CN113537727B - Intelligent risk level recognition system based on Bayesian judgment technology - Google Patents
Intelligent risk level recognition system based on Bayesian judgment technology Download PDFInfo
- Publication number
- CN113537727B CN113537727B CN202110705991.3A CN202110705991A CN113537727B CN 113537727 B CN113537727 B CN 113537727B CN 202110705991 A CN202110705991 A CN 202110705991A CN 113537727 B CN113537727 B CN 113537727B
- Authority
- CN
- China
- Prior art keywords
- risk
- border
- cross
- data
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 121
- 238000007689 inspection Methods 0.000 claims abstract description 25
- 238000005070 sampling Methods 0.000 claims abstract description 21
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 4
- 241000607479 Yersinia pestis Species 0.000 claims description 41
- 238000012502 risk assessment Methods 0.000 claims description 28
- 238000002360 preparation method Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000013398 bayesian method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000010998 test method Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 15
- 241000196324 Embryophyta Species 0.000 description 12
- 239000003181 biological factor Substances 0.000 description 12
- 238000009826 distribution Methods 0.000 description 8
- 235000013305 food Nutrition 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 238000011059 hazard and critical control points analysis Methods 0.000 description 5
- 238000004140 cleaning Methods 0.000 description 4
- 238000003672 processing method Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 244000000010 microbial pathogen Species 0.000 description 3
- 230000037361 pathway Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 241001124181 Bactrocera dorsalis Species 0.000 description 2
- 241000237852 Mollusca Species 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 239000000443 aerosol Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003900 soil pollution Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000005406 washing Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 102100039148 Ankyrin repeat domain-containing protein 49 Human genes 0.000 description 1
- 241000207199 Citrus Species 0.000 description 1
- 208000019331 Foodborne disease Diseases 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 101000889457 Homo sapiens Ankyrin repeat domain-containing protein 49 Proteins 0.000 description 1
- 240000001140 Mimosa pudica Species 0.000 description 1
- 240000005373 Panax quinquefolius Species 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 235000020971 citrus fruits Nutrition 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000005022 packaging material Substances 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000009919 sequestration Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a cross-border hidden factor intelligent risk level recognition system based on a Bayesian judgment technology, which is used for recognizing risks of cross-border hidden factors in different cross-border processes according to cross-border whole process decomposition of the cross-border hidden factors and by adopting the Bayesian judgment technology. According to the cross-border hidden factor intelligent risk level identification system based on the Bayesian judgment technology, the average value metering standard sampling inspection method or the unqualified rate metering standard sampling inspection method is adopted for sampling inspection, so that risks of the cross-border hidden factor in different cross-border processes can be identified according to cross-border whole process analysis of the cross-border hidden factor and the Bayesian judgment technology, and further the cross-border hidden high-risk factor can be effectively managed.
Description
Technical Field
The application relates to the field of biological safety risk analysis, in particular to a risk level identification system based on a Bayesian judgment technology, and especially relates to a cross-border hidden factor intelligent risk level identification system based on the Bayesian judgment technology.
Background
Cross-border organisms, and in particular cross-border pests, can pose a hazard to the area being invaded, thus requiring in-depth analysis of the risk of cross-border organisms ("cross-border organism factor" or "cross-border factor", hereinafter "cross-border factor").
The cross-border factor or pest must follow a particular path (path) to the area being invaded by it, where the path may be some way, process or procedure, and the process by which the cross-border factor follows its path to the area being invaded by it is referred to herein in the context as the cross-border process of the cross-border factor. For example, weeds or insects may reach the area invaded by them by natural diffusion; while pathogenic microorganisms typically require a certain medium to reach. With the globalization of economy, human activities have exceeded natural transmission and become the most dominant way for pest spread, and goods, passenger carriers, mailers, transportation means, wooden packages, containers, etc. in the paths related to human activities can be the medium for pest spread. Various factors in the cross-border process of the cross-border factor necessarily affect the risk of the cross-border factor, so that analysis and identification of the risk of the cross-border factor according to the cross-border process of the cross-border factor are necessary.
In addition, the risk judging technology based on the Bayesian theory can effectively integrate priori knowledge and continuously obtained posterior knowledge to predict, and correct the prediction model based on the posterior knowledge, so that the risk judging technology has good self-upgrading capability.
What is needed is an intelligent risk level recognition system based on a bayesian decision technique, which can be used for recognizing risks of cross-border hidden factors in different cross-border processes according to cross-border overall process decomposition of the cross-border hidden factors and by adopting the bayesian decision technique, so that the cross-border hidden high-risk factors can be managed more effectively.
Disclosure of Invention
According to the present application, an intelligent risk level recognition system based on a bayesian decision technique is provided, which is configured to recognize risks of a cross-border hidden factor according to a cross-border whole process decomposition of the cross-border hidden factor and using the bayesian decision technique, where the intelligent risk level recognition system based on the bayesian decision technique may include:
The data acquisition module is used for acquiring data and providing the data;
The cross-border whole process risk analysis module analyzes the cross-border whole process of the cross-border hidden factors by PRACCP method and determines a plurality of primary risk indexes corresponding to a plurality of links forming the cross-border whole process and a plurality of secondary risk indexes corresponding to each primary risk index;
The risk level construction module is used for constructing a risk level system to determine a risk level corresponding to the risk index;
The data preparation module is used for converting the data provided by the data acquisition module into data represented by the risk level according to the links, the primary risk indexes and the secondary risk indexes determined by the cross-border overall process risk analysis module and the risk level system constructed by the risk level construction module, so as to provide priori data; and
And the Bayesian risk judging module is used for determining the risk of the cross-border hidden factor by using the prior data provided by the data preparing module and based on a Bayesian method.
In an intelligent risk level recognition system based on a bayesian decision technique, according to an embodiment of the present application, the bayesian risk decision module may include:
the Bayesian risk calculation sub-module is used for determining a risk value corresponding to the primary risk index and a risk value corresponding to the secondary risk index based on a Bayesian method;
the risk weight calculation sub-module is used for determining the weight of the risk value corresponding to the primary risk index and the weight of the risk value corresponding to the secondary risk index through an analytic hierarchy process; and
The risk determining module is used for determining the risk of the cross-border hidden factor based on the risk value corresponding to the primary risk index and the risk value corresponding to the secondary risk index determined by the Bayesian risk calculating sub-module and the weight determined by the risk weight calculating sub-module.
In an intelligent risk level recognition system based on a bayesian decision technique, the data preparation module may also combine the risk determined by the bayesian risk decision module with existing prior data to form new prior data.
In an intelligent risk level recognition system based on Bayesian decision technique, a data preparation module may, according to an embodiment of the present application
Performing spot check on the data provided by the data acquisition module and calculating the spot check failure rate by the following steps:
Wherein X ij represents the secondary index of the cross-border overall process X, and k ij secondary indexes exist and are marked as
1.Ltoreq.i.ltoreq.n, 1.ltoreq.j.ltoreq.k, n representing the number of primary indexes X i corresponding to links of the whole process across the border, k representing the number of links corresponding to the primary indexes,
The false positive rate of the secondary index X ij,
K ij denotes the number of secondary indicators X ij,
M l represents the result of the spot check, accept is 1, reject is 0, m l∈{0,1},l＝0,1,…kij; and
The risk level of the secondary indicator may be determined based on the calculated spot check fail rate and based on the risk level hierarchy.
According to an embodiment of the present application, in the intelligent risk level recognition system based on the bayesian decision technique, the data preparation module may determine the risk level of the secondary index based on the spot check failure rate and the following:
| Sampling failure rate | Risk description | Risk level |
| [0.0,0.0001] | Very low | 0 |
| (0.0001,0.001] | Low and low | 1 |
| (0.001,0.01] | In (a) | 2 |
| (0.01 0.1] | High height | 3 |
| (0.1,1.0] | Is very high | 4 |
In an intelligent risk level recognition system based on a bayesian decision technique, according to an embodiment of the present application, a bayesian risk calculation sub-module may calculate a risk by:
wherein R (X) represents the risk of cross-border overall process X,
R i represents the risk level, R i∈{R1,R2,…,Rs, s represents the number of risk levels,
X k represents the risk value of the kth risk indicator of the whole process X, k is equal to or greater than 1 and t is equal to or less than t, t represents the number of the risk indicators of the whole process X,
P (R i) represents the probability of risk level R i,
P (x k|Ri) represents the conditional probability of x k,
D i represents the number of data samples with risk level R i, d represents the total number of data samples, and d ik represents the number of X k that is the index X k in the data samples with risk level R i.
In an intelligent risk level recognition system based on a Bayesian decision technique, according to an embodiment of the present application, the cross-border whole process risk analysis module may analyze the cross-border hidden factor cross-border whole process by PRACCP methods to determine a plurality of links comprising the cross-border whole process including production, processing, shipping, outbound inspection, shipping, and inbound inspection.
In an intelligent risk level recognition system based on a Bayesian decision technique, according to an embodiment of the present application, the risk determination module may determine the risk of the cross-border surviving factor by:
Wherein R (X) represents the risk of the whole process X, Risk of the i-th primary index X i representing X,/>The weight of X i is indicated,
Wherein,Risk of j-th secondary index X ij representing X i,/>Representation/>Is a weight of (2).
According to the embodiment of the application, in the intelligent risk level identification system based on the Bayesian judgment technology, the data preparation module can adopt an average metering standard type sampling inspection method for sampling inspection.
According to the embodiment of the application, in the intelligent risk level identification system based on the Bayesian judgment technology, the data preparation module can adopt a non-qualification rate metering standard sampling inspection method for sampling inspection.
The intelligent risk level recognition system based on the Bayesian judgment technology can be used for recognizing risks of cross-border hidden factor in different cross-border processes according to the cross-border whole process of the cross-border hidden factor and by adopting the Bayesian judgment technology, so that the cross-border hidden high-risk factor can be managed more effectively
Drawings
FIG. 1 illustrates a block diagram of an intelligent risk level identification system based on a Bayesian decision technique in accordance with an embodiment of the present application; and
FIG. 2 illustrates a block diagram of a Bayesian risk decision module of an intelligent risk level identification system based on Bayesian decision techniques in accordance with an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the substances, and not restrictive of the application. For simplicity, the same or similar reference numbers are used in the description of embodiments of the application for the same or similar apparatus/method steps.
In addition, the embodiments of the present application and the features of the embodiments may be combined with each other without collision.
According to the application, an intelligent risk level recognition system based on a Bayesian judgment technology is provided, and is used for recognizing risks of cross-border hidden factors according to the cross-border whole process of the cross-border hidden factors and by adopting the Bayesian judgment technology. FIG. 1 illustrates a Bayesian decision technique-based intelligent risk level identification system in accordance with an embodiment of the present application, as shown in FIG. 1, the Bayesian decision technique-based intelligent risk level identification system 10 comprises: a data acquisition module 100 that can acquire data and provide the data; a cross-border whole process risk analysis module 200, which can analyze the cross-border whole process of the cross-border hidden factor by PRACCP (PEST RISK ANALYSIS AND CRITICAL Control Point, pest risk analysis and key Control Point) method, and determine a plurality of primary risk indexes corresponding to the plurality of links and a plurality of secondary risk indexes corresponding to each primary risk index; a risk level construction module 300 that can construct a risk level hierarchy to determine a risk level corresponding to the risk indicator; the data preparation module 400 can convert the data provided by the data acquisition module into data represented by the risk level according to the links, the primary risk indexes and the secondary risk indexes determined by the cross-border overall process risk analysis module and the risk level system constructed by the risk level construction module, so as to provide priori data; and a bayesian risk decision module 500 that can utilize the a priori data provided by the data preparation module and determine the risk of cross-border surviving factors based on bayesian methods.
The intelligent risk level recognition system based on the Bayesian judgment technology can be used for recognizing the risk of the cross-border hidden factors according to the cross-border whole process of the cross-border hidden factors and by adopting the Bayesian judgment technology, so that the cross-border hidden high-risk factors can be recognized more effectively.
The inventors of the present application noted the following information in the course of conducting a study of cross-border occultation factor risk:
PM5/2 (2) at EPPO (PEST RISK ANALYSIS on detection of A PEST IN AN imported consignment) risk analysis of pests found in imported goods, sets forth a decision framework for pests found in cargo inspection: pest identification (IDENTIFY PEST), analysis area (THE PRAAREA), pre-analysis (EARLIER ANALYSIS), geographic criteria (Geographical criteria), incoming likelihood (Potential for introduction), potential economic importance (Potential economic importance), and management options (MANAGEMENT OPTIONS).
Furthermore, ISPM standard No. 5 defines path as "any way (ANY MEANS THAT allows the entry or spread of a pest) by which pests can enter or diffuse"; the ISPM No. 11 standard also explicitly proposes "PRA (PRAinitiated by the identification of a pathway)" starting from a determined path. Path risk analysis (PATHWAY RISK ANALYSIS) is the process of pest risk assessment and selection of a risk management scheme for one or more paths of pest ingress and egress, according to the regional standard RSPM of NAPPO, path risk analysis guidelines (General Guidelines for PATHWAY RISK ANALYSIS).
The inventors believe that since the spatially afferent spread of pests is an iterative process of entry-colonization, pest risk can be analyzed and predicted in a full-flow management manner. Further, considering that different measures are taken for different management objects in different diffusion stages, the effect and cost of the measures need to be balanced, so that key control points should be comprehensively evaluated, and important interventions are performed in the stages, so that the minimum cost for achieving the target is achieved.
GB/T20879-2007 suggests that quarantine pest risk management measures may be taken against plants and plant products, preventing or reducing plant infection, ensuring that the production area or point of production is free of pests and other measures, and that defined non-quarantine pest management measures may be taken against the production area, against the parent material of the plant to be planted and against the plant cargo itself.
Hazard analysis and key Control Point (HACCP) theory and methods thereof find application in the field of food safety. In the field of food safety, the occurrence of food-borne diseases is prevented and food safety is ensured by using an "analysis-control-detection-correction" system.
In the food safety field, HACCP methods are mainly used to identify and control potential hazards in food production, and systems built using this theory are called "hazard analysis and critical control point systems". By this hazard analysis and key control point system, it is possible to determine in which process, in which way, and how to prevent the hazard affecting food safety.
Considering the natural connection of plant-derived food safety and plant quarantine, the inventor creatively proposes to combine hazard analysis and key Control Point theory with pest risk analysis flow, and firstly and creatively proposes 'pest risk analysis and key Control Point' (PEST RISK ANALYSIS AND CRITICAL Control Point, PRACCP) theory and method to better serve plant quarantine work. In fact, this is also shown in ISPM Standard No. 14 and its corresponding national Standard GB/T27617-2011.
In view of this, the inventors of the present application innovatively applied PRACCP methods to risk analysis and identification of cross-border survivors.
Generally, the hidden high-risk factor cross-border process can comprise 6 links of production, processing, shipment, outbound inspection, shipment and inbound inspection, so that the harm of the cross-border process and key control points can be analyzed based on PRACCP theory.
According to one embodiment of the application, the cross-border whole process risk analysis module analyzes the cross-border sequestration factor cross-border whole process by PRACCP method to determine a plurality of links comprising the cross-border whole process including production, processing, shipping, outbound inspection, shipping, and inbound inspection.
According to one embodiment of the application, the quarantine requirements and key control points of the cross-border process of the hidden high-risk biological factors (harmful organisms) along with the carrier (agricultural products) are analyzed through PRACCP, and the analysis results are shown in the table.
List one
Note that: cases are derived from http:// www.customs.gov.cn/customs/302249/2480148/3018503/index html, post 2020, post 59 (post on U.S. plant quarantine requirements for the export of fresh citrus from china)
As shown in table one, each link in the cross-border process of the cross-border hidden storage factor and whether each link is a key control point are identified and determined according to the HACCP method. In Table one, the 6 links of production, processing, shipment, outbound inspection, shipment, inbound inspection all contain key control points.
Based on the links of the hidden high-risk biological factor cross-border flow shown in the table one, key control points and related factors which influence the hidden high-risk biological factor risk in each link can be continuously analyzed according to the HACCP method.
According to one embodiment of the application, the potential risks and key control points and the like which affect the risks in the links of the cross-border process of the hidden high-risk biological factors are analyzed continuously according to the HACCP method, and the analysis results are shown in the second table.
Watch II
As shown in table two, in the production link, factors that potentially dangerous or affect risk include pest occurrence, whether soil pollution is received, whether monitoring is standard; in the processing link, factors which potentially dangerous or affect the risk include pollution of harmful organisms and soil, whether quarantine treatment is in place or not and whether sampling is standard or not; in the shipping link, factors which potentially dangerous or affect the risk include whether packaging materials are suitable, whether the packaging process is reasonable, whether the storage mode is proper, whether the storage environment is qualified, and whether the transportation mode meets the requirements; and in the context check and the situation check links, the potential danger or the factors affecting the risk include whether the sampling is standard or not.
FIG. 2 illustrates a block diagram of a Bayesian risk determination module in an intelligent risk level identification system based on Bayesian determination techniques in accordance with an embodiment of the present application. As shown in fig. 2, the bayesian risk determination module 500 may include: the bayesian risk calculation sub-module 510 may determine a risk value corresponding to the primary risk indicator and a risk value corresponding to the secondary risk indicator based on a bayesian method; the risk weight calculation sub-module 520 may determine the weight of the risk value corresponding to the primary risk indicator and the weight of the risk value corresponding to the secondary risk indicator through a hierarchical analysis method; and a risk determination module 530 that may determine a risk of the cross-border survivor based on the risk values corresponding to the primary and secondary risk indicators determined by the bayesian risk calculation sub-module and the weights determined by the risk weight calculation sub-module.
In the intelligent risk level recognition system based on the Bayesian decision technique according to the embodiment of the application, the data preparation module also combines the risk determined by the Bayesian risk decision module with the existing prior data to form new prior data.
Under the Bayesian theory framework, the unknown quantity is used as a random variable, the unknown condition of the unknown quantity is described through the probability distribution of the random variable, and the identification and the prediction of risks can be realized. In this sense, it is appropriate to employ bayesian theory and methods in risk management of the whole process of crossing the border factor with enough history data grasped. In the technical scheme of the application, sampling inspection (sampling inspection) is carried out on the data collected and/or cleaned by the data collection module, so that the data can be represented as risks according to the sampling inspection result.
In addition, through analyzing potential risks influencing risks, key control points and the like in various links of the cross-border process of the hidden high-risk biological factors according to the PRACCP method, key control indexes (potential risks marked as key control points, such as pest occurrence and pest and soil pollution) and corresponding standards in the process of performing spot check can be determined in analysis results, so that spot check can be implemented.
In the solution according to the application, the data may be spot checked by any suitable method.
According to one embodiment of the application, sampling tests may be performed using an average metering standard.
According to another embodiment of the application, sampling tests may be performed using a non-compliance rate metering standard.
In the intelligent risk level recognition system based on the Bayesian judgment technology according to the embodiment of the application, the data preparation module performs sampling inspection on the data provided by the data acquisition module and calculates the sampling inspection failure rate by:
Wherein X ij represents the secondary index of the cross-border overall process X, and k ij secondary indexes exist and are marked as
1.Ltoreq.i.ltoreq.n, 1.ltoreq.j.ltoreq.k, n representing the number of primary indexes X i corresponding to links of the whole process across the border, k representing the number of links corresponding to the primary indexes,
The false positive rate of the secondary index X ij,
K ij denotes the number of secondary indicators X ij,
M l represents the result of the spot check, accept is 1, reject is 0, m l∈{0,1},l＝0,1,…kij; and
The data preparation module may also determine a risk level of the secondary indicator based on the calculated spot check failure rate and based on the risk level hierarchy.
In the intelligent risk level recognition system based on the bayesian decision technique according to the embodiment of the present application, the data preparation module may further determine the risk level of the secondary index based on the spot check failure rate and the following table three:
Watch III
| Sampling failure rate | Risk description | Risk level |
| [0.0,0.0001] | Very low | 0 |
| (0.0001,0.001] | Low and low | 1 |
| (0.001,0.01] | In (a) | 2 |
| (0.01 0.1] | High height | 3 |
| (0.1,1.0] | Is very high | 4 |
As shown in table three, the risk class is classified into 5 classes, in which a "very high" risk corresponds to a risk class of 4, a "high" risk corresponds to a risk class of 3, a "medium" risk corresponds to a risk class of 2, a "low" risk corresponds to a risk class of 1, and a "very low" risk corresponds to a risk class of 0.
In an intelligent risk level recognition system based on a Bayesian decision technique according to an embodiment of the present application, a Bayesian risk calculation sub-module calculates risk by:
wherein R (X) represents the risk of cross-border overall process X,
R i represents the risk level, R i∈{R1,R2,…,Rs, s represents the number of risk levels,
X k represents the risk value of the kth risk indicator of the whole process X, k is equal to or greater than 1 and t is equal to or less than t, t represents the number of the risk indicators of the whole process X,
P (R i) represents the probability of risk level R i,
P (x k|Ri) represents the conditional probability of x k,
D i represents the number of data samples with risk level R i, d represents the total number of data samples, and d ik represents the number of X k that is the index X k in the data samples with risk level R i.
In an intelligent risk level recognition system based on a bayesian decision technique according to an embodiment of the present application, the risk determination module may determine the risk of the cross-border surviving factor by:
Wherein R (X) represents the risk of the whole process X, Risk of the i-th primary index X i representing X,/>The weight of X i is indicated,
Wherein,Risk of j-th secondary index X ij representing X i,/>Representation/>Is a weight of (2).
The basic principle of the analytic hierarchy process is to convert complex problems from high level to low level by using a hierarchy structure, and to solve complex target decision problems into a combination of limited hierarchy relations by using system structure. Specifically, in the analytic hierarchy process, the system is divided into a plurality of ordered layers, a hierarchical structure model describing membership and progressive relationships among different layer factors is established, then the relative importance of each layer is quantitatively represented according to the result of mutual comparison of the importance of adjacent upper layer elements, so that a comparison judgment matrix is constructed, and the maximum eigenvalue and the corresponding eigenvector of the comparison judgment matrix are determined. And determining the weight of the relative importance order of the elements in each hierarchy on the premise of passing the consistency check. By analysing each level an analysis of the whole problem is derived, the so-called total ranking weight.
The data acquisition module may perform data acquisition in any suitable manner. In one embodiment according to the present application, data may be collected and processed as disclosed in chinese patent application CN202011557448.5 (publication No. CN112613749 a) entitled "cross-border hidden high risk factor risk intelligent analysis system" submitted by applicant at 12/24/2020 by the following manner. The data acquisition module acquires basic data related to a plurality of cross-border factors through an intelligent algorithm according to the cross-border factor list. In one embodiment according to the application, the data acquisition module may determine the cross-border factor list based at least on the target area.
The data acquisition module may acquire the underlying data in a variety of suitable ways. In one embodiment according to the present application, the data collection module may collect the basic data through an external database, and the external database may include a customs database, a national institute of inspection and quarantine information resource sharing service platform, related papers and species distribution databases GBIF and CABI published at home and abroad, and the like. For example, for ambient climate data, it may be obtained from a database provided by WorldClim (http:// www.worldclim.org /); for map data, a 1:400 ten thousand world vector map can be obtained through a national basic geographic information system, namely China national borders and provincial boundaries and county border administrative demarcation drawings, or a 1:1000 ten thousand world vector map can be obtained from Natural Earth (http: www.naturalearth-data.com); host information can also be obtained by Chinese plant lineage (http:// frps. Eflora. Cn/sheng); or obtaining data information about the planting area and the total yield from FAO (http:// faostat3.FAO. Org /).
In another embodiment according to the application, the data acquisition module may also acquire the underlying data from the internet via a web crawler algorithm.
In yet another embodiment according to the present application, the data collection module may also collect the base data based on an internal database (also referred to as a background library) established by the cross-border multi-carrier hidden high risk biological factor data processing method. The applicant submits a Chinese patent application No. CN201910396568.2 (publication No. CN 110276518A) entitled "a processing method for cross-border multi-carrier hidden high-risk biological factor data" on the 14 th month of 2019, the patent application relates to the technical field of biological identification and information processing, in particular to a processing method for cross-border multi-carrier hidden high-risk biological factor data, which comprises the following steps: the method comprises the steps of collecting biological information in a cross-border carrier, wherein the cross-border carrier comprises one or more of the following steps: cross-border population and carrying, cross-border cargo and e-commerce, cross-border vehicles, and/or aerosol ballast water, the living being comprising one or more of the following: pests, weeds, pathogenic microorganisms, molluscs or other preselected pests; performing risk analysis on the cross-border intercepted organisms to determine whether the cross-border intercepted organisms are quarantine organisms and risk management measures to be adopted; and (3) checking and/or monitoring organisms needing quarantine treatment and performing corresponding quarantine treatment. The patent application realizes the recognition and treatment measures of the cross-border pests, can effectively prevent and kill the harmful cross-border pests, reduces the probability of malignant transmission of the cross-border pests, and is beneficial to better protecting agriculture and forestry production and natural ecological environment. In the patent application, a processing method for cross-border multi-carrier hidden high-risk biological factor data is described, the method comprises the steps of collecting biological information in a cross-border carrier, and the cross-border carrier comprises one or more of the following: cross-border population and carrying, cross-border cargo and e-commerce, cross-border vehicles, and/or aerosol ballast water, the living being comprising one or more of the following: pests, weeds, pathogenic microorganisms, molluscs and other preselected pests; performing risk analysis on the biological information to determine whether the biological information is a quarantine organism and a risk management measure to be adopted; and (3) checking and/or monitoring organisms needing quarantine treatment and corresponding quarantine treatment. After the step of collecting biological information in the cross-border carrier, the biological information in the cross-border carrier is stored in a first database; according to the preselected identification information in the first biological information in the first database, one or more appointed databases are queried to update the identification information of the first biological information, and then the updated identification information of the first biological information is stored in the second database; saving the results of the risk analysis, the results of the inspection and/or monitoring, and the results of the quarantine treatment to a second database; transmitting the collected biological information to a computer in real time; extracting pest information by the computer, and matching the pest information with cross-border organism data pre-stored in a pre-designated first database to determine whether cross-border organism factors exist; when the matching is successful, the computer controls to carry out pest inspection and/or monitoring; the computer records the time of monitoring and/or checking the pests and the identification information of the pests, and constructs a second database by using the recorded information; and (3) carrying out search operation on the data in the second database, wherein one or more acceleration modes of database index, memory and cache acceleration or search engine are adopted in the search operation.
The second database is a self-built database, and in the process of processing cross-border multi-carrier hidden high-risk biological factor data, various information is queried, compared and acquired in different paths, the information is stored, the second database with more perfect data is synchronously built, the second database is continuously updated and perfected, and in the subsequent hidden high-risk biological factor data processing process, the hidden high-risk biological factor data processing can be completed by using only the second database or fewer databases, so that the processing efficiency and the processing precision are improved. The second database in this patent application is the internal database in the embodiment of the present application.
The collected base data may include geographic distribution data, biological data, environmental climate data, host data, trade data, geographic information data, distribution status of cross-border factors, hazard information of cross-border factors, movement information of cross-border factors, hazard management information of cross-border factors, host information, and the like.
In the cross-border hidden factor intelligent risk level identification system based on the Bayesian judgment technology according to the embodiment of the application, the data acquisition module is further provided with a data cleaning function, and basic data acquired by the data acquisition module can be cleaned through an intelligent algorithm. The data with obvious errors in the collected basic data can be processed by cleaning the basic data, so that the reliability and the rationality of the data are improved.
In one embodiment of the present application, the following operations may be performed when cleaning is performed: judging whether the basic data is related to the cross-border factor or not, namely judging the reliability of the basic data, and removing the basic data which does not belong to the corresponding cross-border factor. For example, by washing, the distribution data of the bactrocera dorsalis can be prevented from being used as the basic data of the bactrocera dorsalis.
In one embodiment according to the application, the cross-border factor which does not correspond to the target area is removed from the target cross-border factor list according to the geographic distribution data of the cross-border factor by judging that the basic data are reasonable. For example, by washing, it is possible to avoid the situation that the distribution of terrestrial organisms occurs in the sea and the distribution of organisms in tropical regions occurs in the cold zone. Further, for example, the cleaning may be performed by making such a rule: only one point is reserved in a certain longitude and latitude range, and the data of the rest points are cleaned.
As another specific embodiment of the present application, the data acquisition module may further determine a cross-border hidden factor according to the acquired basic data, and update the cross-border factor list based on the determined cross-border hidden factor, so that the updated cross-border factor list includes the cross-border hidden factor.
In one embodiment of the application, corresponding processing measures can be adopted for defects such as feature loss, text data type, or different numerical value ranges in the data.
For example, for a missing feature data, the missing value may be filled with the mean of the available features, or with the mean of similar samples, or with other machine learning methods to predict the missing value, or discard samples with missing values. In one embodiment according to the application, samples with missing values are discarded directly.
For example, for text data, it can be mapped into a numeric form by a program.
For example, for data with different value ranges, a standardized processing manner may be adopted, that is, the data is scaled and limited to a specific interval, and converted into a dimensionless value. In one embodiment according to the application, the normalization is performed in a way that the dispersion is normalized.
In the description of the present specification, reference to the terms "one embodiment/manner," "some embodiments/manner," "example," "a particular example," "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/manner or example is included in at least one embodiment/manner or example of the application. In this specification, the schematic representations of the above terms are not necessarily for the same embodiment/manner or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/modes or examples described in this specification and the features of the various embodiments/modes or examples can be combined and combined by persons skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
It will be appreciated by persons skilled in the art that the above embodiments are provided for clarity of illustration only and are not intended to limit the scope of the application. Other variations or modifications will be apparent to persons skilled in the art from the foregoing disclosure, and such variations or modifications are intended to be within the scope of the present application.
Claims (6)
1. An intelligent risk level recognition system based on a Bayesian judgment technology, which is used for recognizing risks of a cross-border hidden factor according to cross-border whole process decomposition of the cross-border hidden factor and adopting the Bayesian judgment technology, wherein the intelligent risk level recognition system based on the Bayesian judgment technology comprises:
The data acquisition module is used for acquiring data and providing the data;
The cross-border whole process risk analysis module analyzes the cross-border whole process of the cross-border hidden factors through a pest risk analysis and key control point PRACCP method, determines a plurality of links forming the cross-border whole process, a plurality of first-level risk indexes corresponding to the links and a plurality of second-level risk indexes corresponding to each first-level risk index;
The risk level construction module is used for constructing a risk level system to determine a risk level corresponding to the risk index;
The data preparation module is used for converting the data provided by the data acquisition module into data represented by the risk level according to the links, the primary risk indexes and the secondary risk indexes determined by the cross-border overall process risk analysis module and the risk level system constructed by the risk level construction module, so as to provide priori data; and
The Bayesian risk judging module is used for determining the risk of the cross-border hidden factor by utilizing the prior data provided by the data preparation module and based on a Bayesian method;
the bayesian risk judging module includes:
the Bayesian risk calculation sub-module is used for determining a risk value corresponding to the primary risk index and a risk value corresponding to the secondary risk index based on a Bayesian method;
the risk weight calculation sub-module is used for determining the weight of the risk value corresponding to the primary risk index and the weight of the risk value corresponding to the secondary risk index through an analytic hierarchy process; and
The risk determining module is used for determining the risk of the cross-border hidden factor based on the risk value corresponding to the primary risk index and the risk value corresponding to the secondary risk index determined by the Bayesian risk calculating sub-module and the weight determined by the risk weight calculating sub-module;
And:
the bayesian risk calculation sub-module calculates the risk by:
wherein R (X) represents the risk of cross-border overall process X,
R i represents the risk level, R i∈{R1,R2,…,Rs, s represents the number of risk levels,
X k represents the risk value of the kth risk indicator of the whole process X, k is equal to or greater than 1 and t is equal to or less than t, t represents the number of the risk indicators of the whole process X,
P (R i) represents the probability of risk level R i,
P (x k|Ri) represents the conditional probability of x k,
D i represents the number of data samples with risk level R i, d represents the total number of data samples, and d ik represents the number of X k which is the index X k in the data samples with risk level R i;
The cross-border whole process risk analysis module analyzes the cross-border hidden factor cross-border whole process through a pest risk analysis and key control point PRACCP method, and a plurality of links comprising the cross-border whole process are determined, including production, processing, shipment, outbound inspection, shipment and inbound inspection;
The risk determination module determines a risk of the cross-border surviving factor by:
Wherein R (X) represents the risk of the whole process X, Risk of the i-th primary index X i representing X,/>The weight of X i is indicated,
Wherein,Risk of j-th secondary index X ij representing X i,/>Representation/>Is a weight of (2).
2. The intelligent risk level identification system based on bayesian decision technique according to claim 1, wherein the data preparation module further combines the risk determined by the bayesian risk decision module with existing prior data to form new prior data.
3. The intelligent risk level identification system based on bayesian decision technique according to claim 2, wherein said data preparing module performs a spot check on the data provided by said data collecting module and calculates a spot check failure rate by:
Wherein X ij represents the secondary index of the cross-border overall process X, and k ij secondary indexes exist and are marked as 1.Ltoreq.i.ltoreq.n, 1.ltoreq.j.ltoreq.k, n representing the number of primary indexes X i corresponding to links of the whole process across the border, k representing the number of links corresponding to the primary indexes,
The false positive rate of the secondary index X ij,
K ij denotes the number of secondary indicators X ij,
M l represents the result of the spot check, accept is 1, reject is 0, m l∈{0,1},l＝0,1,…kij; and
And determining the risk level of the secondary index based on the calculated false positive rate and based on the risk level system.
4. The intelligent risk level identification system based on bayesian decision technique according to claim 3, wherein said data preparing module determines a risk level of a secondary indicator based on a spot check failure rate and
。
5. The intelligent risk level identification system based on bayesian decision technique according to claim 4, wherein said data preparing module performs spot check using an average metering standard type sampling test method.
6. The intelligent risk level identification system based on bayesian decision techniques according to claim 4, wherein said data preparation module performs a spot check using a non-compliance rate metering standard type sampling test method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110705991.3A CN113537727B (en) | 2021-06-24 | 2021-06-24 | Intelligent risk level recognition system based on Bayesian judgment technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110705991.3A CN113537727B (en) | 2021-06-24 | 2021-06-24 | Intelligent risk level recognition system based on Bayesian judgment technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113537727A CN113537727A (en) | 2021-10-22 |
| CN113537727B true CN113537727B (en) | 2024-05-14 |
Family
ID=78096666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110705991.3A Active CN113537727B (en) | 2021-06-24 | 2021-06-24 | Intelligent risk level recognition system based on Bayesian judgment technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113537727B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114418600B (en) * | 2022-01-19 | 2023-04-14 | 中国检验检疫科学研究院 | Food input risk monitoring and early warning method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014092230A1 (en) * | 2012-12-13 | 2014-06-19 | 대한민국 (식품의약품안전청장) | System and method for inspecting imported food-based harm prediction |
| KR101805713B1 (en) * | 2017-07-31 | 2017-12-06 | 한국가스안전공사 | Risk Analysis System using Risk Map |
| CN108733748A (en) * | 2018-04-04 | 2018-11-02 | 浙江大学城市学院 | A kind of cross-border product quality risk fuzzy prediction method based on comment on commodity public sentiment |
| CN110276518A (en) * | 2019-05-14 | 2019-09-24 | 中国检验检疫科学研究院 | A kind of hidden processing method for depositing high-risk biotic factor data of cross-border multichip carrier |
| CN112613749A (en) * | 2020-12-24 | 2021-04-06 | 中国检验检疫科学研究院 | Cross-border hidden high-risk factor risk intelligent analysis system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9589235B2 (en) * | 2014-05-23 | 2017-03-07 | Jiali Ding | Method for measuring individual entities' infectivity and susceptibility in contagion |
-
2021
- 2021-06-24 CN CN202110705991.3A patent/CN113537727B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014092230A1 (en) * | 2012-12-13 | 2014-06-19 | 대한민국 (식품의약품안전청장) | System and method for inspecting imported food-based harm prediction |
| KR101805713B1 (en) * | 2017-07-31 | 2017-12-06 | 한국가스안전공사 | Risk Analysis System using Risk Map |
| CN108733748A (en) * | 2018-04-04 | 2018-11-02 | 浙江大学城市学院 | A kind of cross-border product quality risk fuzzy prediction method based on comment on commodity public sentiment |
| CN110276518A (en) * | 2019-05-14 | 2019-09-24 | 中国检验检疫科学研究院 | A kind of hidden processing method for depositing high-risk biotic factor data of cross-border multichip carrier |
| CN112613749A (en) * | 2020-12-24 | 2021-04-06 | 中国检验检疫科学研究院 | Cross-border hidden high-risk factor risk intelligent analysis system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113537727A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Meynard et al. | Beyond taxonomic diversity patterns: how do α, β and γ components of bird functional and phylogenetic diversity respond to environmental gradients across France? | |
| Van Couwenberghe et al. | Can species distribution models be used to describe plant abundance patterns? | |
| Jones et al. | Measuring long‐distance seed dispersal in complex natural environments: an evaluation and integration of classical and genetic methods | |
| CN107256426A (en) | A kind of drug safety confidence index system and construction method based on intelligent algorithm | |
| CN107679167A (en) | Weather Risk appraisal procedure and analysis and early warning platform based on lattice point meteorological data | |
| Smart et al. | Empirical realised niche models for British higher and lower plants–development and preliminary testing | |
| Matos et al. | Tracking global change using lichen diversity: towards a global‐scale ecological indicator | |
| Migliorini et al. | An integrated sustainability score based on agro-ecological and socioeconomic indicators. A case study of stockless organic farming in Italy | |
| Liira et al. | Stand characteristics and biodiversity indicators along the productivity gradient in boreal forests: defining a critical set of indicators for the monitoring of habitat nature quality | |
| Fletcher et al. | Emerging infectious plant diseases | |
| CN112613749B (en) | Cross-border hidden high-risk factor risk intelligent analysis system | |
| WO2015064713A1 (en) | Information presentation method, device, and program | |
| CN113537727B (en) | Intelligent risk level recognition system based on Bayesian judgment technology | |
| Brown et al. | Fly and wasp diversity responds to elements of both the visible and invisible fire mosaic | |
| Kim et al. | Development of a daily epidemiological model of rice blast tailored for seasonal disease early warning in South Korea | |
| Volpi et al. | Predicting symptoms of downy mildew, powdery mildew, and gray mold diseases of grapevine through machine learning | |
| Whitehorn et al. | The effects of climate and land use on British bumblebees: Findings from a decade of citizen‐science observations | |
| van Der Fels-Klerx et al. | Decision support system for integrated management of mycotoxins in feed and food supply chains | |
| Forcey et al. | Spatially explicit modeling of blackbird abundance in the Prairie Pothole Region | |
| Conkling et al. | Impacts of biomass production at civil airports on grassland bird conservation and aviation strike risk | |
| CN115274131A (en) | Epidemic prevention optimization method for epidemic infectious disease of logistics system based on big data | |
| Giordani et al. | Beta diversity and similarity of lichen communities as a sign of the times | |
| Liu et al. | Priority prediction of Asian Hornet sighting report using machine learning methods | |
| Wang et al. | Research of the early warning analysis of crop diseases and insect pests | |
| Roser et al. | Drone imagery protocols to map vegetation are transferable between dryland sites across an elevational gradient |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |