CN115526531A - Wheat quality safety early warning method and system - Google Patents
Wheat quality safety early warning method and system Download PDFInfo
- Publication number
- CN115526531A CN115526531A CN202211293727.4A CN202211293727A CN115526531A CN 115526531 A CN115526531 A CN 115526531A CN 202211293727 A CN202211293727 A CN 202211293727A CN 115526531 A CN115526531 A CN 115526531A
- Authority
- CN
- China
- Prior art keywords
- pollution
- early warning
- interval
- toxin
- sample
- 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.)
- Pending
Links
- 241000209140 Triticum Species 0.000 title claims abstract description 76
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000003053 toxin Substances 0.000 claims abstract description 128
- 231100000765 toxin Toxicity 0.000 claims abstract description 128
- 108700012359 toxins Proteins 0.000 claims abstract description 128
- 231100000678 Mycotoxin Toxicity 0.000 claims abstract description 51
- 239000002636 mycotoxin Substances 0.000 claims abstract description 51
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 238000005065 mining Methods 0.000 claims abstract description 10
- LINOMUASTDIRTM-QGRHZQQGSA-N deoxynivalenol Chemical compound C([C@@]12[C@@]3(C[C@@H](O)[C@H]1O[C@@H]1C=C(C([C@@H](O)[C@@]13CO)=O)C)C)O2 LINOMUASTDIRTM-QGRHZQQGSA-N 0.000 claims description 25
- 229930002954 deoxynivalenol Natural products 0.000 claims description 25
- LINOMUASTDIRTM-UHFFFAOYSA-N vomitoxin hydrate Natural products OCC12C(O)C(=O)C(C)=CC1OC1C(O)CC2(C)C11CO1 LINOMUASTDIRTM-UHFFFAOYSA-N 0.000 claims description 25
- 229930195730 Aflatoxin Natural products 0.000 claims description 24
- 239000005409 aflatoxin Substances 0.000 claims description 24
- RWQKHEORZBHNRI-BMIGLBTASA-N ochratoxin A Chemical compound C([C@H](NC(=O)C1=CC(Cl)=C2C[C@H](OC(=O)C2=C1O)C)C(O)=O)C1=CC=CC=C1 RWQKHEORZBHNRI-BMIGLBTASA-N 0.000 claims description 23
- VYLQGYLYRQKMFU-UHFFFAOYSA-N Ochratoxin A Natural products CC1Cc2c(Cl)cc(CNC(Cc3ccccc3)C(=O)O)cc2C(=O)O1 VYLQGYLYRQKMFU-UHFFFAOYSA-N 0.000 claims description 21
- DAEYIVCTQUFNTM-UHFFFAOYSA-N ochratoxin B Natural products OC1=C2C(=O)OC(C)CC2=CC=C1C(=O)NC(C(O)=O)CC1=CC=CC=C1 DAEYIVCTQUFNTM-UHFFFAOYSA-N 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 18
- MBMQEIFVQACCCH-UHFFFAOYSA-N trans-Zearalenon Natural products O=C1OC(C)CCCC(=O)CCCC=CC2=CC(O)=CC(O)=C21 MBMQEIFVQACCCH-UHFFFAOYSA-N 0.000 claims description 18
- ITCSWEBPTQLQKN-UHFFFAOYSA-N Nivalenol Natural products CC1=CC2OC3C(O)C(O)C(C2(CO)CC1=O)C34CO4 ITCSWEBPTQLQKN-UHFFFAOYSA-N 0.000 claims description 16
- UKOTXHQERFPCBU-YQPARWETSA-N Nivalenol Chemical compound C([C@]12[C@@]3([C@H](O)[C@@H](O)[C@H]1O[C@@H]1C=C(C([C@@H](O)[C@@]13CO)=O)C)C)O2 UKOTXHQERFPCBU-YQPARWETSA-N 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000007726 management method Methods 0.000 claims description 13
- 238000011109 contamination Methods 0.000 claims description 11
- 238000007689 inspection Methods 0.000 claims description 8
- 238000013523 data management Methods 0.000 claims description 7
- 239000003008 fumonisin Substances 0.000 claims description 6
- MBMQEIFVQACCCH-QBODLPLBSA-N zearalenone Chemical compound O=C1O[C@@H](C)CCCC(=O)CCC\C=C\C2=CC(O)=CC(O)=C21 MBMQEIFVQACCCH-QBODLPLBSA-N 0.000 claims description 6
- XWIYFDMXXLINPU-UHFFFAOYSA-N Aflatoxin G Chemical compound O=C1OCCC2=C1C(=O)OC1=C2C(OC)=CC2=C1C1C=COC1O2 XWIYFDMXXLINPU-UHFFFAOYSA-N 0.000 claims description 5
- BXFOFFBJRFZBQZ-QYWOHJEZSA-N T-2 toxin Chemical compound C([C@@]12[C@]3(C)[C@H](OC(C)=O)[C@@H](O)[C@H]1O[C@H]1[C@]3(COC(C)=O)C[C@@H](C(=C1)C)OC(=O)CC(C)C)O2 BXFOFFBJRFZBQZ-QYWOHJEZSA-N 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 3
- XZIDTOHMJBOSOX-UHFFFAOYSA-N 2,3,6-TBA Chemical compound OC(=O)C1=C(Cl)C=CC(Cl)=C1Cl XZIDTOHMJBOSOX-UHFFFAOYSA-N 0.000 claims 1
- 240000008042 Zea mays Species 0.000 claims 1
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 claims 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 claims 1
- 235000009973 maize Nutrition 0.000 claims 1
- 230000006870 function Effects 0.000 abstract description 14
- 238000013461 design Methods 0.000 abstract description 10
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000007418 data mining Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 20
- 235000013305 food Nutrition 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000002688 persistence Effects 0.000 description 3
- 239000003344 environmental pollutant Substances 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- -1 FB) Substances 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 231100000279 safety data Toxicity 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012772 sequence design Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- 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
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a wheat quality safety early warning method and a system, which are combined with an early warning method for excavating mycotoxin association rules in wheat to realize the main related functions of risk early warning and the like of the system. The safety early warning system simplifies the workload of related workers, and is beneficial to early warning and judging the pollution risk grade interval of undetected toxins by the detected value of the detected toxins of the samples when detecting the toxins of the samples, so as to provide some toxin co-pollution information for related monitoring personnel. The method is convenient for the management operation of the wheat sample data by the user, and realizes intelligent input and prediction of sample risk toxin. The design of the system is combined with the early warning model of the data mining association rule method, the mining strong association rule is applied to the risk early warning of the system, and the relevant application of the association rule early warning model is completed.
Description
Technical Field
The invention relates to the technical field of food safety, in particular to a wheat quality safety early warning method and a wheat quality safety early warning system.
Background
The food safety early warning is to detect potential food safety events as early as possible by analyzing daily monitoring data of food, make early warning response to the hidden danger problem and achieve the purpose of pre-intervention control. The effective food safety early warning system can warn the possible risks in advance to control the risks as early as possible, so that the loss caused by safety events is reduced or avoided.
Some mature early warning systems are established abroad, for example, the food safety. Gov system established in the united states includes functions of early warning recall of food safety information, science popularization of food safety knowledge, management of food safety data and the like. The European Union establishes a relatively mature food and feed rapid early warning system to provide a reliable platform for the communication of food safety information data and food early warning between member states, and the system can recall food with early warning risk and the like. The domestic scholars further research the early warning system. Han Yu (Han Yu. Food sampling inspection data management system [ D ] based on data mining, beijing: university of forestry 2020) designs a food sampling inspection data system to realize functions of data management, data analysis, data visualization display, data mining and related information extraction for food sampling inspection data. Li Zongliang (Li Zongliang. Food safety risk early warning system research based on big data mining [ D ]. Hunan: hunan university, 2017) an early warning system is designed by taking preserved meat food as an example by using BP neural network technology, and the designed model takes 19 measured value indexes in the preserved meat product as input of the BP neural network to train the model and output predicted risk coefficients.
The pollution of mycotoxin is an important factor influencing the quality safety of wheat crops, and no related quality safety early warning system exists at present. In order to facilitate the management of wheat mycotoxin random inspection data by relevant departments of food safety supervision and the understanding of relevant early warning information of toxin co-pollution during random inspection of samples and facilitate the simplification of the workload of supervision personnel, the invention designs and implements the wheat quality safety early warning system which is convenient for the operation and management of monitoring personnel. The functional modules of the wheat quality safety early warning system mainly comprise a risk monitoring module, a risk early warning module, a pollution level management and data management module and the like. The risk monitoring module of the system can facilitate the management and the checking of the wheat toxin sample information by monitoring personnel; the risk early warning function can help the supervisor to obtain the joint exposure risk and the co-pollution information of the toxin when detecting the toxin in the sample.
Disclosure of Invention
The invention aims to provide a wheat quality safety early warning method and a wheat quality safety early warning system.
In order to achieve the above purpose, the invention provides the following technical scheme:
on one hand, the invention provides a wheat quality safety early warning method, which comprises the following steps: taking the multidimensional index information source data of mycotoxin in wheat as input, judging and grading detected toxins in the sample according to a risk grade table, and judging whether toxin indexes in a first-level pollution interval exist or not; if not, directly returning a prompt of 'temporary joint exposure risk early warning'; if yes, searching records in an early warning rule table database corresponding to the index toxin in the primary pollution interval, matching the detected toxin pollution level interval in the sample with the early warning rule, and judging whether a co-pollution state exists; if the co-pollution state exists, outputting early warning information of an early warning rule table, if the co-pollution state does not exist, prompting 'temporary joint exposure risk early warning', and finally outputting analysis information of wheat mycotoxin risk; the mycotoxin comprises seven of Fumonisins (Fumonisins, FB), aflatoxins (AFT), deoxynivalenol (DON), nivalenol (NIV), ochratoxin A (OTA), zearalenone (Zealanenone, ZEN) and T-2 toxins (Trichotecenes-2 toxin, T-2), and the early warning rule is a strong association rule of single-item mycotoxin-gathering indexes.
Further, the strong association rule of the single set mycotoxin index is Apriori algorithm mining based on the association rule, and the Apriori algorithm is executed as follows:
s1, discretizing seven mycotoxin index data according to pollution levels to generate a Boolean type transaction database, wherein the pollution levels comprise three level intervals; constructing a transaction database of wheat sample mycotoxin boolean types, wherein each sample simultaneously comprises seven mycotoxin contamination indicators;
s2, scanning a transaction database with a constructed wheat sample mycotoxin Boolean type, respectively counting the occurrence frequency of three grade intervals of seven mycotoxin pollution indexes, counting the support degree of the three grade intervals, and generating a candidate k item set of toxin indexes, wherein k =1,2 …, n;
s3, eliminating the candidate k item set which does not meet the minimum support degree counting, and reserving the rest candidate k item sets which meet the minimum support degree counting to generate a frequent k item set;
s4, connecting the screened frequent k item sets of the toxin indexes with the selected frequent k item sets to generate candidate k +1 item sets;
s5, iterating and traversing the transaction database of the Boolean type of the mycotoxin again, counting the support degree counts of the candidate k +1 item sets, eliminating the item sets which do not meet the minimum support degree counts, and reserving the item sets which meet the minimum support degree to obtain frequent k +1 item sets;
and S6, repeatedly executing the step S4 and the step S5, acquiring the frequent N item sets until the frequent item sets are not generated any more, observing that all subsets of the frequent item sets are necessarily frequent item sets in the executing and connecting process, removing the non-frequent item sets, and generating a single item set mycotoxin index strong association rule.
Further, the pollution classes are divided into: the FB first-stage pollution interval is (30, + ∞), the second-stage pollution interval is (7.5,30), the third-stage pollution interval is (0,7.5 ], (1.5, + ∞) as the AFT first-stage pollution interval, and (0.5,1.5) as the second-stage pollution interval, and (0,0.5 ], (100, + ∞) as the third-stage pollution interval, and (20, 100), the third-stage pollution interval is (0,20 ], the NIV first-stage pollution interval is (17.5, + ∞) as the third-stage pollution interval, and (5,17.5 ], the third-stage pollution interval is (0,5, OTA) (1.5, + ∞), the second-stage pollution interval is (1,1.5), the third-stage pollution interval is (34 zxft 3434 ], the ZEN first-stage pollution interval is (2.5, + ∞) as the second-stage pollution interval, and (3625, and the third-stage pollution interval is (3624 zxft 3724).
Further, the early warning rule is as follows:
when the NIV is in a first-level pollution interval, the co-pollution undetected DON toxin has the possibility of being in the first-level pollution interval at 92.0%;
when the OTA is in a first-level pollution interval, 89.9% of the possibility that the undetected AFT toxin is in the first-level pollution interval is given to the co-polluted OTA;
when ZEN is in a first-level pollution interval, 80.6% of DON toxins which have co-pollution and are not detected are in the first-level pollution interval, 67.3% of AFT toxins which have co-pollution and are not detected are in the first-level pollution interval, and 63.7% of T-2 toxins which have co-pollution and are not detected are in the first-level pollution interval;
when T-2 is in a first-level pollution interval, 74.2% of co-pollution undetected DON toxin is in the first-level pollution interval, and 71.5% of co-pollution undetected ZEN toxin is in the first-level pollution interval;
when AFT is in the first-order pollution interval, the co-contaminated unmeasured DON toxin has a 50.5% probability of being in the first-order pollution interval, and the co-contaminated unmeasured OTA toxin has a 56.6% probability of being in the first-order pollution interval.
On the other hand, the invention also provides a wheat quality safety early warning system, which is used for realizing the method of any one of the above steps, and comprises the following modules:
the risk monitoring module is used for performing data management operation on the wheat toxin spot inspection data in each region, and comprises browsing of small wheat toxin spot inspection data in a database by a user, addition of sample toxin data and regional data query;
the risk early warning analysis module is used for setting and modifying the pollution risk levels of the seven mycotoxins and the corresponding risk detection values thereof, carrying out interval evaluation and prediction on the undetected toxin index detection values in the sample, and prompting the early warning information of the undetected toxins if the sample has joint exposure early warning information; otherwise, prompting that the joint exposure risk is temporarily absent;
the data management module is used for managing user data, sample data, risk grade data, early warning rule data and early warning information data;
and the system basic module comprises a system login module and a log management module, wherein the system login module is used for judging whether the filled user name exists in the database, if so, matching verification is carried out, if matching is successful, the user jumps to a home page of the safety early warning system, and otherwise, an error message is prompted.
Further, the user data includes user name, user number, gender, name, phone, mailbox, password.
Further, the sample data includes sample number, FB, AFT, DON, NIV, OTA, ZEN, T-2, region, and age attribute.
Further, the risk level data includes a contamination level, a toxin type, and maximum and minimum attributes of the detected value of the corresponding level toxin.
Further, the early warning rule data comprises a rule antecedent toxin type, a rule consequent toxin type, a antecedent pollution level, a consequent pollution level and a rule confidence value attribute.
Further, the early warning information data includes the sample number and the early warning information attribute of the corresponding sample.
Compared with the prior art, the invention has the beneficial effects that:
the wheat quality safety early warning method and the system provided by the invention realize the most main related functions of risk early warning and the like of the system by combining the early warning method of mycotoxin association rule mining in wheat. The safety early warning system simplifies the workload of related workers, and can be beneficial to early warning and judging the pollution risk level interval of undetected toxins by detected toxin values of samples when detecting the toxins of the samples, thereby providing some toxin co-pollution information for related monitoring personnel. The method is convenient for the management operation of the wheat sample data by the user, and the intelligent input and the prediction of the sample risk toxin are realized. The design of the system is combined with the early warning model of the data mining association rule method, the mining strong association rule is applied to the risk early warning of the system, and the relevant application of the association rule early warning model is completed.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some of the embodiments described in the present invention, and that other drawings can be derived by those skilled in the art from these drawings.
Fig. 1 is a structural diagram of a wheat quality safety early warning system provided by an embodiment of the present invention.
Fig. 2 is a flowchart of Apriori algorithm according to an embodiment of the present invention.
Fig. 3 is a user E-R diagram provided by an embodiment of the present invention.
FIG. 4 is a graph of samples E-R provided in accordance with an embodiment of the present invention.
Fig. 5 is a graph of risk levels E-R provided by an embodiment of the present invention.
Fig. 6 is an E-R diagram of the warning rule provided in the embodiment of the present invention.
Fig. 7 is a diagram of the warning information E-R provided by the embodiment of the present invention.
Fig. 8 is a functional block diagram of a system according to an embodiment of the present invention.
Fig. 9 is a system architecture diagram according to an embodiment of the present invention.
Fig. 10 is a timing diagram of user login according to an embodiment of the present invention.
Fig. 11 is a flowchart of user login provided in the embodiment of the present invention.
FIG. 12 is a timing diagram of sample addition according to an embodiment of the present invention.
Fig. 13 is a flow chart of sample addition according to an embodiment of the present invention.
Fig. 14 is a timing diagram of risk pre-warning provided in the embodiment of the present invention.
Fig. 15 is a flowchart of risk early warning provided in the embodiment of the present invention.
FIG. 16 is a sample view of mycotoxin in wheat provided by an embodiment of the present invention.
Fig. 17 is a query graph of a region sample according to an embodiment of the present invention.
Fig. 18 is a functional diagram of sample addition provided in the embodiment of the present invention.
Fig. 19 is a sample a1000 early warning diagram provided by an embodiment of the present invention.
Fig. 20 is a sample a1001 early warning diagram provided by an embodiment of the present invention.
Fig. 21 is a sample a1002 early warning diagram provided in an embodiment of the present invention.
Fig. 22 is an interface diagram of warning information provided in the embodiment of the present invention.
Fig. 23 is a risk level management diagram according to an embodiment of the present invention.
Fig. 24 is an index weight chart according to an embodiment of the present invention.
Detailed Description
For a better understanding of the present solution, the method of the present invention is described in detail below with reference to the accompanying drawings.
The invention mainly completes the design and realization work of the wheat quality safety early warning system, and realizes the most main risk early warning and other related functional modules of the system by combining the early warning method of mycotoxin association rule mining in wheat.
The wheat quality safety early warning method comprises the following steps: taking the multidimensional index information source data of mycotoxin in wheat as input, judging and grading detected toxins in the sample according to a risk grade table, and judging whether toxin indexes in a first-level pollution interval exist or not; if not, directly returning a prompt of 'temporary joint exposure risk early warning'; if yes, searching records in an early warning rule table database corresponding to the index toxin in the primary pollution interval, matching the detected toxin pollution level interval in the sample with the early warning rule, and judging whether a co-pollution state exists; if the co-pollution state exists, outputting early warning information of an early warning rule table, if the co-pollution state does not exist, prompting 'temporary joint exposure risk early warning', and finally outputting analysis information of the wheat mycotoxin risk; the mycotoxin comprises seven items of FB, AFT, DON, NIV, OTA, ZEN and T-2, and the early warning rule is a single item set mycotoxin index strong association rule.
The wheat quality safety early warning system disclosed by the invention comprises main functional modules, namely a risk monitoring module, a risk early warning analysis module and the like, as shown in figure 1.
The wheat quality safety early warning system is designed and realized from links of requirement analysis, overall design, detailed design, coding, testing and the like. The system adopts a B/S mode, the SpringBoot framework technology and Java development language are applied, the MySQL database is used for coding the system, a Web site system with a front end and a rear end separated is built, and the system is configured and operated under a Tomcat server. Specifically, the invention takes the multidimensional index information source data of the mycotoxin in the wheat as the input end and takes the analysis information of the risk of the mycotoxin in the wheat as the output end to construct an assessment early warning analysis system. And (3) carrying out internal association rule mining early warning of key risk evaluation index risk factors aiming at typical pollutant mycotoxin which mainly influences the quality and safety of wheat by adopting an association rule mining method in data mining.
A single set toxin index strong association rule mined by an Apriori algorithm of an association rule is used as an early warning basis to construct a risk assessment and early warning model based on seven key risk mycotoxin indexes in wheat, so that a supervisor can be helped to carry out the risk assessment and early warning research and judgment of key types of toxin pollutants for the quality and safety supervision of wheat by combining risk early warning information.
The Apriori algorithm flowchart is shown in fig. 2, and the algorithm execution process is detailed as follows:
the single set mycotoxin index strong association rule is mined based on an Apriori algorithm of the association rule, and the Apriori algorithm is executed as follows:
s1, data preprocessing: and discretizing the seven mycotoxin index data according to the pollution levels by using a pollution level division table to generate a Boolean type transaction database. The contamination level includes three level sections, and the contamination level classification table is shown in table 1.
Table 1 pollution rating scale
Constructing a transaction database of wheat sample mycotoxin Boolean type, wherein each sample simultaneously comprises seven mycotoxin pollution indexes. The transaction database is shown in table 2. Each row represents a sample and each column indicates a level of the indicated contaminant level.
Table 2 transaction database table
A certain sample of the transaction database such as 1424, FB (III), AFT (III), DON (I), NIV (III), OTA (III), ZEN (II) and T-2 (III) represents that fumonisin in the sample is in a tertiary pollution interval, aflatoxin is in a tertiary pollution interval, deoxynivalenol is in a primary pollution interval, nivalenol is in a tertiary pollution interval, ochratoxin A is in a tertiary pollution interval, zearalenone is in a secondary pollution interval, and T-2 toxin is in a tertiary pollution interval.
S2, scanning k item sets in a transaction database with a Boolean type of wheat sample mycotoxins, counting the occurrence frequency of three grade intervals of seven mycotoxin pollution indexes, counting the support degree of the three grade intervals, and generating candidate k item sets of toxin indexes, wherein k =1,2 …, n;
s3, eliminating the candidate k item set which does not meet the minimum support degree counting, and reserving the rest candidate k item sets which meet the minimum support degree counting to generate a frequent k item set;
s4, connecting the screened toxin index frequent 1-item set with the selected toxin index frequent 1-item set to generate a candidate k +1 item set;
s5, iterating and traversing the transaction database of the Boolean type of the mycotoxin again, counting the support degree counts of the candidate k +1 item sets, eliminating the item sets which do not meet the minimum support degree counts, and reserving the item sets which meet the minimum support degree to obtain frequent k +1 item sets;
and S6, repeatedly executing the step S4 and the step S5, acquiring the frequent N item sets until the frequent item sets are not generated any more, wherein all subsets obeying the frequent item sets in the executing and connecting process are necessarily frequent item sets, and removing the non-frequent item sets.
The results of the strong association rule of the single set toxin indexes are shown in table 3.
Support (support): the probability that an item contained by both X and Y appears in the transaction set.
Confidence (confidence): the transaction containing M contains a proportion of N.
Lift (lift): the occurrence probability of Y is changed by the occurrence of X, the value is 1, the two are independent, and the larger the value is, the stronger the relevance of the two is.
Certainty (connection): a value of 1 indicates that the item set X and the item set Y are independent, and a higher certainty factor indicates that the rule is more reliable.
The mining result applied in the system is nine strong association rules of single-item set toxin indexes, as shown in table 3.
TABLE 3 strong association rule table for co-contaminated toxins of K item set
Data objects in the system are typically described in a requirement analysis phase using entity contact graphs (E-R) with reference to subsequent database entity class designs. The entity contact diagram of the wheat quality safety early warning system comprises a user entity, a sample entity, a risk level entity, an early warning rule entity, an early warning information entity and the like.
(1) User entity
The user entity is used to describe user information, and the E-R diagram is shown in fig. 3 and includes user name, user number, gender, name, telephone, mailbox, and password.
(2) Wheat toxin sample entity
The indexes of the wheat toxin sample comprise fumonisin, aflatoxin, deoxynivalenol, nivalenol, ochratoxin A, zearalenone and T-2 toxin. The detection value information of the wheat toxin sample entity for describing seven toxins of the wheat sample comprises sample number, FB, AFT, DON, NIV, OTA, ZEN, T-2, region and detection age attributes. The E-R patterns of the samples are shown in FIG. 4.
(3) Risk level entity
The risk level entity is used for describing the pollution level division information of the detection values of the seven toxins of the wheat sample, and 21 records are recorded in total. The risk level table entity includes the contamination level, the toxin type, the maximum and minimum attributes of the toxin detection value corresponding to the level. The risk level E-R is shown in fig. 5.
(4) Early warning rule entity
The early warning rule entity data comprises a rule antecedent toxin type, a rule postcedent toxin type, an antecedent pollution level, a postcedent pollution level and a rule confidence value attribute. The warning rules E-R are shown in fig. 6.
(5) Early warning information entity
The early warning information entity describes the reserved information after early warning. The early warning information entity comprises a sample number and an early warning information attribute of a corresponding sample. The warning information E-R diagram is shown in fig. 7.
In order to implement the above-mentioned early warning method, the wheat quality safety early warning system provided by the present invention, as shown in fig. 8, includes the following modules:
the risk monitoring module is used for performing data management operation on the wheat toxin spot inspection data in each region, and comprises browsing of small wheat toxin spot inspection data in a database by a user, addition of sample toxin data and regional data query;
the risk early warning analysis module is used for setting and modifying the pollution risk levels of the seven mycotoxins and the corresponding risk detection values thereof, carrying out interval evaluation and prediction on the undetected toxin index detection values in the sample, and prompting the early warning information of the undetected toxins if the sample has joint exposure early warning information; otherwise, prompting that the joint exposure risk is temporarily absent; the user can also check the information after the sample prediction stored in the system is finished, and can check and modify the pollution level risk interval of each pollution index.
The data management module is used for managing user data, sample data, risk grade data, early warning rule data and early warning information data;
the system basic module also comprises system functions commonly used by the Web system, such as a system login module and a log management module, wherein the system login module is used for judging whether the filled user name exists in the database, if yes, matching verification is carried out, if matching is successful, the user jumps to the home page of the safety early warning system, and otherwise, an error message is prompted.
The technical architecture design of the wheat quality safety early warning system mainly adopts a mainstream architecture mode of a spring boot framework at present, and the mainstream architecture mode comprises a control layer (Controller), a Service logic layer (Service), a three-layer architecture of a data persistence layer (Dao), an Entity layer (Entity) and a View layer (View). The system architecture diagram is shown in fig. 9.
The main task of the control layer is to take charge of the interactive work of the front end and the back end, receive the request sent by the front end to carry out the business logic operation and return the data result. The control layer will call the service logic layer and return the processing result. In the system, the request is processed in an annotation mode of a SpringBoot framework technology, and a Service layer interface is called to process a return result.
The service logic layer is mainly used for performing service logic processing work, is responsible for the interface and implementation of the service layer and provides a calling method for the control layer. When the system is programmed and implemented, the Service logic layer is divided into a Service interface and a Service Impl interface implementation part.
The main task of the data persistence layer is to perform persistence operation on the database. And defining an interface for operating the database, and realizing operations such as addition, deletion, modification, check and the like on the database. In the system, a Mybatis persistent layer framework technology is adopted in a Dao layer to operate a MySQL database, wherein data sources and connection parameters related to the database are configured in configuration files, and SQL sentences are stored in mapper files.
The entity class layer is responsible for defining attributes of entity objects and providing the setter and getter methods. Where the attributes must be consistent with the database fields.
The database design of the wheat toxin early warning system comprises a user table (user) (shown in a table 4), a wheat sample toxin table (sample) (shown in a table 5), a risk level table (risk level) (shown in a table 6), a warning rule table (warning rule) (shown in a table 7) and a warning information table (warning information) (shown in a table 8). The seven toxin index attributes in the wheat sample toxin table are set as allowable null values, namely, the wheat sample toxin is allowed to input one or more data, and the matching prediction is carried out on the other index attribute values by using the rule table.
TABLE 4 user table
TABLE 5 wheat sample toxin list
TABLE 6 Risk ratings table
TABLE 7 early warning rules Table
TABLE 8 early warning information table
The flow and time sequence design of the main functional modules are as follows:
(1) User login
As shown in fig. 10 and 11, user login is the time when a user must verify his identity while using the system. If the input information is successfully compared with the information in the database, the login is successful; otherwise, it fails.
(2) Wheat toxin sample adding and inquiring function
As shown in fig. 12 and 13, the user can add the detected value of the detected toxin index in the sample, the sample number, the sample production place, the year of detection, and the like. Meanwhile, the sample data in the database can be screened and inquired through the sample number and the producing area.
(3) Risk early warning analysis
As shown in fig. 14 and fig. 15, an early warning request is first sent to a sample operation to be predicted, and when receiving a risk early warning message, the samplescontrollercontroller invokes a SampleService service logic class to process the risk early warning message. When the business logic is processed, firstly, the records of a pollution level division table in a table 1 stored in a database need to be accessed; secondly, judging and grading the detected toxins in the sample according to a risk grade table, and judging whether toxin indexes in a first-level pollution interval exist or not; if not, directly returning a prompt of 'temporary joint exposure risk early warning'; if yes, searching records in an early warning rule table database corresponding to the index toxin, then accessing the records of a set early warning rule table in the database, corresponding to a table 3, matching the tested toxin pollution level interval in the sample with the early warning rule, and judging whether a co-pollution state exists; if the co-pollution state exists, outputting early warning information of the rule table, and if the co-pollution state does not exist, prompting 'temporary joint exposure risk early warning'; and finally, storing the early warning result information and returning the early warning result information to the front-end page for displaying.
(4) Risk monitoring
The risk monitoring module comprises management monitoring of a sample for the wheat mycotoxin sampling. The method comprises the functions of adding toxin data in a sample, browsing, searching sample numbers, inquiring samples in provinces and the like by a user. The review of the sample data includes the attributes of the various fields of the sample and the contamination status of the sample, as shown in FIG. 16. The area sample query function is shown in fig. 17. The mycotoxin sample addition function in wheat is shown in fig. 18.
The basis of the risk early warning function is that an early warning table mined according to the association rule is used as a judgment basis. The risk early warning function is that if relevant detection personnel only detect certain mycotoxin indexes, the pollution level states of other mycotoxins need to be early warned and evaluated, and the pollution risk of other undetected toxins can be evaluated and judged by applying the early warning function.
If the sample with the detection sample number of A1000 only detects and obtains four toxins, the FB value is 2.9, the AFT value is 2.7, the ZEN is 0.5, and the T-2 is 2.5, whether the three toxins of the undetected DON, NIV and OTA have a co-pollution state with the detected toxins needs to be evaluated, the pollution intervals of the other undetected toxins are evaluated, and early warning is carried out by clicking prediction. According to the rules in the early warning table:
AFT (one) } -OTA (one) } confidence:0.566
AFT (one) } - > (DON (one) } confidence:0.505
Wherein AFT is in the first-class pollution interval, the probability of 50.5% of the undetected DON toxin with co-pollution is in the first-class pollution interval, and the probability of 56.6% of the DON toxin with OTA toxin is in the first-class pollution interval. The warning result graph is shown in fig. 19.
If the sample with the detection sample number of A1001 only detects and obtains four toxins, namely, the FB value is 10, the OTA value is 2.5, the ZEN value is 2.5 and the T-2 value is 15, whether the three toxins of the undetected DON, NIV and AFT have co-pollution states or not needs to be evaluated, and the pollution interval of the other undetected toxins is evaluated, clicking prediction is carried out for early warning. According to the early warning rule:
OTA (one) } - > (AFT (one) } confidence:0.899
Wherein the OTA value is 2.5 in the first-order contamination interval, the co-contaminated undetected AFT toxin has a probability of 89.9% in the first-order contamination interval. The warning result graph is shown in fig. 20.
If only FB toxin and OTA toxin are detected in the detection sample A1002, and whether the co-pollution state of other five undetected toxins, namely AFT toxin, DON toxin, NIV toxin, ZEN toxin and T-2 toxin, which are related to the two detected toxins exists needs to be evaluated, click prediction is carried out for early warning. Because the FB detection value in the sample is 0.75, the OTA detection value is 0.90, the two measured indexes are simultaneously in the three-level low-pollution interval and do not accord with the common-pollution early-warning rule, and the early-warning display shows 'temporary non-joint exposure early warning'. The predictive display is shown in figure 21.
After the early warning of the sample is finished, information such as sample numbers, early warning time, early warning results and the like can be stored in a database, and meanwhile, visual display is carried out on a risk early warning information interface. The early warning information interface implementation diagram is shown in fig. 22.
The risk level management function is that a user sets and modifies three level intervals of seven pollution toxin indexes, and each index corresponds to a risk level interval in the pollution level division table. A risk level implementation is shown in fig. 23.
The index weight analysis function is to visually display the weight ratio of the mycotoxin toxicity index in the wheat calculated by the analytic hierarchy process, wherein the larger the weight is, the higher the ratio is. The index weight map is shown in fig. 24.
In conclusion, the safety early warning system developed by the invention can be beneficial to early warning and judging the pollution risk grade interval of the detected value of the detected toxin of the sample to the undetected toxin when detecting the toxin of the sample, gives information of co-pollution of some toxins to related monitoring personnel, facilitates the management operation of a user on the data of the wheat sample, realizes intelligent input and prediction of the toxin at risk of the sample, and simplifies the workload of the related working personnel. The design of the system is combined with the early warning model of the data mining association rule method, and the mining strong association rule is applied to the risk early warning of the system to complete the related application of the association rule early warning model.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: it is to be understood that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof, but such modifications or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A wheat quality safety early warning method is characterized by comprising the following steps: taking the multidimensional index information source data of mycotoxin in wheat as input, judging and grading detected toxins in the sample according to a risk grade table, and judging whether toxin indexes in a first-level pollution interval exist or not; if not, directly returning to prompt 'temporary joint exposure risk early warning'; if yes, searching records in an early warning rule table database corresponding to the index toxin in the primary pollution interval, matching the detected toxin pollution level interval in the sample with the early warning rule, and judging whether a co-pollution state exists or not; if the co-pollution state exists, outputting early warning information of an early warning rule table, if the co-pollution state does not exist, prompting 'temporary joint exposure risk early warning', and finally outputting analysis information of wheat mycotoxin risk; the mycotoxins comprise seven items of fumonisins, aflatoxins, deoxynivalenol, nivalenol, ochratoxin A, zearalenone and T-2 toxins, and the early warning rule is a strong association rule of single-item collection mycotoxin indexes.
2. The wheat quality safety early warning method according to claim 1, wherein the single set mycotoxin index strong association rule is Apriori algorithm mining based on the association rule, and the Apriori algorithm is executed as follows:
s1, discretizing seven mycotoxin index data according to pollution levels to generate a Boolean type transaction database, wherein the pollution levels comprise three level intervals; constructing a transaction database of wheat sample mycotoxin boolean types, wherein each sample simultaneously comprises seven mycotoxin contamination indicators;
s2, scanning a transaction database with a constructed wheat sample mycotoxin Boolean type, respectively counting the occurrence frequency of three grade intervals of seven mycotoxin pollution indexes, counting the support degree of the three grade intervals, and generating a candidate k item set of toxin indexes, wherein k =1,2 …, n;
s3, eliminating the candidate k item set which does not meet the minimum support degree counting, and reserving the rest candidate k item sets which meet the minimum support degree counting to generate a frequent k item set;
s4, connecting the screened frequent k item sets of the toxin indexes with the selected frequent k item sets to generate candidate k +1 item sets;
s5, iterating and traversing the transaction database of the Boolean type of the mycotoxin again, counting the support degree counts of the candidate k +1 item sets, eliminating the item sets which do not meet the minimum support degree counts, and reserving the item sets which meet the minimum support degree to obtain frequent k +1 item sets;
and S6, repeatedly executing the step S4 and the step S5, acquiring the frequent N item sets until the frequent item sets are not generated any more, observing that all subsets of the frequent item sets are necessarily the frequent item sets in the executing and connecting process, removing the non-frequent item sets, and generating a single item set mycotoxin index strong association rule.
3. The wheat quality safety early warning method according to claim 1, wherein the pollution level is divided into: the fumonisin primary pollution interval is (30, + ∞), the secondary pollution interval is (7.5,30), the tertiary pollution interval is (0,7.5 ]; the aflatoxin primary pollution interval is (1.5, + ∞), (0.5,1.5), the tertiary pollution interval is (0,0.5 ]; the deoxynivalenol primary pollution interval is (100, + ∞), the secondary pollution interval is (20, 100], the tertiary pollution interval is (0,20 ]; the deoxynivalenol primary pollution interval is (17.5, + ∞), (5,17.5 ], the tertiary pollution interval is (3264 zxft 5657),; the ochratoxin A primary pollution interval is (1.5, + ∞), the secondary pollution interval is (1,1.5 ], the tertiary pollution interval is (3234 zxft 3434 ]; the primary pollution interval is 3224, the maize zxft 3224, the tertiary pollution interval is (3624), and the third pollution interval is (3624 zxft).
4. The wheat quality safety early warning method according to claim 1, wherein the early warning rule is as follows:
when the nivalenol is in a primary pollution interval, the possibility that the undetermined deoxynivalenol toxin with co-pollution is in the primary pollution interval is 92.0 percent;
when ochratoxin A is in a first-level pollution interval, 89.9 percent of the possibility of co-pollution of undetected aflatoxin is in the first-level pollution interval;
when the zearalenone is in the primary pollution zone, 80.6% of the possibility that the undetected deoxynivalenol toxin is co-polluted is in the primary pollution zone, 67.3% of the possibility that the undetected AFT toxin is co-polluted is in the primary pollution zone, and 63.7% of the possibility that the undetected T-2 toxin is co-polluted is in the primary pollution zone;
when the T-2 toxin is in a primary pollution interval, 74.2 percent of the possibility that co-polluted undetected deoxynivalenol toxin is in the primary pollution interval, and 71.5 percent of the possibility that co-polluted undetected zearalenone toxin is in the primary pollution interval;
when aflatoxin is in the primary pollution zone, 50.5% of co-pollution undetected deoxynivalenol toxin is in the primary pollution zone, and 56.6% of co-pollution undetected ochratoxin A toxin is in the primary pollution zone.
5. A wheat quality safety early warning system, which is used for realizing the method of any one of claims 1 to 4, and comprises the following modules:
the risk monitoring module is used for performing data management operation on the wheat toxin spot inspection data in each region, and comprises browsing of small wheat toxin spot inspection data in a database by a user, addition of sample toxin data and regional data query;
the risk early warning analysis module is used for setting and modifying the pollution risk levels of the seven mycotoxins and the corresponding risk detection values thereof, carrying out interval evaluation and prediction on the undetected toxin index detection values in the sample, and prompting the early warning information of the undetected toxins if the sample has joint exposure early warning information; otherwise, prompting that the joint exposure risk is temporarily absent;
the data management module is used for managing user data, sample data, risk grade data, early warning rule data and early warning information data;
and the system basic module comprises a system login module and a log management module, the system login module is used for judging whether the filled user name exists in the database, if yes, matching verification is carried out, if matching is successful, the user jumps to a home page of the safety early warning system, and otherwise, an error message is prompted.
6. The wheat quality safety precaution system of claim 1, wherein the user data includes user name, user number, gender, name, phone, mailbox, password.
7. The wheat quality safety precaution system of claim 1, wherein the sample data includes sample number, FB, AFT, DON, NIV, OTA, ZEN, T-2, regional, detected age attributes.
8. The wheat quality safety precaution system of claim 1, wherein the risk level data includes pollution levels, toxin types, maximum and minimum attributes of corresponding level toxin detection values.
9. The wheat quality safety warning system of claim 1, wherein the warning rule data includes a rule antecedent toxin type, a rule consequent toxin type, an antecedent contamination level, a consequent contamination level, a rule confidence value attribute.
10. The wheat quality safety warning system of claim 1, wherein the warning information data includes a sample number and a warning information attribute of the corresponding sample.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211293727.4A CN115526531A (en) | 2022-10-21 | 2022-10-21 | Wheat quality safety early warning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211293727.4A CN115526531A (en) | 2022-10-21 | 2022-10-21 | Wheat quality safety early warning method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115526531A true CN115526531A (en) | 2022-12-27 |
Family
ID=84704493
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211293727.4A Pending CN115526531A (en) | 2022-10-21 | 2022-10-21 | Wheat quality safety early warning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115526531A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117352178A (en) * | 2023-11-10 | 2024-01-05 | 西安艾派信息技术有限公司 | Big data-based drug risk assessment system and method |
-
2022
- 2022-10-21 CN CN202211293727.4A patent/CN115526531A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117352178A (en) * | 2023-11-10 | 2024-01-05 | 西安艾派信息技术有限公司 | Big data-based drug risk assessment system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9223777B2 (en) | Self-learning semantic search engine | |
CN111538844B (en) | Target field knowledge base generation and problem solution method and device | |
CN111967761B (en) | Knowledge graph-based monitoring and early warning method and device and electronic equipment | |
EP3836041A1 (en) | Interpretation of machine learning results using feature analysis | |
CN107872454B (en) | Threat information monitoring and analyzing system and method for ultra-large Internet platform | |
NL2013134A (en) | Data quality monitors. | |
CN112036153B (en) | Work order error correction method and device, computer readable storage medium and computer equipment | |
Bench-Capon | The need for good old fashioned ai and law | |
CN115526531A (en) | Wheat quality safety early warning method and system | |
CN111914141B (en) | Public opinion knowledge base construction method and public opinion knowledge base | |
CN115718472A (en) | Fault scanning and diagnosing method for hydroelectric generating set | |
CN115438199A (en) | Knowledge platform system based on smart city scene data middling platform technology | |
CN110414007A (en) | A kind of legal concept recognition methods based on legal principle rule map engine | |
CN111353085A (en) | Cloud mining network public opinion analysis method based on feature model | |
CN117035563B (en) | Product quality safety risk monitoring method, device, monitoring system and medium | |
CN116541887B (en) | Data security protection method for big data platform | |
CN104462461B (en) | The method and device of investigation processing empty value is carried out to list | |
Düntsch et al. | The rough set engine GROBIAN | |
CN111143624A (en) | Land approval surveying and mapping data-oriented adaptive calculation rule base matching method and system | |
CN116881535A (en) | Public opinion comprehensive supervision system with timely early warning function | |
CN116501733A (en) | Data product generation method, device, equipment and storage medium | |
CN116302984A (en) | Root cause analysis method and device for test task and related equipment | |
KR102410415B1 (en) | Method and apparatus for providing intelligent pharmacovilgilance platform | |
CN114312930A (en) | Train operation abnormity diagnosis method and device based on log data | |
CN113360357A (en) | Data monitoring method, system, equipment and computer program product |
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 |