Intelligent mask production management system and method based on feedback analysis

Abstract

The invention discloses an intelligent mask production management system and method based on feedback analysis. The system comprises an acquisition module I, an acquisition module II, a calculation module I, a judgment module I, a calculation module II, a judgment module II, a feedback module I and the like. The invention relates to the technical field of production management, in particular to an intelligent mask production management system and method based on feedback analysis. The technical problem to be solved by the invention is to provide the intelligent mask production management system and method based on feedback analysis, so that feedback data of a plurality of process links in a production management process can be comprehensively analyzed, the accuracy of feedback data analysis is improved, and the production efficiency and the product quality are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and more specifically, to an intelligent facial mask production management system and method based on feedback analysis. Background Art

[0002] In the process of facial mask production, it is crucial to provide timely feedback and analysis on various parameter indicators of products and the operating status of equipment for discovering and solving production problems and optimizing the production process. By collecting feedback data during production, comprehensive analysis is carried out to provide optimization suggestions, thereby improving the quality and production efficiency of facial masks, etc.

[0003] Currently, facial mask care products are gradually breaking through traditional usage models. For example, by integrating electrode circuits, embedded piezoresistive arrays or multi-channel microfluidic chips, dynamic skin zoning and differential care are achieved, the drug release performance of active ingredients in facial masks is improved, thereby realizing precise drug delivery to the skin, enhancing the self-repair ability of the extracellular matrix of damaged skin, and ultimately improving product quality.

[0004] Traditional production management methods are not comprehensive and accurate enough in data collection for each link in the production process. For example, for the detection of raw material quality, manual sampling inspection is usually relied on, and it is impossible to obtain various quality indicators of raw materials in a timely and accurate manner. The monitoring of the operating status of equipment is also relatively single, and it is impossible to real-time master key parameters such as the temperature, pressure, and humidity of the equipment.

[0005] For example, in some facial mask care products with distributed electrode current circuits, previous production equipment did not fully consider its impact on the production process, resulting in the inability to precisely control current parameters in some production links involving current effects. In the production process of facial masks containing magnetic nanoparticle temperature control materials, the monitoring means for production links are insufficient, resulting in a decrease in the temperature control release efficiency of drug components, ultimately affecting product quality.

[0006] In the existing facial mask production management process, when obtaining feedback information during production, the feedback data of a specific part of the process links are usually analyzed, and only the process link where the abnormal data is located is regulated. Therefore, when equipment parameters and product quality are abnormal, it is difficult to discover and adjust in a timely manner.

[0007] For the above technical solutions, this production management method cannot comprehensively analyze the feedback data of multiple process links, and thus it is difficult to targetedly regulate the production process and equipment parameters, reducing the accuracy of feedback data analysis, thereby affecting production efficiency and product quality. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to provide an intelligent facial mask production management system and method based on feedback analysis, which can comprehensively analyze the feedback data of multiple process links in the production management process, improve the accuracy of feedback data analysis, and thus improve production efficiency and product quality.

[0009] In the first aspect, the present invention provides an intelligent facial mask production management system based on feedback analysis, and the following technical solutions are adopted to achieve the invention purpose:

[0010] The intelligent facial mask production management system based on feedback analysis includes the following modules:

[0011] Acquisition module I: The output end is connected to the input end of acquisition module II, and is used to set N management levels in sequence during the product production process. M types of feedback data are set in each management level. According to the feedback data, the evaluation factor of this management level is obtained, and the historical data stored in the database is obtained. Among them, the mean value set of the historical evaluation factors of the nth management level is The mean value set of the mth historical feedback data of the nth management level is

[0012] Acquisition module II: The input end is connected to the output end of acquisition module I, and the output end is connected to the input end of calculation module I, and is used to obtain the data recorded in I monitoring cycles. Among them, the evaluation factor set of the nth management level in the ith monitoring cycle is The set of the mth feedback data of the nth management level in the ith monitoring cycle is

[0013] Calculation module I: The input end is connected to the output end of acquisition module II, and the output end is connected to the input end of judgment module I, and is used to calculate the error value E of the evaluation factor set in I monitoring cycles, where I , E I The calculation model of is:

[0014]

[0015] Among them, E i is the error value of the evaluation factor set of N sensitive levels in the ith monitoring cycle;

[0016] Judgment module I: The input end is connected to the output end of calculation module I, and the output end is connected to the input end of calculation module II, and is used to obtain the error reference value W of the evaluation factor set according to the historical data. If E I ≤σW, it is judged that the evaluation is consistent. If E I >σW, it is judged that the evaluation is inconsistent, and calculation step II is executed, where σ is the first confidence coefficient, and σ∈(0,1);

[0017] Calculation Module II: The input end is connected to the output end of the Judgment Module I, and the output end is connected to the input end of the Judgment Module II, which is used to calculate the error value ΔF of the m-th feedback data set in I monitoring cycles. m , ΔF m The calculation model is:

[0018] Judgment Module II: The input end is connected to the output end of the Calculation Module II, and the output end is connected to the input end of the Feedback Module I, which is used to obtain the error reference value Q of the m-th feedback data set according to historical data. m , if ΔF m ≤δQ m , it is determined that the feedback data set has not shifted. If ΔF m >δQ m , it is determined that the feedback data set has shifted, where δ is the second confidence coefficient, and δ∈(0,1);

[0019] Feedback Module I: The input end is connected to the output end of the Judgment Module II, which is used to upload data to the management end.

[0020] As a further limitation of this technical solution, it further includes a Calculation Module III and a Judgment Module III;

[0021] Calculation Module III: The input end is connected to the output end of the Feedback Module I, and the output end is connected to the input end of the Judgment Module III, which is used to calculate if ΔF m -Q m >0, let C m =1, V m =0. If ΔF m -Q m =0, let C m =0, V m =0. If ΔF m -Q m <0, let C m =0, V m =1;

[0022] The positive feedback amount is The negative feedback amount is

[0023] Judgment Module III: The input end is connected to the output end of the Calculation Module III, which is used to determine that the feedback data set has a positive shift if C>V, a negative shift if C<V, and a two-way shift in the positive and negative directions if C=V.

[0024] As a further limitation of this technical solution, it further includes a judgment module IV and a feedback module II. In the judgment module III, when it is judged that C < V or C = V, the judgment module IV is executed;

[0025] Judgment module IV: The input end is connected to the output end of the judgment module III, and the output end is connected to the input end of the feedback module II. It is used to obtain the target feedback amount Z according to historical data. If V ≥ Z, it is judged that the feedback result is unacceptable, and the feedback II step is executed. If V < Z, it is judged that the feedback result is acceptable;

[0026] Feedback module II: The input end is connected to the output end of the judgment module IV, and it is used to upload data to the management end, increase a management level in the next detection cycle, and make N = N + 1.

[0027] As a further limitation of this technical solution, in the calculation module I, the calculation model of E I is updated to:

[0028]

[0029] where β n is the error weight of the evaluation factor set of the nth management level, and β ∈ (0, 1).

[0030] As a further limitation of this technical solution, in the calculation module II, the calculation model of ΔF m is updated to:

[0031]

[0032] where γ n is the error weight of the feedback data set of the nth management level, and γ ∈ (0, 1).

[0033] Second, the present invention provides an intelligent mask production management method based on feedback analysis, and the following technical solution is adopted to achieve the invention purpose:

[0034] The intelligent mask production management method based on feedback analysis includes the following steps:

[0035] Obtain data I: During the product production process, N management levels are sequentially set, and M types of feedback data are set in each management level. The evaluation factors of this management level are obtained by converting the feedback data, and the historical data stored in the database is obtained, where the mean set of historical evaluation factors of the nth management level is The mean set of the mth historical feedback data of the nth management level is

[0036] Obtain Data II: Obtain the data recorded in I monitoring periods, where the set of evaluation factors at the nth management level in the ith monitoring period is The set of the mth feedback data at the nth management level in the ith monitoring period is

[0037] Calculation I: Calculate the error value E of the set of evaluation factors in I monitoring periods I , E I The calculation model of is:

[0038]

[0039] where, E i is the error value of the set of evaluation factors at the N sensitive levels in the ith monitoring period;

[0040] Judgment I: Obtain the error reference value W of the set of evaluation factors according to historical data. If E I ≤σW, it is judged that the evaluations are consistent. If E I >σW, it is judged that the evaluations are inconsistent, and perform Step II of the calculation, where σ is the first confidence coefficient and σ∈(0,1);

[0041] Calculation II: Calculate the error value ΔF of the set of the mth feedback data in I monitoring periods m , ΔF m The calculation model of is:

[0042] Judgment II: Obtain the error reference value Q of the set of the mth feedback data according to historical data m , if ΔF m ≤δQ m , it is judged that the set of feedback data has not shifted. If ΔF m >δQ m , it is judged that the set of feedback data has shifted, where δ is the second confidence coefficient and δ∈(0,1);

[0043] Feedback I: Upload the data to the management terminal.

[0044] As a further limitation of this technical solution, after Step I of the feedback, there are also set Step III of the calculation and Step III of the judgment;

[0045] Calculation III: If ΔF m -Q m >0, let C m =1, V m =0. If ΔF m -Q m =0, let C m =0, V m =0. If ΔFm -Q m If it is less than 0, let C m = 0, V m = 1;

[0046] Calculate the positive feedback amount as The negative feedback amount is

[0047] Judgment III: If C > V, it is judged that the feedback data set has a positive deviation; if C < V, it is judged that the feedback data set has a negative deviation; if C = V, it is judged that the feedback data set has a two-way deviation in both the positive and negative directions.

[0048] As a further limitation of this technical solution, after the Judgment III step, there are also a Judgment IV step and a Feedback II step. In the Judgment III step, when it is judged that C < V or C = V, the Judgment IV step is executed;

[0049] Judgment IV: Obtain the target feedback amount Z according to historical data. If V ≥ Z, it is judged that the feedback result is unacceptable, and the Feedback II step is executed; if V < Z, it is judged that the feedback result is acceptable;

[0050] Feedback II: Upload the data to the management terminal, increase a management level in the next detection cycle, and let N = N + 1.

[0051] As a further limitation of this technical solution, in the Calculation I step, the calculation model of E I is updated to:

[0052]

[0053] where β n is the error weight of the evaluation factor set of the nth management level, and β ∈ (0, 1).

[0054] As a further limitation of this technical solution, in the Calculation II step, the calculation model of ΔF m is updated to:

[0055]

[0056] where γ n is the error weight of the feedback data set of the nth management level, and γ ∈ (0, 1).

[0057] Compared with the prior art, the advantages and positive effects of the present invention are:

[0058] 1. By comprehensively analyzing the set of evaluation factors within a specified monitoring period, the error value between it and the set of historical average evaluation factors is judged, and then whether the various parameter indicators of the product are within a reasonable range is analyzed. By analyzing the error value between multiple types of feedback data sets and the historical feedback data set within I monitoring periods, the fluctuation of this type of feedback data is further analyzed. This method can comprehensively analyze the feedback data of multiple process links, and then targetedly adjust the production process and equipment parameters, improving the accuracy of feedback data analysis, facilitating timely adjustment and prevention of equipment abnormalities and product quality abnormalities, etc., thereby improving production efficiency and product quality.

[0059] 2. By counting the number of different types of feedback data that are greater than, equal to, or less than the error reference value within I monitoring periods, analyzing and comparing the quantitative relationship between the positive feedback amount and the negative feedback amount, and judging the deviation situation of the feedback data set. Then, based on the judgment result and the deviation degree of different types of feedback data, an analysis is carried out. Based on the analysis result, the production process and equipment parameters are adjusted. For example, the temperature, pressure, humidity, etc. of the production detection equipment are automatically adjusted, the production process is adjusted, such as adding a quality inspection link, optimizing the lamination time, adjusting the procurement and storage management of raw materials to ensure the quality of raw materials, etc., and then the production process and equipment parameters are targetedly adjusted to improve the accuracy of feedback data analysis.

[0060] 3. When the negative feedback amount V ≥ the target feedback amount Z, it is judged that the feedback result is unacceptable, indicating that within I monitoring periods, there are certain types of feedback data that have all shown large fluctuations, and potential production management risks need to be timely prevented and handled. Therefore, in the next detection period, a management level is increased, such as adding a raw material quality inspection link or a product quality inspection link, etc., which is conducive to timely adjustment and prevention of equipment abnormalities and product quality abnormalities, etc., improving the accuracy of feedback data analysis, and thus improving production efficiency and product quality.

[0061] 4. Through the error weight β of the evaluation factor set n Correct and calculate the error value E between the evaluation factor set of I monitoring periods and the set of historical average evaluation factors I For different management levels, such as the raw material quality inspection link, the packaging link, and the user research link, there are certain differences in the importance of their impact on product quality. Especially the user research link has a greater impact on the direction of product production management. Therefore, different weights are set to calculate the overall error value E of the evaluation factor set of I monitoring periods I Then, the judgment range of the feedback data set error value is adjusted to adapt to the specific production management environment, thereby improving production efficiency and product quality.

[0062] 5. Through the error weight γ of the feedback data setn Modify and calculate the error value ΔF of the m-th feedback data set in I monitoring cycles m , for different management levels or different beauty care products, such as the humidity test data of a hydrating mask, the mask with silver electrodes for local care also has current loop test data. There are different degrees of influence between its different management levels and different types of feedback data. Therefore, different weights are set to calculate the error value ΔF of the m-th feedback data set in I monitoring cycles m . BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation to the present application. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0064] Figure 1 is the system diagram of Embodiment 1 of the present invention;

[0065] Figure 2 is the flowchart of Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] The following will combine the Figure 1 and Figure 2 to clearly and completely describe the technical solutions 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 of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0067] It should be noted that the orientation terms such as left, right, up, down, front, and back in the embodiments of the present invention are only relative concepts to each other or are referenced based on the normal use state of the product, that is, the traveling direction of the product, and should not be considered as restrictive.

[0068] When a component is referred to as "being located" or "being provided on" another component, it can be on another component or there may be an intermediate component at the same time. When a component is referred to as "being connected to" another component, it can be directly connected to another component or there may be an intermediate component at the same time.

[0069] Embodiment 1: An intelligent mask production management system based on feedback analysis, including the following modules:

[0070] Acquisition Module I: The output end is connected to the input end of Acquisition Module II, which is used to set N management levels in sequence during the product production process. M types of feedback data are set in each management level. The evaluation factor of this management level is obtained by converting the feedback data, and the historical data stored in the database is acquired. The mean set of historical evaluation factors for the nth management level is The mean set of the mth historical feedback data for the nth management level is

[0071] Acquisition Module II: The input end is connected to the output end of Acquisition Module I, and the output end is connected to the input end of Calculation Module I, which is used to acquire the data recorded in I monitoring cycles. The evaluation factor set for the nth management level in the ith monitoring cycle is The set of the mth feedback data for the nth management level in the ith monitoring cycle is

[0072] Calculation Module I: The input end is connected to the output end of Acquisition Module II, and the output end is connected to the input end of Judgment Module I, which is used to calculate the error value E of the evaluation factor set in I monitoring cycles. I , E I The calculation model of is:

[0073]

[0074] Among them, E i is the error value of the evaluation factor set for N sensitive levels in the ith monitoring cycle, and β n is the error weight of the evaluation factor set for the nth management level, β ∈ (0, 1);

[0075] Judgment Module I: The input end is connected to the output end of Calculation Module I, and the output end is connected to the input end of Calculation Module II, which is used to obtain the error reference value W of the evaluation factor set according to the historical data. If E I ≤ σW, it is judged that the evaluation is consistent. If E I > σW, it is judged that the evaluation is inconsistent, and calculation step II is executed, where σ is the first confidence coefficient, σ ∈ (0, 1);

[0076] Calculation Module II: The input end is connected to the output end of Judgment Module I, and the output end is connected to the input end of Judgment Module II, which is used to calculate the error value ΔF of the mth feedback data set in I monitoring cycles. m , ΔF m The calculation model of is:

[0077] Among them, γ n is the error weight of the feedback data set for the nth management level, γ ∈ (0, 1);

[0078] Judgment Module II: Its input end is connected to the output end of the Calculation Module II, and its output end is connected to the input end of the Feedback Module I. It is used to obtain the error reference value Q of the m-th feedback data set according to historical data. m , if ΔF m ≤δQ m , then it is judged that the feedback data set has not shifted. If ΔF m >δQ m , then it is judged that the feedback data set has shifted, where δ is the second confidence coefficient, and δ∈(0,1);

[0079] Feedback Module I: Its input end is connected to the output end of the Judgment Module II, and its output end is connected to the input end of the Calculation Module III. It is used to upload data to the management terminal.

[0080] Calculation Module III: Its input end is connected to the output end of the Feedback Module I, and its output end is connected to the input end of the Judgment Module III. It is used to calculate that if ΔF m -Q m >0, let C m =1, V m =0. If ΔF m -Q m =0, let C m =0, V m =0. If ΔF m -Q m <0, let C m =0, V m =1;

[0081] The positive feedback amount is The negative feedback amount is

[0082] Judgment Module III: Its input end is connected to the output end of the Calculation Module III, and its output end is connected to the input end of the Judgment Module IV. It is used to judge that if C>V, the feedback data set has a positive shift. If C<V, the feedback data set has a negative shift, and execute the Judgment Module IV. If C=V, it is judged that the feedback data set has a two-way shift in the positive and negative directions, and execute the Judgment Module IV.

[0083] Judgment Module IV: Its input end is connected to the output end of the Judgment Module III, and its output end is connected to the input end of the Feedback Module II. It is used to obtain the target feedback amount Z according to historical data. If V≥Z, it is judged that the feedback result is unacceptable, and execute the Feedback II step. If V<Z, it is judged that the feedback result is acceptable;

[0084] Feedback Module II: Its input end is connected to the output end of the Judgment Module IV. It is used to upload data to the management terminal, increase a management level in the next detection cycle, and let N=N + 1.

[0085] The working principle of this embodiment is as follows:

[0086] In use, the acquisition module I sets corresponding management levels in the process link, quality inspection link, and user research link during product production. The user research link can be used as the last management level to retrieve the true satisfaction of the product and serve as quality evaluation data. A total of N management levels are set in sequence, and M types of feedback data are set in each management level. For example, data sets such as temperature, humidity, colony count, and moisture retention duration. The acquisition module I converts the corresponding feedback data into evaluation factors through a preset conversion method based on historical data to analyze and evaluate the production management process. In the historical data, the mean set of historical evaluation factors for the nth management level is The mean set of the mth historical feedback data for the nth management level is

[0087] The acquisition module II acquires the data recorded in I monitoring cycles. Among them, the evaluation factor set for the nth management level in the ith monitoring cycle is The set of the mth feedback data for the nth management level in the ith monitoring cycle is The calculation module I calculates the error value E between the evaluation factor set of I monitoring cycles and the mean set of historical evaluation factors I , where β n is the error weight of the evaluation factor set for the nth management level. For different management levels, such as the raw material quality inspection link, packaging link, and user research link, there are certain differences in the importance of their impact on product quality. Especially the user research link has a greater impact on the direction of product production management. Therefore, different weights are set to calculate the overall error value E of the evaluation factor set for I monitoring cycles I .

[0088] The judgment module I obtains the error reference value W of the evaluation factor set according to historical data. Among them, the historical data comes from the data recorded in multiple monitoring cycles. For example, through channels such as user feedback, production line detection, and laboratory tests, various feedback information during the production process of the facial mask is collected and converted through conversion to obtain the error reference value W. If E I ≤σW, the judgment module I determines that the evaluation is consistent, indicating that the error between the data of I monitoring cycles and the historical feedback data is within the set allowable range, and the overall fluctuation of the data is small. If E I >σW, the judgment module I determines that the evaluation is inconsistent, and the fluctuation of the feedback data is large, which is likely to affect production management. Here, σ is the first confidence coefficient, and by adjusting the value of σ, the evaluation range of the error value is adjusted to adapt to the specific production management environment

[0089] When the judgment module I determines that the evaluation is inconsistent, the calculation module II calculates the error value ΔF of the m-th feedback data set in I monitoring cycles m , where γ n is the error weight of the feedback data set of the n-th management level. For different management levels or different beauty care products, such as the humidity test data of a moisturizing mask, the mask with silver electrodes for local care also has current loop test data. There are different degrees of influence between its different management levels and different types of feedback data. Therefore, different weights are set to calculate the error value ΔF of the m-th feedback data set in I monitoring cycles m .

[0090] The judgment module II obtains the error reference value Q of the m-th feedback data set according to historical data m , if ΔF m ≤δQ m , then the judgment module II determines that the feedback data set has not shifted, indicating that within I monitoring cycles, the error between this type of feedback data and the historical feedback data mean is within the set allowable range. If ΔF m >δQ m , then the judgment module II determines that the feedback data set has shifted, indicating that the fluctuation of this type of feedback data in I monitoring cycles is relatively large, and there may be a positive feedback trend or a negative feedback trend. Then, based on the analysis results, the production process and equipment parameters are adjusted. Where δ is the second confidence coefficient, and by adjusting the value of δ, the judgment range of the feedback data set error value is adjusted to adapt to the specific production management environment. The feedback module I feeds back the judgment result and calculation data and uploads the data to the management terminal.

[0091] With such settings, by comprehensively analyzing the values of evaluation factors within a specified monitoring period, the error value between them and the set of historical evaluation factor means is judged, and then whether the various parameter indicators of the product are within a reasonable range is analyzed. By analyzing the error values between multiple types of feedback data sets and the historical feedback data set within I monitoring periods, the fluctuation of this type of feedback data is analyzed. This method can comprehensively analyze the feedback data of multiple process links, and then targetedly adjust the production process and equipment parameters, improving the accuracy of feedback data analysis, facilitating timely adjustment and prevention of equipment anomalies and product quality anomalies, etc., thereby improving production efficiency and product quality. In the production process of mask products equipped with electrode circuits, embedded piezoresistive arrays, or integrated multi-channel microfluidic chips, the comprehensive impact of various parameters of production equipment on the mask production process can be fully considered, so that in some production links involving the action of electric current, the current parameters can be accurately controlled to form a safe and controllable pulsed electric field or optoelectronic synergistic treatment system that meets medical standards, and flexibly integrate the functions of electrical stimulation and drug slow release of the skin. In the production process of masks containing magnetic nanoparticle temperature control materials, multi-faceted monitoring and comprehensive evaluation of the production links can be carried out, which is beneficial to improving the temperature control release efficiency of drug components, accurately identifying damaged areas of the skin, realizing dynamic zoning and differential care of the skin, achieving dynamic simulation optimization, improving the drug release performance of active ingredients in the mask, dynamically regulating the transdermal efficiency of drugs, thereby achieving precise drug delivery to the skin, improving the self-repair ability of the extracellular matrix of damaged skin, and ultimately improving product quality.

[0092] The calculation module III counts the number of different types of feedback data that are greater than, equal to, or less than the error reference value in I monitoring periods. The judgment module III analyzes and compares the quantitative relationship between the positive feedback amount and the negative feedback amount. When the positive feedback amount is greater than the negative feedback amount, the judgment module III judges that the feedback data set has a positive shift. When the positive feedback amount is less than the negative feedback amount, the judgment module III judges that the feedback data set has a negative shift. When the positive feedback amount is equal to the negative feedback amount, the judgment module III judges that the feedback data set has a two-way shift in the positive and negative directions. Then, based on the judgment result and the deviation degree of different types of feedback data, an analysis is carried out. Based on the analysis result, the production process and equipment parameters are adjusted, such as automatically adjusting parameters such as the temperature, pressure, and humidity of production detection equipment, adjusting the production process, such as adding quality inspection links and optimizing the fitting time, and adjusting the procurement and storage management of raw materials to ensure the quality of raw materials, etc.

[0093] When the judgment module III determines that the positive feedback amount is less than or equal to the negative feedback amount, the target feedback amount Z is obtained according to the historical data. If the negative feedback amount V ≥ the target feedback amount Z, the judgment module IV determines that the feedback result is unacceptable, indicating that in the I monitoring cycles, there are certain types of feedback data that have all shown large fluctuations, and potential production management risks need to be prevented and handled in a timely manner. If the negative feedback amount V < the target feedback amount Z, the judgment module IV determines that the feedback result is acceptable, indicating that the fluctuations of certain types of feedback data pose a lower risk to production management, but further management is still required to eliminate potential risks. When the judgment module IV determines that the feedback result is unacceptable, the feedback module II uploads the data to the management end, adds a management level in the next detection cycle, such as adding a raw material quality inspection link or a product quality inspection link, etc., and sets N = N + 1, which is beneficial to timely regulating and preventing equipment abnormalities and product quality abnormalities, improving the accuracy of feedback data analysis, and thus improving production efficiency and product quality.

[0094] Embodiment 2: An intelligent facial mask production management method based on feedback analysis, including the following steps:

[0095] S1. Obtain Data I: During the product production process, N management levels are sequentially set, and M types of feedback data are set in each management level. The evaluation factor of this management level is obtained by converting the feedback data, and the historical data stored in the database is obtained. The mean set of historical evaluation factors for the nth management level is The mean set of the mth historical feedback data for the nth management level is

[0096] S2. Obtain Data II: Obtain the data recorded in I monitoring cycles. The evaluation factor set for the nth management level in the ith monitoring cycle is The set of the mth feedback data for the nth management level in the ith monitoring cycle is

[0097] S3. Calculate I: Calculate the error value of the evaluation factor set for I monitoring cycles as E I , E I The calculation model of is:

[0098]

[0099] where, E i is the error value of the evaluation factor set for N sensitive levels in the ith monitoring cycle, and β n is the error weight of the evaluation factor set for the nth management level, β ∈ (0, 1);

[0100] S4. Judge I: Obtain the error reference value W of the evaluation factor set according to the historical data. If E I≤σW, then it is judged that the evaluation is consistent. If E I >σW, then it is judged that the evaluation is inconsistent, and step S5 of calculation II is executed, where σ is the first confidence coefficient and σ ∈ (0, 1);

[0101] S5. Calculation II: Calculate the error value ΔF of the m-th feedback data set in I monitoring cycles m , ΔF m The calculation model of is:

[0102] where γ n is the error weight of the feedback data set of the n-th management level, and γ ∈ (0, 1);

[0103] S6. Judgment II: Obtain the error reference value Q of the m-th feedback data set according to historical data m , if ΔF m ≤δQ m , then it is judged that the feedback data set has not shifted. If ΔF m >δQ m , then it is judged that the feedback data set has shifted, where δ is the second confidence coefficient and δ ∈ (0, 1);

[0104] S7. Feedback I: Upload the data to the management terminal.

[0105] S8. Calculation III: If ΔF m -Q m >0, let C m =1, V m =0. If ΔF m -Q m =0, let C m =0, V m =0. If ΔF m -Q m <0, let C m =0, V m =1;

[0106] Calculate the positive feedback amount as The negative feedback amount is

[0107] S9. Judgment III: If C > V, then it is judged that the feedback data set has a positive shift. If C < V, then it is judged that the feedback data set has a negative shift, and step S10 of judgment IV is executed. If C = V, then it is judged that the feedback data set has a two-way shift in the positive and negative directions, and step S10 of judgment IV is executed.

[0108] S10. Judgment IV: Obtain the target feedback quantity Z based on historical data. If V ≥ Z, it is determined that the feedback result is unacceptable, and step S11 of Feedback II is executed. If V < Z, it is determined that the feedback result is acceptable;

[0109] S11. Feedback II: Upload the data to the management terminal, add a management level in the next detection cycle, and set N = N + 1.

[0110] The working principle of this embodiment is as follows:

[0111] During use, corresponding management levels are set in the process link, quality inspection link, and user research link during product production. The user research link can be used as the last management level to retrieve the true satisfaction of the product and use it as quality evaluation data. A total of N management levels are set in sequence, and M types of feedback data are set in each management level, such as data sets of temperature, humidity, colony count, moisturizing duration, etc. According to historical data, the corresponding feedback data is converted into evaluation factors through a preset conversion method to analyze and evaluate the production management process. In historical data, the mean set of historical evaluation factors for the nth management level is The mean set of the mth historical feedback data for the nth management level is n = 1, 2, 3,..., N, (n is an integer), m = 1, 2, 3,..., M, (m is an integer).

[0112] Obtain the data recorded in I monitoring cycles, where the evaluation factor set for the nth management level in the ith monitoring cycle is The set of the mth feedback data for the nth management level in the ith monitoring cycle is Calculate the error value E between the evaluation factor set of I monitoring cycles and the mean set of historical evaluation factors I , where β n is the error weight of the evaluation factor set for the nth management level, β ∈ (0, 1). For different management levels, such as the raw material quality inspection link, packaging link, and user research link, there are certain differences in the importance of their impact on product quality. Especially the user research link has a greater impact on the direction of product production management. Therefore, different weights are set to calculate the overall error value E of the evaluation factor set for I monitoring cycles I .

[0113] Obtain the error reference value W of the evaluation factor set based on historical data. Among them, the historical data comes from the data recorded in multiple monitoring cycles. For example, through channels such as user feedback, production line detection, and laboratory tests, various feedback information during the production process of facial masks is collected, and the error reference value W is obtained through conversion. If E I≤σW, it is determined that the evaluation is consistent, indicating that the error between the data of I monitoring periods and the historical feedback data is within the set allowable range, and the overall fluctuation of the data is small. If E I >σW, it is determined that the evaluation is inconsistent, and the fluctuation of the feedback data is large, which is likely to affect production management. Here, σ is the first confidence coefficient, σ ∈ (0, 1). By adjusting the value of σ, the evaluation range of the error value can be adjusted to adapt to the specific production management environment.

[0114] When it is determined that the evaluation is inconsistent, calculate the error value ΔF of the m-th type of feedback data set in I monitoring periods m , where γ n is the error weight of the feedback data set of the n-th management level, γ ∈ (0, 1). For different management levels or different beauty care products, such as the humidity test data of a moisturizing mask, the mask with silver electrodes for local care also has current loop test data. There are different degrees of influence between its different management levels and different types of feedback data. Therefore, different weights are set to calculate the error value ΔF of the m-th type of feedback data set in I monitoring periods m .

[0115] Obtain the error reference value Q of the m-th type of feedback data set according to historical data m , if ΔF m ≤δQ m , it is determined that the feedback data set has not deviated, indicating that within I monitoring periods, the error between this type of feedback data and the mean value of historical feedback data is within the set allowable range. If ΔF m >δQ m , it is determined that the feedback data set has deviated, indicating that the fluctuation of this type of feedback data in I monitoring periods is large, and there may be a positive feedback trend or a negative feedback trend. Then, based on the analysis results, adjust the production process and equipment parameters. Here, δ is the second confidence coefficient, δ ∈ (0, 1). By adjusting the value of δ, the judgment range of the error value of the feedback data set can be adjusted to adapt to the specific production management environment. Upload the feedback judgment results and calculation data to the management terminal.

[0116] With such settings, by comprehensively analyzing the values of evaluation factors within a specified monitoring period, judging the error values between them and the set of historical evaluation factor means, and then analyzing whether the various parameter indicators of the product are within a reasonable range. By analyzing the error values between multiple types of feedback data sets and the historical feedback data set within I monitoring periods, and then analyzing the fluctuation of this type of feedback data. This method can comprehensively analyze the feedback data of multiple process links, and then targetedly regulate the production process and equipment parameters, improving the accuracy of feedback data analysis, facilitating timely regulation and prevention of equipment anomalies and product quality anomalies, etc., thereby improving production efficiency and product quality.

[0117] During the production process of facial mask products equipped with electrode circuits, embedded piezoresistive arrays, or integrated multi-channel microfluidic chips, this production management system can fully consider the comprehensive impact of various parameters of production equipment on the production process of facial mask products. For example, it can automatically adjust parameters such as the temperature, pressure, and humidity of the equipment, add quality inspection links, optimize the fitting time, and then adjust the silver paste content in the electrode to enhance the stability of the electrode. Thus, in some production links involving the action of current, it can accurately control the current parameters to form a safe and controllable pulsed electric field or optoelectronic synergistic treatment system that meets medical standards, and flexibly integrate the functions of electrical stimulation and drug slow release on the skin.

[0118] During the production process of facial masks containing magnetic nanoparticle temperature control materials, this production management system can conduct multi-faceted monitoring and comprehensive evaluation of the production links, such as temperature, humidity, cleanliness, magnetic distribution, etc. This is conducive to improving the temperature control release efficiency of drug components, accurately identifying damaged areas of the skin, realizing dynamic zoning and differential care of the skin, achieving dynamic simulation optimization, enhancing the drug release performance of active ingredients in the facial mask, dynamically regulating the transdermal efficiency of drugs, thereby achieving precise drug delivery to the skin, improving the self-repair ability of the extracellular matrix of damaged skin, and ultimately improving product quality.

[0119] By counting the number of different types of feedback data that are greater than, equal to, or less than the error reference value within I monitoring periods, analyzing and comparing the quantitative relationship between the positive feedback amount and the negative feedback amount. When the positive feedback amount is greater than the negative feedback amount, it is judged that the feedback data set has a positive offset. When the positive feedback amount is less than the negative feedback amount, it is judged that the feedback data set has a negative offset. When the positive feedback amount is equal to the negative feedback amount, it is judged that the feedback data set has a two-way offset in the positive and negative directions. Then, based on the judgment results and the offset degree of different types of feedback data, analyze and adjust the production process and equipment parameters. For example, automatically adjust parameters such as the temperature, pressure, and humidity of the production detection equipment, adjust the production process, such as adding quality inspection links, optimizing the fitting time, adjust the procurement and storage management of raw materials to ensure the quality of raw materials, etc.

[0120] When it is determined that the positive feedback amount is less than or equal to the negative feedback amount, the target feedback amount Z is obtained according to historical data. If the negative feedback amount V ≥ the target feedback amount Z, it is determined that the feedback result is unacceptable, indicating that in the I monitoring cycles, there are certain types of feedback data that have all shown large fluctuations, and potential production management risks need to be promptly prevented and addressed. If the negative feedback amount V < the target feedback amount Z, it is determined that the feedback result is acceptable, indicating that the fluctuations of certain types of feedback data pose a relatively low risk to production management, but further management is still required to eliminate potential risks. When it is determined that the feedback result is unacceptable, the data is uploaded to the management terminal, and a management level is increased in the next detection cycle, such as adding a raw material quality inspection link or a product quality inspection link, etc., and let N = N + 1, which is beneficial to promptly regulating and preventing equipment abnormalities and product quality abnormalities, improving the accuracy of feedback data analysis, and thus improving production efficiency and product quality.

[0121] The specific embodiments of the present invention disclosed above are only for illustration. However, the present invention is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present invention.

Claims

1. An intelligent facial mask production management system based on feedback analysis, characterized in that, It includes the following modules: Obtaining module I: The output end is connected to the input end of the obtaining module II. It is used to set N management levels in sequence during the product production process. M types of feedback data are set in each management level. The evaluation factor of this management level is obtained by converting the feedback data, and the historical data stored in the database is obtained. The mean value set of the historical evaluation factors of the nth management level is The mean value set of the mth historical feedback data of the nth management level is Acquisition Module II: The input end is connected to the output end of Acquisition Module I, and the output end is connected to the input end of Calculation Module I, which is used to acquire the data recorded in I monitoring cycles. Among them, the evaluation factor set of the nth management level in the ith monitoring cycle is The mth feedback data set of the nth management level in the ith monitoring cycle is Calculation module I: Its input end is connected to the output end of the acquisition module II, and its output end is connected to the input end of the judgment module I, and is used to calculate that the error value of the evaluation factor set in I monitoring periods is E I , E I The calculation model of is: Among them, E i is the error value of the evaluation factor set of N sensitive levels in the i-th monitoring period; Judgment module I: The input end is connected to the output end of calculation module I, and the output end is connected to the input end of calculation module II. It is used to obtain the error reference value of the evaluation factor set as W according to historical data. If E I ≤σW, it is judged that the evaluations are consistent. If E I >σW, it is judged that the evaluations are inconsistent, and calculation step II is executed, where σ is the first confidence coefficient and σ ∈ (0, 1); Calculation Module II: Its input end is connected to the output end of the Judgment Module I, and its output end is connected to the input end of the Judgment Module II, and it is used to calculate the error value ΔF of the m-th feedback data set in I monitoring periods m , ΔF m The calculation model of is as follows: Judgment module II: The input end is connected to the output end of the calculation module II, and the output end is connected to the input end of the feedback module I, and is used to obtain the error reference value Q of the m-th feedback data set according to historical data m , if ΔF m ≤δQ m , it is determined that the feedback data set has not shifted. If ΔF m >δQ m , it is determined that the feedback data set has shifted, where δ is the second confidence coefficient, and δ ∈ (0, 1); Feedback Module I: Its input end is connected to the output end of the Judgment Module II, and is used to upload data to the management end.

2. The intelligent facial mask production management system based on feedback analysis according to claim 1, wherein: It also includes a Calculation Module III and a Judgment Module III; Calculation Module III: Its input terminal is connected to the output terminal of Feedback Module I, and its output terminal is connected to the input terminal of Judgment Module III, which is used to calculate if ΔF m -Q m > 0, let C m = 1, V m = 0, if ΔF m -Q m = 0, let C m = 0, V m = 0, if ΔF m -Q m < 0, let C m = 0, V m = 1; The amount of positive feedback calculated is The amount of negative feedback is Judgment Module III: Its input end is connected to the output end of the Calculation Module III, and is used to judge that the feedback data set has a positive offset if C > V, judge that the feedback data set has a negative offset if C < V, and judge that the feedback data set has a two-way offset in the positive and negative directions if C = V.

3. The intelligent facial mask production management system based on feedback analysis according to claim 2, wherein: It also includes a Judgment Module IV and a Feedback Module II. In the Judgment Module III, when it is judged that C < V or C = V, the Judgment Module IV is executed; Judgment Module IV: Its input end is connected to the output end of the Judgment Module III, and its output end is connected to the input end of the Feedback Module II. It is used to obtain the target feedback amount Z according to historical data. If V ≥ Z, it is judged that the feedback result is unacceptable and the Feedback II step is executed. If V < Z, it is judged that the feedback result is acceptable; Feedback Module II: Its input end is connected to the output end of the Judgment Module IV, and is used to upload data to the management end, add a management level in the next detection cycle, and make N = N + 1.

4. The intelligent facial mask production management system based on feedback analysis according to claim 1, wherein: In computing module I, E I The computing model is updated to: Among them, β n is the error weight of the evaluation factor set at the nth management level, and β ∈ (0, 1).

5. The intelligent facial mask production management system based on feedback analysis according to any one of claims 1-4, characterized in that: In calculation module II, the calculation model of ΔF m is updated to: Among them, γ n is the error weight of the feedback data set at the nth management level, and γ ∈ (0, 1).

6. The intelligent facial mask production management method based on feedback analysis is characterized in that It includes the following steps: Obtain data I: In the product production process, N management levels are sequentially set, and M types of feedback data are set in each management level. The evaluation factor of this management level is obtained by converting the feedback data, and the historical data stored in the database is obtained, where the mean value set of the historical evaluation factors of the nth management level is The mean value set of the mth historical feedback data of the nth management level is Obtain data II: Obtain the data recorded in I monitoring cycles, where the set of evaluation factors for the nth management level in the ith monitoring cycle is The set of the mth feedback data for the nth management level in the ith monitoring cycle is Calculation I: Calculate the error value E of the evaluation factor set for I monitoring cycles I , E I The calculation model of is as follows: Among them, E i is the error value of the evaluation factor set of N sensitivity levels in the i-th monitoring period; Judgment I: Obtain the error reference value W of the evaluation factor set according to historical data. If E I ≤σW, it is judged that the evaluations are consistent. If E I >σW, it is judged that the evaluations are inconsistent, and step II of the calculation is executed, where σ is the first confidence coefficient and σ ∈ (0, 1); Calculation II: Calculate the error value ΔF of the m-th feedback data set in I monitoring periods m , ΔF m The calculation model of is as follows: Judgment II: Obtain the error reference value Q of the m-th feedback data set according to historical data m , if ΔF m ≤δQ m , it is judged that the feedback data set has not shifted. If ΔF m >δQ m , it is judged that the feedback data set has shifted, where δ is the second confidence coefficient and δ ∈ (0, 1); Feedback I: Upload data to the management end.

7. The intelligent facial mask production management method based on feedback analysis according to claim 6, characterized in that: After the Feedback I step, there are also a Calculation III step and a Judgment III step; Calculation III: If ΔF m -Q m > 0, let C m = 1, V m = 0. If ΔF m -Q m = 0, let C m = 0, V m = 0. If ΔF m -Q m < 0, let C m = 0, V m = 1; The amount of positive feedback calculated is The amount of negative feedback is Judgment III: If C > V, it is judged that the feedback data set has a positive offset. If C < V, it is judged that the feedback data set has a negative offset. If C = V, it is judged that the feedback data set has a two-way offset in the positive and negative directions.

8. The intelligent facial mask production management method based on feedback analysis according to claim 7, characterized in that: After the Judgment III step, there are also a Judgment IV step and a Feedback II step. In the Judgment III step, when it is judged that C < V or C = V, the Judgment IV step is executed; Judgment IV: Obtain the target feedback amount Z according to historical data. If V ≥ Z, it is judged that the feedback result is unacceptable and the Feedback II step is executed. If V < Z, it is judged that the feedback result is acceptable; Feedback II: Upload data to the management end, add a management level in the next detection cycle, and make N = N + 1.

9. The intelligent facial mask production management method based on feedback analysis according to claim 6, wherein: In the calculation step I, the calculation model of E I is updated to: Among them, β n is the error weight of the evaluation factor set of the nth management level, and β ∈ (0, 1).

10. The intelligent facial mask production management method based on feedback analysis according to any one of claims 6-9, characterized in that: In the second calculation step, the calculation model of ΔF m is updated to: where γ n is the error weight of the feedback data set at the nth management level, and γ ∈ (0, 1).

Images