Food safety data evaluation method and system based on big data

Abstract

The invention discloses a food safety data evaluation method and system based on big data, and relates to the technical field of food safety, and the method comprises the following steps: collecting and preprocessing multi-party information data related to food, obtaining standardized data, integrating the standardized data, and carrying out the weighted calculation of the integrated standardized data, the method comprises the steps of obtaining basic data, establishing a food safety index evaluation model, obtaining a safety evaluation index of target food, and establishing a traceability chain for the target food in combination with related data and the safety evaluation index. The food safety data evaluation method is realized by setting food safety data evaluation based on big data, the basic data is acquired based on data of various sources and types of food, the food safety evaluation index is calculated, the food safety quality is conveniently and visually displayed, the food safety evaluation index is acquired through the data of multiple parties, and the food safety evaluation efficiency is improved. And the authenticity of the safety evaluation index is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of food safety, and in particular to a food safety data evaluation method and system based on big data. Background Art

[0002] Since food safety is directly related to social security and economic development, accurate analysis of food safety status is of great significance to reducing accident losses and improving the food safety control system. The current method for analyzing food safety status is usually to predict the risk status of food safety, but this method is difficult to evaluate food safety data, and it is not convenient to obtain food safety index data and display it intuitively. In addition, due to incomplete data involved in the analysis, the accuracy of the analysis results of existing food safety analysis is low.

[0003] The defects of existing food safety data evaluation are:

[0004] 1. The application document CN114186753A mainly considers how to quantitatively analyze food safety risks from the supply chain system, but does not consider how to obtain food safety index data;

[0005] 2. The patent document US20020161545A1 mainly considers how to improve the shelf life of food by obtaining the characteristic management of food, but does not consider how to improve the accuracy of data and calculation results;

[0006] 3. Patent document CN115964504A mainly considers the prediction of food safety risks, but does not consider how to analyze the correctness of the safety evaluation index and the issue of providing feedback to the data source regarding the safety evaluation index. Summary of the invention

[0007] The purpose of the present invention is to provide a food safety data evaluation method and system based on big data to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solution: a food safety data evaluation method based on big data, comprising the following steps:

[0009] S1: Collect multi-party information data about food, pre-process the information data according to source and / or type, and obtain standardized data;

[0010] S2: Aggregate standardized data by source and / or type;

[0011] S3: Perform weighted calculations on the integrated standardized data to obtain multiple groups of food safety grade index evaluation data, which are recorded as basic data;

[0012] S4: Establish a food safety index evaluation model, and obtain the safety evaluation index of the target food by inputting basic data into the food safety index evaluation model;

[0013] S5: Based on the information data, standardized data, basic data and safety evaluation index in S1, S2, S3 and S4, a traceability chain for target food is established based on blockchain technology.

[0014] Preferably, S1 includes establishing a digital information cloud platform based on big data and cloud computing technology, and the digital information cloud platform is used to receive and store multi-party information data and standardized data.

[0015] Preferably, the multi-party information data in S1 includes animal and plant growth environment data, agricultural product storage and transportation process data, food processing process data, and food periodic sampling test result data, wherein the food periodic sampling test includes the test of agricultural products before storage and transportation, the test of agricultural products before processing after storage and transportation, and the test of processed products;

[0016] The data on the growth environment of animals and plants include the growth region, regional soil composition, regional air composition and regional water quality composition; the sampling test result data of agricultural products in the non-storage and transportation state include the first-stage environmental pollutant test result data H1im, the first-stage pesticide residue test result data N1ix and the first-stage veterinary drug residue test result data S1io of multiple groups of samples; the storage and transportation process data of agricultural products include the storage and transportation method, storage and transportation duration and storage and transportation environment temperature and humidity data; the sampling test result data of agricultural products after storage and transportation but before processing include the second-stage environmental pollutant test result data H2im, the second-stage pesticide residue test result data N2ix, the second-stage veterinary drug residue test result data S2io and the second-stage newly added harmful microorganism test result data W2ip; the food processing process data include the processing type, processing process monitoring and the amount of additives used; the sampling test result data of processed products include the third-stage environmental pollutant test result data H3im, the third-stage pesticide residue test result data N3ix, the third-stage veterinary drug residue test result data S3io, the third-stage newly added harmful microorganism test result data W3ip and the third-stage food additive test result data T3iq;

[0017] Among them, i represents the number of food phase sampling and testing groups, m represents the number of environmental pollutant categories, x represents the number of pesticide categories, o represents the number of veterinary drug categories, p represents the number of newly added harmful microorganism categories, and q represents the number of food additive categories.

[0018] Preferably, S1 also includes identifying and processing multi-party information data through Outlier Detection technology, identifying outlier data, and analyzing and judging the true status of the outlier data, wherein when the outlier data is judged to be true data, the outlier data is retained and recorded as standardized data, and when the outlier data is judged to be false data, the outlier data is eliminated.

[0019] Preferably, the integration of the standardized data includes integrating plant growth environment data, agricultural product storage and transportation process data, and food processing process data into food safety index influencing factor data, and integrating food periodic sampling and testing result data into standardized data for calculation.

[0020] Preferably, the basic data acquisition process includes calculating the basic data Jh1 for the first-stage environmental pollutants based on the first-stage environmental pollutant detection result data H1im, and the calculation formula of Jh1 is as follows:

[0021]

[0022]

[0023] where ξ m represents the weight of the mth type of environmental pollutant index, and 0<<ξ m <<1, H1im represents the test result data of the mth type of environmental pollutants of the i-th group of sampled food in the first stage;

[0024] Based on the first-stage pesticide residue test result data N1in, the basic data Jn1 for the first-stage pesticide residue is calculated, and the calculation formula of Jn1 is as follows:

[0025]

[0026] where ψ x Represents the weight of the x-th category pesticide residue index, and 0<<ψ x <<1, N1ix represents the test result data of the xth type of pesticide residue in the i-th group of sampled food in the first stage;

[0027] Based on the first-stage veterinary drug residue test result data S1io, the basic data Js1 for the first-stage veterinary drug residue is calculated, and the calculation formula of Js1 is as follows:

[0028]

[0029] where ζ o Represents the weight of the oth category veterinary drug residue index, and 0<<ζ o <<1, S1io represents the test result data of the oth type of veterinary drug residue in the ith group of sampled food in the first stage;

[0030] The above calculation method is used to calculate the basic data Jh2 for the second-stage environmental pollutants based on the second-stage environmental pollutant detection result data H2im, calculate the basic data Jn2 for the second-stage pesticide residues based on the second-stage pesticide residue detection result data N2in, calculate the basic data Js2 for the second-stage veterinary drug residues based on the second-stage veterinary drug residue detection result data S2io, and calculate the basic data Jw2 for the second-stage newly added harmful microorganisms based on the second-stage newly added harmful microorganism detection result data W2ip, wherein the calculation formula of Jw2 is as follows:

[0031]

[0032] in represents the weight of the newly added harmful microorganism index of category p, and W1ip represents the test result data of harmful microorganisms of category p in food sampled and tested by group i in the second stage;

[0033] The above calculation method is used to calculate the basic data Jh3 for the third-stage environmental pollutants based on the third-stage environmental pollutant detection result data H3im, calculate the basic data Jn3 for the third-stage pesticide residues based on the third-stage pesticide residue detection result data N3in, calculate the basic data Js3 for the third-stage veterinary drug residues based on the third-stage veterinary drug residue detection result data S3io, calculate the basic data Jw3 for the third-stage new harmful microorganisms based on the third-stage new harmful microorganism detection result data W3ip, and calculate the basic data Jt3 for the third-stage food additives based on the third-stage food additive detection result data T3iq, where the calculation formula for Jt3 is:

[0034]

[0035] where λ p Indicates the weight of the qth food additive index, 0<<λ p <<1, J1ip represents the test result data of the qth type of food additives in the i-th group of sampled foods in the third stage, and the basic data obtained are classified and stored according to type and stage.

[0036] Preferably, the method for establishing a food safety index evaluation model and obtaining the safety evaluation index of the target food based on basic data is as follows:

[0037] Determine the influencing conditions of food safety index data and the basic data for evaluation, where the basic data include Jh1, Jn1, Js1, Jh2, Jn2, Js2, Jw2, Jh3, Jn3, Js3, Jw3 and Jt3;

[0038] Construct a food safety index evaluation model. The safety index evaluation model is as follows:

[0039] Zy=κ1Jhy+κ2Jny+κ3Jsy+κ4Jwy+κ5Jty

[0040] Wherein, Z is the food safety evaluation index data, y is the stage number, and y takes values ​​of 1, 2, and 3; Jhy is the basic data for environmental pollutants in the yth stage, κ1 is the indicator weight of environmental pollutants, Jny is the basic data for pesticide residues in the yth stage, κ2 is the indicator weight of pesticide residues, Jsy is the basic data for veterinary drug residues in the yth stage, κ3 is the indicator weight of veterinary drug residues, Jwy is the basic data for newly added harmful microorganisms in the yth stage, κ4 is the indicator weight of newly added harmful microorganisms, Jty is the basic data for food additives in the yth stage, and κ5 is the indicator weight of food additives.

[0041] Preferably, the step S4 further comprises calculating the index difference ΔZ between the food safety index data Z of adjacent stages, where ΔZ C =Z C -Z (C-1) , c is the number of stages, and c is 2 or 3. When ΔZ c ≠κ4Jwc+κ5Jtc, the reasons for the changes in the safety evaluation index are analyzed in combination with the data of factors affecting the food safety index.

[0042] Preferably, S5 also includes establishing a unique traceability code for the food, and the traceability code stores a safety evaluation index and diversity data of the corresponding food.

[0043] A food safety data evaluation system based on big data, the system includes a data processing module, a model building module, a safety data calculation module, a data analysis module and a traceability chain building module, and the data processing module, the model building module, the safety data calculation module, the data analysis module and the traceability chain building module are arranged in a digital information cloud platform;

[0044] The data processing module includes a data collection unit, a data cleaning unit, a data integration unit and a data storage unit, wherein the data collection unit is used to collect various information about food, the data cleaning unit is used to identify and pre-process the collected data to obtain standardized data, the data integration unit is used to integrate the standardized data according to source and / or type, and the data storage unit is used to store the standardized data;

[0045] The model building module includes a weight allocation unit, a basic data calculation unit and a safety evaluation index calculation unit. The weight allocation unit uses a weighting method that combines the AHP method and the entropy weight method to weight various basic data. The basic data calculation unit is used to obtain basic data based on standardized data and indicator weight calculations. The safety evaluation index calculation unit is used to establish a food safety index evaluation model based on a combination of hierarchical analysis method and fuzzy mathematics method, and obtain the safety evaluation index of the target food through the food safety index model.

[0046] The data analysis module is used to analyze the changes in the safety evaluation index and analyze the reasons for the changes in the safety evaluation index based on the changes in the safety evaluation index combined with multi-party information data;

[0047] The traceability chain construction module is used to build a traceability chain about the food’s growth environment, storage and transportation process, processing process, and phased sampling and testing process based on blockchain technology.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. The present invention sets up a food safety data evaluation based on big data to implement a food safety data evaluation method. Based on data from multiple sources and types of food, basic data is obtained and a food safety evaluation index is calculated, which is convenient for intuitively displaying food safety quality. The food safety evaluation index obtained through multi-party data improves the authenticity of the safety evaluation index.

[0050] 2. The present invention cleans multi-party information data to facilitate the acquisition of real data, and calculates standardized data by combining the AHP method with the entropy weight method to make the calculation result more accurate. A food safety index evaluation model is established based on the hierarchical analysis method and fuzzy mathematics to obtain a food safety evaluation index, thereby further improving the accuracy of the safety evaluation index.

[0051] 3. The present invention calculates the index difference according to the food safety evaluation index and determines the rationality of the index difference. Then, according to the unreasonable index difference combined with the food safety index influencing factor data, the reason for the change of the safety evaluation index is analyzed, and the reason is fed back to the relevant information supplier, so that the information supplier can make timely adjustments according to the cause of the change, thereby improving the information sharing of the system.

[0052] 4. The present invention achieves the purpose of traceability of food information by setting up a traceability chain for multi-party information data on food based on blockchain, while making it easier for consumers to obtain relevant information and safety evaluation indexes of food. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the overall method steps of the present invention;

[0054] Figure 2 It is the overall system structure diagram of the present invention;

[0055] Figure 3 It is a data transmission relationship diagram of the present invention;

[0056] Figure 4 This is a diagram of the module structure of the model construction of the present invention. DETAILED DESCRIPTION

[0057] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1 and Figure 2 , an embodiment provided by the present invention: a food safety data evaluation method based on big data, comprising the following steps:

[0059] S1: Collect multi-party information data about food, pre-process the information data according to source and / or type, and obtain standardized data;

[0060] S2: Aggregate standardized data by source and / or type;

[0061] S3: Perform weighted calculations on the integrated standardized data to obtain multiple groups of food safety grade index evaluation data, which are recorded as basic data;

[0062] S4: Establish a food safety index evaluation model, and obtain the safety evaluation index of the target food by inputting basic data into the food safety index evaluation model;

[0063] S5: Based on the information data, standardized data, basic data and safety evaluation index in S1, S2, S3 and S4, a traceability chain for target food is established based on blockchain technology.

[0064] Furthermore, food safety is displayed in the form of a safety evaluation index through S1, S2, S3 and S4, and the safety level is divided by dividing the index level, which is convenient for intuitively displaying the food safety level. At the same time, different safety levels can be distinguished by different colors, and the food safety level can be displayed in a diversified manner, which is convenient for the elderly to view. Through S1, S2, S3, S4 and S5, a traceability chain based on blockchain is established, which is convenient for tracing and viewing relevant information and data at each stage, realizing data transparency and traceability, and through blockchain technology, the possibility of data tampering is avoided, which is conducive to improving the data security of the traceability chain.

[0065] See also Figure 1 , Figure 2 and Figure 3 , an embodiment provided by the present invention: a food safety data evaluation system based on big data, the system includes a data processing module, a model building module, a safety data calculation module, a data analysis module and a traceability chain building module, and the data processing module, the model building module, the safety data calculation module, the data analysis module and the traceability chain building module are arranged in a digital information cloud platform;

[0066] The data processing module includes a data collection unit, a data cleaning unit, a data integration unit and a data storage unit, wherein the data collection unit is used to collect various information about food, the data cleaning unit is used to identify and pre-process the collected data to obtain standardized data, the data integration unit is used to integrate the standardized data according to source and / or type, and the data storage unit is used to store the standardized data;

[0067] The model building module includes a weight allocation unit, a basic data calculation unit and a safety evaluation index calculation unit. The weight allocation unit uses a weighting method that combines the AHP method and the entropy weight method to weight various basic data. The basic data calculation unit is used to obtain basic data based on standardized data and indicator weight calculations. The safety evaluation index calculation unit is used to establish a food safety index evaluation model based on a combination of hierarchical analysis method and fuzzy mathematics method, and obtain the safety evaluation index of the target food through the food safety index model.

[0068] The data analysis module is used to analyze the changes in the safety evaluation index and analyze the reasons for the changes in the safety evaluation index based on the changes in the safety evaluation index combined with multi-party information data;

[0069] The traceability chain construction module is used to build a traceability chain about the food’s growth environment, storage and transportation process, processing process, and phased sampling and testing process based on blockchain technology.

[0070] See also Figure 1, an embodiment provided by the present invention: a food safety data evaluation method based on big data, S1 includes establishing a digital information cloud platform based on big data and cloud computing technology, and the digital information cloud platform is used to receive and store multi-party information data and standardized data, and a food safety data evaluation system based on big data is set in the digital information cloud platform;

[0071] The multi-party information data in S1 include data on the growth environment of animals and plants, data on the storage and transportation process of agricultural products, data on the food processing process, and data on the results of periodic sampling and testing of food. The periodic sampling and testing of food includes testing of agricultural products before storage and transportation, testing of agricultural products before processing after storage and transportation, and testing of processed products.

[0072] The data on the growth environment of animals and plants include the growth region, regional soil composition, regional air composition and regional water quality composition; the sampling test result data of agricultural products in the non-storage and transportation state include the first-stage environmental pollutant test result data H1im, the first-stage pesticide residue test result data N1ix and the first-stage veterinary drug residue test result data S1io of multiple groups of samples; the storage and transportation process data of agricultural products include the storage and transportation method, storage and transportation duration and storage and transportation environment temperature and humidity data; the sampling test result data of agricultural products after storage and transportation but before processing include the second-stage environmental pollutant test result data H2im, the second-stage pesticide residue test result data N2ix, the second-stage veterinary drug residue test result data S2io and the second-stage newly added harmful microorganism test result data W2ip; the food processing process data include the processing type, processing process monitoring and the amount of additives used; the sampling test result data of processed products include the third-stage environmental pollutant test result data H3im, the third-stage pesticide residue test result data N3ix, the third-stage veterinary drug residue test result data S3io, the third-stage newly added harmful microorganism test result data W3ip and the third-stage food additive test result data T3iq;

[0073] Among them, i represents the number of food phase sampling and testing groups, m represents the number of environmental pollutant categories, x represents the number of pesticide categories, o represents the number of veterinary drug categories, p represents the number of newly added harmful microorganism categories, and q represents the number of food additive categories.

[0074] Furthermore, data from multiple parties are collected through the data processing module; data on the growth environment of animals and plants and data on the results of periodic sampling inspections of food are acquired from data interfaces of relevant government departments and agencies and government food safety inspection structures through the data acquisition unit; data on the storage and transportation process of agricultural products are acquired through the data acquisition unit using intelligent sensors and monitoring equipment; data on the food processing process are acquired through the data acquisition unit from archival records and monitoring equipment of the food processing party. Acquiring multiple types of data is conducive to improving the accuracy of obtaining the safety evaluation index.

[0075] See also Figure 2 An embodiment of the present invention is a food safety data evaluation method based on big data, wherein S1 also includes a data cleaning unit that identifies and processes multi-party information data through Outlier Detection technology, identifies outlier data, and analyzes and determines the true state of the outlier data, wherein when the outlier data is determined to be true data, the outlier data is selected to be retained and recorded as standardized data, and when the outlier data is determined to be false data, the outlier data is selected to be removed and the true data is recorded as standardized data, and the data integration unit integrates the plant growth environment data, agricultural product storage and transportation process data, and food processing process data in the standardized data into food safety index influencing factor data, and integrates the food periodic sampling test result data into standardized data for calculation.

[0076] Furthermore, the identification process of multi-party information data includes setting standard units of corresponding data for data types, constructing box plots or scatter plots of multi-party information data of the same type, source and stage in chronological order, identifying outlier data points that do not conform to the trend through an outlier detection algorithm, and separating the outlier data points from normal data points, analyzing the true state of the outlier data points in combination with the distribution characteristic trends on both sides of the data points and the monitoring information of the time points corresponding to the outlier data points, and when the outlier data points are judged to be false data, the outlier data points are eliminated, which is conducive to improving the authenticity of the information data and the authenticity of the safety evaluation index. At the same time, the cause of the false data is analyzed according to the monitoring information, for example, the false data is generated by measurement errors or generated under extreme circumstances or generated by human intervention and modification, and the false data and the cause of the generation are fed back to the data source to facilitate management by the data source.

[0077] See also Figure 1 , Figure 3 and Figure 4 The present invention provides an embodiment: a food safety data evaluation method based on big data, which calculates basic data based on standardized data. The basic data acquisition process includes calculating the basic data Jh1 for the first stage environmental pollutants based on the first stage environmental pollutant detection result data H1im, and the calculation formula of Jh1 is as follows:

[0078]

[0079]

[0080] where ξ m represents the weight of the mth type of environmental pollutant index, and 0<<ξ m <<1, H1im represents the test result data of the mth type of environmental pollutants of the i-th group of sampled food in the first stage;

[0081] Based on the first-stage pesticide residue test result data N1in, the basic data Jn1 for the first-stage pesticide residue is calculated, and the calculation formula of Jn1 is as follows:

[0082]

[0083] where ψ x Represents the weight of the x-th category pesticide residue index, and 0<<ψ x <<1, N1ix represents the test result data of the xth type of pesticide residue in the i-th group of sampled food in the first stage;

[0084] Based on the first-stage veterinary drug residue test result data S1io, the basic data Js1 for the first-stage veterinary drug residue is calculated, and the calculation formula of Js1 is as follows:

[0085]

[0086] where ζ o Represents the weight of the oth category veterinary drug residue index, and 0<<ζ o <<1, S1io represents the test result data of the oth type of veterinary drug residue in the ith group of sampled food in the first stage;

[0087] The above calculation method is used to calculate the basic data Jh2 for the second-stage environmental pollutants based on the second-stage environmental pollutant detection result data H2im, calculate the basic data Jn2 for the second-stage pesticide residues based on the second-stage pesticide residue detection result data N2in, calculate the basic data Js2 for the second-stage veterinary drug residues based on the second-stage veterinary drug residue detection result data S2io, and calculate the basic data Jw2 for the second-stage newly added harmful microorganisms based on the second-stage newly added harmful microorganism detection result data W2ip, wherein the calculation formula of Jw2 is as follows:

[0088]

[0089] in represents the weight of the newly added harmful microorganism index of category p, and W1ip represents the test result data of harmful microorganisms of category p in food sampled and tested by group i in the second stage;

[0090] The above calculation method is used to calculate the basic data Jh3 for the third-stage environmental pollutants based on the third-stage environmental pollutant detection result data H3im, calculate the basic data Jn3 for the third-stage pesticide residues based on the third-stage pesticide residue detection result data N3in, calculate the basic data Js3 for the third-stage veterinary drug residues based on the third-stage veterinary drug residue detection result data S3io, calculate the basic data Jw3 for the third-stage new harmful microorganisms based on the third-stage new harmful microorganism detection result data W3ip, and calculate the basic data Jt3 for the third-stage food additives based on the third-stage food additive detection result data T3iq, where the calculation formula for Jt3 is:

[0091]

[0092]

[0093] where λ p Indicates the weight of the qth food additive index, 0<<λ p <<1, J1ip represents the test result data of the qth type of food additives in the i-th group of sampled food in the third stage. The basic data obtained are classified and stored according to type and stage, and the allocation of indicator weights in the calculation process of the basic data is assigned by a weighting method that combines the AHP method with the entropy weight method.

[0094] Furthermore, by calculating the basic data in stages, it is convenient to calculate the safety evaluation index in the corresponding stage based on the basic data.

[0095] See also Figure 1 , Figure 3 and Figure 4 The present invention provides an embodiment: a food safety data evaluation method based on big data, S4 also includes a safety evaluation index calculation unit for establishing a food safety index evaluation model based on a hierarchical analysis method and a fuzzy mathematics method, and a method for obtaining a safety evaluation index of a target food based on basic data is as follows:

[0096] Determine the influencing conditions of food safety index data and the basic data for evaluation, where the basic data include Jh1, Jn1, Js1, Jh2, Jn2, Js2, Jw2, Jh3, Jn3, Js3, Jw3 and Jt3;

[0097] Construct a food safety index evaluation model. The safety index evaluation model is as follows:

[0098] Zy=κ1Jhy+κ2Jny+κ3Jsy+κ4Jwy+κ5Jty

[0099] Where Z is the food safety evaluation index data, y is the stage number, and y takes the values ​​of 1, 2, and 3, Jhy is the basic data of environmental pollutants for the yth stage, κ1 is the index weight of environmental pollutants, Jny is the basic data of pesticide residues for the yth stage, κ2 is the index weight of pesticide residues, Jsy is the basic data of veterinary drug residues for the yth stage, κ3 is the index weight of veterinary drug residues, Jwy is the basic data of newly added harmful microorganisms for the yth stage, κ4 is the index weight of newly added harmful microorganisms, Jty is the basic data of food additives for the yth stage, and κ5 is the index weight of food additives;

[0100] S4 also includes calculating the index difference ΔZ between the food safety index data Z of adjacent stages, where ΔZ C =Z C -Z (C-1) , c is the number of stages, and c is 2 or 3. When ΔZ c ≠κ4Jwc+κ5Jtc, the reasons for the changes in the safety evaluation index are analyzed in combination with the data of factors affecting the food safety index.

[0101] Furthermore, the food safety evaluation index of the corresponding stage is calculated after each stage through the food safety index evaluation model, and the safety level of the food can be judged according to the food safety evaluation index. At the same time, based on the food safety evaluation index of adjacent stages, the index difference is calculated, and it is judged whether the index difference is normal. When the index difference is not a normal difference, for example, the food safety evaluation index data of the first stage and the second stage are calculated to obtain the index difference ΔZ2 between the first stage and the second stage. When ΔZ2≠κ4Jw2+κ5Jt2, the agricultural product storage and transportation process data between the two stages are combined to analyze the reasons for the abnormal index difference, and feedback is given to the agricultural product storage and transportation management party to facilitate the adjustment of the agricultural product storage and transportation process.

[0102] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A food safety data evaluation method based on big data, characterized in that: The following steps are involved: S1: Collect multi-party information data about food, pre-process the information data according to source and / or type, and obtain standardized data; S2: Aggregate standardized data by source and / or type; S3: Perform weighted calculations on the integrated standardized data to obtain multiple groups of food safety grade index evaluation data, which are recorded as basic data; S4: Establish a food safety index evaluation model, and obtain the safety evaluation index of the target food by inputting basic data into the food safety index evaluation model; S5: Combine the information data, standardized data, basic data and safety evaluation index in S1, S2, S3 and S4, and establish a traceability chain for the target food based on blockchain technology.

2. A food safety data evaluation method based on big data according to claim 1, characterized in that: The S1 includes establishing a digital information cloud platform based on big data and cloud computing technology, and the digital information cloud platform is used to receive and store multi-party information data and standardized data.

3. A food safety data evaluation method based on big data according to claim 2, characterized in that: The multi-party information data in S1 include animal and plant growth environment data, agricultural product storage and transportation process data, food processing process data, and food periodic sampling test result data, wherein the food periodic sampling test includes the test of agricultural products before storage and transportation, the test of agricultural products before processing after storage and transportation, and the test of processed products; The data on the growth environment of animals and plants include the growth region, regional soil composition, regional air composition and regional water quality composition; the sampling test result data of agricultural products in the non-storage and transportation state include the first-stage environmental pollutant test result data H1im, the first-stage pesticide residue test result data N1ix and the first-stage veterinary drug residue test result data S1io of multiple groups of samples; the storage and transportation process data of agricultural products include the storage and transportation method, storage and transportation duration and storage and transportation environment temperature and humidity data; the sampling test result data of agricultural products after storage and transportation but before processing include the second-stage environmental pollutant test result data H2im, the second-stage pesticide residue test result data N2ix, the second-stage veterinary drug residue test result data S2io and the second-stage newly added harmful microorganism test result data W2ip; the food processing process data include the processing type, processing process monitoring and the amount of additives used; the sampling test result data of processed products include the third-stage environmental pollutant test result data H3im, the third-stage pesticide residue test result data N3ix, the third-stage veterinary drug residue test result data S3io, the third-stage newly added harmful microorganism test result data W3ip and the third-stage food additive test result data T3iq; Among them, i represents the number of food phase sampling and testing groups, m represents the number of environmental pollutant categories, x represents the number of pesticide categories, o represents the number of veterinary drug categories, p represents the number of newly added harmful microorganism categories, and q represents the number of food additive categories.

4. The food safety data evaluation method based on big data according to claim 1, characterized in that: The S1 also includes identifying and processing multi-party information data through Outlier Detection technology, identifying outlier data, and analyzing and judging the true status of the outlier data, wherein when the outlier data is judged to be true data, the outlier data is retained and recorded as standardized data, and when the outlier data is judged to be false data, the outlier data is eliminated.

5. A food safety data evaluation method based on big data according to claim 4, characterized in that: The integration of standardized data includes integrating plant growth environment data, agricultural product storage and transportation process data, and food processing process data into food safety index influencing factor data, and integrating food periodic sampling and testing result data into standardized data for calculation.

6. A food safety data evaluation method based on big data according to claim 5, characterized in that: The basic data acquisition process includes calculating the basic data Jh1 for the first-stage environmental pollutants based on the first-stage environmental pollutant detection result data H1im, and the calculation formula of Jh1 is as follows: in represents the weight of the mth type of environmental pollutant index, and m represents the test result data of the mth type of environmental pollutants of the ith group of sampled food in the first stage; Based on the first-stage pesticide residue test result data N1in, the basic data Jn1 for the first-stage pesticide residue is calculated, and the calculation formula of Jn1 is as follows: in represents the weight of the x-th pesticide residue index, and , N1ix represents the test result data of the xth type of pesticide residue in the i-th group of sampled food in the first stage; Based on the first-stage veterinary drug residue test result data S1io, the basic data Js1 for the first-stage veterinary drug residue is calculated, and the calculation formula of Js1 is as follows: in represents the weight of the oth category veterinary drug residue index, and It represents the test result data of the oth type veterinary drug residue in the ith group of sampled food in the first stage; The above calculation method is used to calculate the basic data Jh2 for the second-stage environmental pollutants based on the second-stage environmental pollutant detection result data H2im, calculate the basic data Jn2 for the second-stage pesticide residues based on the second-stage pesticide residue detection result data N2in, calculate the basic data Js2 for the second-stage veterinary drug residues based on the second-stage veterinary drug residue detection result data S2io, and calculate the basic data Jw2 for the second-stage newly added harmful microorganisms based on the second-stage newly added harmful microorganism detection result data W2ip, wherein the calculation formula of Jw2 is as follows: in p represents the weight of the newly added harmful microorganism index of category p, and W1ip represents the test result data of harmful microorganisms of category p in the food sampled and tested by group i in the second stage; The above calculation method is used to calculate the basic data Jh3 for the third-stage environmental pollutants based on the third-stage environmental pollutant detection result data H3im, calculate the basic data Jn3 for the third-stage pesticide residues based on the third-stage pesticide residue detection result data N3in, calculate the basic data Js3 for the third-stage veterinary drug residues based on the third-stage veterinary drug residue detection result data S3io, calculate the basic data Jw3 for the third-stage new harmful microorganisms based on the third-stage new harmful microorganism detection result data W3ip, and calculate the basic data Jt3 for the third-stage food additives based on the third-stage food additive detection result data T3iq, where the calculation formula for Jt3 is: in represents the weight of the qth category food additive index, It means that for the test result data of the qth type of food additive in the i-th group of sampled food in the third stage, the basic data obtained are classified and stored according to type and stage.

7. A food safety data evaluation method based on big data according to claim 6, characterized in that: The method for establishing a food safety index evaluation model and obtaining the safety evaluation index of the target food based on basic data is as follows: Determine the influencing conditions of food safety index data and the basic data for evaluation, including Jh1, Jn1, , Jh2, Jn2, , Jw2, Jh3, Jn3, 3. Jw3 and ; Construct a food safety index evaluation model. The safety index evaluation model is as follows: Where Z is the food safety evaluation index data, y is the stage number, and y takes values ​​of 1, 2, and 3. Basic data for environmental pollutants in stage y, 1 is the indicator weight of environmental pollutants, Basic data on pesticide residues for stage y, is the index weight of pesticide residues, Basic data on veterinary drug residues for Phase Y, The index weight of veterinary drug residues, Basic data for new harmful microorganisms in phase y, Add the indicator weights of harmful microorganisms, Basic data for food additives in phase y, is the indicator weight of food additives.

8. A food safety data evaluation method based on big data according to claim 7, characterized in that: The step S4 also includes calculating the index difference ∆Z between the food safety index data Z of adjacent stages, where , c is the number of stages, and c takes values ​​of 2 and 3. c+ When analyzing the reasons for changes in the safety evaluation index, we combined the data on factors affecting the food safety index.

9. The food safety data evaluation method based on big data according to claim 1, characterized in that: The S5 also includes establishing a single traceability code for the food, and the traceability code stores a safety evaluation index and diversity data of the corresponding food.

10. A food safety data evaluation system based on big data, used to implement the food safety data evaluation method based on big data according to claim 8, characterized in that: The system includes a data processing module, a model building module, a safety data calculation module, a data analysis module and a traceability chain building module, and the data processing module, the model building module, the safety data calculation module, the data analysis module and the traceability chain building module are arranged in a digital information cloud platform; The data processing module includes a data collection unit, a data cleaning unit, a data integration unit and a data storage unit, wherein the data collection unit is used to collect various information about food, the data cleaning unit is used to identify and pre-process the collected data to obtain standardized data, the data integration unit is used to integrate the standardized data according to source and / or type, and the data storage unit is used to store the standardized data; The model building module includes a weight allocation unit, a basic data calculation unit and a safety evaluation index calculation unit. The weight allocation unit uses a weighting method that combines the AHP method and the entropy weight method to weight various basic data. The basic data calculation unit is used to obtain basic data based on standardized data and indicator weight calculations. The safety evaluation index calculation unit is used to establish a food safety index evaluation model based on a combination of hierarchical analysis method and fuzzy mathematics method, and obtain the safety evaluation index of the target food through the food safety index model. The data analysis module is used to analyze the changes in the safety evaluation index and analyze the reasons for the changes in the safety evaluation index based on the changes in the safety evaluation index combined with multi-party information data; The traceability chain construction module is used to build a traceability chain about the food’s growth environment, storage and transportation process, processing process, and phased sampling and testing process based on blockchain technology.

Images