Food packaging environment compatibility evaluation method

Abstract

The invention discloses a food packaging environment compatibility evaluation method which comprises the following steps: collecting test data and environment data of food packaging, and preprocessing the test data and the environment data; performing stability analysis on the food package according to the test data to obtain stability, and performing screening influence analysis on the environmental data according to the stability to obtain an influence coefficient; performing adaptability analysis on the food bag according to the test data to obtain fitness, and constructing a food packaging environment compatibility evaluation model according to the fitness and the influence coefficient; and optimizing the food packaging environment compatibility evaluation model, inputting to-be-evaluated data into the food packaging environment compatibility evaluation model, and outputting an evaluation result. The method not only can improve the precision of food packaging environment compatibility evaluation, but also has good interpretability, and can be directly applied to an environment compatibility evaluation system.

Description

Technical Field

[0001] The invention relates to the field of evaluation, and in particular to a method for evaluating the environmental compatibility of food packaging. Background Art

[0002] In the modern food industry, food packaging is not only a barrier to protect food from physical damage, chemical pollution and microbial invasion, but also directly related to food quality and safety, shelf life and consumer health. With the increasing awareness of environmental protection and the requirement of sustainable development, the environmental compatibility of food packaging has become the focus of attention within and outside the industry. Environmental compatibility not only requires that packaging materials are harmless to food during use, but also needs to consider their impact on the environment during the entire life cycle of production, use, disposal and recycling.

[0003] Traditional food packaging evaluation methods focus on single-dimensional testing of packaging materials, such as physical properties, chemical stability and barrier properties, and lack a comprehensive assessment of the interaction between packaging and the specific use environment. For example, some packaging materials show excellent performance under laboratory conditions, but in actual storage, transportation or consumption environments, changes in environmental factors such as temperature, humidity, light, and gas composition may significantly affect their performance, thereby affecting the safety and quality of food.

[0004] In addition, existing environmental compatibility evaluation methods often lack systematic and quantitative standards, making it difficult to accurately reflect the complex interaction between packaging and the environment, and unable to provide a scientific basis for the improvement and selection of packaging materials. Therefore, it is particularly important to develop a systematic evaluation method that can comprehensively consider the performance of food packaging materials, environmental conditions of use, and their interaction. Summary of the invention

[0005] The object of the present invention is to provide a method for evaluating the environmental compatibility of food packaging.

[0006] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0007] The present invention comprises the following steps:

[0008] Collecting test data and environmental data of food packaging, and preprocessing the test data and the environmental data;

[0009] Performing stability analysis on the food package according to the test data to obtain stability, and performing screening impact analysis on the environmental data according to the stability to obtain a control coefficient;

[0010] Performing adaptability analysis on the food bag according to the test data to obtain a fitness degree, and constructing a food packaging environmental compatibility evaluation model according to the fitness degree and the regulation coefficient;

[0011] The food packaging environmental compatibility evaluation model is optimized, the data to be evaluated is input into the food packaging environmental compatibility evaluation model, and the evaluation result is output.

[0012] Furthermore, a method for performing stability analysis on the food package according to the test data to obtain stability includes:

[0013] Take the initial test data as a reference, conduct comparative analysis on the test data, and calculate the degree of change based on the comparative analysis:

[0014]

[0015] The ath test data of the cth test is y c,a , the ath test data of the zth test is y z,a , the number of test data is K, and the degree of change of test data y is D(y);

[0016] Calculate the stability based on the degree of change:

[0017]

[0018] The number of tests is The stability of the ath test data is φ a .

[0019] Furthermore, the method of obtaining the control coefficient by screening the environmental data and performing impact analysis according to the stability includes:

[0020] Calculate the information density of environmental data:

[0021]

[0022] The wth environmental data is b w , environmental data b w The information entropy is U(b w ), the number of environmental data is N w , the wth genetic factor is

[0023] Calculate the importance of environmental data based on information density:

[0024]

[0025] The environmental data b w The importance of Environmental datab w The contribution of The control constant is σ;

[0026] Calculate the correlation between environmental data and stability:

[0027]

[0028] The environmental data b w The weight of Environmental datab w The stability when it does not change is Environmental datab w The stability after the change is Resolution coefficient is μ, environmental data b w The correlation degree is

[0029] Sort the environmental data in descending order according to the correlation, and select the environmental data with a correlation greater than 0.353 as key data;

[0030] Calculate the control coefficient based on key data:

[0031]

[0032] The control coefficient of the wth key data is The number of tests is The error constant is τ, and the genetic coefficient of the wth key data is λ w , the L2 norm is ‖·‖2, and the correlation degree of the wth key data in the i-th test is θ i,w , the stability after the wth key data changes in the i-th test is The i-th test environment data b w The stability when it does not change is The number of key data is

[0033] Furthermore, the method of performing adaptability analysis on the food bag according to the test data to obtain the adaptability includes:

[0034] Divide the test data into multiple subsets according to the control coefficient, and calculate the neighborhood set of the test data:

[0035]

[0036] Among them The test data is The ath test data is y a , the number of test data in the bth subset is The jth subset of test data The adaptive neighborhood radius is Test Data and test data y a The Euclidean distance is The jth subset of test data The neighborhood set of The pth test data is y p ;

[0037] Compute adaptive neighborhood mutual information between subsets:

[0038]

[0039] The adaptive neighborhood mutual information between the jth subset and the qth subset is The jth subset of test data The neighborhood set of The union of the jth subset and the qth subset is j∪q, and the adaptive parameter is χ;

[0040] Calculate the weighted average redundancy of the test data:

[0041]

[0042] The ρth test data is k ρ , test data y a The mathematical expectation is F(y a ), test data The mathematical expectation is F(y a ), test data y a and the nearest neighbor test data y a The mathematical expectation of The ath test data cluster is E a , test data y a In the test data cluster β c The weighted average redundancy in is Z(y a ,E a ), the normalized neighborhood mutual information between the b-th subset and the v-th subset is The adjustment factor is Test data y a The mathematical expectation of the square is

[0043] The regression model is constructed according to the objective function, and the expression of the objective function is:

[0044]

[0045] The Frobenius norm of the matrix is The characteristic dimension of the jth group is g j , the regression coefficient of the zth test data is The regression coefficient of the jth test data is The kernel function is G, I, the regularization parameter is γ, and the objective function is

[0046] According to the penalty coefficient, calculate the fitness of the test data:

[0047]

[0048] The likelihood function is W, the number of valid parameters is N, and the fitness of the a-th test data is ζ a , the number of environmental compatibility indicators is M, the inhibition factor is χ, and the cth environmental compatibility indicator before the i-th test is Q i,c (y a ), the cth environmental compatibility index after the ith test is

[0049] Furthermore, a method for constructing a food packaging environmental compatibility evaluation model according to the fitness and the regulation coefficient includes:

[0050] Construct the objective function according to the error characteristics:

[0051]

[0052] The loss function is The penalty coefficient is ω, The error characteristic is The number of error characteristics is The objective function is The slack variable is η, and the control coefficient is The fitness is ζ;

[0053] Remote sensing data error correction models include random forest algorithms, autoencoders, and machine learning algorithms;

[0054] The random forest algorithm divides the input data into training data and test data in a ratio of 4:1;

[0055] The hierarchical clustering algorithm encodes the training data into a low-dimensional representation through unsupervised learning, and then reconstructs it into the original data, and learns the compressed feature representation of the training data to obtain feature data;

[0056] The machine learning algorithm captures the error value caused by the characteristic features through the variation, and adjusts the training data according to the error value to obtain the predicted evaluation value;

[0057] The hyperparameters of the food packaging environmental compatibility evaluation model were adjusted according to the mean square error between the predicted evaluation value data and the actual evaluation value. When the mean square error was less than 0.15, the adjustment was stopped.

[0058] Furthermore, the method for optimizing the food packaging environmental compatibility evaluation model comprises:

[0059] Compute the position of the searcher:

[0060]

[0061] The position of the initial search sub is The random number between 0 and 1 is r1, and the upper bound of the population space range is V u , the lower bound of the population space is V l ;

[0062] Update the position of the searcher, the expression is:

[0063]

[0064] The position of the v-th searcher in the t+1th iteration is The current evaluation number is fr, the random function is random(·), the random number is ε, and the maximum number of iterations is t max ;

[0065] Calculate the threshold:

[0066]

[0067] The threshold is th, the random number between 0 and 1 is r2, and the dynamic inertia weight coefficient is introduced, the expression is:

[0068]

[0069] The dynamic inertia weight coefficient of the t-th iteration is β(t), and the maximum value of the inertia weight is β max , the minimum value of inertia weight is β min ;

[0070] When the optimal individual is not updated, β=β+1, otherwise β=0. When the dynamic inertia weight coefficient is greater than the threshold, Levy flight is used to generate random search sub-positions. The expression is:

[0071]

[0072] The random search subposition of the tth iteration is The parameter of the stable distribution is d, the step size scaling factor is α, the random path of the Levy distribution with parameter d is l(d), and the optimal position of the searcher is The random position of the searcher is

[0073] The combined search sub-position is obtained according to the dynamic inertia weight coefficient and fitness, and the expression is:

[0074]

[0075] The updated search subposition of the tth iteration is The combined search subposition for the t+1th iteration is The fitness of the vth searcher is The global worst fitness is

[0076] Continue to iterate until the maximum number of iterations is reached, otherwise update the dynamic inertia weight coefficient of the searcher.

[0077] In a second aspect, an embodiment of the present application further provides an electronic device, including:

[0078] A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.

[0079] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.

[0080] The beneficial effects of the present invention are:

[0081] The present invention is a method for evaluating the environmental compatibility of food packaging. Compared with the prior art, the present invention has the following technical effects:

[0082] The present invention can improve the accuracy of food packaging environmental compatibility evaluation through pretreatment, stability analysis, screening analysis, adaptability analysis, model construction and model optimization steps, thereby improving the precision of food packaging environmental compatibility evaluation, optimizing food packaging environmental compatibility evaluation, greatly saving resources, improving work efficiency, realizing automatic evaluation of food packaging environmental compatibility, performing data fusion and model optimization on food packaging environmental compatibility evaluation in real time, having important significance for food packaging environmental compatibility evaluation, and adapting to food packaging environmental compatibility evaluation of different standards and different food packaging environmental compatibility evaluation requirements, and having certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 is a flow chart of the steps of the method for evaluating environmental compatibility of food packaging of the present invention;

[0084] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0085] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0086] The method for evaluating environmental compatibility of food packaging of the present invention comprises the following steps:

[0087] like Figure 1 As shown, in this embodiment, the following steps are included:

[0088] Collecting test data and environmental data of food packaging, and preprocessing the test data and the environmental data;

[0089] In the actual evaluation, XXX model of food packaging was used as the research object, and the test data included tensile strength, tear strength, compressive strength, oxygen permeability, water vapor permeability, heavy metal content, solvent residue, total bacteria count, and total mold count;

[0090] Environmental data includes temperature, humidity, and gas concentration;

[0091] Performing stability analysis on the food package according to the test data to obtain stability, and performing screening impact analysis on the environmental data according to the stability to obtain a control coefficient;

[0092] In the actual evaluation, the regulation coefficient is 0.264;

[0093] Performing adaptability analysis on the food bag according to the test data to obtain a fitness degree, and constructing a food packaging environmental compatibility evaluation model according to the fitness degree and the regulation coefficient;

[0094] In the actual evaluation, the fitness of the XXX model food packaging is 0.6174;

[0095] The food packaging environmental compatibility evaluation model is optimized, the data to be evaluated is input into the food packaging environmental compatibility evaluation model, and the evaluation result is output.

[0096] In this embodiment, the method for performing stability analysis on the food package according to the test data to obtain stability includes:

[0097] Take the initial test data as a reference, conduct comparative analysis on the test data, and calculate the degree of change based on the comparative analysis:

[0098]

[0099] The ath test data of the cth test is y c,a , the ath test data of the zth test is y z,a , the number of test data is K, and the degree of change of test data y is D(y);

[0100] Calculate the stability based on the degree of change:

[0101]

[0102] The number of tests is The stability of the ath test data is φ a .

[0103] In this embodiment, the method of performing screening impact analysis on the environmental data according to the stability to obtain the control coefficient includes:

[0104] Calculate the information density of environmental data:

[0105]

[0106] The wth environmental data is b w , environmental data b w The information entropy is U(b w ), the number of environmental data is N w , the wth genetic factor is

[0107] Calculate the importance of environmental data based on information density:

[0108]

[0109] The environmental data b w The importance of Environmental datab w The contribution of The control constant is σ;

[0110] Calculate the correlation between environmental data and stability:

[0111]

[0112] The environmental data b w The weight of Environmental datab w The stability when it does not change is Environmental datab w The stability after the change is Resolution coefficient is μ, environmental data b w The correlation degree is

[0113] Sort the environmental data in descending order according to the correlation, and select the environmental data with a correlation greater than 0.353 as key data;

[0114] Calculate the control coefficient based on key data:

[0115]

[0116] The control coefficient of the wth key data is The number of tests is The error constant is τ, and the genetic coefficient of the wth key data is λ w , the L2 norm is ‖·‖2, and the correlation degree of the wth key data in the i-th test is θ i,w , the stability after the wth key data changes in the i-th test is The i-th test environment data b w The stability when it does not change is The number of key data is

[0117] In this embodiment, the method of performing adaptability analysis on the food bag according to the test data to obtain the adaptability includes:

[0118] Divide the test data into multiple subsets according to the control coefficient, and calculate the neighborhood set of the test data:

[0119]

[0120] Among them The test data is The ath test data is y a , the number of test data in the bth subset is The jth subset of test data The adaptive neighborhood radius is Test Data and test data y a The Euclidean distance is The jth subset of test data The neighborhood set of The pth test data is y p ;

[0121] Compute adaptive neighborhood mutual information between subsets:

[0122]

[0123] The adaptive neighborhood mutual information between the jth subset and the qth subset is The jth subset of test data The neighborhood set of The union of the jth subset and the qth subset is j∪q, and the adaptive parameter is χ;

[0124] Calculate the weighted average redundancy of the test data:

[0125]

[0126] The ρth test data is k ρ , test data y aThe mathematical expectation is F(y a ), test data The mathematical expectation is F(y a ), test data y a and the nearest neighbor test data y a The mathematical expectation of The ath test data cluster is E a , test data y a In the test data cluster β c The weighted average redundancy in is Z(y a ,E a ), the normalized neighborhood mutual information between the b-th subset and the v-th subset is The adjustment factor is Test data y a The mathematical expectation of the square is

[0127] The regression model is constructed according to the objective function, and the expression of the objective function is:

[0128]

[0129] The Frobenius norm of the matrix is The characteristic dimension of the jth group is g j , the regression coefficient of the zth test data is The regression coefficient of the jth test data is The kernel function is G, I, the regularization parameter is γ, and the objective function is

[0130] According to the penalty coefficient, calculate the fitness of the test data:

[0131]

[0132] The likelihood function is W, the number of valid parameters is N, and the fitness of the a-th test data is ζ a , the number of environmental compatibility indicators is M, the inhibition factor is χ, and the cth environmental compatibility indicator before the i-th test is Q i,c (y a ), the cth environmental compatibility index after the ith test is

[0133] In actual evaluation, environmental compatibility indicators include tensile strength and elongation at break, barrier properties, sealing properties, heat seal strength, solvent residue, heavy metal content, additive migration, total bacteria and mold count, pathogenic bacteria detection, color change, odor change, dissolution or penetration, and chemical migration.

[0134] In this embodiment, the method for constructing a food packaging environmental compatibility evaluation model according to the fitness and the regulation coefficient includes:

[0135] Construct the objective function according to the error characteristics:

[0136]

[0137] The loss function is The penalty coefficient is ω, The error characteristic is The number of error characteristics is The objective function is The slack variable is η, and the control coefficient is The fitness is ζ;

[0138] Remote sensing data error correction models include random forest algorithms, autoencoders, and machine learning algorithms;

[0139] The random forest algorithm divides the input data into training data and test data in a ratio of 4:1;

[0140] The hierarchical clustering algorithm encodes the training data into a low-dimensional representation through unsupervised learning, and then reconstructs it into the original data, and learns the compressed feature representation of the training data to obtain feature data;

[0141] The machine learning algorithm captures the error value caused by the characteristic features through the variation, and adjusts the training data according to the error value to obtain the predicted evaluation value;

[0142] The hyperparameters of the food packaging environmental compatibility evaluation model were adjusted according to the mean square error between the predicted evaluation value data and the actual evaluation value. When the mean square error was less than 0.15, the adjustment was stopped.

[0143] In this embodiment, the method for optimizing the food packaging environmental compatibility evaluation model includes:

[0144] Compute the position of the searcher:

[0145]

[0146] The position of the initial search sub is The random number between 0 and 1 is r1, and the upper bound of the population space range is V u , the lower bound of the population space is V l ;

[0147] Update the position of the searcher, the expression is:

[0148]

[0149] The position of the v-th searcher in the t+1th iteration is The current evaluation number is fr, the random function is random(·), the random number is ε, and the maximum number of iterations is t max ;

[0150] Calculate the threshold:

[0151]

[0152] The threshold is th, the random number between 0 and 1 is r2, and the dynamic inertia weight coefficient is introduced, the expression is:

[0153]

[0154] The dynamic inertia weight coefficient of the t-th iteration is β(t), and the maximum value of the inertia weight is β max , the minimum value of inertia weight is β min ;

[0155] When the optimal individual is not updated, β=β+1, otherwise β=0. When the dynamic inertia weight coefficient is greater than the threshold, Levy flight is used to generate random search sub-positions. The expression is:

[0156]

[0157] The random search subposition of the tth iteration is The parameter of the stable distribution is d, the step size scaling factor is α, the random path of the Levy distribution with parameter d is e(d), and the optimal position of the searcher is The random position of the searcher is

[0158] The combined search sub-position is obtained according to the dynamic inertia weight coefficient and fitness, and the expression is:

[0159]

[0160] The updated search subposition of the tth iteration is The combined search subposition for the t+1th iteration is The fitness of the vth searcher is The global worst fitness is

[0161] Continue to iterate until the maximum number of iterations is reached, otherwise update the dynamic inertia weight coefficient of the searcher.

[0162] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0163] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0164] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0165] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a food packaging environmental compatibility evaluation device at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the aforementioned food packaging environmental compatibility evaluation methods.

[0166] The above application Figure 1The method for evaluating the environmental compatibility of food packaging disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0167] The electronic device may also perform Figure 1 Evaluation method for environmental compatibility of food packaging in China, and achieve Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0168] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, any of the aforementioned food packaging environmental compatibility evaluation methods is executed.

[0169] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0170] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0171] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0173] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0174] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0175] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0176] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0177] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0178] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating environmental compatibility of food packaging, characterized in that: The following steps are involved: Collecting test data and environmental data of food packaging, and preprocessing the test data and the environmental data; Performing stability analysis on the food package according to the test data to obtain stability, and performing screening impact analysis on the environmental data according to the stability to obtain a control coefficient; Performing adaptability analysis on the food bag according to the test data to obtain a fitness degree, and constructing a food packaging environmental compatibility evaluation model according to the fitness degree and the regulation coefficient; The food packaging environmental compatibility evaluation model is optimized, the data to be evaluated is input into the food packaging environmental compatibility evaluation model, and the evaluation result is output.

2. The method for evaluating environmental compatibility of food packaging according to claim 1, characterized in that: The method for performing stability analysis on the food package according to the test data to obtain stability comprises: Take the initial test data as a reference, conduct comparative analysis on the test data, and calculate the degree of change based on the comparative analysis: The ath test data of the cth test is y c,a , the ath test data of the zth test is y z,a , the number of test data is K, and the degree of change of test data y is D(y); Calculate the stability based on the degree of change: The number of tests is The stability of the ath test data is φ a .

3. The method for evaluating environmental compatibility of food packaging according to claim 1, characterized in that: The method of performing screening and impact analysis on the environmental data according to the stability to obtain a control coefficient includes: Calculate the information density of environmental data: The wth environmental data is b w , environmental data b w The information entropy is U(b w ), the number of environmental data is N w , the wth genetic factor is Calculate the importance of environmental data based on information density: The environmental data b w The importance of Environmental datab w The contribution of The control constant is σ; Calculate the correlation between environmental data and stability: The environmental data b w The weight of Environmental datab w The stability when it does not change is Environmental datab w The stability after the change is Resolution coefficient is μ, environmental data b w The correlation degree is Sort the environmental data in descending order according to the correlation, and select the environmental data with a correlation greater than 0.353 as key data; Calculate the control coefficient based on key data: The control coefficient of the wth key data is The number of tests is The error constant is τ, and the genetic coefficient of the wth key data is λ w , the L2 norm is ‖·‖2, and the correlation degree of the wth key data in the i-th test is θ i,w , the stability after the wth key data changes in the i-th test is The i-th test environment data b w The stability when it does not change is The number of key data is 4. The method for evaluating environmental compatibility of food packaging according to claim 1, characterized in that: The method for performing adaptability analysis on the food bag according to the test data to obtain the adaptability comprises: Divide the test data into multiple subsets according to the control coefficient, and calculate the neighborhood set of the test data: Among them The test data is The ath test data is y a , the number of test data in the bth subset is The jth subset of test data The adaptive neighborhood radius is Test Data and test data y a The Euclidean distance is The jth subset of test data The neighborhood set of The pth test data is y p ; Compute adaptive neighborhood mutual information between subsets: The adaptive neighborhood mutual information between the jth subset and the qth subset is The jth subset of test data The neighborhood set of The union of the jth subset and the qth subset is j∪q, and the adaptive parameter is χ; Calculate the weighted average redundancy of the test data: The ρth test data is k ρ , test data y a The mathematical expectation is F(y a ), test data The mathematical expectation is F(y a ), test data y a and the nearest neighbor test data y a The mathematical expectation of The ath test data cluster is E a , test data y a In the test data cluster β c The weighted average redundancy in is Z(y a ,E a ), the normalized neighborhood mutual information between the b-th subset and the v-th subset is The adjustment factor is Test data y a The mathematical expectation of the square is The regression model is constructed according to the objective function, and the expression of the objective function is: The Frobenius norm of the matrix is The characteristic dimension of the jth group is g j , the regression coefficient of the zth test data is The regression coefficient of the jth test data is The kernel function is G, I, the regularization parameter is γ, and the objective function is According to the penalty coefficient, calculate the fitness of the test data: The likelihood function is W, the number of valid parameters is N, and the fitness of the a-th test data is ζ a , the number of environmental compatibility indicators is M, the inhibition factor is χ, and the cth environmental compatibility indicator before the i-th test is Q i,c (y a ), the cth environmental compatibility index after the ith test is 5. The method for evaluating environmental compatibility of food packaging according to claim 1, characterized in that: The method for constructing a food packaging environmental compatibility evaluation model according to the fitness and the regulation coefficient comprises: Construct the objective function according to the error characteristics: The loss function is The penalty coefficient is ω, The error characteristic is The number of error characteristics is The objective function is The slack variable is η, and the control coefficient is The fitness is ζ; Remote sensing data error correction models include random forest algorithms, autoencoders, and machine learning algorithms; The random forest algorithm divides the input data into training data and test data in a ratio of 4:1; The hierarchical clustering algorithm encodes the training data into a low-dimensional representation through unsupervised learning, and then reconstructs it into the original data, and learns the compressed feature representation of the training data to obtain feature data; The machine learning algorithm captures the error value caused by the characteristic features through the variation, and adjusts the training data according to the error value to obtain the predicted evaluation value; The hyperparameters of the food packaging environmental compatibility evaluation model were adjusted according to the mean square error between the predicted evaluation value data and the actual evaluation value. When the mean square error was less than 0.15, the adjustment was stopped.

6. The method for evaluating environmental compatibility of food packaging according to claim 1, characterized in that: The method for optimizing the food packaging environmental compatibility evaluation model comprises: Compute the position of the searcher: The position of the initial search sub is The random number between 0 and 1 is r1, and the upper bound of the population space range is V u , the lower bound of the population space is V l ; Update the position of the searcher, the expression is: The position of the vth searcher in the t+1th iteration is The current evaluation number is fr, the random function is random(·), the random number is ε, and the maximum number of iterations is t max ; Calculate the threshold: The threshold is th, the random number between 0 and 1 is r2, and the dynamic inertia weight coefficient is introduced, the expression is: The dynamic inertia weight coefficient of the t-th iteration is β(t), and the maximum value of the inertia weight is β max , the minimum value of inertia weight is β min ; When the optimal individual is not updated, β=β+1, otherwise β=0. When the dynamic inertia weight coefficient is greater than the threshold, Levy flight is used to generate random search sub-positions. The expression is: The random search subposition of the tth iteration is The parameter of the stable distribution is d, the step size scaling factor is α, and the random path of the Levy distribution with parameter d is The optimal position of the searcher is The random position of the searcher is The combined search sub-position is obtained according to the dynamic inertia weight coefficient and fitness, and the expression is: The updated search subposition of the tth iteration is The combined search subposition for the t+1th iteration is The fitness of the vth searcher is The global worst fitness is Continue to iterate until the maximum number of iterations is reached, otherwise update the dynamic inertia weight coefficient of the searcher.

7. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the method according to any one of claims 1 to 6.

8. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 6.

Images