CN105046362A - Real-time prediction method of food safety on the basis of association rule mining - Google Patents
Real-time prediction method of food safety on the basis of association rule mining Download PDFInfo
- Publication number
- CN105046362A CN105046362A CN201510440249.9A CN201510440249A CN105046362A CN 105046362 A CN105046362 A CN 105046362A CN 201510440249 A CN201510440249 A CN 201510440249A CN 105046362 A CN105046362 A CN 105046362A
- Authority
- CN
- China
- Prior art keywords
- food
- risk
- association rule
- factor
- safety
- 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
- 235000013305 food Nutrition 0.000 title claims abstract description 187
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000005065 mining Methods 0.000 title claims abstract description 29
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000004519 manufacturing process Methods 0.000 claims description 16
- 239000004615 ingredient Substances 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 4
- 241000170489 Upis Species 0.000 claims description 3
- 241000287828 Gallus gallus Species 0.000 description 12
- 235000015277 pork Nutrition 0.000 description 9
- 239000000126 substance Substances 0.000 description 7
- 239000005417 food ingredient Substances 0.000 description 6
- 244000052616 bacterial pathogen Species 0.000 description 5
- 238000007418 data mining Methods 0.000 description 5
- 235000012041 food component Nutrition 0.000 description 5
- 241000607479 Yersinia pestis Species 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000002950 deficient Effects 0.000 description 3
- 239000002778 food additive Substances 0.000 description 3
- 239000002994 raw material Substances 0.000 description 3
- 241000272525 Anas platyrhynchos Species 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 2
- 241000758706 Piperaceae Species 0.000 description 2
- 238000011109 contamination Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 235000013601 eggs Nutrition 0.000 description 2
- 235000013373 food additive Nutrition 0.000 description 2
- 230000000813 microbial effect Effects 0.000 description 2
- 210000003739 neck Anatomy 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 241000764238 Isis Species 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- AGVAZMGAQJOSFJ-WZHZPDAFSA-M cobalt(2+);[(2r,3s,4r,5s)-5-(5,6-dimethylbenzimidazol-1-yl)-4-hydroxy-2-(hydroxymethyl)oxolan-3-yl] [(2r)-1-[3-[(1r,2r,3r,4z,7s,9z,12s,13s,14z,17s,18s,19r)-2,13,18-tris(2-amino-2-oxoethyl)-7,12,17-tris(3-amino-3-oxopropyl)-3,5,8,8,13,15,18,19-octamethyl-2 Chemical compound [Co+2].N#[C-].[N-]([C@@H]1[C@H](CC(N)=O)[C@@]2(C)CCC(=O)NC[C@@H](C)OP(O)(=O)O[C@H]3[C@H]([C@H](O[C@@H]3CO)N3C4=CC(C)=C(C)C=C4N=C3)O)\C2=C(C)/C([C@H](C\2(C)C)CCC(N)=O)=N/C/2=C\C([C@H]([C@@]/2(CC(N)=O)C)CCC(N)=O)=N\C\2=C(C)/C2=N[C@]1(C)[C@@](C)(CC(N)=O)[C@@H]2CCC(N)=O AGVAZMGAQJOSFJ-WZHZPDAFSA-M 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 229940029329 intrinsic factor Drugs 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 235000015067 sauces Nutrition 0.000 description 1
- 235000013580 sausages Nutrition 0.000 description 1
- 238000003307 slaughter Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a real-time prediction method of food safety on the basis of association rule mining, and belongs to the field of food safety. The real-time prediction method comprises the following steps: firstly, using a mining method based on an association rule to find other food associated with problem food and relevancy between the problem food and other food; then, according to a food risk index system, measuring weight values and risk coefficients which affect the risk factors of the associated food; and finally, according to the weight values and the risk coefficients of the risk factors, calculating the risk values of the associated food. The method can find other food associated with the safety of certain problem food, can measure the frequencies of various risk factors which cause the certain food to generate a safety problem in a historical database to automatically regulate the weights of the risk factors which affect the food safety so as to calculate the comprehensive influence, i.e. a food safety degree, on the certain food by all risk factors, provides a food safety reference for consumers and provides a decision basis for decision makers.
Description
Technical Field
The invention relates to the field of food safety, in particular to a real-time food safety prediction method based on association rule mining.
Background
The food safety traceability system was first established and perfected gradually in 1997 in the european union to cope with the problem of mad cow disease. The method emphasizes the unique identification and process tracking of the product, and performs tracking and tracing by adopting quality control methods such as ISO9001 and the like in each link of production, transportation, storage, sale and the like of the product, so that the destination of the food can be effectively tracked once the food safety problem occurs, unqualified products can be recalled in time, and the loss is reduced to the minimum.
The existing food safety traceability system has single function, and food traceability application can only finish the collection of relevant data of food and raw materials thereof, and some applications such as visual simple traceability, information statistics and the like. For example, a piece of pork sold in the market is found to be contaminated by microorganisms or carry certain germs, and the existing tracing system can trace out where the piece of pork comes from, but cannot explain the cause of the microbial contamination or the germs, cannot predict whether other pork in the same batch with the piece of pork has a problem, and cannot predict whether other food processed by taking the pork as a raw material has a safety problem. Microbial contamination or carried germs of pork may occur in farms, slaughter plants, transportation processes, marketing links and the like, and in the process, the pork has different degrees of influence on other foods due to accidents in different links. The existing system can not correlate other foods related to the problem food, and can not predict the safety degree of other foods.
Association rule mining is an important direction in data mining technology, first proposed by agrawalr et al. Initially to discover the association between data attributes from a transaction database, a typical application for this is shopping basket analysis. Association rule mining can mine valuable knowledge from a large amount of data describing the relevant connections between attributes in the data.
Due to the fact that the food safety detection data have the relations of time sequence correlation, causal correlation and the like, a data mining method based on association rule mining is adopted. The data mining method based on association rule mining can find other food related to the problem food and meeting the minimum support degree and the minimum confidence degree.
Disclosure of Invention
In order to solve the problem that a food safety tracing system in the prior art cannot predict the safety of other related foods according to the safety of the foods in question, the invention provides a food safety real-time prediction method based on association rule mining, which can monitor, analyze and evaluate food safety information in a system database in real time, continuously update the hazard degree of a risk factor, predict the risk coefficient of the foods in real time according to an index system for measuring the food risk, and visually display the risk coefficient in a graph and digital mode.
The technical scheme adopted by the invention for solving the technical problems is as follows: a real-time food safety prediction method based on association rule mining comprises the following steps:
1) collecting safety information of production and circulation of various foods, and inputting the information into a system database;
2) finding out food associated with the problem food through association rule mining;
3) calculating a risk value for the food of interest;
4) and judging whether the food is safe according to the calculated risk value, and inputting the information into a system database.
Finding out the food associated with the problem food by mining the association rules in the step 2) into three steps, wherein the first step is to find out all frequent sets meeting the support degree, the second step is to use the frequent sets to generate the association rules, and the third step is to find out other food which meets the minimum support degree and the minimum reliability and is related to the problem food by the association rules; the specific operation is as follows:
searching the system database layer by using a breadth first algorithm Apriori, namely exploring a (K +1) -item set by using a K-item set, finding out a set of frequent 1-item sets, and recording the set as a，Collections for finding frequent 2-item setsTo do soFor findingAnd so on until a frequent k-term set cannot be found:
setting upIs a collection of m different data items, where an element is called an item and a collection of items is called an item set;
given a transaction databaseWhere each transaction T is a subset of the set of items I, i.e.；
For the total number of transactions in D, X, Y are all items or sets of items in T,；
if transaction T contains both X and Y, then the association rule can be derived:
（1）
in the formula,in the transaction database D for transactions T satisfying the conditionsThe occupied proportion, namely the Support ratio, is calculated according to the following formula:
（2）
（3）；
and calculating other food related to the problem food meeting the minimum support degree and reliability according to the formula (2) and the formula (3).
The specific operation of calculating the risk value of the related food in the step 3) is as follows:
first, risk factors affecting food safety are classified as internal factorsExternal factorAnd additional factorsCalculating the internal factors separatelyExternal factorAnd additional factorsWeight of (2)、Andand is and；
wherein the internal factorWeight of (2)Is composed of
（4）
External factorWeight of (2)Is composed of
（5）
Second, the internal factors are calculated separatelyExternal factorAnd additional factorsRisk coefficient of、、；
Wherein the internal factorRisk coefficient ofIs composed of
（6）
In the formula,is shown asThe seed materials are planted and mixed,is shown asThe risk value of the seed ingredient(s),is composed ofAnd is weighted, and；
external factorRisk coefficient ofIs composed of
（7）
Wherein,，the risk values respectively representing the production, transportation, storage and sale environments of the food, the risk values of the external factors and the calculation method of the weight are similar to the calculation method of the risk values and the weight of the food ingredients, and a weighted sum method is adopted; in the invention, the last level of risk value, namely the risk value of the harmful substances in the food risk index system, is evaluated by experts in the food field according to the hazard degree of the harmful substances in the food, and comprises the risk value represented by enterprise reputation and consumer feedback. The risk value of each stage is calculated by the risk value of the next stage and the weight of the risk factor, and the weight of each stageThe calculation formula is given in the examples.
Additional factorRisk coefficient ofIs composed of
（8）
In the formula,represents a reputation risk value for a food manufacturing enterprise,indicating the risk value reflected by the consumer's feedback,，、、、the value of (A) is set by comprehensive evaluation of experts in the food field;
finally, according to the formulaCalculating a risk value for the food product, wherein,、、respectively representing risk coefficients of an internal factor, an external factor and an additional factor,。
the idea of the invention is as follows: when a certain food has a safety problem, firstly, other foods related to the food in question and the correlation degree between the foods are found out by using a mining method based on association rules, then the weight value and the risk coefficient of the risk factor influencing the related foods are measured according to a food risk index system, and finally the risk value of the related food is calculated according to the weight value and the risk coefficient of the risk factor. If a certain risk indicator of a food is found to be outside the normal range when measured, the food is directly designated as a high risk food. In the whole process, the weight of the risk factor and the risk coefficient are measured again before use, and the latest value is updated in the database.
Due to the variety of factors affecting food safety, there are many food risk indicators, most of which can be quantified to a specific value. Some indexes influencing the food safety are harmful substances in food ingredients, some indexes are harmful substances in the environment contacted by the food in the processes of production, transportation, storage and sale, and in addition, the feedback of consumers and the credit of manufacturers can reflect the safety degree of the food from the side. All factors that have an effect on food safety are collectively referred to herein as pests.
Has the advantages that: the invention provides a food safety real-time prediction method based on association rule mining, which can find other foods related to the safety of a food with a certain problem, and can automatically adjust the weight of risk factors influencing the food safety by measuring the times of various risk factors causing the safety problem of the food in a historical database, thereby calculating the comprehensive influence of all the risk factors on the food, namely the safety degree of the food, providing food safety reference for consumers, providing decision basis for decision makers and the like. Meanwhile, the invention can also carry out real-time monitoring, analysis and evaluation on food safety information in the system database, continuously update the hazard degree of the risk factor, predict the risk coefficient of the food in real time according to an index system for measuring the food risk, and visually display the risk coefficient in a graph and digital mode, thereby visually showing whether the food related to the risk factor has potential safety hazard when a certain food has a problem.
Drawings
FIG. 1 is a system diagram of food risk indicators in an embodiment of the present invention;
FIG. 2 is a flow chart of calculation of a food risk value in the example;
fig. 3 is a graph of the food risk prediction in the examples.
Detailed Description
A real-time food safety prediction method based on association rule mining comprises the following steps:
1) collecting safety information of production and circulation of various foods, and inputting the information into a system database;
2) finding out food associated with the problem food through association rule mining;
finding out food associated with problem food by association rule mining and dividing into three steps, wherein the first step is to find out all frequent sets meeting the support degree, the second step is to use the frequent sets to generate association rules, and the third step is to find out other food which meets the minimum support degree and the minimum reliability and is related to the problem food by the association rules; the specific operation is as follows:
searching the system database layer by using a breadth first algorithm Apriori, namely exploring a (K +1) -item set by using a K-item set, finding out a set of frequent 1-item sets, and recording the set as a，Collections for finding frequent 2-item setsTo do soFor findingAnd so on until a frequent k-term set cannot be found:
setting upIs a collection of m different data items, where an element is called an item and a collection of items is called an item set;
given a transaction databaseWhere each transaction T is a subset of the set of items I, i.e.；
For the total number of transactions in D, X, Y are all items or sets of items in T,；
if transaction T contains both X and Y, then the association rule can be derived:
（1）
in the formula,in order to satisfy the proportion of the transaction T in the transaction database D, i.e. the Support degree Support, the calculation formula is as follows:
（2）
（3）；
calculating other food related to the problem food meeting the minimum support degree and reliability according to the formula (2) and the formula (3);
3) calculating the risk value of the related food, and specifically operating as follows:
first, risk factors affecting food safety are classified as internal factorsExternal factorAnd additional factorsCalculating the internal factors separatelyExternal factorAnd additional factorsWeight of (2)、Andand is and；
wherein the internal factorWeight of (2)Is composed of
（4）
External factorWeight of (2)Is composed of
（5）
Second, the internal factors are calculated separatelyExternal factorAnd additional factorsRisk coefficient of、、；
Wherein the internal factorRisk coefficient ofIs composed of
（6）
In the formula,is shown asThe seed materials are planted and mixed,is shown asThe risk value of the seed ingredient(s),is composed ofAnd is weighted, and；
external factorRisk coefficient ofIs composed of
（7）
Wherein,，risk values respectively representing production, transportation, storage and sale environments of the food, and the calculation methods of the risk value and the weight of the external factor are the same as those of the risk value and the weight of the internal factor and are calculated by adopting a weighted sum method;
additional factorRisk coefficient ofIs composed of
（8）
In the formula,represents a reputation risk value for a food manufacturing enterprise,indicating the risk value reflected by the consumer's feedback,，、、、the value of (A) is set by comprehensive evaluation of experts in the food field;
finally, according to the formulaCalculating a risk value for the food product, wherein,、、respectively representRisk factors for internal factors, external factors, additional factors,；
4) and judging whether the food is safe according to the calculated risk value, and inputting the information into a system database.
The foregoing is a basic mode of the invention, which is further described with reference to specific embodiments.
When a certain food has a safety problem, firstly, other foods related to the food in question and the correlation degree between the foods are found out by using a mining method based on association rules, then the weight value and the risk coefficient of the risk factor influencing the related foods are measured according to a food risk index system, and finally the risk value of the related food is calculated according to the weight value and the risk coefficient of the risk factor. If a certain risk indicator of a food is found to be outside the normal range when measured, the food is directly designated as a high risk food. In the whole process, the weight of the risk factor and the risk coefficient are measured again before use, and the latest value is updated in the database.
1 Association rule mining
The association rule analysis method has a plurality of mining algorithms, and the breadth-first algorithm Apriori is selected according to the characteristic that the data of the food detection project are not uniformly distributed. The basic idea is as follows: all non-empty subsets of the frequent item set must also be frequent. Apriori uses an iterative approach called layer-by-layer search, with a set of K-terms used to explore a set of (K +1) -terms. First, find the set of frequent 1-item sets, which is written as。Collections for finding frequent 2-item setsTo do soFor findingAnd so on until a frequent k-term set cannot be found. Find eachOne database scan is required.
Is provided withIs a collection of m different data items, where the elements are referred to as items and the collection of items is referred to as a collection of items. Given a transaction databaseWhere each transaction T is a subset of the set of items I, i.e.；Is the total number of transactions in D. X, Y are all items or sets of items in T,. If transaction T contains both X and Y, then the association rule can be derived:
（1）
in the formulaTo satisfy the conditionsThe proportion of the transaction T in the transaction database D, i.e. the Support (Support), is calculated as follows:
（2）
（3）
the goal of data mining is to select strongly associated rules that are both greater than the confidence threshold and the support threshold. The data mining is divided into two steps, wherein in the first step, all frequent sets meeting the support degree are found out; the second step generates association rules using the frequent set. Since the transaction database needs to be scanned multiple times in the first step, the consumption of time and space is a key to restrict the mining efficiency.
Other foods which satisfy a certain relation with the problem food are found by the association rule mining method, for example, if the pork on the market has germs, the foods such as ham sausage, sauced pig trotter and the like which take the pork as the raw material can be found by the association rule, and the correlation degree between the foods. If the bagged sauced chicken wings sold in a supermarket are polluted by germs, the sauced chicken legs, the spiced eggs, the sauced duck necks and the like related to the bagged sauced chicken wings can also cause problems because the bagged sauced chicken legs, the spiced eggs, the sauced duck necks and the like contain a plurality of same ingredients, such as edible essence, salt, pickled peppers, food additives and the like. Regarding food as a transaction, regarding food ingredients as items of the transaction, passing the transactionAnd transactionsAnd (5) mining and calculating the correlation. In summary, by associating rulesThe method can find other foods related to problem foods that meet the minimum support and confidence level.
Setting of 2 Risk values
The food risk value is defined in the present invention asWhereinThe setting is made to be a low risk,the setting is made to be a medium risk,the setting is high risk, and the corresponding range of the risk level is set by experts in the food field and can be adjusted. In the following cases, the risk grade of the food is directly judged as high risk and the risk value is 10, without weighted calculation according to the food risk index system:
the harmful substances in the food are limited, some are forbidden, and the limited use is not allowed as long as the limited use is harmless to people within a specified range. In food spot inspection, if forbidden harmful substances appear, the food risk value is directly set to 10;
if a certain limited harmful substance in the food exceeds a certain value, the food risk value is directly set to 10;
third, if the food is complained more than the ratio of the complaining times to the total complaining times of the food of the category to which the food belongs in the last monthThen the food risk value is set directly to 10;
if the defective rate of a certain food exceeds a certain value, the food risk value is set to 10 as it is, and the defective rate = (number of defective items/total number of detected items).
The indexes are not fixed, and field experts can adjust the indexes according to actual conditions and can add some indexes. Some special cases can be set up to directly judge the food as medium risk.
3 Risk value assessment
The weight of the risk factors influencing food safety is obtained by counting the historical records of food safety events, the weight represents the influence degree of a certain risk factor on food, and the larger the weight is, the more obvious the influence of the factor on the food safety is. For example, for bagged seasoned chicken legs sold in supermarkets, there are many risk factors affecting the safety of the seasoned chicken legs. According to the food risk index system, the risk factors affecting the sauced chicken leg are divided into internal factorsExternal factorAnd additional factorsThe internal factors are: the external factors of the ingredients comprise the following ingredients of edible essence, salt, pickled peppers, food additives and the like: growth environment pollution index of live chicken, colony index of sauced chicken leg production workshop, temperature of production workshop, and atmospheric pollution index and environment temperature contacted by sauced chicken legs in transportation, storage and sale links, and the like, wherein the additional factors comprise: the reputation of the manufacturing enterprise, the number of complaints of the consumer, and the like. Risk value of sauced drumstickWherein、、Respectively representing risk coefficients of an internal factor, an external factor and an additional factor,，has a weight of，Has a weight of，Has a weight of(constant, value estimated from historical experience),andrespectively represents the times of the safety events of the chicken legs with the sauce caused by internal factors and external factors in the historical records,indicates the sum of both.
Many cofactors of the intrinsic factor, e.g. flavourings as in the case of the aforementioned catsup chicken legSaltPickled peppersFood additiveThe weights of these sub-factors are:，，，wherein. Similarly, there are many sub-factors in the external factor, and the weight representation of these sub-factors is similar to the representation of the internal sub-factor.
In summary, the general expression of the internal factor weight is:
（4）
the general expression of the extrinsic factor weight is:
（5）
the weight of the additional factor isIs aA constant greater than 0 and less than 1. Its value is evaluated by a domain expert based on historical experience.
Risk value of food ingredientWhereinThe second of the foodSeed preparation;indicates the first in the ingredientsA risk value for the seed pest, the value being set by a domain expert;is as followsThe weight of the seed pest is such that,. The risk value of the food being influenced by the ingredients, i.e. the risk value of the internal factor, is:
（6）
wherein,is shown asThe seed materials are planted and mixed,is shown asThe risk value of the seed ingredient(s),is composed ofAnd is weighted, and。
the risk values for external factors are:
（7）
wherein,，the risk values respectively representing the production, transportation, storage and sale environments of the food, the risk values of the external factors and the weights are calculated in a similar way as the risk values and the weights of the food ingredients, and the calculation method of the risk values and the weights of the external factors is similar to the calculation method of the risk values of the food ingredients and adopts a weighted sum method.
The risk values for the additional factors are:
（8）
wherein,to representThe reputation risk value of a food production enterprise,indicating the risk value reflected by the consumer's feedback,，、、、the value of (a) is set by comprehensive evaluation of a food field expert.
The risk values for a food product are:
（9）
wherein,、、respectively representing risk coefficients of an internal factor, an external factor and an additional factor,。
4 real-time prediction of food risk value
Since the risk value of food is influenced by various factors, it changes every moment. The system predicts the food safety in real time, measures the risk values of all foods at regular intervals according to a set frequency, and records the calculation result in a database for convenient query. The system can set early warning threshold values for each food, and the system automatically alarms when the risk value of the food exceeds the threshold values. The food risk value prediction graph is shown in fig. 2. The prediction result can be displayed in a graphic and digital mode, and the prediction result and the food safety trend are clear at a glance. The risk value and the safety trend of food in the last week, the last month, the last year and the like can be checked by selecting the checking condition, and the risk value and the safety trend of a certain type of food or a certain type of food can also be checked. The food risk prediction graph is shown in fig. 3.
Claims (3)
1. A real-time food safety prediction method based on association rule mining is characterized by comprising the following steps:
1) collecting safety information of production and circulation of various foods, and inputting the information into a system database;
2) finding out food associated with the problem food through association rule mining;
3) calculating a risk value for the food of interest;
4) and judging whether the food is safe according to the calculated risk value, and inputting the information into a system database.
2. The real-time food safety prediction method based on association rule mining as claimed in claim 1, wherein the step 2) of finding out the food associated with the problem food by association rule mining is divided into three steps, wherein the first step of finding out all frequent sets meeting the support degree, the second step of using the frequent sets to generate the association rule, and the third step of finding out other food related to the problem food meeting the minimum support degree and reliability degree by association rule; the specific operation is as follows:
searching the system database layer by using a breadth first algorithm Apriori, namely exploring a (K +1) -item set by using a K-item set, finding out a set of frequent 1-item sets, and recording the set as a，Collections for finding frequent 2-item setsTo do soFor findingAnd so on until a frequent k-term set cannot be found:
setting upIs a collection of m different data items, where an element is called an item and a collection of items is called an item set;
given a transaction databaseWherein each isA transaction T is a subset of the set of items I, i.e.；
For the total number of transactions in D, X, Y are all items or sets of items in T,；
if transaction T contains both X and Y, then the association rule can be derived:
（1）
in the formula,in order to satisfy the proportion of the transaction T in the transaction database D, i.e. the Support degree Support, the calculation formula is as follows:
（2）
for the proportion that the transaction containing X in D also contains Y, namely Confidence Confidence, the calculation formula is as follows:
（3）；
and calculating other food related to the problem food meeting the minimum support degree and reliability according to the formula (2) and the formula (3).
3. The real-time food safety prediction method based on association rule mining as claimed in claim 1, wherein the specific operation of calculating the risk value of the related food in step 3) is as follows:
first, risk factors affecting food safety are classified as internal factorsExternal factorAnd additional factorsCalculating the internal factors separatelyExternal factorAnd additional factorsWeight of (2)、Andand is and；
wherein the internal factorWeight of (2)Is composed of
（4）
External factorWeight of (2)Is composed of
（5）
Second, the internal factors are calculated separatelyExternal factorAnd additional factorsRisk coefficient of、、；
Wherein the internal factorRisk coefficient ofIs composed of
（6）
In the formula,is shown asThe seed materials are planted and mixed,is shown asThe risk value of the seed ingredient(s),is composed ofAnd is weighted, and；
external factorRisk coefficient ofIs composed of
（7）
Wherein,，risk values respectively representing production, transportation, storage and sale environments of the food, and the calculation methods of the risk value and the weight of the external factor are the same as those of the risk value and the weight of the internal factor and are calculated by adopting a weighted sum method;
additional factorRisk coefficient ofIs composed of
（8）
In the formula,represents a reputation risk value for a food manufacturing enterprise,indicating the risk value reflected by the consumer's feedback,，、、、the value of (A) is set by comprehensive evaluation of experts in the food field;
finally, according toFormula (II)Calculating a risk value for the food product, wherein,、、respectively representing risk coefficients of an internal factor, an external factor and an additional factor,。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510440249.9A CN105046362A (en) | 2015-07-24 | 2015-07-24 | Real-time prediction method of food safety on the basis of association rule mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510440249.9A CN105046362A (en) | 2015-07-24 | 2015-07-24 | Real-time prediction method of food safety on the basis of association rule mining |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105046362A true CN105046362A (en) | 2015-11-11 |
Family
ID=54452889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510440249.9A Pending CN105046362A (en) | 2015-07-24 | 2015-07-24 | Real-time prediction method of food safety on the basis of association rule mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105046362A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913164A (en) * | 2016-03-24 | 2016-08-31 | 张远 | Construction method of food safety risk early warning system |
| CN106651166A (en) * | 2016-12-15 | 2017-05-10 | 中国南方电网有限责任公司电网技术研究中心 | Natural disaster risk processing method and system based on Internet of Things |
| CN107870956A (en) * | 2016-09-28 | 2018-04-03 | 腾讯科技（深圳）有限公司 | A kind of effective item set mining method, apparatus and data processing equipment |
| CN107871277A (en) * | 2017-07-25 | 2018-04-03 | 平安普惠企业管理有限公司 | The method and computer-readable recording medium that server, customer relationship are excavated |
| CN109801005A (en) * | 2019-03-26 | 2019-05-24 | 北京金和网络股份有限公司 | The construction method of food safety risk model based on machine learning |
| CN111222767A (en) * | 2019-12-29 | 2020-06-02 | 航天信息股份有限公司 | Grain and food flow process quality safety risk assessment method and system |
| CN111341446A (en) * | 2020-02-11 | 2020-06-26 | 中山大学 | Personalized physical examination package recommendation method |
| CN111382918A (en) * | 2018-12-28 | 2020-07-07 | 内蒙古伊利实业集团股份有限公司 | Food monitoring method and system |
| CN111915206A (en) * | 2020-08-11 | 2020-11-10 | 成都市食品药品检验研究院 | Method for recognizing food risk conduction |
| CN112232703A (en) * | 2019-12-09 | 2021-01-15 | 马鞍山钢铁股份有限公司 | Casting blank quality determination method and system |
| CN113112279A (en) * | 2021-03-16 | 2021-07-13 | 中国科学院计算机网络信息中心 | Imported cold chain food tracing method and system based on secondary tracing |
| CN113762764A (en) * | 2021-09-02 | 2021-12-07 | 南京大学 | Automatic grading and early warning system and method for safety risk of imported food |
| 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 |
| CN118378897A (en) * | 2024-06-21 | 2024-07-23 | 杭州祐全科技发展有限公司 | Data processing method and system for food material safety risk identification |
-
2015
- 2015-07-24 CN CN201510440249.9A patent/CN105046362A/en active Pending
Non-Patent Citations (2)
| Title |
|---|
| 田春园: "基于数据挖掘的食品安全风险评价与预警系统", 《中国优秀硕士学位论文全文数据库工程科技I辑》 * |
| 第11期: "基于关联规则挖掘的食品安全信息预警模型", 《软科学》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913164A (en) * | 2016-03-24 | 2016-08-31 | 张远 | Construction method of food safety risk early warning system |
| CN107870956A (en) * | 2016-09-28 | 2018-04-03 | 腾讯科技（深圳）有限公司 | A kind of effective item set mining method, apparatus and data processing equipment |
| CN107870956B (en) * | 2016-09-28 | 2021-04-27 | 腾讯科技（深圳）有限公司 | High-utility item set mining method and device and data processing equipment |
| CN106651166A (en) * | 2016-12-15 | 2017-05-10 | 中国南方电网有限责任公司电网技术研究中心 | Natural disaster risk processing method and system based on Internet of Things |
| CN106651166B (en) * | 2016-12-15 | 2020-06-30 | 中国南方电网有限责任公司电网技术研究中心 | Natural disaster risk processing method and system based on Internet of things |
| CN107871277A (en) * | 2017-07-25 | 2018-04-03 | 平安普惠企业管理有限公司 | The method and computer-readable recording medium that server, customer relationship are excavated |
| CN107871277B (en) * | 2017-07-25 | 2021-04-13 | 平安普惠企业管理有限公司 | Server, client relationship mining method and computer readable storage medium |
| CN111382918A (en) * | 2018-12-28 | 2020-07-07 | 内蒙古伊利实业集团股份有限公司 | Food monitoring method and system |
| CN109801005A (en) * | 2019-03-26 | 2019-05-24 | 北京金和网络股份有限公司 | The construction method of food safety risk model based on machine learning |
| CN112232703A (en) * | 2019-12-09 | 2021-01-15 | 马鞍山钢铁股份有限公司 | Casting blank quality determination method and system |
| CN111222767A (en) * | 2019-12-29 | 2020-06-02 | 航天信息股份有限公司 | Grain and food flow process quality safety risk assessment method and system |
| CN111341446A (en) * | 2020-02-11 | 2020-06-26 | 中山大学 | Personalized physical examination package recommendation method |
| CN111341446B (en) * | 2020-02-11 | 2022-11-29 | 中山大学 | Personalized physical examination package recommendation method |
| CN111915206A (en) * | 2020-08-11 | 2020-11-10 | 成都市食品药品检验研究院 | Method for recognizing food risk conduction |
| CN111915206B (en) * | 2020-08-11 | 2024-02-27 | 成都市食品药品检验研究院 | Method for identifying food risk conduction |
| CN113112279A (en) * | 2021-03-16 | 2021-07-13 | 中国科学院计算机网络信息中心 | Imported cold chain food tracing method and system based on secondary tracing |
| CN113762764A (en) * | 2021-09-02 | 2021-12-07 | 南京大学 | Automatic grading and early warning system and method for safety risk of imported food |
| CN113762764B (en) * | 2021-09-02 | 2024-04-12 | 南京大学 | Automatic grading and early warning system and method for imported food safety risks |
| 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 |
| CN118378897A (en) * | 2024-06-21 | 2024-07-23 | 杭州祐全科技发展有限公司 | Data processing method and system for food material safety risk identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105046362A (en) | Real-time prediction method of food safety on the basis of association rule mining | |
| Roccato et al. | Analysis of domestic refrigerator temperatures and home storage time distributions for shelf-life studies and food safety risk assessment | |
| Duong et al. | A review of robotics and autonomous systems in the food industry: From the supply chains perspective | |
| Wang et al. | A fuzzy model for aggregative food safety risk assessment in food supply chains | |
| Feng et al. | Modeling and evaluation on WSN-enabled and knowledge-based HACCP quality control for frozen shellfish cold chain | |
| Frey et al. | Recommended practice regarding selection, application, and interpretation of sensitivity analysis methods applied to food safety process risk models | |
| Xiao et al. | Development and evaluation of an intelligent traceability system for frozen tilapia fillet processing | |
| Mateo et al. | A comparison of statistical methods to standardize catch-per-unit-effort of the Alaska longline sablefish fishery | |
| Xiao et al. | Developing an intelligent traceability system for aquatic products in cold chain logistics integrated WSN with SPC | |
| KR101864252B1 (en) | Artificial intelligence based food putrefaction model developing system and food putrefaction alarm system using food putrefaction model | |
| Wijaya et al. | Seafood quality detection using electronic nose and machine learning algorithms with hyperparameter optimization | |
| Augustin et al. | Design of control charts to monitor the microbiological contamination of pork meat cuts | |
| Kusolchoo et al. | Digital Technologies for Food Loss and Waste in Food Supply Chain Management | |
| Putro et al. | A Classification Approach to Predicting Beef Knuckle Quality using the Decision Tree and Naïves Bayes Method: Case Study: Tiga Bersaudara Factory | |
| KR20200122652A (en) | Nutrient Profiling-based Pet Food Recommendation System | |
| Kusbandhini et al. | Rice shelf-life prediction using support vector regression algorithm based on electronic nose dataset | |
| Martínez-Simarro et al. | Applications and business impact of artificial intelligence in the industrial production of food and beverages | |
| Pujiati et al. | The projection model as an early warning of food price commodity fluctuation | |
| KR20180078395A (en) | Apparatus And Method For Predicting Dynamic Microbial Growth In livestock Products, A Computer-readable Storage Medium For Executing The Method, And System For Managing Food Safety | |
| US10607174B2 (en) | Proactive simulation and detection of outbreaks based on product data | |
| Talley et al. | A vector-borne contamination model to assess food-borne outbreak intervention strategies | |
| Rauf | Risk analysis of supply chain food loss on fishery products using failure mode effect and supply chain operation reference model | |
| Batlajery et al. | prFood: ontology principles for provenance and risk in the food domain | |
| KR102635331B1 (en) | Method and apparatus for predicting food poisoning bacteria under dynamic temperature condition | |
| Biondo et al. | An updated review of the marine ornamental fish trade in the European Union |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151111 |