Food additive safety detection analysis method and system based on Internet of Things

Abstract

The invention discloses a food additive safety detection analysis method and system based on the Internet of Things, and relates to the technical field of additive detection.The method comprises the following steps that produced food is selected as a sample, high performance liquid chromatography is used for testing additives in the food, and the structure, purity and content of the additives are obtained; simulating food states of additives with different contents under different temperature and humidity conditions according to a test result, and judging the storage safety of the food according to a simulation result; selecting the content ratio with the optimal storage performance according to the judgment result to formulate a production strategy, and adjusting the additive component in the food; acquiring the historical food sales volume by using the Internet of Things technology, estimating the daily intake of the crowd, and evaluating the safety risk value of the additive according to the production strategy; and determining the daily maximum intake of the food according to the safety risk value. According to the method, the safety risk of the additive is comprehensively evaluated by analyzing the sales volume and intake estimation.

Description

Technical Field

[0001] The present invention relates to the technical field of additive detection, and in particular to a food additive safety detection and analysis method and system based on the Internet of Things. Background Art

[0002] Food is any substance for human consumption, including beverages, processed foods, raw materials, additives and other consumer products. The main function of food is to provide nutrition to meet the basic needs of human survival and development, while food additives are substances added to food to improve its taste, appearance, shelf life or other qualities. The types and uses of additives are very wide, and they can be mainly divided into preservatives, antioxidants, colorants, flavor enhancers, stabilizers and emulsifiers.

[0003] In the modern food industry, the use of additives is common and necessary. They help ensure the safety, quality and long-term stability of food. At the same time, food additive testing is a key food safety measure to ensure that the use of additives in food meets safety standards and regulatory requirements. Commonly used testing methods include chromatography, mass spectrometry, infrared spectroscopy, atomic absorption spectroscopy, etc. Food additive testing is an important part of ensuring food safety and is of great significance to protecting consumer health and maintaining food market order.

[0004] However, the prior art can only measure the content of ingredients when testing additives, and cannot adjust the ingredients of the additives according to the temperature and humidity of the food storage. At the same time, excessive consumption of additives will have an impact on human health. If intake prompts are not set for consumers based on the added content of the additives, it will easily cause health risks due to excessive intake. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a food additive safety detection and analysis method and system based on the Internet of Things, so as to achieve the purpose of determining the optimal storage conditions and adjusting the additive content.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a food additive safety detection and analysis method based on the Internet of Things, the food additive safety detection and analysis method based on the Internet of Things comprises the following steps: S1. Select finished food as samples and use high performance liquid chromatography to test the additives in the food to obtain the structure, purity and content of the additives; S2. Simulate the state of food with different additive contents under different temperature and humidity conditions according to the test results, and judge the storage safety of the food according to the simulation results; S3. According to the judgment results, select the content ratio with the best storage performance to formulate a production strategy and adjust the amount of additives in the food; S4. Use IoT technology to obtain historical food sales to estimate people’s daily intake, and evaluate the safety risk value of additives based on production strategies; S5. Determine the maximum daily food intake based on the safety risk value, and include risk warnings on food packaging to remind purchasers of the intake.

[0007] Preferably, simulating the state of food with different contents of additives under different temperature and humidity conditions according to the test results, and judging the storage safety of the food according to the simulation results comprises the following steps: S21, selecting a simulation algorithm based on the test results to establish a simulation model based on the chemical properties of the additive and the change of the food matrix; S22, setting different additive contents in the variation simulation model, and inputting different temperature and depth conditions to simulate the actual storage environment; S23. After setting the input, run the model to observe the behavior of the additive and the state change of the food, record the simulation results, and evaluate the performance of the additive under different conditions based on the simulation results; S24. Determine the storage status of the food under different temperature and humidity conditions based on the evaluation results, and establish a storage change matrix to determine the safety of foods with different additive contents during storage.

[0008] Preferably, selecting a simulation algorithm according to the test results to establish a simulation model based on the chemical properties of the additive and the change of the food matrix includes the following steps: S211. Using the chemical propagation characteristics of additives to establish their oxidation equation and constitutive relationship equation, and combining the search algorithm to construct a multiphase discrete random medium model; S212, inputting the test results into a multiphase discrete random medium model, and outputting the chemical characteristics of the existing content additive; S213. Use a simulation algorithm to perform forward simulation on the chemical property results, and establish a change simulation model based on the simulation results to determine the change characteristics of the chemical properties of the additives and the food matrix.

[0009] Preferably, using the chemical propagation characteristics of the additive to establish its oxidation equation and constitutive relationship equation, and combining the search algorithm to construct a multiphase discrete random medium model includes the following steps: S2111. Determine the type of oxidation that occurs based on the propagation characteristics of the additive, and write the oxidation equation of the additive to describe the chemical oxidation reaction process of the additive; S2112. Determine the conditions for the reaction of the additive based on the test results of the additive, and construct a constitutive relationship equation to describe the oxidation reaction dynamics; S2113. Determine the reaction rate constant, redox potential and activation energy of the additive based on the oxidation equation and the constitutive relationship equation; S2114, searching for a threshold value set for the reaction rate along the maximum value direction according to the numerical distribution of the redox potential, and setting this part as the reaction value item, searching for a threshold value set for the activation energy along the minimum value direction, and setting this part as the activation value item; S2115, traverse all points in the grid to determine whether their attribute values ​​are the relative dielectric constant corresponding to the reaction rate. If the determination result is yes, no processing is performed. If the determination result is no, the relative dielectric constant of this point is set to the relative dielectric constant of the additive. S2116, dividing the preset model into a number of sub-grids with equal amplitude and numbering them, and calculating the reaction value and activation value in the grid to determine the normalization coefficient and substitute it into the normalization equation for iteration; S2117. After iteration, the reaction value and activation value are inferred based on the updated normalization coefficient, and used as the model threshold to reconstruct the model in the subgrid until the normalization coefficient is iterated to the preset value, and each subgrid is merged in sequence to complete the construction of the multiphase discrete random medium model.

[0010] Preferably, forward modeling the chemical property results using a simulation algorithm, and establishing a change simulation model based on the simulation results to determine the change characteristics of the chemical properties of the additive and the food matrix includes the following steps: S2131. Determine the initial state and boundary conditions of the simulation according to the machine learning model, input the chemical property results into the machine learning model, and divide the chemical property results into forward modeling steps; S2132, using a finite difference simulation algorithm and a forward modeling step size to perform a forward modeling of chemical property results, and establishing a change simulation model based on the forward modeling result data; S2133. Generate orthogonal test combinations with different forward modeling coefficients using statistical analysis software, and substitute the forward modeling coefficients into the change simulation model to solve the food change matrix, and obtain the change matrix data corresponding to the different forward modeling coefficients; S2134. Use genetic algorithm to construct the nonlinear mapping relationship between the chemical properties of additives and the forward coefficients, and substitute the change matrix data to determine the change characteristics of the chemical properties of additives and the food matrix.

[0011] Preferably, using the Internet of Things technology to obtain historical food sales to estimate the daily intake of the population, and evaluating the safety risk value of additives according to the production strategy includes the following steps: S41. Deploy IoT sensors at food sales points to record food sales data, upload the sales data to the database, and clean and integrate the sales data; S42. Using statistical methods to establish a sales model based on sales data to predict food sales trends and sales volumes, and using the data on the composition of food additives obtained through testing to establish a model for estimating the intake of additives by the population; S43. Construct a potential health risk assessment model based on the cumulative intake of additives based on population intake and pathological data, and determine the safety risk value of food under the production strategy.

[0012] Preferably, constructing a potential health risk assessment model based on the cumulative intake of additives according to population intake and pathological data, and determining the safety risk value of food under the production strategy includes the following steps: S431. Based on the population intake estimation results, pathological data are used to determine the food safety risk assessment indicators and construct an assessment indicator system using the morbid index cycle analysis method; S432. Establish a cumulative intake model based on population intake and additive content data, and set the weight value of the evaluation index in combination with the analytical method; S433. Design a risk assessment model based on the assessment algorithm and comprehensive method, and integrate the cumulative intake model with the risk assessment model to form a safety value solution model; S434. Add the content of additives under the production strategy as an input value to the safety value solution model to determine the food safety risk value.

[0013] Preferably, designing a risk assessment model based on the assessment algorithm and the comprehensive method, and integrating the cumulative intake model with the risk assessment model to synthesize a safety value solution model includes the following steps: S4331. Determine the input variables and output variables of the risk assessment model according to the comprehensive method, and determine the weight set and the initial state of the model; S4332. Set the evaluation credibility according to the initial state of the model, calculate the transition state when the risk occurs according to the credibility, and judge the similarity between the transition state and the initial state of the model; S4333. Output a risk assessment model by judging the assessment indicators under the changing state through an assessment algorithm, integrate the cumulative intake model with the risk assessment model, and set the integrated model as a food safety value solution model.

[0014] Preferably, the calculation formula for the transition state when the risk occurs is: ; In the formula, L Indicates the transition state value when the risk occurs. T k Indicates k Input variable values, K represents the weight set value, Yrepresents the credibility value, E k Indicates k Output variable value.

[0015] In a second aspect, the present invention further provides a food additive safety detection and analysis system based on the Internet of Things, the food additive safety detection and analysis system based on the Internet of Things includes an additive testing and analysis module, an additive status judgment module, a production ratio formulation module, an intake assessment module and a risk warning module; Among them, the additive testing and analysis module is connected to the additive status judgment module, the additive status judgment module is connected to the production ratio formulation module, the production ratio formulation module is connected to the intake assessment module, and the intake assessment module is connected to the risk warning module; The additive testing and analysis module is used to select finished food as samples and use high performance liquid chromatography to test the additives in the food to obtain the structure, purity and content of the additives; The additive state judgment module is used to simulate the state of food with different additive contents under different temperature and humidity conditions according to the test results, and judge the storage safety of the food according to the simulation results; The production ratio formulation module is used to select the content ratio with the best storage performance according to the judgment results to formulate production strategies and adjust the amount of additives in food; The intake assessment module is used to obtain historical food sales using IoT technology to estimate the daily intake of the population, and to assess the safety risk value of additives based on production strategies; The risk warning module is used to determine the maximum daily food intake based on the safety risk value, and to formulate risk warnings on food packaging to remind purchasers of intake.

[0016] The beneficial effects of the present invention are: 1. The present invention obtains the structure, purity and content of additives under the premise of testing food additives by high performance liquid chromatography, and simulates and predicts the influence of additives on the state of food under different temperature and humidity conditions according to the test results, helps to determine the optimal storage conditions to adjust the content of additives, optimizes food quality and safety according to actual conditions, and comprehensively evaluates the safety risks of additives by analyzing sales volume and intake estimates, thereby improving food safety, and informing consumers through risk warnings to improve consumers' awareness of food safety.

[0017] 2. The present invention establishes a model based on the chemical properties of additives and the food matrix to simulate the state of food with different amounts of additives under different temperature and humidity conditions, evaluates the stability of additives under various conditions, and judges the storage safety of food based on the simulation results, which helps companies identify and manage risk points in the food storage process and improve food safety.

[0018] 3. The present invention utilizes Internet of Things technology to obtain historical food sales to estimate the daily intake of the population. Based on the additive ingredient data and sales volume, it estimates the daily additive intake of the population, provides a more targeted risk assessment, and combines pathological data and intake models to evaluate the potential health risks of cumulative intake of additives. This can not only help companies evaluate the safety risk value of food based on production strategies, but also provide consumers with safety risk warnings to ensure that the amount of additives consumed by consumers is within a safe range and protect consumer health. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0020] Figure 1 is a flow chart of a food additive safety detection and analysis method based on the Internet of Things according to an embodiment of the present invention; Figure 2 The present invention is a block diagram of a food additive safety detection and analysis system based on the Internet of Things according to an embodiment of the present invention.

[0021] In the figure: 1. Additive testing and analysis module; 2. Additive status judgment module; 3. Production ratio formulation module; 4. Intake assessment module; 5. Risk warning module. DETAILED DESCRIPTION

[0022] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0023] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0024] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0026] See also Figure 1 The present invention provides a food additive safety detection and analysis method based on the Internet of Things, and the food additive safety detection and analysis method based on the Internet of Things comprises the following steps: S1. Select finished food as samples and use high performance liquid chromatography to test the additives in the food to obtain the structure, purity and content of the additives.

[0027] In this embodiment, the finished food is selected as a sample, and the additives in the food are tested by high performance liquid chromatography. The structure, purity and content of the additives include the following steps: Select representative samples from the finished food, dilute the food samples or treat them with specific solvents according to the test requirements, use appropriate solvents to extract additives from the food samples, and remove impurities in the samples through filtration, centrifugation, etc., so as to facilitate more accurate detection of additives.

[0028] Select a suitable chromatographic column based on the chemical properties of the target additive, prepare a suitable mobile phase, such as water, ethanol or acetonitrile, inject the treated sample into the HPLC, run the chromatography under controlled conditions, allow the sample to pass through the chromatographic column and interact with the mobile phase, and use a detector (including UV / visible detector, mass spectrometer, etc.) to detect the substances passing through the chromatographic column and record the data.

[0029] Identify the peaks representing additives in the chromatogram, determine the chemical structure of the additives in the sample by comparing the chromatographic data of known standards, calculate the amount of additives in the sample by comparing the peak area or peak height with the standard curve, interpret the obtained chromatographic data, and determine the type, purity and amount of the additives.

[0030] Among them, High-Performance Liquid Chromatography (HPLC) is an analytical technique used to separate, identify and quantify components in a mixture. This method is widely used in many fields such as food safety, drug analysis, environmental monitoring and chemical research. HPLC can effectively separate multiple components in complex mixtures. According to different application requirements, different types of detectors can be used, such as UV / visible light detectors, fluorescence detectors, mass spectrometer detectors, etc.

[0031] S2. Simulate the state of food with different amounts of additives under different temperature and humidity conditions based on the test results, and judge the storage safety of the food based on the simulation results.

[0032] In this embodiment, simulating the state of food with different additive contents under different temperature and humidity conditions according to the test results, and judging the storage safety of the food according to the simulation results includes the following steps: S21. Based on the test results, a simulation algorithm is selected to establish a simulation model based on the changes in the chemical properties of the additives and the food matrix.

[0033] Specifically, the simulation algorithm is selected according to the test results to establish a simulation model based on the chemical properties of the additive and the change of the food matrix, including the following steps: S211. The oxidation equation and constitutive relationship equation of the additive are established by using the chemical propagation characteristics of the additive, and a multiphase discrete random medium model is constructed in combination with the search algorithm.

[0034] Among them, the oxidation equation and constitutive relationship equation of the additive are established by using the chemical propagation characteristics, and the multiphase discrete random medium model is constructed by combining the search algorithm, including the following steps: S2111. Determine the type of oxidation that occurs based on the propagation characteristics of the additive, and write the oxidation equation of the additive to describe the chemical oxidation reaction process of the additive; S2112. Determine the conditions for the reaction of the additive based on the test results of the additive, and construct a constitutive relationship equation to describe the oxidation reaction dynamics; S2113. Determine the reaction rate constant, redox potential and activation energy of the additive based on the oxidation equation and the constitutive relationship equation; S2114, searching for a threshold value set for the reaction rate along the maximum value direction according to the numerical distribution of the redox potential, and setting this part as the reaction value item, searching for a threshold value set for the activation energy along the minimum value direction, and setting this part as the activation value item; S2115, traverse all points in the grid to determine whether their attribute values ​​are the relative dielectric constant corresponding to the reaction rate. If the determination result is yes, no processing is performed. If the determination result is no, the relative dielectric constant of this point is set to the relative dielectric constant of the additive. S2116, dividing the preset model into a number of sub-grids with equal amplitude and numbering them, and calculating the reaction value and activation value in the grid to determine the normalization coefficient and substitute it into the normalization equation for iteration; S2117. After iteration, the reaction value and activation value are inferred based on the updated normalization coefficient, and used as the model threshold to reconstruct the model in the subgrid until the normalization coefficient is iterated to the preset value, and each subgrid is merged in sequence to complete the construction of the multiphase discrete random medium model.

[0035] S212, input the test results into a multiphase discrete random medium model, and output the chemical characteristics of the existing content of the additive.

[0036] S213. Use a simulation algorithm to perform forward simulation on the chemical property results, and establish a change simulation model based on the simulation results to determine the change characteristics of the chemical properties of the additives and the food matrix.

[0037] Among them, using simulation algorithms to perform forward simulation on the chemical property results, and establishing a change simulation model based on the simulation results to determine the change characteristics of the chemical properties of the additives and the food matrix includes the following steps: S2131. Determine the initial state and boundary conditions of the simulation according to the machine learning model, input the chemical property results into the machine learning model, and divide the chemical property results into forward modeling steps; S2132, using a finite difference simulation algorithm and a forward modeling step size to perform a forward modeling of chemical property results, and establishing a change simulation model based on the forward modeling result data; S2133. Generate orthogonal test combinations with different forward modeling coefficients using statistical analysis software, and substitute the forward modeling coefficients into the change simulation model to solve the food change matrix, and obtain the change matrix data corresponding to the different forward modeling coefficients; S2134. Use genetic algorithm to construct the nonlinear mapping relationship between the chemical properties of additives and the forward coefficients, and substitute the change matrix data to determine the change characteristics of the chemical properties of additives and the food matrix.

[0038] S22. Setting different additive contents in the variation simulation model, and inputting different temperature and depth conditions to simulate the actual storage environment.

[0039] Specifically, setting different additive contents in the variation simulation model and inputting different temperature and depth conditions to simulate the actual storage environment includes the following steps: Different levels of additive content are set in the variation simulation model to simulate various situations that may actually exist, and different temperature conditions are set to simulate different environments in which food may be stored.

[0040] Input different humidity levels, run the simulation under set conditions, observe the behavior of additives in different environments, and record important data during the simulation, such as the stability of additives, reaction products, etc.

[0041] S23. After setting the input, run the model to observe the behavior of the additive and the state change of the food, record the simulation results, and evaluate the performance of the additive under different conditions based on the simulation results.

[0042] Specifically, after setting the input, running the model to observe the behavior of the additive and the state change of the food, recording the simulation results, and evaluating the performance of the additive under different conditions based on the simulation results include the following steps: After all parameters and conditions are set, start the simulation model and monitor the progress of the simulation in real time to ensure that the model operates as expected, record the reaction of the additive in the simulated environment and the state changes under different additive contents and environmental conditions.

[0043] Analyze the trends of additives and food states changing over time and conditions, compare the performance differences of additives and foods under different environmental conditions, and evaluate the performance of additives under different conditions.

[0044] S24. Determine the storage status of the food under different temperature and humidity conditions based on the evaluation results, and establish a storage change matrix to determine the safety of foods with different additive contents during storage.

[0045] Specifically, judging the storage status of food under different temperature and humidity conditions based on the evaluation results, and establishing a storage change matrix to judge the safety of food with different additive contents during storage includes the following steps: Analyze the simulation evaluation results, define the parameters in the matrix, such as temperature range, humidity range and additive content, and fill in the food safety and quality information under each condition combination in the matrix based on the evaluation results.

[0046] Analyze food safety and quality changes under different storage conditions, evaluate potential risks and problems under specific storage conditions, and evaluate the safety of foods with different additive contents under specific conditions based on the matrix results.

[0047] Therefore, by building a model based on the chemical properties of additives and the food matrix, we can simulate the state of food with different amounts of additives under different temperature and humidity conditions, evaluate the stability of additives under various conditions, and judge the storage safety of food based on the simulation results. This will help companies identify and manage risk points in the food storage process and improve food safety.

[0048] S3. Based on the judgment results, select the content ratio with the best storage performance to formulate a production strategy and adjust the amount of additives in food.

[0049] In this embodiment, the production strategy is formulated by selecting the content ratio with the best storage performance according to the judgment result, and the amount of additives in the food is adjusted, including the following steps: Based on the storage variation matrix and evaluation results, determine the best combination of additive content ratios in terms of storage performance, and adjust the production plan and formula based on the optimal content ratio to ensure the quality control strategy for additive content consistency and food safety.

[0050] Adjust the proportion of additives to meet the optimal content during food production, evaluate actual performance and quality during production, and conduct performance and safety tests on finished products.

[0051] S4. Use IoT technology to obtain historical food sales to estimate people’s daily intake, and evaluate the safety risk value of additives based on production strategies.

[0052] In this embodiment, using the Internet of Things technology to obtain the historical sales volume of food to estimate the daily intake of the population, and evaluating the safety risk value of the additives according to the production strategy includes the following steps: S41. Deploy IoT sensors at food sales points to record food sales data, upload the sales data to the database, and clean and integrate the sales data.

[0053] Specifically, IoT sensors are deployed at food sales points to record food sales data, and the sales data is uploaded to a database. Cleaning and integrating the sales data includes the following steps: Select IoT sensors based on the food sales data that needs to be monitored, install the sensors at the sales point, configure them appropriately to ensure accurate data recording, use the sensors to automatically record relevant data at the sales point, and set the sensors to regularly upload the collected data to a preset database.

[0054] Delete errors and duplications, clean and integrate the uploaded sales data to ensure that all data follows a unified format standard and convert the data into a structured format that is easy to analyze and process.

[0055] S42. Use statistical methods to establish a sales model based on sales data to predict food sales trends and sales volumes, and use the ingredient data of food additives obtained through testing to establish a model for estimating the intake of additives by the population.

[0056] Specifically, using statistical methods to establish a sales model based on sales data to predict the sales trend and sales volume of food, and using the component data of food additives obtained by detection to establish a population additive intake estimation model includes the following steps: Conduct basic statistical analysis based on historical sales data, analyze the correlation between different variables, such as the relationship between price and sales volume, determine the variables that affect sales volume and construct influencing features.

[0057] Select a machine learning model to build a sales model based on data characteristics and business needs, use historical sales data to train the model, and predict future sales trends and volumes based on the sales model.

[0058] Based on the detailed composition and content data of food additives, consumers' food consumption habits and quantity data are estimated, and the intake is determined based on the additive content and food consumption. A population additive intake estimation model is established using a statistical model to estimate the intake.

[0059] S43. Construct a potential health risk assessment model based on the population intake and pathological data under the premise of cumulative intake of additives, and determine the safety risk value of food under the production strategy.

[0060] Specifically, the potential health risk assessment model based on the cumulative intake of additives is constructed based on population intake and pathological data, and the safety risk value of food under the production strategy is determined, including the following steps: S431. Based on the population intake estimation results, pathological data are used to determine the food safety risk assessment indicators and construct an assessment indicator system using the pathological index cycle analysis method.

[0061] S432. Establish a cumulative intake model based on population intake and additive content data, and set the weight values ​​of evaluation indicators in combination with analytical methods.

[0062] S433. Design a risk assessment model based on the assessment algorithm and comprehensive method, and integrate the cumulative intake model with the risk assessment model to form a synthetic safety value solution model.

[0063] Among them, designing a risk assessment model based on the assessment algorithm and the comprehensive method, and integrating the cumulative intake model with the risk assessment model to synthesize a safety value solution model includes the following steps: S4331. Determine the input variables and output variables of the risk assessment model according to the comprehensive method, and determine the weight set and the initial state of the model; S4332. Set the evaluation credibility according to the initial state of the model, and calculate the transition state when the risk occurs according to the credibility, and judge the similarity between the transition state and the initial state of the model; S4333. Output a risk assessment model by judging the assessment indicators under the changing state through an assessment algorithm, integrate the cumulative intake model with the risk assessment model, and set the integrated model as a food safety value solution model.

[0064] Specifically, the calculation formula for the transition state when the risk occurs is: ; In the formula, L Indicates the transition state value when the risk occurs. T k Indicates k Input variable values, K represents the weight set value, Y represents the credibility value, E k Indicates k Output variable value.

[0065] S434. Add the content of additives under the production strategy as an input value to the safety value solution model to determine the food safety risk value.

[0066] Therefore, by using the Internet of Things technology to obtain historical food sales to estimate people's daily intake, and based on additive ingredient data and sales volume, estimate people's daily additive intake, provide more targeted risk assessments, and provide consumers with safety risk warnings to ensure that the amount of additives consumers consume is within a safe range and protect consumer health.

[0067] S5. Determine the maximum daily food intake based on the safety risk value, and include risk warnings on food packaging to remind purchasers of the intake.

[0068] In this embodiment, determining the maximum daily intake of food according to the safety risk value and formulating a risk warning on the food packaging to remind the purchaser of the intake includes the following steps: Collect safety data on food ingredients and additives, and based on the safety data, determine the safety risk value of various ingredients to obtain the maximum safe daily intake of specific ingredients in food.

[0069] Based on the results of the maximum safe intake, clear risk warning information is designed, and the risk warning information is integrated into the food packaging design to remind purchasers of intake.

[0070] See also Figure 2 The present invention also provides a food additive safety detection and analysis system based on the Internet of Things, which includes an additive testing and analysis module 1, an additive state judgment module 2, a production ratio formulation module 3, an intake assessment module 4 and a risk warning module 5; Among them, the additive testing and analysis module 1 is connected to the additive state judgment module 2, the additive state judgment module 2 is connected to the production ratio formulation module 3, the production ratio formulation module 3 is connected to the intake assessment module 4, and the intake assessment module 4 is connected to the risk warning module 5; The additive testing and analysis module 1 is used to select the finished food as a sample and test the additives in the food using high performance liquid chromatography to obtain the structure, purity and content of the additives; The additive state judgment module 2 is used to simulate the state of food with different additive contents under different temperature and humidity conditions according to the test results, and judge the storage safety of the food according to the simulation results; The production ratio formulation module 3 is used to select the content ratio with the best storage performance according to the judgment result to formulate the production strategy and adjust the amount of additives in the food; Intake assessment module 4 is used to obtain historical food sales using IoT technology to estimate the daily intake of the population, and to assess the safety risk value of additives based on production strategies; The risk warning module 5 is used to determine the maximum daily intake of food according to the safety risk value, and formulate risk warnings on the food packaging to remind the purchaser of the intake.

[0071] In summary, with the aid of the above technical scheme of the present invention, the present invention obtains the structure, purity and content of additives under the premise of testing food additives by high performance liquid chromatography, and simulates and predicts the influence of additives on the state of food under different temperature and humidity conditions according to the test results, helps determine the optimal storage conditions to adjust the content of additives, optimizes food quality and safety according to actual conditions, and at the same time, comprehensively evaluates the safety risks of additives by analyzing sales volume and intake estimates, thereby improving food safety, and informs consumers through risk warnings to improve consumers' awareness of food safety. The present invention establishes a model based on the chemical properties of additives and food matrices to simulate the state of food with different contents of additives under different temperature and humidity conditions, evaluates the stability of additives under various conditions, and judges the storage safety of food based on the simulation results, which helps enterprises identify and manage risk points in the food storage process and improve food safety. The present invention utilizes Internet of Things technology to obtain historical food sales to estimate the daily intake of the population, estimates the daily intake of additives of the population based on additive ingredient data and sales, provides a more targeted risk assessment, and combines pathological data and intake models to assess the potential health risks of cumulative intake of additives, thereby not only helping companies to assess the safety risk value of food based on production strategies, but also providing safety risk warnings to consumers to ensure that the amount of additives consumed by consumers is within a safe range, thereby protecting consumer health.

[0072] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0073] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A food additive safety detection and analysis method based on the Internet of Things, characterized in that: The food additive safety detection and analysis method based on the Internet of Things includes the following steps: S1. Select finished food as samples and use high performance liquid chromatography to test the additives in the food to obtain the structure, purity and content of the additives; S2. Simulate the state of food with different additive contents under different temperature and humidity conditions according to the test results, and judge the storage safety of the food according to the simulation results; S3. According to the judgment results, select the content ratio with the best storage performance to formulate a production strategy and adjust the amount of additives in the food; S4. Use IoT technology to obtain historical food sales to estimate people’s daily intake, and evaluate the safety risk value of additives based on production strategies; S5. Determine the maximum daily food intake based on the safety risk value, and include risk warnings on food packaging to remind purchasers of the intake.

2. The method for food additive safety detection and analysis based on the Internet of Things according to claim 1, characterized in that: The method of simulating the state of food with different additive contents under different temperature and humidity conditions according to the test results, and judging the storage safety of the food according to the simulation results comprises the following steps: S21, selecting a simulation algorithm based on the test results to establish a simulation model based on the chemical properties of the additive and the change of the food matrix; S22, setting different additive contents in the variation simulation model, and inputting different temperature and depth conditions to simulate the actual storage environment; S23. After setting the input, run the model to observe the behavior of the additive and the state change of the food, record the simulation results, and evaluate the performance of the additive under different conditions based on the simulation results; S24. Determine the storage status of the food under different temperature and humidity conditions based on the evaluation results, and establish a storage change matrix to determine the safety of foods with different additive contents during storage.

3. A food additive safety detection and analysis method based on the Internet of Things according to claim 2, characterized in that: The method of selecting a simulation algorithm according to the test results to establish a simulation model based on the chemical properties of the additive and the change of the food matrix includes the following steps: S211. Using the chemical propagation characteristics of additives to establish their oxidation equation and constitutive relationship equation, and combining the search algorithm to construct a multiphase discrete random medium model; S212, inputting the test results into a multiphase discrete random medium model, and outputting the chemical characteristics of the existing content additive; S213. Use a simulation algorithm to perform forward simulation on the chemical property results, and establish a change simulation model based on the simulation results to determine the change characteristics of the chemical properties of the additives and the food matrix.

4. A food additive safety detection and analysis method based on the Internet of Things according to claim 3, characterized in that: The method of using the chemical propagation characteristics of the additive to establish its oxidation equation and constitutive relationship equation, and combining the search algorithm to construct a multiphase discrete random medium model includes the following steps: S2111. Determine the type of oxidation that occurs based on the propagation characteristics of the additive, and write the oxidation equation of the additive to describe the chemical oxidation reaction process of the additive; S2112. Determine the conditions for the reaction of the additive based on the test results of the additive, and construct a constitutive relationship equation to describe the oxidation reaction dynamics; S2113. Determine the reaction rate constant, redox potential and activation energy of the additive based on the oxidation equation and the constitutive relationship equation; S2114, searching for a threshold value set for the reaction rate along the maximum value direction according to the numerical distribution of the redox potential, and setting this part as the reaction value item, searching for a threshold value set for the activation energy along the minimum value direction, and setting this part as the activation value item; S2115, traverse all points in the grid to determine whether their attribute values ​​are the relative dielectric constant corresponding to the reaction rate. If the determination result is yes, no processing is performed. If the determination result is no, the relative dielectric constant of this point is set to the relative dielectric constant of the additive. S2116, dividing the preset model into a number of sub-grids with equal amplitude and numbering them, and calculating the reaction value and activation value in the grid to determine the normalization coefficient and substitute it into the normalization equation for iteration; S2117. After iteration, the reaction value and activation value are inferred based on the updated normalization coefficient, and used as the model threshold to reconstruct the model in the subgrid until the normalization coefficient is iterated to the preset value, and each subgrid is merged in sequence to complete the construction of the multiphase discrete random medium model.

5. A food additive safety detection and analysis method based on the Internet of Things according to claim 4, characterized in that: The method of forward modeling the chemical property results using a simulation algorithm and establishing a change simulation model based on the simulation results to determine the change characteristics of the chemical properties of the additive and the food matrix includes the following steps: S2131. Determine the initial state and boundary conditions of the simulation according to the machine learning model, input the chemical property results into the machine learning model, and divide the chemical property results into forward modeling steps; S2132, using a finite difference simulation algorithm and a forward modeling step size to perform a forward modeling of chemical property results, and establishing a change simulation model based on the forward modeling result data; S2133. Generate orthogonal test combinations with different forward modeling coefficients using statistical analysis software, and substitute the forward modeling coefficients into the change simulation model to solve the food change matrix, and obtain the change matrix data corresponding to the different forward modeling coefficients; S2134. Use genetic algorithm to construct the nonlinear mapping relationship between the chemical properties of additives and the forward coefficients, and substitute the change matrix data to determine the change characteristics of the chemical properties of additives and the food matrix.

6. The method for food additive safety detection and analysis based on the Internet of Things according to claim 1, characterized in that: The method of using the Internet of Things technology to obtain the historical sales volume of food to estimate the daily intake of the population, and evaluating the safety risk value of the additive according to the production strategy includes the following steps: S41. Deploy IoT sensors at food sales points to record food sales data, upload the sales data to the database, and clean and integrate the sales data; S42. Using statistical methods to establish a sales model based on sales data to predict food sales trends and sales volumes, and using the data on the composition of food additives obtained through testing to establish a model for estimating the intake of additives by the population; S43. Construct a potential health risk assessment model based on the population intake and pathological data under the premise of cumulative intake of additives, and determine the safety risk value of food under the production strategy.

7. A food additive safety detection and analysis method based on the Internet of Things according to claim 6, characterized in that: The method of constructing a potential health risk assessment model based on the cumulative intake of additives according to population intake and pathological data, and determining the safety risk value of food under the production strategy includes the following steps: S431. Based on the population intake estimation results, pathological data are used to determine the food safety risk assessment indicators and construct an assessment indicator system using the morbid index cycle analysis method; S432. Establish a cumulative intake model based on population intake and additive content data, and set the weight value of the evaluation index in combination with the analytical method; S433. Design a risk assessment model based on the assessment algorithm and comprehensive method, and integrate the cumulative intake model with the risk assessment model to form a safety value solution model; S434. Add the content of additives under the production strategy as an input value to the safety value solution model to determine the food safety risk value.

8. The method for food additive safety detection and analysis based on the Internet of Things according to claim 7, characterized in that: The design of the risk assessment model based on the assessment algorithm and the comprehensive method, and the integration of the cumulative intake model and the risk assessment model to form a safety value solution model include the following steps: S4331. Determine the input variables and output variables of the risk assessment model according to the comprehensive method, and determine the weight set and the initial state of the model; S4332. Set the evaluation credibility according to the initial state of the model, and calculate the transition state when the risk occurs according to the credibility, and judge the similarity between the transition state and the initial state of the model; S4333. Output a risk assessment model by judging the assessment indicators under the changing state through an assessment algorithm, integrate the cumulative intake model with the risk assessment model, and set the integrated model as a food safety value solution model.

9. A food additive safety detection and analysis method based on the Internet of Things according to claim 8, characterized in that: The calculation formula for the transition state when the risk occurs is: ； In the formula, L Indicates the transition state value when the risk occurs; T k Indicates k Input variable values; K Represents the weight set value; Y represents the credibility value; E k Indicates k Output variable value.

10. A food additive safety detection and analysis system based on the Internet of Things, used to implement the food additive safety detection and analysis method based on the Internet of Things as described in any one of claims 1 to 9, characterized in that: The food additive safety detection and analysis system based on the Internet of Things includes an additive testing and analysis module, an additive status judgment module, a production ratio formulation module, an intake assessment module and a risk warning module; Wherein, the additive testing and analysis module is connected to the additive status judgment module, the additive status judgment module is connected to the production ratio formulation module, the production ratio formulation module is connected to the intake assessment module, and the intake assessment module is connected to the risk warning module; The additive testing and analysis module is used to select the finished food as a sample and test the additives in the food using high performance liquid chromatography to obtain the structure, purity and content of the additives; The additive state judgment module is used to simulate the state of food with different additive contents under different temperature and humidity conditions according to the test results, and judge the storage safety of the food according to the simulation results; The production ratio formulation module is used to select the content ratio with the best storage performance according to the judgment result to formulate a production strategy and adjust the amount of additives in the food; The intake assessment module is used to obtain historical food sales using IoT technology to estimate the daily intake of the population, and to assess the safety risk value of additives based on production strategies; The risk warning module is used to determine the maximum daily food intake according to the safety risk value, and formulate risk warnings on food packaging to remind purchasers of intake.

Images