031] Figure 2 The Bayesian network model provided by the first embodiment of the present invention is shown;

[0032] Figure 3The evaluation model provided by the third embodiment of the present invention is shown. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] First embodiment

[0035] The present invention provides a human-computer interactive method for assessing the whole process of bioterrorism risk in public places, such as Figure 1 As shown, the following steps are included:

[0036] S1. Obtain a list of risk factors for bioterrorism incidents at the target location.

[0037] A list of risk factors for bioterrorism incidents can be screened out through literature research and expert interviews. The list of risk factors includes pre-event risk factors, in-event risk factors, and post-event risk factors.

[0038] The ex ante risk factors are prevention and preparation, including monitoring and testing indicators and emergency support indicators. Specifically, such as insufficient construction of monitoring and early warning systems, operational failures of monitoring and early warning systems, false alarms and missed alarms of monitoring and early warning systems, insufficient monitoring scope, too slow monitoring and testing speed, insufficient emergency preparedness, incomplete emergency teams, insufficient professionalism of emergency personnel, lack of emergency training and drills, insufficient emergency material reserves, and no detailed and reliable emergency plans;

[0039] The risk factors during the event are response and disposal, including risk diffusion indicators and emergency response indicators; specifically, such as the spread of risk pathogens at different levels, accelerated transmission due to the density of people in the venue, long exposure time of people in the venue, insufficient on-site disposal and treatment measures, untimely emergency command decisions, failure to take timely response actions, lack of emergency protective equipment, inaccurate estimation of the event situation, failure to set up isolated and controllable areas, and inefficient on-site safety and management, etc.

[0040] Post-event risk factors are governance and recovery, including safety indicators and event spillover risk indicators; specifically, such as improper evacuation and dispersal measures, failure to divide control areas, lack of safeguards for the evacuation of personnel, failure to divide disinfection areas for timely disinfection, the possibility of secondary pollution incidents, failure to disinfect and provide emergency treatment to the wounded, irregular handling of the dead, unstable public order, panic among the crowd, and failure to safely manage evacuees.

[0041] S2. Experts score the risk factor list to obtain scoring data, and construct a risk assessment index system for bioterrorism incidents at the target site based on the scoring data; the risk assessment index system includes several risk factors, each risk factor, scoring data, and event history data corresponding to the scoring data and event history data.

[0042] Specifically, it also includes the following:

[0043] S21. Collect the scoring data of the importance of each risk factor in the risk factor list provided by multiple rounds of experts;

[0044] S22. Statistically analyze the scoring data to obtain the weight of each risk factor, that is, to obtain a risk assessment index system for bioterrorism incidents in important places.

[0045] S3. Use the Fp-growth algorithm to perform data mining on various risk factors, scoring data, and event history data to obtain the correlation between risk assessment indicators.

[0046] Specifically, the steps include:

[0047] S31. Create a header table: collect historical data of each risk factor to obtain the frequency, and arrange them in descending order according to the frequency;

[0048] S32, constructing an initial FP tree: traversing the historical data of risk factors and creating a tree structure;

[0049] S33, extracting frequent item sets from the FP tree: for the items in the item header table, creating a conditional pattern base for each item; the conditional pattern base is a set of paths ending with the corresponding item;

[0050] S34, constructing a conditional FP tree: constructing a FP tree using the conditional pattern base to reflect the situation of frequent item sets containing corresponding items;

[0051] S35, recursive mining: recursively execute S31 to S34 for each conditional FP tree until the FP tree contains a single path or is empty;

[0052] S36. Output: A list of frequent itemsets, including all itemsets that meet the minimum support requirements and support counts.

[0053] Among them, the screening indicators are support not less than 0.6, confidence not less than 0.75, and lift not less than 1.

[0054] Exemplarily, the table shows a result of data mining;

[0055] Table 1 Data mining results

[0056] Previous Item After Support Confidence Lift Monitoring and early warning false alarms and missed alarms Inadequate monitoring and early warning system construction 0.66 0.90 1.02 Insufficient monitoring coverage Inadequate monitoring and early warning system construction 0.67 0.94 1.06 Insufficient emergency supplies Inadequate emergency preparedness 0.61 0.83 1.11 Lack of emergency training and drills Inadequate emergency preparedness 0.63 0.85 1.13 Lack of professionalism of emergency personnel Inadequate emergency preparedness 0.62 0.79 1.06 Lack of professionalism of emergency personnel Inadequate emergency response team 0.63 0.81 1.10 Lack of emergency training and drills Lack of professionalism of emergency personnel 0.63 0.85 1.08 Emergency command decision-making is not timely Inadequate on-site handling and treatment measures 0.62 0.82 1.05 Excessive crowd density in places accelerates the spread of the virus Inadequate on-site handling and treatment measures 0.61 0.87 1.11 Lack of evacuation routes and shelters Crowd panic 0.63 0.85 1.04 Lack of available safeguards for evacuation of personnel Lack of evacuation routes and shelters 0.67 0.83 1.11 Crowd panic Public order is unstable 0.72 0.89 1.21 Lack of available safeguards for evacuation of personnel Public order is unstable 0.61 0.76 1.03

[0057] S4. Constructing a Bayesian network structure of a Bayesian network model according to the mutual correlation relationship.

[0058] like Figure 2 As shown, each node in the Bayesian network follows the Bayesian theorem, that is,

[0059]

[0060] Among them, P(A) is the probability of event A occurring, P(B) is the probability of event B occurring, P(B|A) is the probability of event B occurring when event A occurs, that is, the probability of the latter occurring under the condition that the former occurs, and P(A|B) is the probability of event A occurring when event B occurs.

[0061] S5, calculating the conditional probability table of the Bayesian network model according to the Bayesian network structure and the scoring data;

[0062] Among them, the conditional probability table is obtained by the maximum likelihood estimation method.

[0063] S6. Input real-time data into the Bayesian network model to update the probability of each node and conduct risk level assessment.

[0064] Specifically, the steps include:

[0065] S61. Input the real-time data into the Bayesian network model to calculate the risk value; the calculation formula of the risk value is:

[0066]

[0067] Among them, P(B|e) is the posterior probability after real-time evidence e is given, P(B) is the prior probability of event B, P(e|B) is the probability of evidence given event B, and P(e) is the predefined posterior probability of evidence. is the joint distribution of e; real-time data is also real-time evidence, such as the type, location, number of people of biological terrorism, etc.

[0068] S62. Obtain the corresponding risk level according to the risk value.

[0069] The risk threshold of the risk level is determined by the following formula:

[0070]

[0071] Where N is the number of risk levels, Threshold i Represents the lower limit of the threshold range corresponding to the i-th risk level, 1≤i≤N, R max is the maximum risk value, R min is the minimum risk value.

[0072] Table 2 shows the specified threshold division range, corresponding to the calculated risk threshold and the corresponding level.

[0073] Table 2 Risk threshold classification

[0074]

[0075]

[0076] The higher the level, the greater the risk. The corresponding risk threshold interval is found based on the obtained risk value, which is the corresponding risk level, and then the dynamic risk assessment results of the event and the identification of high-risk points are provided.

[0077] Second embodiment

[0078] Based on the human-computer interactive public place bioterrorism risk full process assessment method in the first embodiment, a system is provided, including:

[0079] Data acquisition module: obtain a list of risk factors for bioterrorism incidents at target sites; perform expert scoring on the list of risk factors to obtain scoring data, and construct a risk assessment index system for bioterrorism incidents at target sites based on the scoring data; the risk assessment index system includes several risk factors, scoring data for each risk factor, and scoring data and event history data corresponding to the event history data;

[0080] Data processing module: Use the Fp-growth algorithm to perform data mining on various risk factors, scoring data, and event history data to obtain the inter-correlation relationship between risk assessment indicators; construct the Bayesian network structure of the Bayesian network model based on the inter-correlation relationship; calculate the conditional probability table of the Bayesian network model based on the Bayesian network structure and scoring data;

[0081] Risk assessment module: input real-time data into the Bayesian network model to update the probability of each node and conduct risk level assessment.

[0082] For other contents, please refer to the first embodiment.

[0083] Third embodiment

[0084] In a specific embodiment, real-time data, i.e., real-time evidence, is input, such as the discovery of a type A pathogen in a certain area, an outbreak of type A pathogen, a preliminary estimate of the transmission route as airborne, and the current known number of exposed people is 1,000;

[0085] As the situation develops, the data nodes in the network are updated, such as changes in crowd density, emergency response measures, etc., and the probability distribution of subsequent nodes is recalculated; the probabilities in the network are updated once every hour.

[0086] like Figure 3 As shown, the infection rate caused by airborne transmission is high. For the final node R Low = 0.3 and R High =0.7, then

[0087] Therefore, the risk level is V, and isolation measures need to be taken quickly.

[0088] Fourth embodiment

[0089] The present invention provides an electronic device, which includes a processor for storing instructions executable by the processor; when the processor is configured to execute the instructions, the electronic device implements the human-computer interactive public place bioterrorism risk full-process assessment method as described in the first embodiment.

[0090] Fifth embodiment

[0091] The present invention provides a computer program product, including a computer program. When the computer program is executed by a processor, the computer program implements the human-computer interactive public place bioterrorism risk full-process assessment method described in the first embodiment.

[0092] Based on the above technical solution, the present invention eliminates the influence of the traditional evaluation method's lack of consideration of the correlation of indicators, so that risk assessment can obtain more accurate results.

[0093] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When the use is implemented in whole or in part in the form of a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL) or wireless (e.g., infrared, wireless, microwave, etc.) mode) to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk SolidState Disk (SSD)), etc.

[0094] The above is only a preferred embodiment of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A human-computer interactive method for assessing the whole process of bioterrorism risk in public places, characterized in that: The following steps are involved: S1. Obtain a list of risk factors for bioterrorism incidents at target locations; S2. Experts score the risk factor list to obtain scoring data, and construct a risk assessment index system for bioterrorism incidents at target sites based on the scoring data; the risk assessment index system includes several risk factors, scoring data for each risk factor, and scoring data and event history data corresponding to the event history data; S3, using the Fp-growth algorithm to perform data mining on various risk factors, scoring data, and event history data to obtain the correlation between risk assessment indicators; S4, constructing a Bayesian network structure of a Bayesian network model according to the mutual correlation relationship; S5, calculating the conditional probability table of the Bayesian network model according to the Bayesian network structure and the scoring data; S6. Input real-time data into the Bayesian network model to update the probability of each node and conduct risk level assessment.

2. The whole process assessment method of bioterrorism risk in public places based on human-computer interaction according to claim 1 is characterized in that: The risk factor list includes ex ante risk factors, in-process risk factors and ex post risk factors; among which: The ex ante risk factors include monitoring and testing indicators and emergency support indicators; The risk factors during the event include risk diffusion indicators and emergency response indicators; The post-event risk factors include safety indicators and event spillover risk indicators.

3. The whole process assessment method of bioterrorism risk in public places based on human-computer interaction according to claim 1 is characterized in that: The S2 further includes: S21. Collect the scoring data of the importance of each risk factor in the risk factor list provided by multiple rounds of experts; S22. Statistically analyze the scoring data to obtain the weight of each risk factor, that is, to obtain a risk assessment index system for bioterrorism incidents in important places.

4. The whole process assessment method of bioterrorism risk in public places based on human-computer interaction according to claim 1 is characterized in that: The S3 comprises the following steps: S31. Create a header table: collect historical data of each risk factor to obtain the frequency, and arrange them in descending order according to the frequency; S32, constructing an initial FP tree: traversing the historical data of risk factors and creating a tree structure; S33, extracting frequent item sets from the FP tree: for the items in the item header table, creating a conditional pattern base for each item; the conditional pattern base is a set of paths ending with the corresponding item; S34, constructing a conditional FP tree: constructing a FP tree using the conditional pattern base to reflect the situation of frequent item sets containing corresponding items; S35, recursive mining: recursively execute S31 to S34 for each conditional FP tree until the FP tree contains a single path or is empty; S36. Output: A list of frequent itemsets, including all itemsets that meet the minimum support requirements and support counts.

5. The whole process assessment method of bioterrorism risk in public places based on human-computer interaction according to claim 4 is characterized in that: In the Fp-growth algorithm, the support is not less than 0.6, the confidence is not less than 0.75, and the lift is not less than 1.

6. The whole process assessment method of bioterrorism risk in public places based on human-computer interaction according to claim 1 is characterized in that: The conditional probability table is obtained by maximum likelihood estimation method.

7. The whole process assessment method of bioterrorism risk in public places based on human-computer interaction according to claim 1 is characterized in that: The S6 includes: S61. Input the real-time data into the Bayesian network model to calculate the risk value; the calculation formula of the risk value is: Among them, P(B|e) is the posterior probability after real-time evidence e is given, P(B) is the prior probability of event B, P(e|B) is the probability of evidence given event B, and P(e) is the predefined posterior probability of evidence. is the joint distribution of e; S62. Obtain the corresponding risk level according to the risk value.

8. The whole process assessment method of bioterrorism risk in public places based on human-computer interaction according to claim 7 is characterized in that: S62 also includes: calculating a risk threshold to obtain a corresponding risk level; The risk threshold is determined by the following formula: Where N is the number of risk levels, Threshold i Represents the lower limit of the threshold range corresponding to the i-th risk level, 1≤i≤N, R max is the maximum risk value, R min is the minimum risk value.

Citation Information

Cited By

  • Rock stability analysis device and method in mining process

    CN119147051A

  • Urban safety risk assessment method and system based on digital standard

    CN119398525A

  • Human activity interference risk assessment method and system based on Bayesian network

    CN121481274A