Method and system for optimizing process parameters of facial mask preparation using artificial intelligence

Abstract

The present invention relates to a method and system for optimizing the process parameters of mask preparation using artificial intelligence, which relates to the field of preparation optimization. It collects the light-transmitting images of the mask fabric to be impregnated, and identifies the thickness of the mask fabric to obtain the first and second thicknesses; collects the viscosity information of the essence liquid to obtain the range of impregnation process parameters, randomly generates the first impregnation parameter within it, and combines the viscosity information, the first and second thicknesses to conduct impregnation simulation prediction to obtain the first and second impregnation amounts; based on the first and second impregnation amounts, combines the first and second thicknesses and viscosity information to conduct mask usage prediction to obtain the first and second essence dripping rates and the first and second mask fabric deformation rates, combines the first and second impregnation amounts to calculate the first and second mask scores for impregnation parameter optimization, obtains the optimal impregnation parameter for mask impregnation preparation, and solves the technical problems that in the mask preparation process, the setting of impregnation parameters depends on manual experience, it is difficult to achieve precise optimization, and it affects the quality and consistency of masks.

Description

Technical Field

[0001] The present invention relates to the field of preparation optimization, and particularly to a method and system for optimizing the process parameters of facial mask preparation using artificial intelligence. Background Art

[0002] In the facial mask preparation process, the impregnation process is a key step in evenly adsorbing the essence on the mask cloth. As an important process parameter in this process, the setting of the impregnation time directly affects the quality of the facial mask and the user experience. The setting of the impregnation time mainly relies on the experience of the operator and experimental adjustment. This method is not only inefficient but also difficult to ensure the quality consistency of each batch of facial masks. If the impregnation time is too short, the essence cannot be fully adsorbed on the mask cloth, resulting in uneven distribution of the essence, which affects the skin care effect of the facial mask and the user experience. On the other hand, if the impregnation time is too long, it may cause the mask cloth to swell and deform excessively. Especially for some special material mask cloths, such as biological fiber mask cloths, long-term impregnation will make the mask cloth become soft and easy to deform, thus affecting the fit and use feeling of the facial mask. Summary of the Invention

[0003] Aiming at the technical problem in the prior art that the setting of impregnation parameters in the facial mask preparation process depends on manual experience, it is difficult to achieve precise optimization, and it affects the quality and consistency of the facial mask, the present invention provides a method and system for optimizing the process parameters of facial mask preparation using artificial intelligence to solve this problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] In the first aspect, the present invention provides a method for optimizing the process parameters of facial mask preparation using artificial intelligence. The method includes: collecting a light-transmitting image of the target mask cloth to be impregnated, identifying the thickness of the mask cloth, and obtaining the first thickness of the first region and the second thickness of the second region; collecting the viscosity information of the essence, and obtaining the impregnation parameter range of the impregnation process parameters; randomly generating a first impregnation parameter within the impregnation parameter range, combining the viscosity information, the first thickness, and the second thickness, and performing impregnation simulation prediction to obtain the first impregnation amount and the second impregnation amount; according to the first impregnation amount and the second impregnation amount, combining the first thickness, the second thickness, and the viscosity information, performing facial mask use prediction to obtain the first essence dripping rate, the first mask cloth deformation rate, the second essence dripping rate, and the second mask cloth deformation rate, combining the first impregnation amount and the second impregnation amount, calculating to obtain the first facial mask score and the second facial mask score, performing impregnation parameter optimization to obtain the optimal impregnation parameter, and performing facial mask impregnation preparation.

[0006] Second aspect, the present invention provides a system for optimizing process parameters of mask preparation using artificial intelligence. The system includes: an image acquisition module for performing light-transmitting image acquisition on a target mask cloth to be impregnated, identifying the thickness of the mask cloth, and obtaining a first thickness of a first region and a second thickness of a second region; a parameter acquisition module for collecting viscosity information of the essence liquid and obtaining an impregnation parameter range of the impregnation process parameters; a simulation prediction module for randomly generating a first impregnation parameter within the impregnation parameter range, combining the viscosity information, the first thickness, and the second thickness to perform impregnation simulation prediction, and obtaining a first impregnation amount and a second impregnation amount; an optimization preparation module for performing mask usage prediction based on the first impregnation amount and the second impregnation amount, combining the first thickness, the second thickness, and the viscosity information, obtaining a first essence dripping rate, a first mask cloth deformation rate, a second essence dripping rate, and a second mask cloth deformation rate, calculating a first mask score and a second mask score based on the first impregnation amount and the second impregnation amount, optimizing the impregnation parameters, obtaining the optimal impregnation parameters, and performing mask impregnation preparation.

[0007] The beneficial effects of the present invention are: by collecting the light-transmitting image of the mask cloth to identify the thickness, collecting the viscosity information of the essence liquid, combining with the randomly generated impregnation parameters for simulation prediction, further predicting the essence dripping rate and the mask cloth deformation rate when using the mask, and calculating the mask score to optimize the impregnation parameters, so as to achieve precise control of the impregnation process and improve the mask quality and user experience. Description of the Drawings

[0008] Figure 1 It is a schematic flowchart of a method for optimizing process parameters of mask preparation using artificial intelligence provided by the present invention.

[0009] Figure 2 It is a schematic structural diagram of a system for optimizing process parameters of mask preparation using artificial intelligence provided by the present invention.

[0010] Description of the reference numerals: image acquisition module 11, parameter acquisition module 12, simulation prediction module 13, optimization preparation module 14. Detailed Embodiments

[0011] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0012] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0013] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without the use of these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0014] Embodiment 1:

[0015] As Figure 1 shown, the embodiment of the present invention provides a method for optimizing the process parameters of a facial mask preparation using artificial intelligence. The method includes:

[0016] S10: Collect a light-transmitting image of the target fabric to be impregnated, identify the fabric thickness, and obtain the first thickness of the first region and the second thickness of the second region.

[0017] Exemplarily, a transmissive image of the target membrane to be impregnated is collected. This step is usually carried out by illuminating the back of the membrane, allowing the light to penetrate the membrane and project onto the image acquisition device, thereby obtaining the transmissive image of the membrane. Then, image processing techniques and deep learning algorithms are used to identify the thickness of the membrane from the collected transmissive image. During this process, the first region (i.e., the T region) and the second region (i.e., the U region) on the membrane can be accurately distinguished. Since the T region is usually located in the central part of the face, such as near the nose, forehead, and chin, these regions require more essence during mask application to achieve better skin care effects. Therefore, the membrane in the T region is designed to be relatively thick to adsorb more essence. The U region is located on both sides of the face, such as the cheek area. These regions are relatively flat and require less essence. Therefore, the membrane in the U region is designed to be relatively thin. Through transmissive image collection and thickness identification techniques, the thicknesses of the membranes in the T region and the U region can be accurately obtained, providing basic data support for the optimization of subsequent impregnation parameters. For example, if the thickness of the membrane in the T region is insufficient, it may lead to insufficient adsorption of the essence, affecting the skin care effect of the mask; while if the membrane in the U region is too thick, it may cause the mask to be not well-fitted during application, affecting the user experience.

[0018] S20: Collect the viscosity information of the essence to obtain the impregnation parameter range of the impregnation process parameters.

[0019] Optionally, the viscosity of the essence directly affects the effect of the impregnation process. Therefore, it is necessary to specifically collect the viscosity information of the essence currently used for mask production. Usually, a dedicated device such as a viscometer is used to complete the viscosity information collection, and the viscosity value of the essence can be accurately measured. After obtaining the viscosity information, combined with the conventional range of the impregnation time, the impregnation parameter range of the impregnation process parameters can be determined. The conventional range of the impregnation time is usually 10 - 30 minutes, but it specifically depends on the membrane material and the viscosity of the essence. Among them, the impregnation parameter range is a reasonable impregnation time range, aiming to ensure that the essence can be fully and evenly adsorbed on the membrane, while avoiding the membrane from swelling and deforming due to too long impregnation time. For example, if the viscosity of the essence is high, then the impregnation time may need to be appropriately extended to ensure that the essence can fully penetrate into the membrane; conversely, if the viscosity of the essence is low, then the impregnation time can be appropriately shortened to avoid excessive swelling of the membrane. By collecting the viscosity information of the essence and determining the impregnation parameter range, accurate data support can be provided for subsequent impregnation simulation prediction and mask use prediction.

[0020] S30: Randomly generate a first impregnation parameter within the impregnation parameter range, and combine the viscosity information, the first thickness, and the second thickness to conduct an impregnation simulation prediction to obtain a first impregnation amount and a second impregnation amount.

[0021] Further, after determining the impregnation parameter range, a first impregnation parameter is randomly generated within this range, which is usually a specific impregnation time value. Then, this impregnation parameter is combined with the essence viscosity information collected previously, as well as the first thickness of the first region (T-zone) and the second thickness of the second region (U-zone) obtained through the light-transmitting image acquisition and thickness recognition technology, and input into the pre-trained impregnation simulation prediction model. The impregnation simulation prediction model can simulate the adsorption of the essence on the membrane cloth under different impregnation parameters by using machine learning algorithms. Through simulation prediction, the impregnation amounts in the first region and the second region after impregnation can be obtained, that is, the distribution amounts of the essence in the T-zone and the U-zone. For example, if the simulation prediction result shows that the impregnation amount in the T-zone is insufficient, then it may be necessary to adjust the impregnation parameters, such as increasing the impregnation time or increasing the viscosity of the essence, to ensure that the T-zone can adsorb enough essence; conversely, if the impregnation amount in the U-zone is excessive, resulting in the deformation of the membrane cloth, then it is necessary to appropriately reduce the impregnation time or decrease the viscosity of the essence. Through this step, precise control of the impregnation process can be achieved, providing key data support for subsequent mask usage prediction and impregnation parameter optimization.

[0022] S40: According to the first impregnation amount and the second impregnation amount, combined with the first thickness, the second thickness and the viscosity information, perform mask usage prediction to obtain the first essence dripping rate, the first membrane cloth deformation rate, the second essence dripping rate and the second membrane cloth deformation rate, calculate and obtain the first mask score and the second mask score by combining the first impregnation amount and the second impregnation amount, perform impregnation parameter optimization to obtain the optimal impregnation parameter, and perform mask impregnation preparation.

[0023] Specifically, after obtaining the first impregnation amount and the second impregnation amount, further prediction of mask usage is carried out in combination with the first thickness, the second thickness, and the essence viscosity information. This step aims to simulate the possible situations during the actual use of the mask, such as the dripping of the essence and the deformation of the mask cloth. Specifically, if the impregnation time is too long or the essence is too much, it may cause the mask cloth to swell and deform. Especially for some mask cloth materials that are easily softened, the deformation will be more obvious. At the same time, too much essence may also cause the essence to drip during the use of the mask, affecting the user experience. Therefore, through the mask usage prediction model, the essence dripping rate and the mask cloth deformation rate of the first area (T-zone) and the second area (U-zone) can be predicted. For example, if the prediction result shows that the essence dripping rate in the T-zone is high, then the impregnation parameters may need to be adjusted to reduce the amount of essence in the T-zone; if the mask cloth deformation rate in the U-zone is high, then the impregnation process needs to be optimized to avoid excessive swelling of the mask cloth. Based on the prediction results, the first mask score and the second mask score are calculated in combination with the first impregnation amount and the second impregnation amount. These two scores are comprehensive evaluation indicators that comprehensively consider multiple factors such as essence distribution, mask cloth deformation, and user experience. By comparing the mask scores under different impregnation parameters, impregnation parameter optimization can be carried out to find the optimal combination of impregnation parameters for subsequent mask impregnation preparation. This can not only ensure the quality and consistency of the mask, but also improve the user experience and satisfaction.

[0024] In a preferred embodiment, a light-transmitting image of the target mask cloth to be impregnated is collected, and the mask cloth thickness is identified to obtain the first thickness of the first area and the second thickness of the second area, including: collecting a light-transmitting image of the target mask cloth to be impregnated under preset light-transmitting parameters to obtain a mask cloth light-transmitting image; inputting the mask cloth light-transmitting image into a mask cloth thickness identification channel, and identifying and outputting to obtain the first thickness of the first area and the second thickness of the second area, where the first area is the T-zone and the second area is the U-zone.

[0025] Preferably, in order to achieve precise optimization of the impregnation parameters, it is necessary to collect a light-transmitting image of the target mask cloth to be impregnated. The light-transmitting image collection process is carried out under preset light-transmitting parameters to ensure that the collected image can clearly reflect the thickness distribution of the mask cloth. The preset light-transmitting parameters usually include the light source type, light intensity, collection angle, etc. The setting of these parameters needs to be adjusted according to the material and characteristics of the mask cloth to obtain the best image collection effect.

[0026] After the light-transmitting image of the mask cloth is collected, it will then be input into a specially trained mask cloth thickness recognition channel for processing. The mask cloth thickness recognition channel is constructed based on a deep learning algorithm and can automatically identify and extract the mask cloth thickness information of the first region (T region) and the second region (U region) in the image. In the first region, since the facial contour is relatively prominent, the mask cloth needs to be designed relatively thick to provide better fit and essence adsorption ability; while in the second region, the facial contour is relatively flat, and the mask cloth is designed relatively thin to reduce unnecessary essence waste and mask cloth deformation.

[0027] Through the processing of the mask cloth thickness recognition channel, the mask cloth thickness of the T region and the U region can be accurately obtained, providing key data support for the optimization of subsequent impregnation parameters. For example, if the recognition result shows that the mask cloth thickness in the T region is insufficient, then the impregnation parameters may need to be adjusted to increase the essence adsorption amount in the T region; if the mask cloth in the U region is too thick, then the impregnation process may need to be optimized to reduce the essence distribution in the U region and avoid mask cloth deformation. The implementation of this step not only improves the accuracy and efficiency of mask preparation, but also lays a solid foundation for enhancing the user experience and mask quality.

[0028] In a preferred embodiment, the training steps of the mask cloth thickness recognition channel include: using deep learning to construct the mask cloth thickness recognition channel; according to the detection data log of the mask cloth, collecting a set of sample mask cloth light-transmitting images, and annotating the average thickness of the first region and the second region of the mask cloth in different sample mask cloth light-transmitting images to obtain a sample first thickness set and a sample second thickness set; using the set of sample mask cloth light-transmitting images, the sample first thickness set and the sample second thickness set to perform supervised training, verification and testing on the mask cloth thickness recognition channel, and completing the training when the accuracy rate is greater than or equal to the accuracy rate threshold.

[0029] Specifically, the training of the mask cloth thickness recognition channel is a process based on deep learning. First, a channel specifically for mask cloth thickness recognition is constructed through deep learning technology, which can automatically learn and extract the feature information in the mask cloth light-transmitting image. Next, according to the detection data log of the mask cloth, a series of light-transmitting images of sample mask cloths are collected, and these images cover mask cloths of different materials, thicknesses and light transmittances to ensure the diversity and representativeness of the training data.

[0030] After the set of sample mask cloth light-transmitting images is collected, it is necessary to annotate the average thickness of the first region (T region) and the second region (U region) of the mask cloth in each image. This step is usually completed by manual measurement or high-precision instruments to ensure the accuracy of the annotation data. After the annotation is completed, a sample first thickness set and a sample second thickness set are obtained, and these two sets respectively correspond to the mask cloth thickness information of the T region and the U region.

[0031] Finally, the film thickness recognition channel is supervised and trained using the set of light-transmitting images of the sample film, the set of sample first thicknesses, and the set of sample second thicknesses. During the training process, the channel continuously learns and adjusts its own parameters to minimize the error between the predicted thickness and the actual thickness. At the same time, through the validation and testing steps, the performance and accuracy of the channel are evaluated. When the accuracy is greater than or equal to the preset accuracy threshold, it is considered that the channel has been trained and can be put into actual use. For example, if the accuracy threshold is set at 95%, then when the accuracy of the channel on the test set reaches or exceeds 95%, it can be considered that it has sufficient recognition ability to accurately predict the thickness of the film.

[0032] In a preferred embodiment, the viscosity information of the essence is collected, and the impregnation parameter range of the impregnation process parameters is obtained, including: collecting the viscosity information of the essence currently used in mask production; obtaining the impregnation parameter range of the impregnation process parameters, where the impregnation process parameters include the impregnation time.

[0033] Specifically, viscosity, as a key physical property of the essence, directly affects its adsorption and penetration effects on the film. Therefore, it is necessary to accurately collect the viscosity information of the essence currently used in mask production, which is usually completed by professional equipment such as viscometers to ensure the accuracy and reliability of the measurement results. Based on the collected viscosity information and the understanding of the mask production process, it is necessary to obtain the impregnation parameter range of the impregnation process parameters. Among the impregnation process parameters, the impregnation time determines the residence time of the essence on the film, which in turn affects the final quality of the mask. The determination of the impregnation parameter range is obtained by comprehensively considering various factors such as the viscosity of the essence, the material of the film, and the desired mask effect. For example, for an essence with a higher viscosity, it may be necessary to appropriately extend the impregnation time to ensure that it can fully penetrate into the film; while for an essence with a lower viscosity, the impregnation time can be relatively shortened to avoid excessive swelling of the film. By scientifically and reasonably determining the impregnation parameter range, it can provide strong process guidance for subsequent mask production.

[0034] In a preferred embodiment, a first impregnation parameter is randomly generated within the impregnation parameter range, and combined with the viscosity information, the first thickness, and the second thickness, impregnation simulation prediction is performed to obtain the first impregnation amount and the second impregnation amount, including: randomly generating a first impregnation parameter within the impregnation parameter range; inputting the first impregnation parameter, viscosity information, first thickness, and second thickness into a pre-trained impregnation amount prediction channel, and predicting and outputting the first impregnation amount and the second impregnation amount, where the impregnation amount prediction channel is trained using sample impregnation parameters, sample viscosity information, sample first thickness, and sample second thickness as input features, and sample first impregnation amount and sample second impregnation amount as output features.

[0035] Further, after determining the impregnation parameter range, a first impregnation parameter is randomly generated within this range. This parameter represents a specific condition during the impregnation process, such as a random value of the impregnation time, which will play a key role in subsequent simulation predictions.

[0036] Subsequently, the generated first impregnation parameter, together with the essence viscosity information collected previously, and the first thickness of the first region (T region) and the second thickness of the second region (U region) obtained by identifying the membrane cloth thickness, are input into the pre-trained impregnation amount prediction channel. This impregnation amount prediction channel is a machine learning-based model that has established a complex relationship between impregnation parameters, viscosity information, membrane cloth thickness, and impregnation amount by learning a large number of sample data.

[0037] During the training process, the impregnation amount prediction channel uses sample impregnation parameters, sample viscosity information, sample first thickness, and sample second thickness as input features, while sample first impregnation amount and sample second impregnation amount are used as output features. Through this training method, the model can learn the variation rules of the impregnation amount of the essence on the T region and U region of the membrane cloth under different conditions.

[0038] When new data (i.e., the generated first impregnation parameter, viscosity information, first thickness, and second thickness) is input, the impregnation amount prediction channel can predict and output the first impregnation amount and the second impregnation amount according to the rules learned previously, such as 11 ml and 6 ml respectively. These two impregnation amounts represent the adsorption amounts of the essence in the T region and U region respectively, and are important indicators for evaluating the impregnation effect. For example, if the prediction result shows that the impregnation amount in the T region is insufficient, then it may be necessary to adjust the impregnation parameters or optimize the essence formula to improve the adsorption effect in the T region.

[0039] In a preferred embodiment, based on the first impregnation amount and the second impregnation amount, in combination with the first thickness, the second thickness and the viscosity information, a mask usage prediction is performed to obtain a first essence dripping rate, a first mask cloth deformation rate, a second essence dripping rate and a second mask cloth deformation rate, including: according to the historical preparation data log of the first region, collecting a sample first impregnation amount set, a first thickness set, a sample viscosity information set, a sample first essence dripping rate set, and a sample first mask cloth deformation rate set as the first usage training data of the first region, wherein the first mask cloth deformation rate includes the proportion of the size deformation of the mask cloth in the first region after impregnation; based on machine learning, constructing a first usage prediction branch for the first region, and using the first usage training data for supervised training, verification and testing until convergence; according to the historical preparation data log of the second region, collecting a sample second impregnation amount set, a second thickness set, a sample viscosity information set, a sample second essence dripping rate set, and a sample second mask cloth deformation rate set as the second usage training data of the second region; based on machine learning, constructing a second usage prediction branch for the second region, and using the second usage training data for supervised training, verification and testing until convergence; inputting the first impregnation amount, the first thickness and the viscosity information into the first usage prediction branch, and predicting and outputting to obtain the first essence dripping rate and the first mask cloth deformation rate; inputting the second impregnation amount, the second thickness and the viscosity information into the second usage prediction branch, and predicting and outputting to obtain the second essence dripping rate and the second mask cloth deformation rate.

[0040] Optionally, in order to accurately predict the usage effect of the mask, especially the essence dripping rate and the mask cloth deformation rate, a prediction method based on machine learning is adopted. First, for the first region (T-zone) of the mask, a series of sample data are collected according to the historical preparation data log, including a sample first impregnation amount set, a first thickness set, a sample viscosity information set, and the corresponding sample first essence dripping rate set and sample first mask cloth deformation rate set. These sample data constitute the first usage training data of the first region, wherein the first mask cloth deformation rate specifically refers to the proportion of the size deformation of the mask cloth in the T-zone after impregnation. For example, if the flattened area of the mask cloth in the T-zone after deformation is 11 square centimeters, and the flattened area of the mask cloth in the T-zone when not deformed is 10 square centimeters under normal circumstances, then the first mask cloth deformation rate is (11 - 10) / 10 = 0.1. The first mask cloth deformation rate is an important indicator for evaluating the fit and comfort of the mask. The sample first essence dripping rate is, for example, the probability of essence dripping during use. For example, if the number of essence drippings when using 10 masks with the same first impregnation amount, first thickness, and viscosity information is 3, then the sample first essence dripping rate is 0.3.

[0041] Furthermore, based on these rich training data, a first usage prediction branch specifically for the T-zone is constructed using machine learning algorithms. Through continuous supervised training, validation, and testing, this prediction branch gradually learns the complex relationships between the impregnation amount, membrane thickness, viscosity information, essence dripping rate, and membrane deformation rate until the model converges, i.e., the prediction performance reaches a stable state.

[0042] Similarly, for the second area (U-zone) of the facial mask, a similar method is adopted. Corresponding sample data is collected according to the historical preparation data log of the U-zone, and a second usage prediction branch for the second area is constructed. This branch also undergoes strict training, validation, and testing to ensure its prediction accuracy.

[0043] In practical applications, when new first impregnation amount, first thickness, and viscosity information are obtained, these data are input into the already trained first usage prediction branch, and the first essence dripping rate and first membrane deformation rate of the T-zone can be predicted and output. Similarly, by inputting the second impregnation amount, second thickness, and viscosity information into the second usage prediction branch, the second essence dripping rate and second membrane deformation rate of the U-zone can be obtained. For example, if the prediction result shows a high essence dripping rate in the T-zone, it may be necessary to adjust the impregnation parameters or optimize the membrane material to reduce the waste of essence; if the membrane deformation rate in the U-zone is large, then it is necessary to consider improving the production process of the membrane or selecting a more suitable membrane material to improve the overall quality of the facial mask.

[0044] In a preferred embodiment, by combining the first impregnation amount and the second impregnation amount, the first facial mask score and the second facial mask score are calculated, and the impregnation parameters are optimized to obtain the optimal impregnation parameters for facial mask impregnation preparation, including: based on the first impregnation amount, first essence dripping rate, and first membrane deformation rate, using the first area preparation function, the first facial mask score is calculated; based on the second impregnation amount, second essence dripping rate, and second membrane deformation rate, using the second area preparation function, the second facial mask score is calculated; according to the first facial mask score and the second facial mask score, the facial mask preparation score is calculated by weighted calculation; continue to randomly generate impregnation parameters and calculate the facial mask preparation score, and optimize the impregnation parameters until convergence, and obtain the optimal impregnation parameters with the maximum facial mask preparation score for facial mask impregnation preparation.

[0045] Specifically, in order to evaluate the quality of facial masks under different impregnation parameters and optimize the impregnation parameters to obtain the best preparation effect, according to the first impregnation amount, first essence dripping rate, and first membrane deformation rate, using a specially designed first area preparation function, the first facial mask score is calculated. This score comprehensively reflects the essence adsorption amount, dripping situation, and membrane deformation degree of the T-zone after impregnation, and is an important indicator for evaluating the quality of the T-zone facial mask.

[0046] Similarly, for the U area, according to the second impregnation amount, the second essence dripping rate, and the second mask cloth deformation rate, through the second area preparation function, the second mask score is calculated and obtained. This score also comprehensively considers various key indicators of the U area, providing a quantitative basis for evaluating the quality of the mask in the U area.

[0047] Next, in order to comprehensively evaluate the preparation effect of the entire mask, a weighted calculation is performed based on the first mask score and the second mask score to obtain the mask preparation score. This score comprehensively considers the mask quality in the T area and the U area and is a comprehensive indicator for evaluating the preparation effect of the entire mask.

[0048] To find the optimal impregnation parameters, a random search method is used to continuously generate new impregnation parameters and calculate the corresponding mask preparation scores. By comparing the mask preparation scores under different impregnation parameters, the optimal solution can be gradually approached. This process continues until the mask preparation score converges, that is, when it no longer changes significantly with the change of impregnation parameters, the optimal impregnation parameters with the maximum mask preparation score can be determined.

[0049] Finally, using the optimal impregnation parameters for mask impregnation preparation can ensure that the mask can achieve the best essence adsorption amount, the least essence dripping, and the smallest mask cloth deformation in both the T area and the U area, thus providing the best user experience. For example, if it is found through optimization that at a certain impregnation time, the essence adsorption amount in the T area is the largest and the dripping rate is the lowest, and at the same time the mask cloth deformation rate in the U area is also the smallest, then this impregnation time is the optimal impregnation parameter and will be used in the subsequent mask preparation process.

[0050] In a preferred embodiment, the first area preparation function is as follows: ; where is the first mask score, , and are weights, is the first impregnation amount, is the preset first impregnation amount for the first area, for example, 10 ml, is the first essence dripping rate, is the first mask cloth deformation rate.

[0051] Specifically, in order to quantitatively evaluate the quality of the mask in the first area (T area), a specially designed first area preparation function is adopted, and the specific calculation formula is: . This function comprehensively considers key indicators such as the first impregnation amount, the first essence dripping rate, and the first mask cloth deformation rate, and obtains the first mask score through weighted calculation. Specifically, the calculation formula of the first mask score includes three main parts: the first impregnation amount ( ) and the preset first impregnation amount ( ), which reflects the closeness between the actual impregnation amount and the desired impregnation amount; the first essence dripping rate ( ), which measures the dripping of the essence during the impregnation process, and the lower the dripping rate, the better the adsorption effect of the essence; and the first membrane deformation rate ( ), which represents the dimensional deformation ratio of the membrane in the T area after impregnation. The smaller the deformation rate, the better the membrane can maintain its original shape, providing better fit and comfort.

[0052] Optionally, the second area preparation function can replace the preset first impregnation amount in the first area preparation function with the preset second impregnation amount in the second area, for example, 5 ml, and the other parameters are the same, that is, it respectively includes the second membrane deformation rate, the second essence dripping rate and the second impregnation amount, and calculates the score of the second facial mask.

[0053] In this formula, , and are weight coefficients, which respectively represent the relative importance of the first impregnation amount, the first essence dripping rate and the first membrane deformation rate in the score. By adjusting these weight coefficients, the priorities of different indicators can be flexibly set according to actual needs. For example, if it is considered that maintaining the shape of the membrane in the T area is more important than reducing the essence dripping, then the value of can be appropriately increased so that the influence of the membrane deformation rate in the score is greater. For example, they are 0.3, 0.4 and 0.3 respectively.

[0054] Taking the actual preparation process as an example, assume that a preset first impregnation amount is set, and the actual impregnation amount , the first essence dripping rate and the first membrane deformation rate are collected. Substituting these data into the first area preparation function, the score of the first facial mask can be calculated. By comparing the values under different impregnation parameters, the influence of different preparation conditions on the quality of the facial mask in the T area can be evaluated, and then the impregnation parameters can be optimized to improve the overall quality of the facial mask.

[0055] A method for optimizing the process parameters of facial mask preparation using artificial intelligence provided by an embodiment of the present invention has at least the following technical effects:

[0056] 1. Through the membrane thickness recognition channel constructed by deep learning, the membrane thickness of different areas (T area and U area) of the facial mask can be accurately recognized, which not only improves the accuracy of membrane thickness measurement, but also provides key data support for the subsequent optimization of impregnation process parameters. The regional analysis makes the facial mask preparation more suitable for the skin needs of different areas of the face, improving the use effect and comfort of the facial mask.

[0057] 2. By utilizing a pre-trained impregnation amount prediction channel, combining randomly generated impregnation parameters, viscosity information, and membrane cloth thickness data, impregnation simulation prediction is carried out to obtain the first impregnation amount and the second impregnation amount, which can predict in advance the essence adsorption amount under different impregnation conditions, providing a scientific basis for optimizing the impregnation process parameters. At the same time, through the prediction branch constructed by machine learning, the essence dripping rate and membrane cloth deformation rate during the use of the facial mask can be accurately predicted, further improving the accuracy and reliability of facial mask preparation.

[0058] 3. By constructing the preparation functions of the first region and the second region, combining key indicators such as the impregnation amount, essence dripping rate, and membrane cloth deformation rate, the first facial mask score and the second facial mask score are calculated, and the facial mask preparation score is obtained by weighted calculation. This comprehensive scoring system can comprehensively evaluate the preparation quality of the facial mask, providing a quantitative basis for optimizing the impregnation parameters. By continuously randomly generating impregnation parameters and calculating the facial mask preparation score until the optimal impregnation parameters are obtained by convergence, the intelligent optimization of the facial mask preparation process parameters is realized, significantly improving the preparation efficiency and quality of the facial mask.

[0059] Example 2:

[0060] As Figure 2 shown, based on the same inventive concept as the method for optimizing the process parameters of facial mask preparation using artificial intelligence provided in Example 1, the embodiment of the present invention further provides a system for optimizing the process parameters of facial mask preparation using artificial intelligence, and the system includes:

[0061] An image acquisition module 11, configured to perform light-transmitting image acquisition on a target membrane cloth to be impregnated, perform membrane cloth thickness identification, and obtain the first thickness of the first region and the second thickness of the second region.

[0062] A parameter acquisition module 12, configured to collect the viscosity information of the essence and obtain the impregnation parameter interval of the impregnation process parameters.

[0063] A simulation prediction module 13, configured to randomly generate a first impregnation parameter within the impregnation parameter interval, combine the viscosity information, the first thickness, and the second thickness, and perform impregnation simulation prediction to obtain the first impregnation amount and the second impregnation amount.

[0064] An optimization preparation module 14, configured to perform facial mask use prediction according to the first impregnation amount and the second impregnation amount, combine the first thickness, the second thickness, and the viscosity information, obtain the first essence dripping rate, the first membrane cloth deformation rate, the second essence dripping rate, and the second membrane cloth deformation rate, combine the first impregnation amount and the second impregnation amount, calculate the first facial mask score and the second facial mask score, perform impregnation parameter optimization, obtain the optimal impregnation parameters, and perform facial mask impregnation preparation.

[0065] Furthermore, the image acquisition module 11 is further configured to perform the following steps:

[0066] Collect a light-transmitting image of the target membrane to be impregnated under a preset light-transmitting parameter to obtain a membrane light-transmitting image; input the membrane light-transmitting image into a membrane thickness recognition channel, and recognize and output to obtain a first thickness of a first region and a second thickness of a second region, where the first region is the T region and the second region is the U region.

[0067] Furthermore, the image acquisition module 11 is further configured to perform the following steps:

[0068] Adopt deep learning to construct a membrane thickness recognition channel; according to the detection data log of the membrane, collect a set of sample membrane light-transmitting images, and label the average thickness of the first region and the second region of the membrane in different sample membrane light-transmitting images to obtain a set of sample first thicknesses and a set of sample second thicknesses; use the set of sample membrane light-transmitting images, the set of sample first thicknesses and the set of sample second thicknesses to perform supervised training, verification and testing on the membrane thickness recognition channel, and complete the training when the accuracy rate is greater than or equal to the accuracy rate threshold.

[0069] Furthermore, the parameter acquisition module 12 is further configured to perform the following steps:

[0070] Collect the viscosity information of the essence for current facial mask production; obtain the impregnation parameter range of the impregnation process parameters, where the impregnation process parameters include impregnation time.

[0071] Furthermore, the simulation prediction module 13 is further configured to perform the following steps:

[0072] Randomly generate a first impregnation parameter within the impregnation parameter range; input the first impregnation parameter, the viscosity information, the first thickness and the second thickness into a pre-trained impregnation amount prediction channel, and predict and output a first impregnation amount and a second impregnation amount, where the impregnation amount prediction channel uses sample impregnation parameters, sample viscosity information, sample first thickness and sample second thickness as input features and is trained with sample first impregnation amount and sample second impregnation amount as output features.

[0073] Furthermore, the optimization preparation module 14 is further configured to perform the following steps:

[0074] According to the historical preparation data log of the first region, collect the first sample impregnation amount set, the first thickness set, the sample viscosity information set, the first essence dripping rate set of the sample, and the first film cloth deformation rate set of the sample as the first usage training data of the first region, where the first film cloth deformation rate includes the proportion of the size deformation of the film cloth in the first region after impregnation; based on machine learning, construct the first usage prediction branch of the first region, and use the first usage training data for supervised training, verification, and testing until convergence; according to the historical preparation data log of the second region, collect the second sample impregnation amount set, the second thickness set, the sample viscosity information set, the second essence dripping rate set of the sample, and the second film cloth deformation rate set of the sample as the second usage training data of the second region; based on machine learning, construct the second usage prediction branch of the second region, and use the second usage training data for supervised training, verification, and testing until convergence; input the first impregnation amount, the first thickness, and the viscosity information into the first usage prediction branch, and predict and output to obtain the first essence dripping rate and the first film cloth deformation rate; input the second impregnation amount, the second thickness, and the viscosity information into the second usage prediction branch, and predict and output to obtain the second essence dripping rate and the second film cloth deformation rate.

[0075] Furthermore, the optimization preparation module 14 is further configured to perform the following steps:

[0076] According to the first impregnation amount, the first essence dripping rate, and the first film cloth deformation rate, calculate the first facial mask score based on the preparation function of the first region, and according to the second impregnation amount, the second essence dripping rate, and the second film cloth deformation rate, calculate the second facial mask score based on the preparation function of the second region; calculate the weighted facial mask preparation score according to the first facial mask score and the second facial mask score; continue to randomly generate impregnation parameters, calculate the facial mask preparation score, and optimize the impregnation parameters until convergence, obtain the optimal impregnation parameters with the maximum facial mask preparation score, and perform facial mask impregnation preparation.

[0077] Furthermore, the optimization preparation module 14 further includes:

[0078] The preparation function of the first region is as follows: ; where is the first facial mask score, , and are weights, is the first impregnation amount, is the preset first impregnation amount of the first region, is the first essence dripping rate, is the first film cloth deformation rate.

[0079] Through the foregoing detailed description of a method for optimizing the process parameters of a facial mask preparation using artificial intelligence, those skilled in the art can clearly know a system for optimizing the process parameters of a facial mask preparation using artificial intelligence in this embodiment. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For related parts, reference may be made to the description in the method part.

[0080] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing the process parameters of mask preparation using artificial intelligence, characterized in that, The method includes: Performing light-transmitting image acquisition on the target membrane to be impregnated, performing membrane thickness identification, and obtaining the first thickness of the first region and the second thickness of the second region; Collecting the viscosity information of the essence, and obtaining the impregnation parameter interval of the impregnation process parameters; Randomly generating a first impregnation parameter within the impregnation parameter interval, and combining the viscosity information, the first thickness, and the second thickness to perform impregnation simulation prediction, obtaining a first impregnation amount and a second impregnation amount, including: Randomly generating a first impregnation parameter within the impregnation parameter interval; Inputting the first impregnation parameter, the viscosity information, the first thickness, and the second thickness into a pre-trained impregnation amount prediction channel, and predicting and outputting the first impregnation amount and the second impregnation amount, where the impregnation amount prediction channel is trained with sample impregnation parameters, sample viscosity information, sample first thickness, and sample second thickness as input features, and sample first impregnation amount and sample second impregnation amount as output features; According to the first impregnation amount and the second impregnation amount, combining the first thickness, the second thickness, and the viscosity information, performing facial mask usage prediction, obtaining a first essence dripping rate, a first membrane deformation rate, a second essence dripping rate, and a second membrane deformation rate, combining the first impregnation amount and the second impregnation amount, calculating to obtain a first facial mask score and a second facial mask score, optimizing the impregnation parameters, obtaining the optimal impregnation parameters, and performing facial mask impregnation preparation; Among them, according to the historical preparation data log of the first region, collecting a sample first impregnation amount set, a first thickness set, a sample viscosity information set, a sample first essence dripping rate set, and a sample first membrane deformation rate set as the first usage training data of the first region, where the first membrane deformation rate includes the proportion of the membrane size deformation within the first region after impregnation; Based on machine learning, constructing a first usage prediction branch for the first region, and performing supervised training, verification, and testing using the first usage training data until convergence; According to the historical preparation data log of the second region, collecting a sample second impregnation amount set, a second thickness set, a sample viscosity information set, a sample second essence dripping rate set, and a sample second membrane deformation rate set as the second usage training data of the second region; Based on machine learning, constructing a second usage prediction branch for the second region, and performing supervised training, verification, and testing using the second usage training data until convergence; Inputting the first impregnation amount, the first thickness, and the viscosity information into the first usage prediction branch, and predicting and outputting to obtain a first essence dripping rate and a first membrane deformation rate; Inputting the second impregnation amount, the second thickness, and the viscosity information into the second usage prediction branch, and predicting and outputting to obtain a second essence dripping rate and a second membrane deformation rate.

2. The method for optimizing the process parameters of mask preparation using artificial intelligence according to claim 1, wherein Performing light-transmitting image acquisition on the target membrane to be impregnated, performing membrane thickness identification, and obtaining the first thickness of the first region and the second thickness of the second region, including: Performing light-transmitting image acquisition on the target membrane to be impregnated under preset light-transmitting parameters to obtain a membrane light-transmitting image; Input the light-transmitting image of the membrane cloth into the membrane cloth thickness recognition channel, and recognize and output to obtain the first thickness of the first region and the second thickness of the second region, where the first region is the T region and the second region is the U region.

3. The method for optimizing the process parameters of mask preparation using artificial intelligence according to claim 2, characterized in that, The training steps of the membrane cloth thickness recognition channel include: Adopt deep learning to construct a membrane cloth thickness recognition channel; According to the detection data log of the membrane cloth, collect a set of sample membrane cloth light-transmitting images, and label the average thickness of the first region and the second region of the membrane cloth in different sample membrane cloth light-transmitting images to obtain a set of sample first thicknesses and a set of sample second thicknesses; Use the set of sample membrane cloth light-transmitting images, the set of sample first thicknesses, and the set of sample second thicknesses to perform supervised training, verification, and testing on the membrane cloth thickness recognition channel. When the accuracy rate is greater than or equal to the accuracy threshold, the training is completed.

4. The method for optimizing the process parameters of mask preparation using artificial intelligence according to claim 1, characterized in that, Collect the viscosity information of the essence, and obtain the impregnation parameter interval of the impregnation process parameters, including: Collect the viscosity information of the essence currently used in mask production; Obtain the impregnation parameter interval of the impregnation process parameters, where the impregnation process parameters include impregnation time.

5. The method for optimizing the process parameters of mask preparation using artificial intelligence according to claim 1, characterized in that, Combine the first impregnation amount and the second impregnation amount, calculate to obtain the first mask score and the second mask score, optimize the impregnation parameters, obtain the optimal impregnation parameters, and perform mask impregnation preparation, including: According to the first impregnation amount, the first essence dripping rate, and the first membrane cloth deformation rate, calculate the first mask score based on the first region preparation function. According to the second impregnation amount, the second essence dripping rate, and the second membrane cloth deformation rate, calculate the second mask score based on the second region preparation function; According to the first mask score and the second mask score, calculate the mask preparation score by weighted calculation; Continue to randomly generate impregnation parameters, calculate the mask preparation score, and optimize the impregnation parameters until convergence, obtain the optimal impregnation parameters with the maximum mask preparation score, and perform mask impregnation preparation.

6. The method for optimizing the process parameters of mask preparation using artificial intelligence according to claim 5, characterized in that, The first region preparation function is as follows: Among them, is the first facial mask score, and is the weight, is the first impregnation amount, is the preset first impregnation amount of the first area, is the first essence dripping rate, is the first mask deformation rate.

7. A system for optimizing the process parameters of mask preparation using artificial intelligence, characterized in that, For implementing the method for optimizing the mask preparation process parameters using artificial intelligence according to any one of claims 1-6, the system includes: An image acquisition module, configured to perform light-transmitting image acquisition on the target membrane cloth to be impregnated, perform membrane cloth thickness recognition, and obtain the first thickness of the first region and the second thickness of the second region; A parameter acquisition module, configured to collect the viscosity information of the essence and obtain the impregnation parameter interval of the impregnation process parameters; A simulation prediction module, configured to randomly generate the first impregnation parameter within the impregnation parameter interval, combine the viscosity information, the first thickness, and the second thickness, perform impregnation simulation prediction, and obtain the first impregnation amount and the second impregnation amount; An optimization preparation module, configured to perform mask use prediction according to the first impregnation amount and the second impregnation amount, in combination with the first thickness, the second thickness, and the viscosity information, obtain the first essence dripping rate, the first membrane cloth deformation rate, the second essence dripping rate, and the second membrane cloth deformation rate, combine the first impregnation amount and the second impregnation amount, calculate the first mask score and the second mask score, optimize the impregnation parameters, obtain the optimal impregnation parameters, and perform mask impregnation preparation.

Images