Bread baking simulation method and system

Abstract

The invention discloses a bread baking simulation method and system, belongs to the technical field of novel information technology services, and aims to solve the problem of unstable baking results caused by user operation differences. Comprising the following steps that a quinoa dough formula parameter set input by a user is obtained, and the quinoa dough formula parameter set comprises the quinoa flour mass ratio, the hydration time, the primary fermentation temperature and the duration time; performing parameter normalization processing on the quinoa dough formula parameter set to generate a standard input vector; inputting the standard input vector into a pre-trained multi-physical field coupling prediction model for forward calculation to obtain a prediction result set containing a dough expansion coefficient matrix, an acidity distribution vector and a browning intensity value; generating a three-dimensional volume prediction map according to the dough expansion coefficient matrix, and generating a taste evaluation index based on the acidity distribution vector and the browning intensity value; and sending the three-dimensional volume prediction map and the taste evaluation index to a preset terminal for visual display.

Description

Technical Field

[0001] The present invention relates to the technical field of new information technology services, and specifically to a method and system for simulating bread baking. Background Art

[0002] In the field of bread baking, the final production effect and taste of bread are jointly shaped by the collaborative action of the preparation stage and the baking stage. Among them, the preparation steps mainly rely on manual operations by users and involve operations such as the preparation and fermentation of quinoa dough. Due to differences in their own experience levels and operating habits, different users are difficult to achieve complete consistency when preparing the dough. For example, when preparing quinoa dough, there are obvious deviations among different users in controlling key parameters such as the mass ratio of quinoa flour, hydration time, primary fermentation temperature, and duration. Such differences will result in different textures and compositions of the dough obtained each time.

[0003] Affected by this, the working parameters (i.e., temperature, humidity, time, etc.) at each stage of the baking machine need to be dynamically adjusted accordingly; however, due to the lack of a standardized benchmark, it is often difficult to accurately control, which easily leads to the final baked bread not meeting the user's expectations in terms of taste or color, or even being inedible, resulting in waste of materials and time.

[0004] The disclosure of the above background art content is only used to assist in understanding the concept and technical solution of the present invention, and it does not necessarily belong to the prior art of this patent application. Without clear evidence indicating that the above content was publicly available on the filing date of this patent application, the above background art should not be used to evaluate the novelty and inventiveness of this application. Summary of the Invention

[0005] This application provides a method and system for simulating bread baking to solve the problem of unstable baking results caused by differences in user operations.

[0006] To achieve the above object, the embodiments of this application disclose the following technical solutions:

[0007] In a first aspect, the embodiments of this application provide a method for simulating bread baking, including the following steps:

[0008] Obtain a set of quinoa dough recipe parameters input by the user, where the set of quinoa dough recipe parameters includes the mass ratio of quinoa flour, hydration time, primary fermentation temperature, and duration;

[0009] Perform parameter normalization processing on the set of quinoa dough recipe parameters to generate a standard input vector;

[0010] Input the standard input vector into a pre-trained multi-physics field coupling prediction model for forward calculation to obtain a set of prediction results including a dough expansion coefficient matrix, an acidity distribution vector, and a browning intensity value;

[0011] Generate a three-dimensional volume prediction map based on the dough expansion coefficient matrix, and generate a taste evaluation index based on the acidity distribution vector and the browning intensity value;

[0012] Send the three-dimensional volume prediction map and the taste evaluation index to a preset terminal for visual display.

[0013] In the embodiments of the present application, parameters such as the mass ratio of quinoa flour input by the user, the hydration time, the initial fermentation temperature and duration, etc. have significant fluctuations in dimensions and numerical ranges due to differences in experience. Directly using the original parameters will cause model prediction deviations. The min-max scaling algorithm is used to normalize the parameters, and linear parameters with different dimensions are uniformly mapped to the interval [0,1] to eliminate the influence of parameter scale differences on model calculations, enabling the model to process various input data based on a unified standard. After the preprocessed standard input vector is input into the pre-trained multi-physical field coupling prediction model, the model comprehensively calculates the dough expansion coefficient matrix, acidity distribution vector, and browning intensity value during the baking process by coupling multi-dimensional physical fields such as heat conduction, mass transfer, biochemical reactions, and deformation mechanics, and converts the differences in user input parameters into a quantifiable prediction result set. The visual display of the three-dimensional volume prediction map and the taste evaluation index converts the abstract data output by the model into intuitive graphs and scores, enabling users to directly observe the expansion form and taste characteristics of the dough under different parameters, so as to adjust the operation parameters based on a unified prediction benchmark, thereby effectively solving the problem of unstable baking results caused by differences in user operations.

[0014] In some possible implementation manners of the first aspect, the parameter normalization process adopts the min-max scaling algorithm to linearly transform parameters with different dimensions to the interval [0,1] to generate a standard input vector. The specific calculation formula is:

[0015]

[0016] Where: X (i) : The i-th original parameter; The minimum value of the i-th parameter in the historical data; The maximum value of the i-th parameter in the historical data; The normalized value of the i-th parameter.

[0017] In some possible implementation manners of the first aspect, the multi-physical field coupling prediction model includes a coupling structure of a heat conduction sub-model, a mass transfer sub-model, a biochemical reaction sub-model, and a deformation mechanics sub-model. The steps of inputting the standard input vector into the pre-trained multi-physical field coupling prediction model for forward calculation to obtain a prediction result set including the dough expansion coefficient matrix, acidity distribution vector, and browning intensity value include:

[0018] Input the standard input vector into the heat conduction sub-model and the mass transfer sub-model simultaneously;

[0019] The heat conduction sub-model calculates the temperature field distribution inside the dough according to the fermentation temperature parameter, and its partial differential equation and boundary conditions are:

[0020]

[0021] Where: T: temperature field distribution matrix; α: dough thermal diffusivity; β: yeast heat production conversion factor; Q yeast (t): yeast heat production rate, k1: yeast heat production rate base; k2: temperature sensitivity coefficient; Dynamic fermentation average temperature; T oven : oven ambient temperature;

[0022] The mass transfer sub-model calculates the three-dimensional moisture diffusion flux according to the hydration time parameter, and its governing equation is:

[0023]

[0024] Where: J w : three-dimensional moisture flux vector; D w : moisture diffusion coefficient; C w : moisture concentration field; v w : three-dimensional convective velocity field caused by expansion;

[0025] The biochemical reaction sub-model receives the temperature field distribution matrix and the moisture flux vector, and calculates the yeast activity parameter Y(t) and the lactic acid bacteria metabolism parameter L(t). The specific formulas are as follows:

[0026]

[0027] Where: t hydrate : hydration time input by the user; T ferment : initial fermentation temperature input by the user; T ref Yeast metabolism reference temperature;

[0028] The deformation mechanics sub-model calculates the dough expansion coefficient matrix E according to the temperature field distribution matrix, the moisture flux vector and the yeast activity parameter ij :

[0029]

[0030] Where: E ij : expansion coefficient matrix element; γ T : temperature deformation weight coefficient; γ w : moisture deformation weight coefficient; x-direction gradient of the temperature field at the (i, j) position; The time rate of change of the moisture flux modulus at the (i,j) position.

[0031] Among them, the heat conduction sub-model calculates the internal temperature field distribution of the dough according to the fermentation temperature parameter, quantifies the dynamic balance between yeast heat generation and environmental heat transfer through partial differential equations, and provides temperature gradient data support for the mass transfer sub-model. The mass transfer sub-model calculates the three-dimensional moisture diffusion flux according to the hydration time parameter, determines the spatial variation of the moisture concentration field and the convective velocity field in combination with the temperature field distribution, and provides dynamic moisture diffusion parameters for the biochemical reaction sub-model. The biochemical reaction sub-model integrates the temperature field distribution matrix and the moisture flux vector, calculates the yeast activity parameter and the lactic acid bacteria metabolism parameter through integration and weighting, and quantifies the spatio-temporal distribution characteristics of microbial metabolites during fermentation. The deformation mechanics sub-model constructs a calculation equation for the expansion coefficient matrix based on the temperature field gradient, the time derivative of the moisture flux, and the yeast activity parameter, and couples the thermal expansion effect and the wet expansion effect into a unified deformation prediction model. Each sub-model forms a closed-loop feedback through data interaction. The outputs of heat conduction and mass transfer drive biochemical reactions, and the metabolic parameters of biochemical reactions further affect the expansion prediction of deformation mechanics. The results of deformation mechanics inversely constrain the update of the boundary conditions of the temperature field and the moisture field. The deep coupling of multiple physical fields effectively captures the non-linear interaction of temperature-moisture-microorganism-deformation during dough fermentation, realizes the synchronous optimization of cross-scale physical property parameters through the simultaneous solution of differential equations, significantly improves the prediction accuracy of the expansion coefficient, acidity distribution and browning intensity, and provides a high-confidence quantitative basis for adjusting baking process parameters.

[0032] In some possible implementations of the first aspect, the acidity distribution vector is generated through the output of the biochemical reaction sub-model, and the specific formula is as follows:

[0033] A k = η·Y(t)·(1 - exp(-λt)) + μ·L(t)·exp(-κt);

[0034] Where: A k : The k-th component of the acidity distribution vector, reflecting the local acidity value; η: Yeast acid production coefficient; λ: Yeast metabolism time decay coefficient; μ: Lactic acid bacteria acid production coefficient; κ: Lactic acid bacteria metabolism time decay coefficient.

[0035] In some possible implementations of the first aspect, the generation of the three-dimensional volume prediction map specifically includes: converting the dough expansion coefficient matrix into spatial geometric data through a discretized grid mapping algorithm, and the height calculation formula of the (i,j) grid point is:

[0036]

[0037] Where: h ij: The height value of the (i, j) grid point in the three-dimensional model; E ij : The element of the expansion coefficient matrix; Δt: The baking time step; T ferment : The initial fermentation temperature input by the user; T base : The reference temperature constant.

[0038] In some possible implementation manners of the first aspect, the generation of the taste evaluation index specifically includes:

[0039] Using the fuzzy logic algorithm to perform acidity balance scoring on the acidity distribution vector, and the scoring function is:

[0040]

[0041] Where: S acid : The acidity balance score, in the range of 0 - 1, and 1 represents the best balance; The average value of the acidity distribution vector; ξ: The sensitivity coefficient; n: The dimension of the acidity distribution vector;

[0042] Performing coking degree scoring on the browning intensity value B pred ;

[0043] Generating a taste evaluation index according to the acidity balance score and the coking degree score.

[0044] In some possible implementation manners of the first aspect, the multi-physical field coupling prediction model is trained by error backpropagation through the historical baking data set; the loss function of the multi-physical field coupling prediction model is defined as:

[0045] L = α·‖E pred - E true ‖2 + β·‖A pred - A true ‖1 + γ·|B pred - B true |;

[0046] Where: α, β, γ: The weight coefficients, satisfying α + β + γ = 1; E pred : The predicted expansion coefficient matrix; E true : The measured expansion coefficient matrix in the historical data; A pred : The predicted acidity distribution vector; A true : The measured acidity distribution vector in the historical data; B pred : The predicted browning intensity value; B true : The measured browning intensity value in the historical data.

[0047] Among them, in the loss function, the dilation coefficient matrix uses the L2 norm to constrain the overall shape error, the acidity distribution vector uses the L1 norm to strengthen the local sparsity error, the browning intensity value uses the absolute value loss to control the scalar deviation, and the weight coefficient dynamically adjusts the contribution of the three types of errors to the update of the model parameters. During the training process, the temperature field distribution error output by the heat conduction sub-model affects the moisture diffusion parameter of the mass transfer sub-model and the yeast activity calculation parameter of the biochemical reaction sub-model through backpropagation at the same time; the moisture flux error of the mass transfer sub-model reversely corrects the dilation coefficient calculation weight of the deformation mechanics sub-model; the acidity prediction error of the biochemical reaction sub-model adjusts the boundary condition constraints of heat conduction and mass transfer through the time integral term feedback. The prediction errors of the dilation coefficient, acidity distribution, and browning intensity form cross-couplings in the backpropagation link, forcing the parameter update processes of the heat conduction, mass transfer, biochemical reaction, and deformation mechanics sub-models to simultaneously meet the joint convergence conditions of multiple physical fields. In this way, the isolated optimization mode of the traditional single-field model is broken, and through the joint error constraint of dilation-acidity-browning, the deep coupling of the temperature field-moisture field-microbial field-deformation field is realized, effectively improving the cross-scale prediction ability of the model for the fermentation swelling dynamics, acidity spatial distribution, and Maillard reaction degree.

[0048] In some possible implementations of the first aspect, after generating the visual display, it further includes: calculating based on the deviation degree between the prediction result set and the historical optimal parameters, and the deviation degree is defined as:

[0049] D = ‖E pred - E opt ‖2 + ‖A pred - A opt ‖1 + |B pred - B opt |

[0050] When D > D th , a recipe parameter adjustment suggestion table including the hydration time correction amount and the fermentation temperature compensation value is generated, where: D: comprehensive deviation degree; E opt : historical optimal dilation coefficient matrix; A opt : historical optimal acidity distribution vector; B opt : historical optimal browning intensity value; D th : deviation degree threshold. In this way, by calculating the comprehensive deviation degree between the predicted parameters and the historical optimal values, recipe correction suggestions can be generated, so as to effectively reduce the finished product defects caused by parameter deviations and improve the baking success rate and resource utilization rate.

[0051] In a second aspect, an embodiment of the present application provides a bread baking simulation system, including:

[0052] The first acquisition module is used to acquire a set of quinoa dough formula parameters input by the user, and the set of quinoa dough formula parameters includes the mass ratio of quinoa flour, the hydration time, the primary fermentation temperature and the duration;

[0053] The first generation module is used to perform parameter normalization processing on the set of quinoa dough formula parameters to generate a standard input vector;

[0054] The first calculation module is used to input the standard input vector into a pre-trained multi-physical field coupling prediction model for forward calculation to obtain a set of prediction results including a dough expansion coefficient matrix, an acidity distribution vector and a browning intensity value;

[0055] The second generation module is used to generate a three-dimensional volume prediction map based on the dough expansion coefficient matrix, and generate a taste evaluation index based on the acidity distribution vector and the browning intensity value;

[0056] The visualization module is used to send the three-dimensional volume prediction map and the taste evaluation index to a preset terminal for visual display.

[0057] In a third aspect, an embodiment of the present application provides an electronic device, including one or more processors; a storage device storing one or more programs thereon; when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any technical solution of the first aspect.

[0058] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any technical solution of the first aspect is implemented.

[0059] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method described in any technical solution of the first aspect is implemented.

[0060] Among them, the technical effects brought by any of the design methods in the second aspect to the fifth aspect can refer to the technical effects brought by different design methods in the first aspect, which will not be elaborated here. Description of the Drawings

[0061] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, other implementation drawings can be obtained by extension according to the provided drawings without creative efforts.

[0062] Figure 1A schematic flowchart of a bread baking simulation method provided by some embodiments of the present application;

[0063] Figure 2 A schematic structural diagram of a bread baking simulation system provided by some embodiments of the present application;

[0064] Figure 3 A schematic structural diagram of an electronic device suitable for implementing some embodiments of the present application. Detailed implementation manners

[0065] Now, specific embodiments of the present invention will be described in detail. Although the present invention is described in conjunction with these specific embodiments, it should be understood that it is not intended to limit the present invention to these specific embodiments. On the contrary, these embodiments are intended to cover alternatives, modifications, or equivalent embodiments that may be included within the spirit and scope of the invention defined by the claims. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. The present invention may be practiced without some or all of these specific details.

[0066] When used in conjunction with the terms "comprising", "the method comprises", or similar language in this specification and the appended claims, the singular forms "a", "an", "the" include plural references unless the context clearly dictates otherwise. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which the present invention belongs.

[0067] Application overview: In the field of bread baking, the final production effect and taste of bread are jointly shaped by the preparation stage and the baking stage. Among them, the preparation steps mainly rely on manual operation by users, involving operations such as the preparation and fermentation of quinoa dough. Due to differences in their own experience levels and operating habits, different users are difficult to achieve complete consistency when preparing the dough. For example, when preparing quinoa dough, there will be obvious deviations among different users in controlling key parameters such as the mass ratio of quinoa flour, the hydration time, the initial fermentation temperature and duration. This difference will result in different textures and compositions of the dough obtained each time.

[0068] Affected by this, the working parameters (i.e., temperature, humidity, time, etc.) at each stage of the baking machine need to be dynamically adjusted accordingly; however, due to the lack of a standardized benchmark, it is often difficult to accurately control, which easily leads to the final baked bread not meeting the user's expectations in terms of taste or color, or even being inedible, resulting in waste of materials and time.

[0069] In view of the above technical problems, the general idea of the technical solution provided by this application is as follows: Provide a method for simulating bread baking, including the following steps: Obtain a set of quinoa dough recipe parameters input by the user, where the set of quinoa dough recipe parameters includes the mass ratio of quinoa flour, the hydration time, the primary fermentation temperature and the duration; Perform parameter normalization processing on the set of quinoa dough recipe parameters to generate a standard input vector; Input the standard input vector into a pre-trained multi-physical field coupling prediction model for forward calculation to obtain a set of prediction results including a dough expansion coefficient matrix, an acidity distribution vector, and a browning intensity value; Generate a three-dimensional volume prediction map based on the dough expansion coefficient matrix, and generate a taste evaluation index based on the acidity distribution vector and the browning intensity value; Send the three-dimensional volume prediction map and the taste evaluation index to a preset terminal for visual display.

[0070] Since there are significant fluctuations in the dimensions and numerical ranges of parameters such as the mass ratio of quinoa flour, the hydration time, the primary fermentation temperature, and the duration input by the user due to differences in experience, directly using the original parameters will cause model prediction deviations. This method uses the min-max scaling algorithm to normalize the parameters, uniformly mapping linear parameters with different dimensions to the interval [0,1], eliminating the influence of parameter scale differences on model calculations, and enabling the model to process various input data based on a unified standard. After the preprocessed standard input vector is input into the pre-trained multi-physical field coupling prediction model, the model comprehensively calculates the dough expansion coefficient matrix, the acidity distribution vector, and the browning intensity value during the baking process by coupling multi-dimensional physical field effects such as heat conduction, mass transfer, biochemical reactions, and deformation mechanics, converting the differences in user input parameters into a quantifiable set of prediction results. The visual display of the three-dimensional volume prediction map and the taste evaluation index converts the abstract data output by the model into intuitive graphics and scores, enabling users to directly observe the expansion morphology and taste characteristics of the dough under different parameters, and thus adjust the operating parameters based on a unified prediction benchmark, effectively solving the problem of unstable baking results caused by user operation differences.

[0071] After introducing the basic principle of this application, the following will specifically introduce various non-limiting implementation manners of this application in conjunction with the accompanying drawings of the specification. Please refer to Figure 1 , An embodiment of this application provides a method for simulating bread baking, including the following steps:

[0072] S101: Obtain a set of quinoa dough recipe parameters input by the user, where the set of quinoa dough recipe parameters includes the mass ratio of quinoa flour, the hydration time, the primary fermentation temperature and the duration;

[0073] S102: Perform parameter normalization processing on the set of quinoa dough recipe parameters to generate a standard input vector;

[0074] Specifically, the execution entity of the bread baking simulation method adopts the min-max scaling algorithm to linearly transform parameters with different dimensions into the interval [0,1] to generate a standard input vector. The specific calculation formula is:

[0075]

[0076] Where: X (i) : The i-th original parameter (quinoa flour mass ratio, hydration time, primary fermentation temperature or duration)

[0077] ; The minimum value of the i-th parameter in the historical data; The maximum value of the i-th parameter in the historical data; The normalized value of the i-th parameter.

[0078] S103: Input the standard input vector into the pre-trained multi-physics coupling prediction model for forward calculation to obtain a prediction result set including the dough expansion coefficient matrix, acidity distribution vector, and browning intensity value;

[0079] Specifically, in some embodiments, the multi-physics coupling prediction model includes a coupling structure of a heat conduction sub-model, a mass transfer sub-model, a biochemical reaction sub-model, and a deformation mechanics sub-model;

[0080] The above-mentioned execution entity can input the standard input vector into the pre-trained multi-physics coupling prediction model for forward calculation through the following steps to obtain a prediction result set including the dough expansion coefficient matrix, acidity distribution vector, and browning intensity value:

[0081] First step, input the standard input vector into the heat conduction sub-model and the mass transfer sub-model simultaneously;

[0082] Second step, the heat conduction sub-model calculates the temperature field distribution inside the dough according to the fermentation temperature parameter, and its partial differential equation and boundary conditions are:

[0083]

[0084] Where: T: Temperature field distribution matrix; α: Dough thermal diffusivity; β: Yeast heat production conversion factor; Q yeast (t): Yeast heat production rate, k1: Yeast heat production rate base; k2: Temperature sensitivity coefficient; Dynamic fermentation average temperature; T oven : Oven ambient temperature;

[0085] Third step, the mass transfer sub-model calculates the three-dimensional moisture diffusion flux according to the hydration time parameter, and its control equation is:

[0086]

[0087] Where: J w : Three-dimensional moisture flux vector; D w : Moisture diffusion coefficient; C w : Moisture concentration field; v w : Three-dimensional convective velocity field caused by swelling;

[0088] In the fourth step, the biochemical reaction sub-model receives the temperature field distribution matrix and the moisture flux vector, and calculates the yeast activity parameter Y(t) and the lactic acid bacteria metabolism parameter L(t). The specific formulas are as follows:

[0089]

[0090] Where: t hydrate : Hydration time input by the user; T ferment : Initial fermentation temperature input by the user; T ref Yeast metabolism reference temperature;

[0091] In the fifth step, the deformation mechanics sub-model calculates the dough swelling coefficient matrix E according to the temperature field distribution matrix, the moisture flux vector and the yeast activity parameter ij :

[0092]

[0093] Where: E ij : Element of the swelling coefficient matrix; γ T : Temperature deformation weight coefficient; γ w : Moisture deformation weight coefficient; X-direction gradient of the temperature field at the (i, j) position; Time change rate of the moisture flux modulus at the (i, j) position.

[0094] Among them, the heat conduction sub-model calculates the temperature field distribution inside the dough based on the fermentation temperature parameter, quantifies the dynamic balance between yeast heat generation and environmental heat transfer through partial differential equations, and provides temperature gradient data support for the mass transfer sub-model. The mass transfer sub-model calculates the three-dimensional moisture diffusion flux based on the hydration time parameter, determines the spatial variations of the moisture concentration field and the convective velocity field in combination with the temperature field distribution, and provides dynamic moisture diffusion parameters for the biochemical reaction sub-model. The biochemical reaction sub-model integrates the temperature field distribution matrix and the moisture flux vector, calculates the yeast activity parameter and the lactic acid bacteria metabolism parameter through integration and weighting, and quantifies the spatio-temporal distribution characteristics of microbial metabolites during fermentation. The deformation mechanics sub-model constructs a calculation equation for the expansion coefficient matrix based on the temperature field gradient, the time derivative of the moisture flux, and the yeast activity parameter, and couples the thermal expansion effect and the wet expansion effect into a unified deformation prediction model. Each sub-model forms a closed-loop feedback through data interaction. The outputs of heat conduction and mass transfer drive biochemical reactions, and the metabolic parameters of biochemical reactions further affect the expansion prediction of deformation mechanics. The results of deformation mechanics inversely constrain the update of the boundary conditions of the temperature field and the moisture field. The deep coupling of multiple physical fields effectively captures the non-linear interaction of temperature-moisture-microbe-deformation during dough fermentation, realizes the synchronous optimization of cross-scale physical property parameters through the simultaneous solution of differential equations, significantly improves the prediction accuracy of the expansion coefficient, acidity distribution, and browning intensity, and provides a high-confidence quantitative basis for adjusting baking process parameters.

[0095] Based on the above embodiments, the acidity distribution vector is generated from the output of the biochemical reaction sub-model, and the specific formula is as follows:

[0096] A k = η·Y(t)·(1 - exp(-λt)) + μ·L(t)·exp(-κt);

[0097] Where: A k : the k-th component of the acidity distribution vector, reflecting the local acidity value; η: yeast acid production coefficient; λ: yeast metabolism time decay coefficient; μ: lactic acid bacteria acid production coefficient; κ: lactic acid bacteria metabolism time decay coefficient.

[0098] Based on the above embodiments, the above-mentioned execution subject generates the browning intensity value according to the temperature field distribution matrix of the heat conduction sub-model and the moisture concentration field of the mass transfer sub-model, following these steps:

[0099] First step, based on the temperature field T surface (x, t) of the dough surface area and the average moisture concentration calculate the surface browning reaction rate based on the Arrhenius equation, and the specific formula is as follows:

[0100]

[0101] where k b : the base number of the browning reaction rate; E a : the activation energy of the Maillard reaction; C crit : the critical moisture concentration of the browning reaction; R: the ideal gas constant;

[0102] Second, perform a time integral on the browning reaction rate to generate a browning intensity value:

[0103]

[0104] where: t bake-start and t bake-end : the start and end times of the baking stage input by the user.

[0105] Based on the above embodiments, the multi-physical field coupling prediction model is trained by error backpropagation through a historical baking data set; the loss function of the multi-physical field coupling prediction model is defined as:

[0106] L = α·‖E pred - E true ‖2 + β·‖A pred - A true ‖1 + γ·|B pred - B true |;

[0107] where: α, β, γ: weight coefficients, satisfying α + β + γ = 1; E pred : the predicted expansion coefficient matrix; E true : the measured expansion coefficient matrix in historical data; A pred : the predicted acidity distribution vector; A true : the measured acidity distribution vector in historical data; B pred : the predicted browning intensity value; B true : the measured browning intensity value in historical data.

[0108] Among them, in the loss function, the dilation coefficient matrix uses the L2 norm to constrain the overall shape error, the acidity distribution vector uses the L1 norm to strengthen the local sparsity error, the browning intensity value uses the absolute value loss to control the scalar deviation, and the weight coefficient dynamically adjusts the contribution of the three types of errors to the update of the model parameters. During the training process, the temperature field distribution error output by the heat conduction sub-model affects the water diffusion parameters of the mass transfer sub-model and the yeast activity calculation parameters of the biochemical reaction sub-model simultaneously through backpropagation; the water flux error of the mass transfer sub-model reversely corrects the weight of the dilation coefficient calculation of the deformation mechanics sub-model; the acidity prediction error of the biochemical reaction sub-model adjusts the boundary condition constraints of heat conduction and mass transfer through the time integral term feedback. The prediction errors of the dilation coefficient, acidity distribution, and browning intensity form cross-couplings in the backpropagation link, forcing the parameter update processes of the heat conduction, mass transfer, biochemical reaction, and deformation mechanics sub-models to simultaneously meet the joint convergence conditions of multiple physical fields. In this way, the isolated optimization mode of the traditional single-field model is broken, and through the joint error constraint of dilation-acidity-browning, the deep coupling of the temperature field-water field-microbial field-deformation field is realized, effectively improving the cross-scale prediction ability of the model for the fermentation expansion dynamics, acidity spatial distribution, and Maillard reaction degree.

[0109] S104: Generate a three-dimensional volume prediction map based on the dough dilation coefficient matrix and generate a taste evaluation index based on the acidity distribution vector and the browning intensity value;

[0110] Specifically, in some embodiments, the generation of the three-dimensional volume prediction map specifically includes: converting the dough dilation coefficient matrix into spatial geometric data through a discretized grid mapping algorithm, where the height calculation formula for the (i,j) grid point is:

[0111]

[0112] where: h ij : The height value of the (i,j) grid point in the three-dimensional model; E ij : The element of the dilation coefficient matrix; Δt: The baking time step; T ferment : The initial fermentation temperature input by the user; T base : The reference temperature constant.

[0113] Based on the above embodiments, the generation of the taste evaluation index specifically includes:

[0114] In the first step, use the fuzzy logic algorithm to perform an acidity balance score on the acidity distribution vector, and the scoring function is:

[0115]

[0116] where: S acid: Acidity balance score, in the range of 0 - 1, where 1 represents the best balance; The average value of the acidity distribution vector; ξ: Sensitivity coefficient; n: Dimension of the acidity distribution vector;

[0117] In the second step, for the browning intensity value B pred Perform coking degree scoring;

[0118] In the third step, generate a taste evaluation index based on the acidity balance score and the coking degree score.

[0119] S105: Send the three - dimensional volume prediction map and the taste evaluation index to a preset terminal for visual display.

[0120] Preferably, in some embodiments, after generating the visual display, it further includes: Based on the calculation of the deviation degree between the prediction result set and the historical optimal parameters, the deviation degree is defined as:

[0121] D = ‖E pred - E opt ‖2 + ‖A pred - A opt ‖1 + |B pred - B opt |

[0122] When D > D th Generate a formula parameter adjustment suggestion table including the hydration time correction amount and the fermentation temperature compensation value, where: D: Comprehensive deviation degree; E opt : Historical optimal expansion coefficient matrix; A opt : Historical optimal acidity distribution vector; B opt : Historical optimal browning intensity value; D th : Deviation degree threshold. In this way, by calculating the comprehensive deviation degree between the prediction parameters and the historical optimal values, a formula correction suggestion can be generated, thereby effectively reducing the product defects caused by parameter deviation and improving the baking success rate and resource utilization rate.

[0123] Based on the above - mentioned embodiments, the calculation formula for the hydration time correction amount is as follows: The calculation formula for the fermentation temperature compensation value is as follows: Where, K h : Hydration time correction coefficient; K t : Fermentation temperature compensation coefficient.

[0124] Please refer to Figure 2 , based on the same inventive concept as the bread baking simulation method in the foregoing embodiments, the embodiments of the present application provide a bread baking simulation system, including:

[0125] The first acquisition module 201 is configured to acquire a set of quinoa dough formula parameters input by a user, and the set of quinoa dough formula parameters includes the mass ratio of quinoa flour, the hydration time, the initial fermentation temperature, and the duration;

[0126] The first generation module 202 is configured to perform parameter normalization processing on the set of quinoa dough formula parameters to generate a standard input vector;

[0127] The first calculation module 203 is configured to input the standard input vector into a pre-trained multi-physical-field coupling prediction model for forward calculation to obtain a set of prediction results including a dough expansion coefficient matrix, an acidity distribution vector, and a browning intensity value;

[0128] The second generation module 204 is configured to generate a three-dimensional volume prediction map based on the dough expansion coefficient matrix, and generate a taste evaluation index based on the acidity distribution vector and the browning intensity value;

[0129] The visualization module 205 is configured to send the three-dimensional volume prediction map and the taste evaluation index to a preset terminal for visual display.

[0130] In some embodiments, the first generation module 202 is specifically configured to use the min-max scaling algorithm to linearly transform parameters with different dimensions into the interval [0,1] to generate a standard input vector. The specific calculation formula is:

[0131]

[0132] Where: X (i) : The i-th original parameter; The minimum value of the i-th parameter in the historical data; The maximum value of the i-th parameter in the historical data; The value of the i-th parameter after normalization.

[0133] In some embodiments, the multi-physical-field coupling prediction model includes a coupling structure of a heat conduction sub-model, a mass transfer sub-model, a biochemical reaction sub-model, and a deformation mechanics sub-model; the first calculation module 203 is specifically configured to:

[0134] Input the standard input vector into the heat conduction sub-model and the mass transfer sub-model simultaneously;

[0135] The heat conduction sub-model calculates the temperature field distribution inside the dough according to the fermentation temperature parameter, and its partial differential equation and boundary conditions are:

[0136]

[0137] Where: T: Temperature field distribution matrix; α: Dough thermal diffusivity; β: Yeast heat production conversion factor; Q yeast (t): Yeast heat production rate, k1: Base value of the heat production rate of yeast; k2: Temperature sensitivity coefficient; Average temperature of dynamic fermentation; T oven : Oven ambient temperature;

[0138] The mass transfer sub-model calculates the three-dimensional moisture diffusion flux based on the hydration time parameter, and its governing equation is:

[0139]

[0140] Where: J w : Three-dimensional moisture flux vector; D w : Moisture diffusion coefficient; C w : Moisture concentration field; v w : Three-dimensional convective velocity field caused by swelling;

[0141] The biochemical reaction sub-model receives the temperature field distribution matrix and the moisture flux vector, and calculates the yeast activity parameter Y(t) and the lactic acid bacteria metabolism parameter L(t). The specific formulas are as follows:

[0142]

[0143] Where: t hydrate : Hydration time input by the user; T ferment : Primary fermentation temperature input by the user; T ref Yeast metabolism reference temperature;

[0144] The deformation mechanics sub-model calculates the dough swelling coefficient matrix E according to the temperature field distribution matrix, the moisture flux vector and the yeast activity parameter ij :

[0145]

[0146] Where: E ij : Element of the swelling coefficient matrix; γ T : Temperature deformation weight coefficient; γ w : Moisture deformation weight coefficient; X-direction gradient of the temperature field at the (i,j) position; Time change rate of the moisture flux modulus at the (i,j) position.

[0147] In some embodiments, the first calculation module 203 is specifically further configured to generate an acidity distribution vector through the biochemical reaction sub-model. The specific formula is as follows:

[0148] A k = η·Y(t)·(1 - exp(-λt)) + μ·L(t)·exp(-κt);

[0149] Where: Ak : The k-th component of the acidity distribution vector, reflecting the local acidity value; η: Yeast acid production coefficient; λ: Yeast metabolic time decay coefficient; μ: Lactic acid bacteria acid production coefficient; κ: Lactic acid bacteria metabolic time decay coefficient.

[0150] In some embodiments, the first calculation module 203 is further specifically configured to generate a browning intensity value according to the temperature field distribution matrix of the heat conduction sub-model and the moisture concentration field of the mass transfer sub-model according to the following steps:

[0151] According to the temperature field T surface (x, t) of the dough surface area and the average moisture concentration Based on the Arrhenius equation, calculate the surface browning reaction rate, and the specific formula is as follows:

[0152]

[0153] Among them, k b : Browning reaction rate base number; E a : Maillard reaction activation energy; C crit : Browning reaction critical moisture concentration; R: Ideal gas constant;

[0154] Perform time integration on the browning reaction rate to generate a browning intensity value:

[0155]

[0156] Among them: t bake-start 、t bake-end : The start and end times of the baking stage input by the user.

[0157] In some embodiments, the second generation module 204 is specifically configured to: convert the dough expansion coefficient matrix into spatial geometric data through a discretized grid mapping algorithm, and the height calculation formula of the (i, j) grid point is:

[0158]

[0159] Among them: h ij : The height value of the (i, j) grid point in the three-dimensional model; E ij : Expansion coefficient matrix element; Δt: Baking time step; T ferment : The initial fermentation temperature input by the user; T base : Benchmark temperature constant.

[0160] In some embodiments, the second generation module 204 is further specifically configured to:

[0161] Use a fuzzy logic algorithm to perform an acidity balance score on the acidity distribution vector, and the scoring function is:

[0162]

[0163] Where: S acid : Acidity balance score, in the range of 0 - 1, where 1 represents the best balance; Acidity score

[0164] The average value of the acidity distribution vector; ξ: Sensitivity coefficient; n: Dimension of the acidity distribution vector;

[0165] For the browning intensity value B pred Perform coking degree scoring;

[0166] Generate a taste evaluation index based on the acidity balance score and the coking degree score.

[0167] In some embodiments, the multi - physical - field coupling prediction model is trained by error backpropagation through a historical baking data set; the loss function of the multi - physical - field coupling prediction model is defined as:

[0168] L = α·‖E pred - E true ‖2 + β·‖A pred - A true ‖1 + γ·|B pred - B true |;

[0169] Where: α, β, γ: Weight coefficients, satisfying α + β + γ = 1; E pred : Predicted expansion coefficient matrix; E true : Measured expansion coefficient matrix in historical data; A pred : Predicted acidity distribution vector; A true : Measured acidity distribution vector in historical data; B pred : Predicted browning intensity value; B true : Measured browning intensity value in historical data.

[0170] In some embodiments, the bread baking simulation system further includes a second calculation module 206, which is used to calculate the deviation degree based on the prediction result set and the historical optimal parameters after generating the visual display. The specific formula is as follows:

[0171] D = ‖E pred - E opt ‖2 + ‖A pred - A opt ‖1 + |B pred - B opt |

[0172] When D > D th At this time, generate a recipe parameter adjustment suggestion table including the hydration time correction amount and the fermentation temperature compensation value, where: D: Comprehensive deviation degree; E opt: Historical optimal expansion coefficient matrix; A opt : Historical optimal acidity distribution vector; B opt : Historical optimal browning intensity value; D th : Deviation threshold.

[0173] It can be understood that the various modules recorded by this bread baking simulation system correspond to the respective steps in the bread baking simulation method described in the reference Figure 1 description. Thus, the operations, features, and beneficial effects described above for the method also apply to the bread baking simulation system and the modules included therein, and will not be elaborated here.

[0174] Please refer to Figure 3 , based on the inventive concept of a bread baking simulation method in the foregoing embodiment, an embodiment of the present application provides an electronic device. The electronic device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device includes a processing device 301 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in the ROM 302 (Read Only Memory) or a program loaded from the storage device 308 into the RAM 303 (Random Access Memory). In the RAM 303, various programs and data required for the operation of the electronic device are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. The input / output interface (i.e., the I / O interface 305) is also connected to the bus 304.

[0175] Generally, the following devices can be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 can allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data.

[0176] In particular, according to some embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program code for performing the methods shown in the flowcharts. In such some embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above functions defined in the methods of some embodiments of the present application are performed.

[0177] It should be noted that the computer-readable medium described in some embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in some embodiments of the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0178] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0179] The computer-readable medium described above can be included in the above-mentioned electronic device; it can also exist separately without being assembled into the electronic device. The computer-readable medium carries one or more programs, and when the above one or more programs are executed by the electronic device, the electronic device can implement the method steps of any of the above technical solutions.

[0180] Computer program code for performing the operations of some embodiments of the present application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0181] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0182] The modules described in some embodiments of the present application can be implemented in software or in hardware. The described modules can also be provided in a processor. It can be understood that the names of these modules do not constitute a limitation on the modules themselves.

[0183] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Arrays (FPGA), Application Specific Integrated Circuits (ASIC), Application Specific Standard Products (ASSP), System on a Chip (SOC), Complex Programmable Logic Devices (CPLD), and so on.

[0184] Some embodiments of the present application also provide a computer program product, including a computer program that, when executed by a processor, implements any one of the above-described bread baking simulation methods.

[0185] Although the present invention has been described in detail above with general descriptions and specific embodiments, on the basis of the present invention, some modifications or improvements can be made, which are obvious to those skilled in the art. Therefore, these modifications or improvements made without departing from the spirit of the present invention all fall within the scope of the present invention claimed.

Claims

1. A bread baking simulation method, characterized in that, It includes the following steps: Obtain the quinoa dough formula parameter set input by the user, where the quinoa dough formula parameter set includes the mass ratio of quinoa flour, the hydration time, the primary fermentation temperature and the duration; Perform parameter normalization on the quinoa dough formula parameter set to generate a standard input vector; Input the standard input vector into a pre-trained multi-physics field coupling prediction model for forward calculation to obtain a prediction result set including a dough expansion coefficient matrix, an acidity distribution vector and a browning intensity value; Generate a three-dimensional volume prediction map based on the dough expansion coefficient matrix, and generate a taste evaluation index based on the acidity distribution vector and the browning intensity value; Send the three-dimensional volume prediction map and the taste evaluation index to a preset terminal for visual display.

2. The bread baking simulation method according to claim 1, wherein The parameter normalization process uses the min-max scaling algorithm to linearly transform parameters with different dimensions into the [0,1] interval to generate the standard input vector. The specific calculation formula is: Where: X (i) : the i-th original parameter; the minimum value of the i-th parameter in the historical data; the maximum value of the i-th parameter in the historical data; the value of the i-th parameter after normalization.

3. The bread baking simulation method according to claim 2, wherein The multi-physics field coupling prediction model includes a coupling structure of a heat conduction sub-model, a mass transfer sub-model, a biochemical reaction sub-model and a deformation mechanics sub-model. The step of inputting the standard input vector into the pre-trained multi-physics field coupling prediction model for forward calculation to obtain a prediction result set including a dough expansion coefficient matrix, an acidity distribution vector and a browning intensity value includes: Input the standard input vector into both the heat conduction sub-model and the mass transfer sub-model simultaneously; The heat conduction sub-model calculates the temperature field distribution inside the dough according to the fermentation temperature parameter, and its partial differential equation and boundary conditions are: Where: T: temperature field distribution matrix; α: dough heat diffusion coefficient; β: yeast heat production conversion factor; Q yeast (t): yeast heat production rate, k1: yeast heat production rate base; k2: temperature sensitivity coefficient; Average temperature of dynamic fermentation; T oven : oven ambient temperature; The mass transfer sub-model calculates the three-dimensional moisture diffusion flux according to the hydration time parameter, and its control equation is: Where: J w : three-dimensional moisture flux vector; D w : moisture diffusion coefficient; C w : moisture concentration field; v w : three-dimensional convective velocity field caused by swelling; The biochemical reaction sub-model receives the temperature field distribution matrix and the moisture flux vector, and calculates the yeast activity parameter Y(t) and the lactic acid bacteria metabolism parameter L(t). The specific formulas are as follows: where: t hydrate : the hydration time input by the user; T ferment : the primary fermentation temperature input by the user; T ref the reference temperature for yeast metabolism; The deformation mechanics sub-model calculates the dough expansion coefficient matrix E according to the temperature field distribution matrix, the moisture flux vector and the yeast activity parameters ij : Where: E ij : the element of the coefficient matrix of expansion; γ T : the weight coefficient of temperature deformation; γ w : the weight coefficient of moisture deformation; The x-direction gradient of the temperature field at the position (i, j); The time variation rate of the moisture flux modulus at the position (i, j).

4. The bread baking simulation method according to claim 3, characterized in that, The acidity distribution vector is generated through the output of the biochemical reaction sub-model. The specific formula is as follows: A k = η·Y(t)·(1 - exp(-λt)) + μ·L(t)·exp(-κt); Where: A k : the k-th component of the acidity distribution vector, reflecting the local acidity value; η: the acid production coefficient of yeast; λ: the time decay coefficient of yeast metabolism; μ: the acid production coefficient of lactic acid bacteria; κ: the time decay coefficient of lactic acid bacteria metabolism.

5. The bread baking simulation method according to claim 4, characterized in that, The generation of the three-dimensional volume prediction map specifically includes: converting the dough expansion coefficient matrix into spatial geometric data through a discretized grid mapping algorithm, where the height of the (i,j) grid point is calculated as: Where: h ij : The height value of the (i, j) grid point in the three-dimensional model; E ij : The element of the expansion coefficient matrix; Δt: The baking time step; T ferment : The initial fermentation temperature input by the user; T base : The reference temperature constant.

6. The bread baking simulation method according to claim 5, characterized in that The generation of the taste evaluation index specifically includes: Use the fuzzy logic algorithm to perform an acidity balance score on the acidity distribution vector, and the scoring function is: Where: S acid : Acidity balance score, in the range of 0 - 1, where 1 represents the best balance; The average value of the acidity distribution vector; ξ: Sensitivity coefficient; n: Dimension of the acidity distribution vector; For the browning intensity value B pred Perform coking degree scoring; Generate the taste evaluation index according to the acidity balance score and the coking degree score.

7. A bread baking simulation system, characterized in that, It includes: The first acquisition module is used to obtain the quinoa dough formula parameter set input by the user, where the quinoa dough formula parameter set includes the mass ratio of quinoa flour, the hydration time, the primary fermentation temperature and the duration; The first generation module is used to perform parameter normalization on the quinoa dough formula parameter set to generate a standard input vector; The first calculation module is used to input the standard input vector into a pre-trained multi-physics field coupling prediction model for forward calculation to obtain a prediction result set including a dough expansion coefficient matrix, an acidity distribution vector and a browning intensity value; A second generation module, configured to generate a three-dimensional volume prediction map according to the dough expansion coefficient matrix, and generate a taste evaluation index based on the acidity distribution vector and the browning intensity value; A visualization module, configured to send the three-dimensional volume prediction map and the taste evaluation index to a preset terminal for visual display.

8. An electronic device, characterized in that, Comprising: One or more processors; A storage device storing one or more programs thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processing device, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processing device, the method according to any one of claims 1 to 6 is implemented.

Images