Food production enterprise HACCP system efficiency evaluation method

Abstract

The invention discloses a food production enterprise HACCP system efficiency evaluation method. The method comprises the steps of obtaining system data, historical data and waste data of a food production enterprise; comparing the system data with the historical data to obtain change data, and predicting the change data to obtain influence data; performing influence analysis on the waste data based on the historical data to obtain defect data, and obtaining an efficiency index based on the influence data and the defect data; and establishing a performance index model based on the performance index, optimizing the performance index model by adopting a dung beetle optimization algorithm, and inputting to-be-evaluated data into the performance index model to obtain an evaluation result. The method not only can improve the efficiency evaluation precision of the HACCP system of the food production enterprise, but also has good interpretability, and can be directly applied to the efficiency evaluation system of the HACCP system of the food production enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of food safety management, and in particular to a method for evaluating the effectiveness of a HACCP system in a food production enterprise. Background Art

[0002] Today, as food safety is increasingly valued, the quality control system of food production enterprises has become an important part of ensuring food safety. As an internationally recognized means of effectively preventing food safety hazards, the HACCP (Hazard Analysis and Critical Control Point) system is crucial for improving food quality and reducing safety risks. However, the existing HACCP system effectiveness evaluation methods mostly rely on subjective judgment and experience summary, lack of scientific and systematic quantitative evaluation methods, and it is difficult to accurately reflect the true effect of the system operation. Therefore, the development of a scientific and efficient HACCP system effectiveness evaluation method is of great significance to improving the management level and market competitiveness of food production enterprises. Summary of the invention

[0003] The purpose of the present invention is to provide a method for evaluating the effectiveness of the HACCP system in a food production enterprise.

[0004] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0005] The present invention comprises the following steps:

[0006] Obtain system data, historical data and waste data of food production enterprises;

[0007] Comparing the system data with the historical data to obtain change data, and predicting the change data to obtain impact data;

[0008] Performing an impact analysis on the discarded data based on the historical data to obtain defect data, and obtaining a performance index based on the impact data and the defect data;

[0009] A performance index model is established based on the performance index, the performance index model is optimized by using a dung beetle optimization algorithm, and the data to be evaluated is input into the performance index model to obtain an evaluation result.

[0010] Furthermore, the method for obtaining system data, historical data and discarded data of a food production enterprise includes:

[0011] The system data includes the key control points, key limits, key control point monitoring values ​​and quality inspection data of the HACCP system; the historical data includes historical risk data, quality inspection data and user complaint rates; the waste data includes records of unqualified products, waste raw materials and equipment failures.

[0012] Furthermore, the method of comparing the system data with the historical data to obtain change data and predicting the change data to obtain impact data includes:

[0013] Compare the quality inspection data of system data and historical data to obtain the change ratio data of each time step as the change data, convert the system data and historical data into numerical vectors, use the system data and historical data as independent variables, and the change data as the dependent variable to train the prediction model:

[0014] The quantile objective function of the prediction model is:

[0015]

[0016] Among them, q is the quantile, q∈(0,1), ε represents the model parameter set of the prediction model, E is the number of samples, is the sequence length of the sample, y e,τ is the dependent variable of the e-th sample at time step τ, is the predicted data of the e-th sample in the prediction model at time step τ, μ is the coefficient of the L1 regularization term, and δ is a constant term used to ensure numerical stability, and δ is taken as 1×10 -6 , is an indicator function, if If yes, it is 1, otherwise it is 0.

[0017] Forget Gate:

[0018]

[0019] in, is the output of the forget gate, σ is the sigmoid activation function, H is the dimension of the hidden layer, Z(h τ-1 ,x τ ) is the attention weight vector, is the weight matrix of the forget gate, [h τ-1 ,x τ ] j Indicates h τ-1 and x τ The jth dimension, h τ-1 is the hidden state of the previous time step, x τ is the independent variable of the current time step, b is the bias term,

[0020] Output Gate:

[0021]

[0022]

[0023] Among them, τis the output of the current output gate, o τ,j is the j-th dimension output of the output gate, is the j-th dimension bias term of the cell state, h τ is the hidden state at the current time step,

[0024] Output the predicted sequence of the change data, and accumulate the change data after applying the HACCP system and the predicted sequence to obtain the impact data.

[0025] Furthermore, the method of performing impact analysis on the discarded data based on the historical data to obtain defective data includes:

[0026] The risk data and user complaint rate of historical data and the corresponding discarded data are used to form data points and train the clustering model:

[0027] Estimation of kernel density:

[0028]

[0029] in For The kernel density estimated using the kernel function K and kernel width h, is the jth cluster S j The center point, c K is a constant, N is the total number of data points, p is the dimension of the data points, and w i is the weight of the i-th data point, X i is the i-th data point, ||·|| represents the Euclidean distance,

[0030] The kernel function K uses the radial basis kernel function:

[0031]

[0032] in At the center point and data point X i The value calculated using the kernel function K, e is the base of the natural logarithm,

[0033] Gradient of the kernel density estimate:

[0034]

[0035] in for The gradient of X, g is a function defined based on the kernel function K, g(X) = -K ′ (X), K ′ is the derivative of the kernel function K, η is the noise term,

[0036] The formula for the mean shift vector is:

[0037]

[0038] in is the mean shift vector, c g is a constant coefficient used to adjust the scaling of g, For The kernel density estimated using the kernel function G and kernel width h, G(X) = c g g(||X|| 2 ), by iteratively calculating the mean shift vector, the center point of the cluster is updated.

[0039] The trained clustering model is used to divide the discarded data corresponding to the system data into clusters, and the inverse of the Euclidean distance between the discarded data and the center point is used as the membership of the data point. The linear regression model is used to learn the correlation between the discarded data and membership of the data points in the clusters and the risk data and user complaint rate, and the predicted risk data and predicted user complaint rate of the system data are obtained as defect data.

[0040] Furthermore, a method for obtaining a performance index based on the impact data and the defect data includes:

[0041] Normalize the impact data and defect data and calculate the performance index:

[0042]

[0043] in, To influence the weight of the data, is the weight of risk data, is the weight of user complaint rate, For the The impact data of food For the Predicted risk data for various foods, For the Predicted user complaint rate for food, For the The weight of each critical control point, is the number of critical control points, For the The critical limits of the critical control points are For at time point No. The critical limits of the critical control points are The number of time points that are critical control points.

[0044] Furthermore, a method for establishing a performance index model based on the performance index includes:

[0045] The efficiency index is fitted by using changing data and discarded data to train the neural network. The back propagation algorithm is used to calculate the gradient of the loss function with respect to the network parameters. The network parameters are updated through the dung beetle optimization algorithm to minimize the loss function and establish the efficiency index model.

[0046] Furthermore, the method of optimizing the performance index model using the dung beetle optimization algorithm includes:

[0047] Bernoulli mapping is used to initialize network parameters to obtain the initial individual positions of dung beetles. The inverse of the loss function value is used as the fitness value. The maximum fitness value corresponds to the optimal solution.

[0048] Rolling ball behavior position update formula:

[0049]

[0050] in, and are the positions of the i-th dung beetle in the previous iteration, the current iteration, and the next iteration, ξ is the natural factor that causes the dung beetle to deviate from its original direction, k and p are random numbers in the interval (0,1), ω ξ and λ p are the weight coefficients of ξ and p respectively, is the noise term,

[0051] Dance behavior update formula:

[0052]

[0053] Among them, φ is the impact factor, θ is the angle of the rolling dung beetle after encountering an obstacle, and δ θ is the optimization term, f opt is an optimization function,

[0054] The formula for updating the breeding area boundary is:

[0055]

[0056] in, is the lower boundary of the breeding area, is the upper boundary of the breeding area, is the reference position of the breeding area, ρ t is the weight coefficient of the tth iteration, R is the proportional coefficient of the breeding area adjustment, U p is the initial upper boundary of the foraging area, L p is the initial lower boundary of the foraging area,

[0057] Spawn position update formula:

[0058]

[0059] in, and are the egg-laying positions of the i-th dung beetle in the current iteration and the next iteration respectively, p1 and p2 are random numbers in the interval (0,1), for, and are the random perturbation coefficients of p1 and p2, ζ i is the random perturbation vector of the ith dung beetle,

[0060] Foraging area boundary update formula:

[0061]

[0062]

[0063] in, and are the lower and upper boundaries of the foraging area, respectively. is the reference position of the foraging area, g is the exponential function for adjusting the boundary of the foraging area,

[0064] Foraging position update formula:

[0065]

[0066] Among them, γ t is the adjustment factor for the tth iteration, A1 and A2 are and The weight coefficient of the influence on the foraging position update,

[0067] Stealing position update formula:

[0068]

[0069] Among them, ∈ is a constant, S is the success rate of theft, is a 1×D random vector, D is the dimension of the network parameters, ∥·∥ represents the Euclidean distance,

[0070] Iterate until the maximum number of iterations is reached.

[0071] In a second aspect, an embodiment of the present application further provides an electronic device, including:

[0072] 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.

[0073] 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.

[0074] The beneficial effects of the present invention are:

[0075] The present invention is a method for evaluating the effectiveness of the HACCP system of a food production enterprise. Compared with the prior art, the present invention has the following technical effects:

[0076] Compared with the prior art solutions, the present invention has the following advantages:

[0077] Comprehensive data: Comprehensively collect system data, historical data and discarded data to ensure the comprehensiveness and accuracy of the evaluation.

[0078] Accurate prediction: Use deep learning technology and prediction models to predict changing data and improve prediction accuracy.

[0079] In-depth analysis: Use clustering models and linear regression models to analyze the impact of discarded data and deeply explore the intrinsic connections between data.

[0080] Model optimization: The dung beetle optimization algorithm is used to optimize the performance index model to improve the prediction accuracy and generalization ability of the model.

[0081] Dynamic adjustment: In the face of changes in the production environment, the present invention can adjust the evaluation system in real time to ensure the timeliness and effectiveness of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 A flowchart of the steps of a method for evaluating the effectiveness of a HACCP system in a food production enterprise according to the present invention;

[0083] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0084] 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.

[0085] The present invention provides a method for evaluating the effectiveness of a HACCP system in a food production enterprise, comprising the following steps:

[0086] like Figure 1 As shown, in this embodiment, the following steps are included:

[0087] Obtain system data, historical data and waste data of food production enterprises;

[0088] In the actual evaluation, the system data is:

[0089] Critical Control Point 1 (CCP1): Temperature control, critical limit 20°C, monitoring values ​​[21°C, 20.5°C, 19.8°C]; Critical Control Point 2 (CCP2): Time control, critical limit 30 minutes, monitoring values ​​[31 minutes, 29 minutes, 30 minutes]; Food 1, quality inspection data [97% qualified, 97.5% qualified, 98% qualified], Food 2, quality inspection data [94% qualified, 94.5% qualified, 95% qualified];

[0090] Historical data:

[0091] Historical risk data: health risk of food 1, [0.01, 0.02, 0.01], food 2, [0.02, 0.018, 0.015]; historical quality inspection data: food 1, [95% qualified, 94.5% qualified, 94% qualified, 94% qualified, 93.5% qualified], food 2, [90% qualified, 89.5% qualified, 89% qualified, 89% qualified, 88.5% qualified]; user complaint rate: food 1, [0.005, 0.003, 0.004], food 2, [0.005, 0.0045, 0.004];

[0092] Discarded data:

[0093] Unqualified product records: [10 pieces, 5 pieces, 10 pieces, 0 pieces], waste material records: [5 kg, 3 kg, 4 kg, 0 kg], equipment failure records: [1 time, 0 times, 1 time, 0 times];

[0094] Comparing the system data with the historical data to obtain change data, and predicting the change data to obtain impact data;

[0095] In the actual evaluation, the change data are: Food 1, [-0.5%, -0.5%, 0%, -0.5%, 3.5%, 0.5%, 0.5%], Food 2, [-0.5%, -0.5%, 0%, -0.5%, 5.5%, 0.5%, 0.5%]; the impact data are: Food 1, 5%, Food 2, 7.5%;

[0096] Performing an impact analysis on the discarded data based on the historical data to obtain defect data, and obtaining a performance index based on the impact data and the defect data;

[0097] In the actual evaluation, the defect data are: predicted risk data: food 1, 0.0005, food 2, 0.0008; predicted user complaint rate: food 1, 0.015, food 2, 0.02; the performance index is: 0.55;

[0098] A performance index model is established based on the performance index, the performance index model is optimized by using a dung beetle optimization algorithm, and the data to be evaluated is input into the performance index model to obtain an evaluation result.

[0099] In this embodiment, the method for obtaining system data, historical data and discarded data of a food production enterprise includes:

[0100] The system data includes the key control points, key limits, key control point monitoring values ​​and quality inspection data of the HACCP system; the historical data includes historical risk data, quality inspection data and user complaint rates; the waste data includes records of unqualified products, waste raw materials and equipment failures.

[0101] In this embodiment, the method of comparing the system data with the historical data to obtain change data and predicting the change data to obtain impact data includes:

[0102] Compare the quality inspection data of system data and historical data to obtain the change ratio data of each time step as the change data, convert the system data and historical data into numerical vectors, use the system data and historical data as independent variables, and the change data as the dependent variable to train the prediction model:

[0103] The quantile objective function of the prediction model is:

[0104]

[0105] Among them, q is the quantile, q∈(0,1), ε represents the model parameter set of the prediction model, E is the number of samples, is the sequence length of the sample, y e,τ is the dependent variable of the e-th sample at time step τ, is the predicted data of the e-th sample in the prediction model at time step τ, μ is the coefficient of the L1 regularization term, and δ is a constant term used to ensure numerical stability, and δ is taken as 1×10 -6 , is an indicator function, if If yes, it is 1, otherwise it is 0.

[0106] Forget Gate:

[0107]

[0108] in, is the output of the forget gate, σ is the sigmoid activation function, H is the dimension of the hidden layer, Z(h τ-1 ,x τ ) is the attention weight vector, is the weight matrix of the forget gate, [h τ-1 ,x τ ] j Indicates h τ-1 and x τ The jth dimension, h τ-1 is the hidden state of the previous time step, x τ is the independent variable of the current time step, b is the bias term,

[0109] Output Gate:

[0110]

[0111]

[0112] Among them, τ is the output of the current output gate, o τ,j is the j-th dimension output of the output gate, is the j-th dimension bias term of the cell state, h τ is the hidden state at the current time step,

[0113] Output the predicted sequence of the change data, and accumulate the change data after applying the HACCP system and the predicted sequence to obtain the impact data.

[0114] In this embodiment, the method for obtaining defective data by performing impact analysis on the discarded data based on the historical data includes:

[0115] The risk data and user complaint rate of historical data and the corresponding discarded data are used to form data points and train the clustering model:

[0116] Estimation of kernel density:

[0117]

[0118] in For The kernel density estimated using the kernel function K and kernel width h, is the jth cluster S j The center point, c K is a constant, N is the total number of data points, p is the dimension of the data points, and w i is the weight of the i-th data point, X i is the i-th data point, ||·|| represents the Euclidean distance,

[0119] The kernel function K uses the radial basis kernel function:

[0120]

[0121] in At the center point and data point X i The value calculated using the kernel function K, e is the base of the natural logarithm,

[0122] Gradient of the kernel density estimate:

[0123]

[0124] in for The gradient of X, g is a function defined based on the kernel function K, g(X) = -K ′ (X), K ′ is the derivative of the kernel function K, η is the noise term,

[0125] The formula for the mean shift vector is:

[0126]

[0127] in is the mean shift vector, c g is a constant coefficient used to adjust the scaling of g, For The kernel density estimated using the kernel function G and kernel width h, G(X) = c g g(||X|| 2 ), by iteratively calculating the mean shift vector, the center point of the cluster is updated.

[0128] The trained clustering model is used to divide the discarded data corresponding to the system data into clusters, and the inverse of the Euclidean distance between the discarded data and the center point is used as the membership of the data point. The linear regression model is used to learn the correlation between the discarded data and membership of the data points in the clusters and the risk data and user complaint rate, and the predicted risk data and predicted user complaint rate of the system data are obtained as defect data.

[0129] In this embodiment, the method for obtaining the performance index based on the impact data and the defect data includes:

[0130] Normalize the impact data and defect data and calculate the performance index:

[0131]

[0132] in, To influence the weight of the data, is the weight of risk data, is the weight of user complaint rate, For the The impact data of food For the Predicted risk data for various foods, For the Predicted user complaint rate for food products, For the The weight of each critical control point, is the number of critical control points, For the The critical limits of the critical control points are For at time point No. The critical limits of the critical control points are The number of time points that are critical control points.

[0133] In this embodiment, the method of establishing a performance index model based on the performance index includes:

[0134] The efficiency index is fitted by using changing data and discarded data to train the neural network. The back propagation algorithm is used to calculate the gradient of the loss function with respect to the network parameters. The network parameters are updated through the dung beetle optimization algorithm to minimize the loss function and establish the efficiency index model.

[0135] In this embodiment, the method of optimizing the performance index model using the dung beetle optimization algorithm includes:

[0136] Bernoulli mapping is used to initialize network parameters to obtain the initial individual positions of dung beetles. The inverse of the loss function value is used as the fitness value. The maximum fitness value corresponds to the optimal solution.

[0137] Rolling ball behavior position update formula:

[0138]

[0139] in, and are the positions of the i-th dung beetle in the previous iteration, the current iteration, and the next iteration, ξ is the natural factor that causes the dung beetle to deviate from its original direction, k and p are random numbers in the interval (0,1), ω ξ and λ p are the weight coefficients of ξ and p respectively, is the noise term,

[0140] Dance behavior update formula:

[0141]

[0142] Among them, φ is the impact factor, θ is the angle of the rolling dung beetle after encountering an obstacle, and δθ is the optimization term, f opt is an optimization function,

[0143] The formula for updating the breeding area boundary is:

[0144]

[0145] in, is the lower boundary of the breeding area, is the upper boundary of the breeding area, is the reference position of the breeding area, ρ t is the weight coefficient of the tth iteration, R is the proportional coefficient of the breeding area adjustment, U p is the initial upper boundary of the foraging area, L p is the initial lower boundary of the foraging area,

[0146] Spawn position update formula:

[0147]

[0148] in, and are the egg-laying positions of the i-th dung beetle in the current iteration and the next iteration respectively, p1 and p2 are random numbers in the interval (0,1), for, and are the random perturbation coefficients of p1 and p2, ζ i is the random perturbation vector of the ith dung beetle,

[0149] Foraging area boundary update formula:

[0150]

[0151]

[0152] in, and are the lower and upper boundaries of the foraging area, respectively. is the reference position of the foraging area, g is the exponential function for adjusting the boundary of the foraging area,

[0153] Foraging position update formula:

[0154]

[0155] Among them, γ t is the adjustment factor for the tth iteration, A1 and A2 are and The weight coefficient of the influence on the foraging position update,

[0156] Stealing position update formula:

[0157]

[0158] Among them, ∈ is a constant, S is the success rate of theft, is a 1×D random vector, D is the dimension of the network parameters, ∥·∥ represents the Euclidean distance,

[0159] Iterate until the maximum number of iterations is reached.

[0160] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At 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.

[0161] 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.

[0162] 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.

[0163] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a food production enterprise HACCP system performance 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 production enterprise HACCP system performance evaluation methods.

[0164] The above application Figure 1The method for evaluating the effectiveness of the HACCP system of a food production enterprise 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.

[0165] The electronic device may also perform Figure 1 A method for evaluating the effectiveness of the HACCP system in food production enterprises and implementing Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0166] 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 one of the aforementioned food production enterprise HACCP system effectiveness evaluation methods is executed.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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 the effectiveness of the HACCP system in a food production enterprise, characterized in that: The following steps are involved: Obtain system data, historical data and waste data of food production enterprises; Comparing the system data with the historical data to obtain change data, and predicting the change data to obtain impact data; Performing an impact analysis on the discarded data based on the historical data to obtain defect data, and obtaining a performance index based on the impact data and the defect data; A performance index model is established based on the performance index, the performance index model is optimized by using a dung beetle optimization algorithm, and the data to be evaluated is input into the performance index model to obtain an evaluation result.

2. A method for evaluating the effectiveness of a HACCP system in a food production enterprise according to claim 1, characterized in that: Methods for obtaining systematic data, historical data and discarded data of food production enterprises, including: The system data includes the key control points, key limits, key control point monitoring values ​​and quality inspection data of the HACCP system; the historical data includes historical risk data, quality inspection data and user complaint rates; the waste data includes records of unqualified products, waste raw materials and equipment failures.

3. A method for evaluating the effectiveness of a HACCP system in a food production enterprise according to claim 1, characterized in that: The method of comparing the system data with the historical data to obtain change data, and predicting the change data to obtain impact data comprises: Compare the quality inspection data of system data and historical data to obtain the change ratio data of each time step as the change data, convert the system data and historical data into numerical vectors, use the system data and historical data as independent variables, and the change data as the dependent variable to train the prediction model: The quantile objective function of the prediction model is: Among them, q is the quantile, q∈(0,1), ε represents the model parameter set of the prediction model, E is the number of samples, is the sequence length of the sample, y e,τ is the dependent variable of the e-th sample at time step τ, is the predicted data of the e-th sample in the prediction model at time step τ, μ is the coefficient of the L1 regularization term, and δ is a constant term used to ensure numerical stability, and δ is taken as 1×10 -6 , is an indicator function, if If yes, it is 1, otherwise it is 0. Forget Gate: in, is the output of the forget gate, σ is the sigmoid activation function, H is the dimension of the hidden layer, Z(h τ-1 ,x τ ) is the attention weight vector, is the weight matrix of the forget gate, [h τ-1 ,x τ ] j Indicates h τ-1 and x τ The jth dimension, h τ-1 is the hidden state of the previous time step, x τ is the independent variable of the current time step, b is the bias term, Output Gate: Among them, τ is the output of the current output gate, o τ,j is the j-th dimension output of the output gate, is the j-th dimension bias term of the cell state, h τ is the hidden state at the current time step, Output the predicted sequence of the change data, and accumulate the change data after applying the HACCP system and the predicted sequence to obtain the impact data.

4. A method for evaluating the effectiveness of a HACCP system in a food production enterprise according to claim 1, characterized in that: The method for obtaining defective data by performing an impact analysis on the discarded data based on the historical data includes: The risk data and user complaint rate of historical data and the corresponding discarded data are used to form data points and train the clustering model: Estimation of kernel density: in For The kernel density estimated using the kernel function K and kernel width h, is the jth cluster S j The center point, c K is a constant, N is the total number of data points, p is the dimension of the data points, and w i is the weight of the i-th data point, X i is the i-th data point, ||·|| represents the Euclidean distance, The kernel function K uses the radial basis kernel function: in At the center point and data point X i The value calculated using the kernel function K, e is the base of the natural logarithm, Gradient of the kernel density estimate: in for The gradient of X, g is a function defined based on the kernel function K, g(X) = -K ′ (X), K ′ is the derivative of the kernel function K, η is the noise term, The formula for the mean shift vector is: in is the mean shift vector, c g is a constant coefficient used to adjust the scaling of g, For The kernel density estimated using the kernel function G and kernel width h, G(X) = c g g(||X|| 2 ), by iteratively calculating the mean shift vector, the center point of the cluster is updated. The trained clustering model is used to divide the discarded data corresponding to the system data into clusters, and the inverse of the Euclidean distance between the discarded data and the center point is used as the membership of the data point. The linear regression model is used to learn the correlation between the discarded data and membership of the data points in the clusters and the risk data and user complaint rate, and the predicted risk data and predicted user complaint rate of the system data are obtained as defect data.

5. A method for evaluating the effectiveness of a HACCP system in a food production enterprise according to claim 1, characterized in that: The method for obtaining the performance index based on the impact data and the defect data comprises: Normalize the impact data and defect data and calculate the performance index: in, To influence the weight of the data, is the weight of risk data, is the weight of user complaint rate, For the The impact data of food For the Predicted risk data for various foods, For the Predicted user complaint rate for food products, For the The weight of each critical control point, is the number of critical control points, For the The critical limits of the critical control points are For at time point No. The critical limits of the critical control points are The number of time points that are critical control points.

6. A method for evaluating the effectiveness of a HACCP system in a food production enterprise according to claim 1, characterized in that: The method for establishing a performance index model based on the performance index comprises: The efficiency index is fitted by using changing data and discarded data to train the neural network. The back propagation algorithm is used to calculate the gradient of the loss function with respect to the network parameters. The network parameters are updated through the dung beetle optimization algorithm to minimize the loss function and establish the efficiency index model.

7. A method for evaluating the effectiveness of a HACCP system in a food production enterprise according to claim 1, characterized in that: The method of optimizing the performance index model using a dung beetle optimization algorithm comprises: Bernoulli mapping is used to initialize network parameters to obtain the initial individual positions of dung beetles. The inverse of the loss function value is used as the fitness value. The maximum fitness value corresponds to the optimal solution. Rolling ball behavior position update formula: in, and are the positions of the i-th dung beetle in the previous iteration, the current iteration, and the next iteration, ξ is the natural factor that causes the dung beetle to deviate from its original direction, k and p are random numbers in the interval (0,1), ω ξ and λ p are the weight coefficients of ξ and p respectively, is the noise term, Dance behavior update formula: Among them, φ is the impact factor, θ is the angle of the rolling dung beetle after encountering an obstacle, and δ θ is the optimization term, f opt is an optimization function, The formula for updating the breeding area boundary is: in, is the lower boundary of the breeding area, is the upper boundary of the breeding area, is the reference position of the breeding area, ρ t is the weight coefficient of the tth iteration, R is the proportional coefficient of the breeding area adjustment, U p is the initial upper boundary of the foraging area, L p is the initial lower boundary of the foraging area, Spawn position update formula: in, and are the egg-laying positions of the i-th dung beetle in the current iteration and the next iteration respectively, p1 and p2 are random numbers in the interval (0,1), for, and are the random perturbation coefficients of p1 and p2 respectively, is the random perturbation vector of the ith dung beetle, Foraging area boundary update formula: in, and are the lower and upper boundaries of the foraging area, respectively. is the reference position of the foraging area, g is the exponential function for adjusting the boundary of the foraging area, Foraging position update formula: Among them, γ t is the adjustment factor for the tth iteration, A1 and A2 are and The weight coefficient of the influence on the foraging position update, Stealing position update formula: Among them, ∈ is a constant, S is the success rate of theft, is a 1×D random vector, D is the dimension of the network parameters, ∥·∥ represents the Euclidean distance, Iterate until the maximum number of iterations is reached.

8. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method according to any one of claims 1 to 7.

9. 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 7.

Images