Multi-parameter rapid screening food detection system

Abstract

The invention discloses a multi-parameter rapid screening food detection system, which relates to the technical field of food detection, and comprises the following steps: acquiring raw material production place information of screened food, and evaluating a pollution risk confidence index of the screened food; establishing a known pollutant knowledge database; original signal parameters of the screened food are collected, signal fingerprints corresponding to the original signal parameters are analyzed, pollution risk confidence indexes of the screened food are used as interference factors to be associated and matched with the known pollutant knowledge database, and a pollutant list of the screened food is generated; according to the pollutant list of the screened food, determining a corresponding detection mode of the pollutant list of the screened food, collecting characteristic parameter data of each pollutant list, and evaluating the comprehensive pollutant probability of the screened food; and judging whether the comprehensive pollutant probability of the screened food exceeds a preset food safety tolerance threshold value or not, and if yes, judging that shipment is not allowed. The method has the advantages that the detection efficiency is remarkably improved, and the detection cost is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of food detection, and in particular to a multi-parameter rapid screening food detection system. Background Art

[0002] Food testing refers to the process of qualitative or quantitative analysis of ingredients, contaminants, additives, microorganisms and other indicators in food raw materials, processed products and finished products through physical, chemical, biological or instrumental analysis to assess their safety, nutritional value, authenticity and compliance.

[0003] Existing food testing for contaminants is unable to meet the needs of simultaneous screening of multiple pollutants in complex matrix foods; and rapid screening of food testing relies on step-by-step operations and manual interpretation, which takes up to several hours for a single sample. This results in low efficiency of current screening food testing and is unable to meet the needs of rapid screening in large-scale food circulation links. Summary of the Invention

[0004] In order to solve the above technical problems, a multi-parameter rapid screening food detection system is provided. This technical solution solves the problem that the existing food detection mentioned above is difficult to meet the needs of simultaneous screening of multiple pollutants in complex matrix foods when detecting pollutants; and rapid screening of food detection relies on step-by-step operations and manual interpretation, and it takes up to several hours to detect a single sample, resulting in low efficiency of current screening food detection and inability to adapt to the rapid screening needs of large-scale food circulation links.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] A multi-parameter rapid screening food detection method comprising:

[0007] Obtain the origin information of the raw materials of the screened food, mark the potential contamination factors of the raw materials' origin information, and evaluate the contamination risk confidence index of the screened food;

[0008] Establish a knowledge database of known contaminants based on historical food safety incidents around the world;

[0009] Collect the original signal parameters of the screened food, analyze the signal fingerprint corresponding to the original signal parameters, use the contamination risk confidence index of the screened food as an interference factor, and associate and match it with the known contaminant knowledge database to generate a list of contaminants in the screened food;

[0010] According to the list of contaminants in the screened food, determine the corresponding detection method for the list of contaminants in the screened food, collect characteristic parameter data for each contaminant list, and evaluate the comprehensive contaminant probability of the screened food;

[0011] Determine whether the comprehensive contaminant probability of the screened food exceeds the predetermined food safety tolerance threshold. If not, determine that shipment is allowed; if so, determine that shipment is not allowed.

[0012] Furthermore, based on the raw material origin supply chain data of the screened food, historical contamination events in the raw material origin supply chain data are marked to determine the characteristic parameters of potential contamination factors of the screened food;

[0013] Obtain the geographic coordinate parameters of potential contamination factors of the screened food and associate them with the characteristic parameters of the potential contamination factors of the screened food to construct a historical contamination event distribution matrix;

[0014] Taking historical pollution events as label data, the mutual information value between each element in the historical pollution event distribution matrix and the label data is calculated, and the elements with positive correlation in mutual information value are screened out to obtain the set A of pollution factors positively correlated with historical pollution events.

[0015] Furthermore, normalization processing is performed on the set of pollution factors that are positively correlated with historical pollution events;

[0016] Calculate the standard deviation and correlation coefficient between the characteristic parameters of each pollution factor in the set of pollution factors positively correlated with historical pollution events;

[0017] Using the CRITIC objective weighting method, a weight is assigned to each pollution factor characteristic parameter according to the standard deviation and correlation coefficient between the characteristic parameters of each pollution factor in the set of pollution factors positively correlated with historical pollution events, and the weighted set B of pollution factors positively correlated with historical pollution events is obtained.

[0018] Furthermore, based on the Bayesian network, the weighted set of pollution factors of historical pollution events is used as input, and the pollution probability of the pollution factors of historical pollution events is used as output;

[0019] The contamination risk confidence index of the screened food is calculated based on the contamination probability of the contamination factors in historical contamination events and the characteristic parameter weight of each contamination factor in historical contamination events.

[0020] 5. A multi-parameter rapid screening food detection method according to claim 4, characterized in that:

[0021] Based on microfluidic chips, the original signal parameter data of the screened food is collected;

[0022] The PCA principal component analysis method is used to perform data dimension reduction on the original signal parameters of the screened food to obtain the original signal dimension reduction parameter data of the screened food;

[0023] According to the original signal dimension reduction parameter data of the screened food, the time domain and frequency domain eigenvalues of the original signal dimension reduction parameter data are extracted using the wavelet transform method to obtain the original signal fingerprint set of the screened food;

[0024] The contamination risk confidence index of the screened food is used as an interference factor to correct the original signal fingerprint set of the screened food, and the corrected signal fingerprint set of the screened food is obtained.

[0025] Furthermore, based on the known pollutant knowledge database, the standardized signal fingerprint corresponding to each pollutant is determined, and a standardized signal fingerprint set of known pollutants is established;

[0026] Using linear mapping, vector conversion is performed on the corrected signal fingerprint set of the screened food and the standardized signal fingerprint set of the known pollutants to obtain the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint vector set of the known pollutants;

[0027] Based on the cosine similarity formula, the contamination risk confidence index of the screened food is used as an interference factor, and the matching degree between the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint vector set of known pollutants is calculated to generate a list of contaminants in the screened food.

[0028] Further, based on the list of contaminants in the screened food and the corresponding detection method of the list of contaminants in the screened food, characteristic parameter data of the list of contaminants in the screened food are obtained;

[0029] Standardize the characteristic parameter data for the contaminant list of food to be screened;

[0030] Determine the characteristic toxicity weights of the list of contaminants in the screened food according to the contaminant toxicology data corresponding to the characteristic parameter data of the list of contaminants in the screened food;

[0031] Based on the matching degree between the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint vector set of known pollutants, the characteristic parameter data of each pollutant list of the screened food and the characteristic toxicity weight of each pollutant list of the screened food, the original sample data set of the screened food is packaged.

[0032] Furthermore, a single contaminant assessment model for food screening was established based on logistic regression;

[0033] Using the original sample data set of the screened food, a single contaminant assessment model for the screened food is trained to quantify the risk probability of each contaminant in the screened food;

[0034] The probability multiplication formula is used for correction and the risk probability of each contaminant in the screened food is integrated to obtain the comprehensive contaminant probability of the screened food.

[0035] Furthermore, a multi-parameter rapid screening food detection system includes:

[0036] Confidence module, knowledge base, pollutant inventory module, pollution rate assessment module, screening and judgment module;

[0037] The confidence module is used to obtain the origin information of the raw materials of the screened food, mark the potential contamination factors of the raw materials origin information, and evaluate the contamination risk confidence index of the screened food;

[0038] The knowledge base is used to establish a knowledge database of known contaminants based on global historical food safety incidents;

[0039] The contaminant list module is electrically connected to the knowledge base and the confidence module. The contaminant list module is used to collect the original signal parameters of the screened food, analyze the signal fingerprint corresponding to the original signal parameters, and use the contamination risk confidence index of the screened food as an interference factor to correlate and match it with the known contaminant knowledge database to generate a contaminant list for the screened food;

[0040] The contamination rate assessment module is electrically connected to the contaminant list module. The contamination rate assessment module is used to determine the corresponding detection method for the contaminant list of the screened food based on the contaminant list of the screened food, collect characteristic parameter data of each contaminant list, and assess the comprehensive contaminant probability of the screened food;

[0041] The screening and judgment module is electrically connected to the contamination rate assessment module. The screening and judgment module is used to judge whether the comprehensive contaminant probability of the screened food exceeds a predetermined food safety tolerance threshold. If not, it determines that shipment is allowed; if so, it determines that shipment is not allowed.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] This invention proposes a multi-parameter rapid food screening solution. By pre-setting dual food contaminant detection technology, it predicts potential risks based on raw material origin information and a historical contamination database. Signal fingerprints are then matched against a database of known contaminants to rapidly generate a list of contaminants for screening. Comprehensive testing of this list is then conducted, with characteristic data collected. The combined contamination probability is calculated and compared against safety thresholds to enable rapid decision-making. This solution significantly improves testing efficiency and optimizes testing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 The following is a flow chart of a multi-parameter rapid screening method for food detection;

[0045] Figure 2 This is a framework diagram of a multi-parameter rapid screening food detection system. DETAILED DESCRIPTION

[0046] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0047] Reference Figure 1 As shown, a multi-parameter rapid screening food detection method comprises:

[0048] Step 1: Obtain the origin information of the raw materials of the screened food, mark the potential contamination factors of the raw materials' origin information, and evaluate the contamination risk confidence index of the screened food;

[0049] The step 1 includes the following:

[0050] Step 101: Based on the raw material origin supply chain data of the screened food, mark the historical contamination events in the raw material origin supply chain data, and determine the characteristic parameters of potential contamination factors of the screened food;

[0051] Obtain the geographic coordinate parameters of potential contamination factors of the screened food and associate them with the characteristic parameters of the potential contamination factors of the screened food to construct a historical contamination event distribution matrix;

[0052] Taking historical pollution events as label data, we calculate the mutual information value between each element in the historical pollution event distribution matrix and the label data, filter out the elements with positive correlation in mutual information value, and obtain the set of pollution factors with positive correlation in historical pollution events A=[Z i1 ,Z i2 ,…,Z ij ]; among them, Z ij is the characteristic parameter value of the jth pollution factor that is positively correlated with the i-th pollution event in history;

[0053] Step 102: normalize the set of pollution factors positively correlated with historical pollution events;

[0054] Calculate the standard deviation and correlation coefficient between the characteristic parameters of each pollution factor in the set of pollution factors positively correlated with historical pollution events;

[0055] Using the CRITIC objective weighting method, we assign weights to each pollution factor characteristic parameter based on the standard deviation and correlation coefficient between the characteristic parameters of each pollution factor in the set of pollution factors positively associated with historical pollution events, and obtain the weighted set B of pollution factors positively associated with historical pollution events, as follows:

[0056]

[0057] Among them, W ijis the characteristic parameter weight of the jth pollution factor positively associated with the i-th pollution event in history, σ ij is the standard deviation between the characteristic parameters of the jth pollution factor that are positively correlated with the i-th pollution event in history, and rij is the correlation coefficient between the characteristic parameters of the jth pollution factor that are positively correlated with the i-th pollution event in history;

[0058] Step 103: Based on the Bayesian network, a weighted set of pollution factors of historical pollution events is used as input, and the pollution probability of the pollution factors of historical pollution events is used as output;

[0059] Based on the contamination probability of the contamination factors of historical contamination events and the characteristic parameter weight of each contamination factor of historical contamination events, the contamination risk confidence index of the screened food is calculated as follows:

[0060]

[0061] Where P is the confidence index of the contamination risk of the screened food, f() is the probability function, and Y is a binary random variable;

[0062] When using, combine the contents in 101 to 103.

[0063] As a further step, we achieve accurate food contamination risk assessment by binding historical pollution events with corresponding geographic information, performing mutual information screening, CRITIC weighting, and then performing Bayesian evaluation. First, we construct a historical pollution event distribution matrix based on origin supply chain data, and obtain a set of positively correlated pollution factors through mutual information screening. Then, we use the CRITIC method to calculate the objective weight of each factor to form a weighted feature set. Finally, we calculate the weighted contamination probability through a Bayesian network and generate a risk confidence index.

[0064] The beneficial effects are:

[0065] 1. Improve screening targeting through the temporal and spatial correlation of geographic information and pollution factors;

[0066] 2. Use mutual information-CRITIC double screening to ensure the objectivity of key factor identification;

[0067] 3. The evaluation model integrating Bayesian network and weight makes the risk quantification results applicable to large-scale real-time screening scenarios.

[0068] Step 2: Establish a knowledge database of known contaminants based on historical food safety incidents around the world.

[0069] Step 3: Collect the original signal parameters of the screened food, analyze the signal fingerprint corresponding to the original signal parameters, use the contamination risk confidence index of the screened food as an interference factor, and correlate and match it with the known contaminant knowledge database to generate a list of contaminants in the screened food;

[0070] The step three includes the following:

[0071] Step 301: Collecting raw signal parameter data of the screened food based on the microfluidic chip;

[0072] The PCA principal component analysis method is used to perform data dimension reduction on the original signal parameters of the screened food to obtain the original signal dimension reduction parameter data of the screened food;

[0073] According to the original signal dimension reduction parameter data of the screened food, the time domain and frequency domain eigenvalues of the original signal dimension reduction parameter data are extracted using the wavelet transform method to obtain the original signal fingerprint set of the screened food;

[0074] The contamination risk confidence index of the screened food is used as an interference factor to correct the original signal fingerprint set of the screened food to obtain the corrected signal fingerprint set of the screened food. The method is as follows:

[0075] C adjusted =C×(1+α·P)

[0076] Among them, C adjusted is the modified signal fingerprint set of the screened food, C is the original signal fingerprint set of the screened food, and α is the adjustment coefficient

[0077] As a further content, the value range of α for the adjustment coefficient is based on the least squares method to fit the influence curve of risk confidence on fingerprint signal matching error, and the α value that minimizes the misjudgment rate. This coefficient is essentially a coupling factor between risk confidence and fingerprint signal detection sensitivity;

[0078] Step 302: Based on the known pollutant knowledge database, determine the standardized signal fingerprint corresponding to each pollutant and build a standardized signal fingerprint set of known pollutants;

[0079] Using linear mapping, vector conversion is performed on the corrected signal fingerprint set of the screened food and the standardized signal fingerprint set of the known pollutants to obtain the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint vector set of the known pollutants;

[0080] Based on the cosine similarity formula, the contamination risk confidence index of the screened food is used as an interference factor. The matching degree between the set of corrected signal fingerprint vectors of the screened food and the set of standardized signal fingerprint vectors of known contaminants is calculated to generate a list of contaminants in the screened food. The method is as follows:

[0081]

[0082] Among them, List is the list of contaminants to be screened in food, U jis the jth pollutant standardized signal fingerprint vector in the set of known pollutant standardized signal fingerprint vectors, Sim j is the matching degree between the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint of the jth pollutant in the standardized signal fingerprint vector set of known pollutants, D is the standardized signal fingerprint vector set of known pollutants, τ0 is the benchmark threshold, β is the adjustment factor, and m is the total number of pollutant standardized signal fingerprint vectors.

[0083] When used, combine the content from 301 to 302:

[0084] As a further content, accurate screening of pollutants is achieved through the technical path of microfluidic chip-PCA dimensionality reduction-wavelet feature extraction-risk weight correction-dynamic cosine matching. First, multi-dimensional signal data is collected through the microfluidic chip, and the time-frequency domain features are extracted through PCA dimensionality reduction and wavelet transform to form a signal fingerprint; then the signal fingerprint is weighted and corrected using the pollution risk confidence index calculated in the early stage to enhance the sensitive signal of high-risk samples; finally, the corrected signal fingerprint is compared with the pollutant standard database through linear mapping and dynamically adjusted cosine similarity matching to generate a list.

[0085] The beneficial effects are:

[0086] 1. The combination of microfluidic chips and PCA-wavelet improves signal acquisition efficiency and feature expression capabilities, and reduces data redundancy compared to traditional methods;

[0087] 2. The risk confidence dual interference mechanism (signal correction + dynamic threshold) improves the detection rate of low-concentration pollutants;

[0088] 3. Standardized vector mapping ensures the comparability of results across different test batches. It is suitable for rapid screening on production lines and can accurately screen potential contaminants in food, optimizing the accuracy and efficiency of food safety testing.

[0089] Step 4: Determine the corresponding detection method for the contaminant list of the screened food based on the contaminant list of the screened food, collect characteristic parameter data for each contaminant list, and evaluate the comprehensive contaminant probability of the screened food;

[0090] The step 4 includes the following contents:

[0091] Step 401: Based on the list of contaminants in the screened food and the corresponding detection method of the list of contaminants in the screened food, characteristic parameter data of the list of contaminants in the screened food are obtained;

[0092] Standardize the characteristic parameter data for the contaminant list of food to be screened;

[0093] Determine the characteristic toxicity weights of the list of contaminants in the screened food according to the contaminant toxicology data corresponding to the characteristic parameter data of the list of contaminants in the screened food;

[0094] According to the matching degree between the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint vector set of the known contaminants, the characteristic parameter data of each contaminant list of the screened food, and the characteristic toxicity weight of each contaminant list of the screened food, the data are packaged into an original sample data set of the screened food;

[0095] Step 402: Establish a single contaminant assessment model for food screening based on logistic regression;

[0096] Using the original sample dataset of the screened food, a single contaminant assessment model for the screened food is trained to quantify the risk probability of each contaminant in the screened food as follows:

[0097]

[0098] Among them, R j is the risk probability of screening the jth contaminant in food, Sigmoid() is the logistic function, v j is the standardized characteristic parameter for the jth contaminant list of food to be screened, δ j is the regression coefficient of the jth pollutant inventory;

[0099] Using the probability multiplication formula to correct the risk of each contaminant in the screened food, the comprehensive contaminant probability of the screened food is obtained as follows:

[0100]

[0101] Among them, Risk is the comprehensive probability of contaminants in screened food, is the characteristic toxicity weight of the jth contaminant list for screening food.

[0102] When used, combine the content from 401 to 402:

[0103] As a further step, the technical path of multi-source data fusion-toxicity weight correction-logistic regression modeling is used to achieve accurate quantification of pollutant risks: first, quantitative characteristic parameters are obtained based on the pollutant list matching detection method, characteristic toxicity weights are assigned in combination with toxicological data, and the matching degree, detection data and toxicity weights are packaged into a standardized data set; then, a single pollutant risk probability model is constructed through logistic regression, and the toxicity weight and detection concentration are fused using the Sigmoid function to output the single pollutant risk probability, and the single pollutant risk probability is fused according to the probability multiplication formula to generate a comprehensive pollutant probability for the screened food.

[0104] The beneficial effects are:

[0105] 1. The coordinated correction of toxicity weights and test data makes risk assessment consistent with toxicological laws and avoids the limitations of relying solely on concentration judgment;

[0106] 2. The Logistic regression model is highly interpretable and supports threshold decision-making for risk probability, thus improving the accuracy of risk assessment.

[0107] 3. The standardized data packaging mechanism is compatible with results from multiple testing platforms and is suitable for the integration of heterogeneous data for rapid laboratory and on-site screening.

[0108] Step 5: Determine whether the comprehensive contaminant probability of the screened food exceeds the predetermined food safety tolerance threshold. If not, determine that shipment is allowed; if so, determine that shipment is not allowed.

[0109] Reference Figure 2 As shown, a multi-parameter rapid screening food detection system includes:

[0110] Confidence module, knowledge base, pollutant inventory module, pollution rate assessment module, screening and judgment module;

[0111] The confidence module is used to obtain the origin information of the raw materials of the screened food, mark the potential contamination factors of the raw materials origin information, and evaluate the contamination risk confidence index of the screened food;

[0112] The knowledge base is used to establish a knowledge database of known contaminants based on global historical food safety incidents;

[0113] The contaminant list module is electrically connected to the knowledge base and the confidence module. The contaminant list module is used to collect the original signal parameters of the screened food, analyze the signal fingerprint corresponding to the original signal parameters, and use the contamination risk confidence index of the screened food as an interference factor to correlate and match it with the known contaminant knowledge database to generate a contaminant list for the screened food;

[0114] The contamination rate assessment module is electrically connected to the contaminant list module. The contamination rate assessment module is used to determine the corresponding detection method for the contaminant list of the screened food based on the contaminant list of the screened food, collect characteristic parameter data of each contaminant list, and assess the comprehensive contaminant probability of the screened food;

[0115] The screening and judgment module is electrically connected to the contamination rate assessment module. The screening and judgment module is used to judge whether the comprehensive contaminant probability of the screened food exceeds a predetermined food safety tolerance threshold. If not, it determines that shipment is allowed; if so, it determines that shipment is not allowed.

[0116] In summary, the advantages of the present invention are:

[0117] The solution uses pre-defined dual food contaminant detection technology to predict potential risks using raw material origin information and a historical contamination database. It then uses signal fingerprints to match known contaminants against a database to quickly generate a list of contaminants for screening. It then conducts comprehensive testing on this list, collects characteristic data, and calculates a comprehensive contamination probability, comparing it to safety thresholds to enable rapid decision-making. This solution significantly improves testing efficiency and optimizes testing costs.

[0118] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-parameter rapid screening food detection method, characterized in that: include: Obtain the origin information of the raw materials of the screened food, mark the potential contamination factors of the raw materials' origin information, and evaluate the contamination risk confidence index of the screened food; Establish a knowledge database of known contaminants based on historical food safety incidents around the world; Collect the original signal parameters of the screened food, analyze the signal fingerprint corresponding to the original signal parameters, use the contamination risk confidence index of the screened food as an interference factor, and associate and match it with the known contaminant knowledge database to generate a list of contaminants in the screened food; According to the list of contaminants in the screened food, determine the corresponding detection method for the list of contaminants in the screened food, collect characteristic parameter data for each contaminant list, and evaluate the comprehensive contaminant probability of the screened food; Determine whether the comprehensive contaminant probability of the screened food exceeds the predetermined food safety tolerance threshold. If not, determine that shipment is allowed; if so, determine that shipment is not allowed.

2. A multi-parameter rapid screening food detection method according to claim 1, characterized in that: Based on the raw material origin supply chain data of the screened food, mark the historical contamination events in the raw material origin supply chain data and determine the characteristic parameters of potential contamination factors of the screened food; Obtain the geographic coordinate parameters of potential contamination factors of the screened food and associate them with the characteristic parameters of the potential contamination factors of the screened food to construct a historical contamination event distribution matrix; Taking historical pollution events as label data, the mutual information value between each element in the historical pollution event distribution matrix and the label data is calculated, and the elements with positive correlation in mutual information value are screened out to obtain the set A of pollution factors positively correlated with historical pollution events.

3. A multi-parameter rapid screening food detection method according to claim 2, characterized in that: Normalize the set of pollution factors positively correlated with historical pollution events; Calculate the standard deviation and correlation coefficient between the characteristic parameters of each pollution factor in the set of pollution factors positively correlated with historical pollution events; Using the CRITIC objective weighting method, a weight is assigned to each pollution factor characteristic parameter according to the standard deviation and correlation coefficient between the characteristic parameters of each pollution factor in the set of pollution factors positively correlated with historical pollution events, and the weighted set B of pollution factors positively correlated with historical pollution events is obtained.

4. A multi-parameter rapid screening food detection method according to claim 3, characterized in that: Based on the Bayesian network, the weighted set of pollution factors of historical pollution events is used as input, and the pollution probability of the pollution factors of historical pollution events is used as output; The contamination risk confidence index of the screened food is calculated based on the contamination probability of the contamination factors in historical contamination events and the characteristic parameter weight of each contamination factor in historical contamination events.

5. A multi-parameter rapid screening food detection method according to claim 4, characterized in that: Based on microfluidic chips, the original signal parameter data of the screened food is collected; The PCA principal component analysis method is used to perform data dimension reduction on the original signal parameters of the screened food to obtain the original signal dimension reduction parameter data of the screened food; According to the original signal dimension reduction parameter data of the screened food, the time domain and frequency domain eigenvalues of the original signal dimension reduction parameter data are extracted using the wavelet transform method to obtain the original signal fingerprint set of the screened food; The contamination risk confidence index of the screened food is used as an interference factor to correct the original signal fingerprint set of the screened food, and the corrected signal fingerprint set of the screened food is obtained.

6. A multi-parameter rapid screening food detection method according to claim 5, characterized in that: Based on the known pollutant knowledge database, determine the standardized signal fingerprint corresponding to each pollutant and establish a standardized signal fingerprint set of known pollutants; Using linear mapping, vector conversion is performed on the corrected signal fingerprint set of the screened food and the standardized signal fingerprint set of the known pollutants to obtain the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint vector set of the known pollutants; Based on the cosine similarity formula, the contamination risk confidence index of the screened food is used as an interference factor, and the matching degree between the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint vector set of known pollutants is calculated to generate a list of contaminants in the screened food.

7. A multi-parameter rapid screening food detection method according to claim 6, characterized in that: Based on the list of contaminants in the screened food and the corresponding detection method of the list of contaminants in the screened food, characteristic parameter data of the list of contaminants in the screened food are obtained; Standardize the characteristic parameter data for the contaminant list of food to be screened; Determine the characteristic toxicity weights of the list of contaminants in the screened food according to the contaminant toxicology data corresponding to the characteristic parameter data of the list of contaminants in the screened food; Based on the matching degree between the corrected signal fingerprint vector set of the screened food and the standardized signal fingerprint vector set of known pollutants, the characteristic parameter data of each pollutant list of the screened food and the characteristic toxicity weight of each pollutant list of the screened food, the original sample data set of the screened food is packaged.

8. A multi-parameter rapid screening food detection method according to claim 7, characterized in that: Based on logistic regression, a single contaminant assessment model for food screening was established; Using the original sample data set of the screened food, a single contaminant assessment model for the screened food is trained to quantify the risk probability of each contaminant in the screened food; The probability multiplication formula is used for correction and the risk probability of each contaminant in the screened food is integrated to obtain the comprehensive contaminant probability of the screened food.

9. A multi-parameter rapid screening food detection system comprising: Confidence module, knowledge base, pollutant inventory module, pollution rate assessment module, screening and judgment module; The confidence module is used to obtain the origin information of the raw materials of the screened food, mark the potential contamination factors of the raw materials origin information, and evaluate the contamination risk confidence index of the screened food; The knowledge base is used to establish a knowledge database of known contaminants based on global historical food safety incidents; The contaminant list module is electrically connected to the knowledge base and the confidence module. The contaminant list module is used to collect the original signal parameters of the screened food, analyze the signal fingerprint corresponding to the original signal parameters, and use the contamination risk confidence index of the screened food as an interference factor to correlate and match it with the known contaminant knowledge database to generate a contaminant list for the screened food; The contamination rate assessment module is electrically connected to the contaminant list module. The contamination rate assessment module is used to determine the corresponding detection method for the contaminant list of the screened food based on the contaminant list of the screened food, collect characteristic parameter data of each contaminant list, and assess the comprehensive contaminant probability of the screened food; The screening and judgment module is electrically connected to the contamination rate assessment module. The screening and judgment module is used to judge whether the comprehensive contaminant probability of the screened food exceeds a predetermined food safety tolerance threshold. If not, it determines that shipment is allowed; if so, it determines that shipment is not allowed.

Images