CN116011802A - Risk early warning management system and method for monitoring livestock and poultry products - Google Patents
Risk early warning management system and method for monitoring livestock and poultry products Download PDFInfo
- Publication number
- CN116011802A CN116011802A CN202211100849.7A CN202211100849A CN116011802A CN 116011802 A CN116011802 A CN 116011802A CN 202211100849 A CN202211100849 A CN 202211100849A CN 116011802 A CN116011802 A CN 116011802A
- Authority
- CN
- China
- Prior art keywords
- risk
- enterprise
- module
- samples
- animal
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a risk early warning management system and method for monitoring livestock and poultry products. According to the system, after an enterprise needing spot inspection on the same day is selected through the intelligent extraction module, spot inspection is carried out on products of the enterprise on the same day, after data detection, risk analysis and data comparison are carried out on spot inspection products, samples exceeding a threshold value are marked as dangerous samples through the risk early warning module, and veterinary medicine, fresh milk and feed information related to the dangerous samples are marked and then sent to a relevant platform together with sample information of the dangerous samples, so that supervision staff are reminded of carrying out detection. According to the system, through the spot inspection of the product on the same day and the whole-course information tracing of the industrial chain, the management and control of the risk products and related products are realized, and the diffusion of the risk products is avoided.
Description
Technical Field
The invention relates to the field of intelligent detection, in particular to a risk early warning management system and method for monitoring livestock and poultry products.
Background
In recent years, the government has repeatedly come out of the platform and the agriculture has strong agricultural policy measures, the development of agricultural information service technology is gradually promoted, and the technologies of information acquisition, accurate operation and information management, remote digitization and visualization, food safety early warning and the like are developed in a key way, so that the production and management informatization of enterprises is continuously promoted.
At present, all nationwide provinces have traceable systems in terms of animal risk products, feeds, raw milk, veterinary drugs and the like, but the traceable and investigation problems are only limited to the problem that quality problems occur, so that the animal risk products, feeds, raw milk and veterinary drugs with quality problems cannot be controlled by the system for the first time, continue to diffuse outwards, or the traceable systems are incomplete, and various information cannot be comprehensively recorded, so that the traceability of the risk products is incomplete, omission is caused, and harm and loss are brought to society.
Disclosure of Invention
The invention aims to provide a risk early warning management system and method for monitoring livestock and poultry products, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a risk early warning management system for monitoring livestock and poultry products, comprising: the system comprises a database module, an information acquisition module, an intelligent extraction module, a data detection module, a risk analysis module, a data comparison module and a risk early warning module; the system comprises a database module, an intelligent extraction module, a data detection module, a risk analysis module, a data comparison module, a risk early warning module and a supervisory personnel, wherein the database module is used for storing information in the whole system, the information acquisition module is used for acquiring information stored in the database, the intelligent extraction module is used for automatically selecting enterprises for performing spot check, the data detection module is used for detecting extracted samples, the risk analysis module is used for performing risk analysis on detection data of the extracted samples, the data comparison module is used for comparing risk analysis data of the extracted samples with a standard threshold, and the risk early warning module is used for sending sample information of samples with risk indexes exceeding the standard threshold to the supervisory personnel to remind the supervisory personnel to perform check; the intelligent extraction module is connected with the data detection module, the data detection module is connected with the risk analysis module, the risk analysis module is connected with the data comparison module, the data comparison module is connected with the risk early warning module, the database module is connected with the information acquisition module, the information acquisition module is connected with the intelligent extraction module, the information acquisition module is connected with the data detection module, the information acquisition module is connected with the risk analysis module, the information acquisition module is connected with the data comparison module, and the information acquisition module is connected with the risk early warning module. The whole system realizes integration of product spot check, detection and risk early warning, improves efficiency and comprehensiveness of risk early warning, records information of all processing, transportation and detection in the middle of products from production places to markets, and ensures that all related risk products can be found after problems occur.
Further, the intelligent extraction module is used for obtaining the spot check score of a certain enterprise, and performing spot check on the current day product of the enterprise with the highest spot check score according to the formula:
T＝J+K+L
calculating a spot check score T of an enterprise A, wherein J represents an employee pressure index of the enterprise A, K represents a historical spot check qualification index of the enterprise A, L is a random index, L is randomly assigned when the spot check score of the enterprise A is calculated, the L value is between 0 and 1, and A represents any enterprise;
according to the formula:
calculating employee stress indexes J of the enterprise A, wherein c represents average annual income of the enterprise A employee, d represents average daily working time of the enterprise A employee, e represents average local annual average diet expense, g represents weight of the average daily working time of the enterprise A employee, f represents weight of the average annual income of the enterprise A employee, and h represents weight of daily diet expense proportion of the enterprise A employee;
according to the formula:
calculating a historical spot check qualification index K of an enterprise A, wherein a is as follows i Indicating the proportion of the problem sample in the ith detection of the enterprise A to all the problem samples, b i The ratio of the non-problem sample to all the non-problem samples in the ith detection is represented, n represents the historical sampling number of times of enterprise A, B i Indicating the number of problem samples in the ith detection of enterprise A, G i Indicating the number of samples without problems in the ith detection of the enterprise A, B T Representing the number of samples of all problems of enterprise A, G T Indicating the number of all problem-free samples for enterprise a.
Furthermore, the intelligent extraction module comprises a weight calculation module, wherein the weight calculation module is used for assigning the weight g occupied by the average daily working time of the staff of the enterprise A, the weight f occupied by the average annual income of the staff of the enterprise A and the weight h occupied by the daily diet indication proportion of the staff of the enterprise A through an entropy weight method.
Further, the risk analysis module comprises an animal product risk analysis module, an animal tissue risk analysis module and a circulation link animal product analysis module;
the animal product risk analysis module is used for calculating an animal product risk index according to the formula:
calculating risk index P of animal products x Wherein P is x Representing the risk index, px, of animal products of the x-th class i An animal product risk index representing the ith sample, n representing a total of n samples taken;
the animal tissue risk analysis module is used for calculating an animal tissue risk index according to the formula:
calculating animal tissue risk index P y Wherein P is y Represents the risk index, py, of the group y animal tissue i An animal tissue risk index representing the ith sample;
the circulation link animal product risk analysis module is used for calculating a circulation link animal product risk index according to the formula:
calculating risk index P of circulating link animal products z Wherein P is z Risk index, pz, representing the z-th class of animal product of a circulation loop i Representing the risk index of the animal product of the ith sample.
Further, the data comparison module reads the animal product risk index, the animal tissue risk index and the circulation link animal product risk index stored in the database, compares the animal product risk index, the animal tissue risk index and the circulation link animal product risk index calculated by the risk analysis module with the standard threshold values of the three risk indexes, and stores sample information of samples with the risk indexes exceeding the standard threshold values into the database; after the risk early warning module reads sample information of samples with risk indexes exceeding a standard threshold value stored in a database, the samples with the risk indexes exceeding the standard threshold value are marked as dangerous samples, information of veterinary drugs, fresh milk and feeds related to the dangerous samples is marked, and the sample information of the dangerous samples and the marked information of the veterinary drugs, the fresh milk and the feeds are sent to a supervisor to remind the supervisor to carry out inspection.
Further, the risk early warning management method for monitoring the livestock and poultry products comprises the following steps:
step S1: reading employee data and enterprise history spot check data of each enterprise in a database, and intelligently extracting one enterprise for detection;
step S2: reading animal product information, animal tissue information and circulation link animal product information of the enterprise on the same day extracted from the database, and extracting part of animal products, animal tissues and circulation link animal products for detection;
step S3: storing the detected data in a database for calling;
step S4: the detected animal product data, animal tissue data and circulation link animal product data are read for risk analysis, and animal product risk indexes, animal tissue risk indexes and circulation link animal product risk indexes are obtained and stored in a database;
step S5: reading an animal product risk index, an animal tissue risk index and a circulation link animal product risk index, comparing the animal product risk index, the animal tissue risk index and the circulation link animal product risk index with respective standard thresholds, and storing sample information of samples with risk indexes exceeding the standard thresholds into a database;
step S6: reading sample information of samples with risk indexes exceeding a standard threshold, reading information of veterinary drugs, raw fresh milk and feeds associated with the samples, performing risk marking on the samples with risk indexes exceeding the standard threshold and the veterinary drugs, raw fresh milk and feeds associated with the samples, sending the sample information of the samples with risk indexes exceeding the standard threshold and the information of the veterinary drugs, raw fresh milk and feeds associated with the samples to a supervisor, and reminding the supervisor to perform inspection.
Further, the intelligent extraction includes the following steps:
step S1: determining a certain enterprise, and calculating the spot check score of the enterprise;
step S2: reading average annual income c of staff of the enterprise, average daily working time d of staff, average annual local food expense e;
step S3: assigning a weight g occupied by the average daily working time of the enterprise staff, a weight f occupied by the average annual income of the enterprise staff and a weight h occupied by the daily diet expenditure proportion of the enterprise staff through an entropy weight method;
step S4: according to the formula:
calculating employee pressure index J of the enterprise;
step S5: reading the proportion a of the problem sample in the ith detection of the enterprise to all the problem samples i The proportion b of the non-problematic sample in the ith test to all non-problematic samples i The historical sampling number n of the enterprise and the number B of the problem samples in the ith detection of the enterprise i No-problem sample number G in ith detection of enterprise i Number of samples of all questions of the enterprise B T ，G T Number of samples G of the enterprise T ；
Step S6: according to the formula:
calculating a historical spot check qualification index K of the enterprise;
step S7: carrying out random assignment on the random index L;
step S8: according to the formula:
T＝J+K+L
calculating a spot check score T of the enterprise;
step S9: repeating the steps S1-S8, calculating and obtaining the spot check scores T of different enterprises, sequencing, and performing spot check on the enterprise with the highest spot check score T. Through the mode of firstly determining enterprises and then extracting products, the risk detection and early warning of products produced by the enterprises which are easy to be problematic can be increased, meanwhile, the supervision of the enterprises can be enhanced, and the enterprises can be promoted to correct the problems as soon as possible. And selecting relevant data qualified by the historical spot check of the enterprise, wherein the enterprise spot check index with more historical spot check problem times is higher. By adding analysis on the daily working pressure of workers, the daily average working time length, the average annual income and the daily diet expenditure of the workers are selected as reference data, and the higher the daily working time length of the workers is, the lower the average annual income is, the higher the daily diet expenditure is, the higher the spot check index of enterprises is, and the prevention of misoperation caused by overlong working time length or overlarge life pressure of the workers can be enhanced by adopting the calculation mode, so that the risk prevention and control capability of spot check is improved.
Further, the step S3 includes the following steps:
step S301: the average annual income of staff is used as a first characteristic value, the average daily working time is used as a second characteristic value, the average annual diet consumption expense ratio of local people of the enterprise is used as a third characteristic value, and n is acquired through a crawler acquisition tool 2 The first characteristic value, the second characteristic value and the third characteristic value of each employee;
step S302: normalization processing is carried out on all the characteristic values:
wherein x is ij The j characteristic value of the ith employee, i is less than or equal to n 2 ，j＝1,2,3；
Step S303: calculate the feature value of the ith employee in the jth feature valueSpecific gravity p of the occupancy ij
Step S304: calculating entropy value e of jth eigenvalue j ：
Wherein k=1/ln (n 2 )>0；
Step S305: calculating information entropy redundancy d j
d j ＝1-e j ；
Step S306: calculating the weight w of each characteristic value j ：
Step S307: and assigning a weight g occupied by the average daily working time of the enterprise staff, a weight f occupied by the average annual income of the enterprise staff and a weight h occupied by the daily diet expenditure proportion of the enterprise staff. By selecting the historical data of average daily working time, average annual income and daily diet expenditure of a large number of enterprise staff, carrying out data analysis on the data and distributing weights for the three characteristic values, the influence of the three characteristic values on staff work can be obtained more scientifically, and the management and control capability of risks is improved.
Further, risk analysis includes animal product risk analysis, animal tissue risk analysis, and circulation loop animal product analysis;
the risk analysis steps are as follows:
step S9-1: acquiring detected sample data;
step S9-2: by the formula
Calculating risk index P of animal products x Wherein px is i An animal product risk index representing the ith sample, n representing a total of n samples taken;
step S9-3: by the formula
Calculating animal tissue risk index P y Wherein py i An animal tissue risk index representing the ith sample;
step S9-4: by the formula
Calculating risk index P of circulating link animal products z Wherein pz i Representing the risk index of the animal product of the ith sample.
Compared with the prior art, the invention has the following beneficial effects: through the system of whole spot check, detection, analysis and early warning, the efficient risk early warning function has been realized to select the enterprise that has aimed at, improved the supervision to the enterprise that some have problems, carry out the processing of problem from the root, and carry out spot check at follow-up product whole journey, the link that appears the problem is located to the accuracy, the convenience is to seeking and handling the risk reason, also be favorable to the countermeasure to the problem, reduce the probability that appears similar problem later, improve animal product's safety, provide health guarantee for the consumer.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of steps of a risk early warning management method for monitoring livestock and poultry products according to the present invention;
FIG. 2 is a schematic diagram of intelligent extraction steps of a risk early warning management method for monitoring livestock and poultry products according to the present invention;
fig. 3 is a schematic diagram of a weight calculation step of a risk early warning management method for monitoring livestock and poultry products.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-3, the present invention provides the following technical solutions: a risk early warning management system for monitoring livestock and poultry products, comprising: the system comprises a database module, an information acquisition module, an intelligent extraction module, a data detection module, a risk analysis module, a data comparison module and a risk early warning module; the system comprises a database module, an intelligent extraction module, a data detection module, a risk analysis module, a data comparison module, a risk early warning module and a supervisory personnel, wherein the database module is used for storing information in the whole system, the information acquisition module is used for acquiring information stored in the database, the intelligent extraction module is used for automatically selecting enterprises for performing spot check, the data detection module is used for detecting extracted samples, the risk analysis module is used for performing risk analysis on detection data of the extracted samples, the data comparison module is used for comparing risk analysis data of the extracted samples with a standard threshold, and the risk early warning module is used for sending sample information of samples with risk indexes exceeding the standard threshold to the supervisory personnel to remind the supervisory personnel to perform check; the intelligent extraction module is connected with the data detection module, the data detection module is connected with the risk analysis module, the risk analysis module is connected with the data comparison module, the data comparison module is connected with the risk early warning module, the database module is connected with the information acquisition module, the information acquisition module is connected with the intelligent extraction module, the information acquisition module is connected with the data detection module, the information acquisition module is connected with the risk analysis module, the information acquisition module is connected with the data comparison module, and the information acquisition module is connected with the risk early warning module.
The intelligent extraction module is used for obtaining the spot check score of a certain enterprise, carrying out spot check on the current day product of the enterprise with the highest spot check score, and carrying out spot check according to the formula:
T＝J+K+L
calculating a spot check score T of an enterprise A, wherein J represents an employee pressure index of the enterprise A, K represents a historical spot check qualification index of the enterprise A, L is a random index, L is randomly assigned when the spot check score of the enterprise A is calculated, the L value is between 0 and 1, and A represents any enterprise;
according to the formula:
calculating employee stress indexes J of the enterprise A, wherein c represents average annual income of the enterprise A employee, d represents average daily working time of the enterprise A employee, e represents average local annual average diet expense, g represents weight of the average daily working time of the enterprise A employee, f represents weight of the average annual income of the enterprise A employee, and h represents weight of daily diet expense proportion of the enterprise A employee;
according to the formula:
calculating a historical spot check qualification index K of an enterprise A, wherein a is as follows i Indicating the proportion of the problem sample in the ith detection of the enterprise A to all the problem samples, b i The ratio of the non-problem sample to all the non-problem samples in the ith detection is represented, n represents the historical sampling number of times of enterprise A, B i Indicating the number of problem samples in the ith detection of enterprise A, G i Indicating the number of samples without problems in the ith detection of the enterprise A, B T Representing the number of samples of all problems of enterprise A, G T Representing all of enterprise ANumber of samples without problems.
The intelligent extraction module comprises a weight calculation module, wherein the weight calculation module is used for assigning the weight g occupied by the average daily working time of the staff of the enterprise A, the weight f occupied by the average annual income of the staff of the enterprise A and the weight h occupied by the daily diet indication proportion of the staff of the enterprise A through an entropy weight method.
The risk analysis module comprises an animal product risk analysis module, an animal tissue risk analysis module and a circulation link animal product analysis module;
the animal product risk analysis module is used for calculating an animal product risk index according to the formula:
calculating risk index P of animal products x Wherein P is x Representing the risk index, px, of animal products of the x-th class i An animal product risk index representing the ith sample, n representing a total of n samples taken;
the animal tissue risk analysis module is used for calculating an animal tissue risk index according to the formula:
calculating animal tissue risk index P y Wherein P is y Represents the risk index, py, of the group y animal tissue i An animal tissue risk index representing the ith sample;
the circulation link animal product risk analysis module is used for calculating a circulation link animal product risk index according to the formula:
calculating risk index P of circulating link animal products z Wherein P is z Representing the z-th class of a circulation linkRisk index, pz, of animal products i Representing the risk index of the animal product of the ith sample.
The data comparison module reads the animal product risk index, the animal tissue risk index and the circulation link animal product risk index stored in the database, compares the animal product risk index, the animal tissue risk index and the circulation link animal product risk index obtained by calculation of the risk analysis module with the standard threshold values of the three risk indexes, and stores sample information of samples with the risk indexes exceeding the standard threshold values into the database; after the risk early warning module reads sample information of samples with risk indexes exceeding a standard threshold value stored in a database, the samples with the risk indexes exceeding the standard threshold value are marked as dangerous samples, information of veterinary drugs, fresh milk and feeds related to the dangerous samples is marked, and the sample information of the dangerous samples and the marked information of the veterinary drugs, the fresh milk and the feeds are sent to a supervisor to remind the supervisor to carry out inspection.
The risk early warning management method for animal detection comprises the following steps:
step S1: reading employee data and enterprise history spot check data of each enterprise in a database, and intelligently extracting one enterprise for detection;
step S2: reading animal product information, animal tissue information and circulation link animal product information of the enterprise on the same day extracted from the database, and extracting part of animal products, animal tissues and circulation link animal products for detection;
step S3: storing the detected data in a database for calling;
step S4: the detected animal product data, animal tissue data and circulation link animal product data are read for risk analysis, and animal product risk indexes, animal tissue risk indexes and circulation link animal product risk indexes are obtained and stored in a database;
step S5: reading an animal product risk index, an animal tissue risk index and a circulation link animal product risk index, comparing the animal product risk index, the animal tissue risk index and the circulation link animal product risk index with respective standard thresholds, and storing sample information of samples with risk indexes exceeding the standard thresholds into a database;
step S6: reading sample information of samples with risk indexes exceeding a standard threshold, reading information of veterinary drugs, raw fresh milk and feeds associated with the samples, performing risk marking on the samples with risk indexes exceeding the standard threshold and the veterinary drugs, raw fresh milk and feeds associated with the samples, sending the sample information of the samples with risk indexes exceeding the standard threshold and the information of the veterinary drugs, raw fresh milk and feeds associated with the samples to a supervisor, and reminding the supervisor to perform inspection.
The intelligent extraction comprises the following steps:
step S1: determining a certain enterprise, and calculating the spot check score of the enterprise;
step S2: reading average annual income c of staff of the enterprise, average daily working time d of staff, average annual local food expense e;
step S3: assigning a weight g occupied by the average daily working time of the enterprise staff, a weight f occupied by the average annual income of the enterprise staff and a weight h occupied by the daily diet expenditure proportion of the enterprise staff through an entropy weight method;
step S4: according to the formula:
calculating employee pressure index J of the enterprise;
step S5: reading the proportion a of the problem sample in the ith detection of the enterprise to all the problem samples i The proportion b of the non-problematic sample in the ith test to all non-problematic samples i The historical sampling number n of the enterprise and the number B of the problem samples in the ith detection of the enterprise i No-problem sample number G in ith detection of enterprise i Number of samples of all questions of the enterprise B T ，G T Number of samples G of the enterprise T ；
Step S6: according to the formula:
calculating a historical spot check qualification index K of the enterprise;
step S7: carrying out random assignment on the random index L;
step S8: according to the formula:
T＝J+K+L
calculating a spot check score T of the enterprise;
step S9: repeating the steps S1-S8, calculating and obtaining the spot check scores T of different enterprises, sequencing, and performing spot check on the enterprise with the highest spot check score T.
The step S3 includes the steps of:
step S301: the average annual income of staff is used as a first characteristic value, the average daily working time is used as a second characteristic value, the average annual diet consumption expense ratio of local people of the enterprise is used as a third characteristic value, and n is acquired through a crawler acquisition tool 2 The first characteristic value, the second characteristic value and the third characteristic value of each employee;
step S302: normalization processing is carried out on all the characteristic values:
wherein x is ij The j characteristic value of the ith employee, i is less than or equal to n 2 ，j＝1,2,3；
Step S303: calculating the proportion p of the characteristic value of the ith employee in the jth characteristic value ij
Step S304: calculating entropy value e of jth eigenvalue j ：
Wherein k=1/ln (n 2 )>0；
Step S305: calculating information entropy redundancy d j
d j ＝1-e j ；
Step S306: calculating the weight w of each characteristic value j ：
Step S307: and assigning a weight g occupied by the average daily working time of the enterprise staff, a weight f occupied by the average annual income of the enterprise staff and a weight h occupied by the daily diet expenditure proportion of the enterprise staff.
In this embodiment, c=6.8, d=10, e=1.3, l=0.13, n=5, B 1 ＝1、B 2 ＝0、B 3 ＝1、B 4 ＝2、B 5 ＝0、G 1 ＝99、G 2 ＝100、G 3 ＝99、G 4 ＝98、G 5 =100, then
a 2 ＝0、/>
a 5 ＝0、
n 2 ＝10，x 11 ＝5.3、x 21 ＝5.1、x 31 ＝4.8、x 41 ＝5.4、x 51 ＝5.0、x 61 ＝4.9、x 71 ＝4.9、x 81 ＝5.1、x 91 ＝5.0、x 101 ＝5.2、x 12 ＝10、x 22 ＝11、x 32 ＝10、x 42 ＝11、x 52 ＝12、x 62 ＝8、x 72 ＝11、x 82 ＝9、x 92 ＝10、x 102 ＝8、x 13 ＝0.245、x 23 ＝0.255、x 33 ＝0.271、x 43 ＝0.241、x 53 ＝0.26、x 63 ＝0.265、x 73 ＝0.265、x 83 ＝0.255、x 93 ＝0.26、x 103 ＝0.25；
And carrying out normalization processing on the characteristic values: x is x 11 ＝0.83、x 21 ＝0.5、x 31 ＝0、x 41 ＝1、x 51 ＝0.33、x 61 ＝0.17、x 71 ＝0.17、x 81 ＝0.5、x 91 ＝0.33、x 101 ＝0.67、x 12 ＝0.5、x 22 ＝0.75、x 32 ＝0.5、x 42 ＝0.75、x 52 ＝1、x 62 ＝0、x 72 ＝0.75、x 82 ＝0.25、x 92 ＝0.5、x 102 ＝0、x 13 ＝0.15、x 23 ＝0.47、x 33 ＝1、x 43 ＝0、x 53 ＝0.64、x 63 ＝0.82、x 73 ＝0.82、x 83 ＝0.47、x 93 ＝0.64、x 103 ＝0.31；
Calculating the proportion of the characteristic value of the ith employee in the jth characteristic value: p is p 11 ＝0.105、p 21 ＝0.101、p 31 ＝0.095、p 41 ＝0.107、p 51 ＝0.099、p 61 ＝0.097、p 71 ＝0.097、p 81 ＝0.101、p 91 ＝0.099、p 101 ＝0.103、p 12 ＝0.1、p 22 ＝0.11、p 32 ＝0.1、p 42 ＝0.11、p 52 ＝0.12、p 62 ＝0.08、p 72 ＝0.11、p 82 ＝0.09、p 92 ＝0.1、p 102 ＝0.08、p 13 ＝0.095、p 23 ＝0.099、p 33 ＝0.106、p 43 ＝0.094、p 53 ＝0.101、p 63 ＝0.103、p 73 ＝0.103、p 83 ＝0.099、p 93 ＝0.101、p 103 ＝0.097；
Calculating entropy value of the j-th eigenvalue: e, e 1 ＝0.992、e 2 ＝0.986、e 3 ＝0.988；
Calculating information entropy redundancy: d, d 1 ＝0.008、d 2 ＝0.014、d 3 ＝0.012；
Calculating the weight of each characteristic value: w (w) 1 ＝0.24、w 2 ＝0.41、w 3 =0.35, i.e. f=0.24, g=0.41, h=0.35;
calculated k=0.24, j=0.07, t=0.44, the final spot check score for the enterprise is 0.44.
The risk analysis comprises animal product risk analysis, animal tissue risk analysis and circulation link animal product analysis;
the risk analysis steps are as follows:
step S9-1: acquiring detected sample data;
step S9-2: by the formula
Calculating risk index P of animal products x Wherein px is i An animal product risk index representing the ith sample, n representing a total of n samples taken;
step S9-3: by the formula
Calculating animal tissue risk index P y Wherein py i An animal tissue risk index representing the ith sample;
step S9-4: by the formula
Calculating risk index P of circulating link animal products z Wherein pz i Representing the risk index of the animal product of the ith sample.
In this embodiment, x takes a value of 1-6 and P is taken as 1 x Representative beef productsRisk index, P when x is taken to be 2 x Represents the risk index of mutton products, and P is taken as x is 3 x Represents the risk index of pork products, and P is taken as x 4 times x Represents the risk index of chicken products, and P is taken as x is 5 x Represents the risk index of the egg product, and P is taken when x is 6 x Representing a milk product risk index;
x＝2、n＝10、px 1 ＝0.1、px 2 ＝0.11、px 3 ＝0.13、px 4 ＝0.11、px 5 ＝0.08、px 6 ＝0.07、px 7 ＝0.09、px 8 ＝0.08、px 9 ＝0.11、px 10 =0.06, calculate P 2 ＝0.094；
y takes a value of 1-6, P when y takes 1 y Represents the risk index of muscle tissue, P when y is taken to be 2 y Representing liver tissue risk index, P when y is taken to be 3 y Represents the kidney tissue risk index, P when y is taken to be 4 y Representing the adipose tissue risk index, P at y-time of 5 y Represents the risk index of the egg tissue, and P is taken at 6 times by y y Representing a milk tissue risk index;
y＝3、n＝10、py 1 ＝0.08、py 2 ＝0.09、py 3 ＝0.1、py 4 ＝0.08、py 5 ＝0.07、py 6 ＝0.11、py 7 ＝0.1、py 8 ＝0.08、py 9 ＝0.09、py 10 =0.08, calculate P 3 ＝0.088；
z takes a value of 1-6, P when z takes 1 z Represents the risk index of beef products, P when z is taken to be 2 z Represents the risk index of mutton products, P is taken 3 times by z z Represents the risk index of pork products, and P is taken at 4 times by z z Represents the risk index of chicken products, and P is taken at 5 z z Represents the risk index of the egg product, and P is taken at 6 times in z z Representing a milk product risk index;
z＝1、n＝10、pz 1 ＝0.11、pz 2 ＝0.11、pz 3 ＝0.12、pz 4 ＝0.11、pz 5 ＝0.1、pz 6 ＝0.08、pz 7 ＝0.09、pz 8 ＝0.09、pz 9 ＝0.1、pz 10 =0.11, calculate P 1 ＝0.098。
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The utility model provides a risk early warning management system for monitoring of beasts and birds product which characterized in that includes: the system comprises a database module, an information acquisition module, an intelligent extraction module, a data detection module, a risk analysis module, a data comparison module and a risk early warning module; the system comprises a database module, an intelligent extraction module, a data detection module, a risk analysis module, a data comparison module, a risk early warning module and a supervisory personnel, wherein the database module is used for storing information in the whole system, the information acquisition module is used for acquiring information stored in the database, the intelligent extraction module is used for automatically selecting enterprises for performing spot check, the data detection module is used for detecting extracted samples, the risk analysis module is used for performing risk analysis on detection data of the extracted samples, the data comparison module is used for comparing risk analysis data of the extracted samples with a standard threshold, and the risk early warning module is used for sending sample information of samples with risk indexes exceeding the standard threshold to the supervisory personnel to remind the supervisory personnel to perform check; the intelligent extraction module is connected with the data detection module, the data detection module is connected with the risk analysis module, the risk analysis module is connected with the data comparison module, the data comparison module is connected with the risk early warning module, the database module is connected with the information acquisition module, the information acquisition module is connected with the intelligent extraction module, the information acquisition module is connected with the data detection module, the information acquisition module is connected with the risk analysis module, the information acquisition module is connected with the data comparison module, and the information acquisition module is connected with the risk early warning module.
2. The risk early warning management system for monitoring livestock and poultry products according to claim 1, wherein: the intelligent extraction module is used for obtaining the spot check score of a certain enterprise, carrying out spot check on the current day product of the enterprise with the highest spot check score, and carrying out spot check according to the formula:
T＝J+K+L
calculating a spot check score T of an enterprise A, wherein J represents an employee pressure index of the enterprise A, K represents a historical spot check qualification index of the enterprise A, L is a random index, L is randomly assigned when the spot check score of the enterprise A is calculated, the L value is between 0 and 1, and A represents any enterprise;
according to the formula:
calculating employee stress indexes J of the enterprise A, wherein c represents average annual income of the enterprise A employee, d represents average daily working time of the enterprise A employee, e represents average local annual average diet expense, g represents weight of the average daily working time of the enterprise A employee, f represents weight of the average annual income of the enterprise A employee, and h represents weight of daily diet expense proportion of the enterprise A employee;
according to the formula:
calculating a historical spot check qualification index K of an enterprise A, wherein a is as follows i Indicating the proportion of the problem sample in the ith detection of the enterprise A to all the problem samples, b i The ratio of the non-problem sample to all the non-problem samples in the ith detection is represented, n represents the historical sampling number of times of enterprise A, B i Indicating the number of problem samples in the ith detection of enterprise A, G i Indicating the number of samples without problems in the ith detection of the enterprise A, B T Representing the number of samples of all problems of enterprise A, G T Indicating the number of all problem-free samples for enterprise a.
3. The risk early warning management system for monitoring livestock and poultry products according to claim 2, wherein: the intelligent extraction module comprises a weight calculation module, wherein the weight calculation module is used for assigning the weight g occupied by the average daily working time of the staff of the enterprise A, the weight f occupied by the average annual income of the staff of the enterprise A and the weight h occupied by the daily diet indication proportion of the staff of the enterprise A through an entropy weight method.
4. The risk early warning management system for monitoring livestock and poultry products according to claim 1, wherein: the risk analysis module comprises an animal product risk analysis module, an animal tissue risk analysis module and a circulation link animal product analysis module;
the animal product risk analysis module is used for calculating an animal product risk index according to the formula:
calculating risk index P of animal products x Wherein P is x Representing the risk index, px, of animal products of the x-th class i An animal product risk index representing the ith sample, n representing a total of n samples taken;
the animal tissue risk analysis module is used for calculating an animal tissue risk index according to the formula:
calculating animal tissue risk index P y Wherein P is y Represents the risk index, py, of the group y animal tissue i An animal tissue risk index representing the ith sample;
the circulation link animal product risk analysis module is used for calculating a circulation link animal product risk index according to the formula:
calculating risk index P of circulating link animal products z Wherein P is z Risk index, pz, representing the z-th class of animal product of a circulation loop i Representing the risk index of the animal product of the ith sample.
5. The risk early warning management system for monitoring livestock and poultry products according to claim 4, wherein: the data comparison module reads the animal product risk index, the animal tissue risk index and the circulation link animal product risk index stored in the database, compares the animal product risk index, the animal tissue risk index and the circulation link animal product risk index obtained by calculation of the risk analysis module with the standard threshold values of the three risk indexes, and stores sample information of samples with the risk indexes exceeding the standard threshold values into the database; after the risk early warning module reads sample information of samples with risk indexes exceeding a standard threshold value stored in a database, the samples with the risk indexes exceeding the standard threshold value are marked as dangerous samples, information of veterinary drugs, fresh milk and feeds related to the dangerous samples is marked, and the sample information of the dangerous samples and the marked information of the veterinary drugs, the fresh milk and the feeds are sent to a supervisor to remind the supervisor to carry out inspection.
6. A risk early warning management method for monitoring livestock and poultry products is characterized in that: the risk early warning management method for monitoring the livestock and poultry products comprises the following steps:
step S1: reading employee data and enterprise history spot check data of each enterprise in a database, and intelligently extracting one enterprise for detection;
step S2: reading animal product information, animal tissue information and circulation link animal product information of the enterprise on the same day extracted from the database, and extracting part of animal products, animal tissues and circulation link animal products for detection;
step S3: storing the detected data in a database for calling;
step S4: the detected animal product data, animal tissue data and circulation link animal product data are read for risk analysis, and animal product risk indexes, animal tissue risk indexes and circulation link animal product risk indexes are obtained and stored in a database;
step S5: reading an animal product risk index, an animal tissue risk index and a circulation link animal product risk index, comparing the animal product risk index, the animal tissue risk index and the circulation link animal product risk index with respective standard thresholds, and storing sample information of samples with risk indexes exceeding the standard thresholds into a database;
step S6: reading sample information of samples with risk indexes exceeding a standard threshold, reading information of veterinary drugs, raw fresh milk and feeds associated with the samples, performing risk marking on the samples with risk indexes exceeding the standard threshold and the veterinary drugs, raw fresh milk and feeds associated with the samples, sending the sample information of the samples with risk indexes exceeding the standard threshold and the information of the veterinary drugs, raw fresh milk and feeds associated with the samples to a supervisor, and reminding the supervisor to perform inspection.
7. The risk early warning management method for monitoring livestock and poultry products according to claim 6, wherein the risk early warning management method comprises the following steps: the intelligent extraction comprises the following steps:
step S1: determining a certain enterprise, and calculating the spot check score of the enterprise;
step S2: reading average annual income c of staff of the enterprise, average daily working time d of staff, average annual local food expense e;
step S3: assigning a weight g occupied by the average daily working time of the enterprise staff, a weight f occupied by the average annual income of the enterprise staff and a weight h occupied by the daily diet expenditure proportion of the enterprise staff through an entropy weight method;
step S4: according to the formula:
calculating employee pressure index J of the enterprise;
step S5: reading the proportion a of the problem sample in the ith detection of the enterprise to all the problem samples i The proportion b of the non-problematic sample in the ith test to all non-problematic samples i The historical sampling number n of the enterprise and the number B of the problem samples in the ith detection of the enterprise i No-problem sample number G in ith detection of enterprise i Number of samples of all questions of the enterprise B T ，G T Number of samples G of the enterprise T ；
Step S6: according to the formula:
calculating a historical spot check qualification index K of the enterprise;
step S7: carrying out random assignment on the random index L;
step S8: according to the formula:
T＝J+K+L
calculating a spot check score T of the enterprise;
step S9: repeating the steps S1-S8, calculating and obtaining the spot check scores T of different enterprises, sequencing, and performing spot check on the enterprise with the highest spot check score T.
8. The risk early warning management method for monitoring livestock and poultry products according to claim 6, wherein the risk early warning management method comprises the following steps: the step S3 includes the steps of:
step S301: the average annual income of staff is used as a first characteristic value, the average daily working time is used as a second characteristic value, the average annual diet consumption expense ratio of local people of the enterprise is used as a third characteristic value, and n is acquired through a crawler acquisition tool 2 The first characteristic value, the second characteristic value and the third characteristic value of each employee;
step S302: normalization processing is carried out on all the characteristic values:
wherein x is ij The j characteristic value of the ith employee, i is less than or equal to n 2 ，j＝1,2,3；
Step S303: calculating the proportion p of the characteristic value of the ith employee in the jth characteristic value ij
Step S304: calculating entropy value e of jth eigenvalue j ：
Wherein k=1/ln (n 2 )>0；
Step S305: calculating information entropy redundancy d j
d j ＝1-e j ；
Step S306: calculating the weight w of each characteristic value j ：
Step S307: and assigning a weight g occupied by the average daily working time of the enterprise staff, a weight f occupied by the average annual income of the enterprise staff and a weight h occupied by the daily diet expenditure proportion of the enterprise staff.
9. The risk early warning management method for monitoring livestock and poultry products according to claim 6, wherein the risk early warning management method comprises the following steps: the risk analysis comprises animal product risk analysis, animal tissue risk analysis and circulation link animal product analysis;
the risk analysis steps are as follows:
step S9-1: acquiring detected sample data;
step S9-2: by the formula
Calculating risk index P of animal products x Wherein px is i An animal product risk index representing the ith sample, n representing a total of n samples taken;
step S9-3: by the formula
Calculating animal tissue risk index P y Wherein py i An animal tissue risk index representing the ith sample;
step S9-4: by the formula
Calculating risk index P of circulating link animal products z Wherein pz i Representing the risk index of the animal product of the ith sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211100849.7A CN116011802A (en) | 2022-09-09 | 2022-09-09 | Risk early warning management system and method for monitoring livestock and poultry products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211100849.7A CN116011802A (en) | 2022-09-09 | 2022-09-09 | Risk early warning management system and method for monitoring livestock and poultry products |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116011802A true CN116011802A (en) | 2023-04-25 |
Family
ID=86020023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211100849.7A Pending CN116011802A (en) | 2022-09-09 | 2022-09-09 | Risk early warning management system and method for monitoring livestock and poultry products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116011802A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117875987A (en) * | 2024-01-08 | 2024-04-12 | 重庆泰通动物药业有限公司 | Intelligent traceability system for veterinary drug safety information |
-
2022
- 2022-09-09 CN CN202211100849.7A patent/CN116011802A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117875987A (en) * | 2024-01-08 | 2024-04-12 | 重庆泰通动物药业有限公司 | Intelligent traceability system for veterinary drug safety information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111666269B (en) | Automatic coding and full-chain traceability system for big food safety data | |
| Besag et al. | Simple Monte Carlo tests for spatial pattern | |
| EFSA Panel on Animal Health and Welfare (AHAW) | Statement on the use of animal‐based measures to assess the welfare of animals | |
| CN113938503A (en) | Early warning system for diseases through live pig behavior sign monitoring and construction method | |
| CA2520679C (en) | System and method for collecting, processing and managing livestock data | |
| CN112116277A (en) | Full-chain food safety big data acquisition method | |
| Czycholl et al. | Review of the assessment of animal welfare with special emphasis on the “Welfare Quality® animal welfare assessment protocol for growing pigs” | |
| CN111695836B (en) | Clinical trial online operation management and control integrated system | |
| CN116151626B (en) | Risk management and control capability evaluating method, system, electronic equipment and storage medium | |
| Persson et al. | Analysing mortality patterns in salmon farming using daily cage registrations | |
| CN116011802A (en) | Risk early warning management system and method for monitoring livestock and poultry products | |
| CN115240060A (en) | Starfish disaster early warning method and system | |
| Moya et al. | Use of pattern recognition techniques for early detection of morbidity in receiving feedlot cattle | |
| CN117634752B (en) | Forestry pest quarantine information management system | |
| CN114298604A (en) | Intelligent comprehensive evaluation management system for incubator living enterprise based on big data dynamic monitoring analysis | |
| Hulsegge et al. | A time-series approach for clustering farms based on slaughterhouse health aberration data | |
| CN117787869A (en) | Germplasm resource warehousing and ex-warehouse method and device and terminal equipment | |
| Salamone et al. | Prediction of first test day milk yield using historical records in dairy cows | |
| McCosker et al. | Reproductive performance of northern Australia beef herds. 5. Factors influencing risk of non-pregnancy | |
| Arhipova et al. | Smart platform designed to improve poultry productivity and reduce greenhouse gas emissions | |
| Lupo et al. | Feasibility of screening broiler chicken flocks for risk markers as an aid for meat inspection | |
| CN114266478A (en) | Power transformation operation standardization comprehensive evaluation method and related device | |
| CN113408334A (en) | Crayfish full-chain data acquisition and intelligent detection method and device | |
| CN113052510A (en) | Management and control method for epidemic situation early warning and drug inventory supervision in animal husbandry industry | |
| CN116720666B (en) | Automatic monitoring method and system for ocean pasture based on big data |
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 |