Three-dimensional model generation method and system of breathing mask and storage medium

Abstract

The invention relates to the technical field of three-dimensional model processing, in particular to a three-dimensional model generation method and system of a breathing mask and a storage medium. The method comprises the following steps: acquiring a multi-dimensional original data set of the breathing mask; performing data preprocessing on the multi-dimensional original data set of the breathing mask to generate a multi-dimensional processing data set of the breathing mask; performing static multi-dimensional data linkage on the multi-dimensional processing data set of the breathing mask to generate static multi-dimensional linkage data; performing data set scoring on the multi-dimensional processing data set of the breathing mask to generate dynamic multi-dimensional scoring data; personalized modeling is carried out based on the static multi-dimensional linkage data and the dynamic multi-dimensional scoring data, and a user personalized portrait model is generated; therefore, by combining static linkage and dynamic scoring of the multi-dimensional data, the problems that traditional breathing mask design lacks individuation and is insufficient in adaptation degree are solved, the accuracy and comfort of mask design are improved, and user experience and product performance are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional model processing, and in particular to a three-dimensional model generation method, system and storage medium for a breathing mask. Background Art

[0002] At present, the design of most respiratory masks still relies on traditional empirical models and standardized production processes, lacking the accurate capture and reflection of user facial features and personalized needs. The existing technology uses a universal template for design, ignoring the differences between the facial geometry, bone structure and comfort requirements of different users, resulting in discomfort and poor airflow. In addition, when evaluating and optimizing mask design, the existing system can only rely on single static data and traditional comfort testing methods, lacking dynamic data feedback and real-time wearing adjustment capabilities. In terms of comfort evaluation, traditional technologies mainly rely on subjective evaluation or simulation based on static models. These methods often cannot accurately reflect the changes and use effects of masks during actual wearing, and cannot evaluate the airflow smoothness, facial adaptability and breathing resistance factors of masks in real time. At the same time, the existing technology fails to take into account the dynamic factors of airflow changes, pressure distribution and mask deformation in multiple dimensions during wearing, resulting in the final design being difficult to meet the needs of users in different wearing scenarios. In terms of personalized design, the existing technology also has limitations. Many respiratory mask designs cannot be customized according to the facial features of each user, but can only provide limited size options or mold adjustments. Although some emerging technologies attempt to combine 3D scanning and printing technologies for personalized customization, they are still insufficient in real-time data fusion, dynamic adjustment, and multi-dimensional evaluation, and cannot achieve truly accurate personalized design. Summary of the invention

[0003] Based on this, it is necessary to provide a method, system and storage medium for generating a three-dimensional model of a respiratory mask to solve at least one of the above technical problems.

[0004] To achieve the above object, a method, system and storage medium for generating a three-dimensional model of a respiratory mask are provided, wherein the method comprises the following steps: Step S1: obtaining a multidimensional original data set of a respiratory mask; performing data preprocessing on the multidimensional original data set of the respiratory mask to generate a multidimensional processed data set of the respiratory mask; Step S2: performing static multidimensional data linkage on the multidimensional processing data set of the respiratory mask to generate static multidimensional linkage data; performing data set scoring on the multidimensional processing data set of the respiratory mask to generate dynamic multidimensional scoring data; performing personalized modeling based on the static multidimensional linkage data and the dynamic multidimensional scoring data to generate a user personalized portrait model; Step S3: acquiring real-time user facial scanning data; supplementing the user personalized portrait model with three-dimensional personalized model data based on the real-time user facial scanning data to generate a personalized three-dimensional model of the breathing mask; Step S4: construct a model report based on the personalized three-dimensional model of the breathing mask, generate a breathing mask model generation report, and thus complete the three-dimensional model generation operation of the breathing mask.

[0005] The beneficial effect of the present invention is that by obtaining a multidimensional raw data set of a respiratory mask and performing data preprocessing on it, the raw data can be effectively cleaned and standardized, thereby improving the quality and reliability of the data and laying a solid foundation for subsequent modeling and analysis. The multidimensional processed data set after data preprocessing provides a unified and structured basis for further static linkage and dynamic scoring analysis, ensuring the consistency and operability of the data in the subsequent process. In the static multidimensional data linkage stage, by performing linkage analysis on different dimensions of the data, the relationship between various design elements can be revealed, providing a theoretical basis for the design optimization of the respiratory mask. In addition, the generation of dynamic scoring data enables the mask design to meet user needs more accurately by evaluating the fitness and performance of each design dimension in real time. The personalized modeling stage combines static and dynamic data to tailor a personalized mask model for each user, thereby achieving more efficient matching and better wearing comfort. By obtaining real-time user facial scanning data and combining the user's personalized portrait model for three-dimensional supplementation, the accurate matching of the mask can be achieved in details, further improving the wearing comfort and sealing. Finally, the generated report based on the personalized three-dimensional mask model can not only comprehensively summarize the design and effect of the mask, but also provide a scientific basis for subsequent production links, ensuring the improvement of production efficiency and product quality. Through this innovative process, the design accuracy and user satisfaction of the respiratory mask can be significantly improved, thereby providing users with a customized and personalized wearing experience. Therefore, the present invention solves the problems of lack of personalization and insufficient adaptability in the design of traditional respiratory masks by combining the static linkage and dynamic scoring of multi-dimensional data, improves the accuracy and comfort of the mask design, and significantly improves the user experience and product performance.

[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire a multi-dimensional original data set of a respiratory mask; Step S12: performing data redundancy reduction processing on the multidimensional original data set of the breathing mask to generate a multidimensional redundancy reduced data set of the breathing mask; performing data set calibration on the multidimensional redundancy reduced data set of the breathing mask to generate a multidimensional calibration data set of the breathing mask; Step S13: performing data set standardization processing on the respiratory mask multidimensional calibration data set to generate a respiratory mask multidimensional processing data set, wherein the respiratory mask multidimensional processing data set includes a static multidimensional processing data set and a dynamic multidimensional processing data set.

[0007] The present invention obtains a multi-dimensional raw data set of a respiratory mask. The system first collects basic data of multiple parameters (such as mask shape, pressure distribution, and material properties), laying the foundation for subsequent analysis and modeling. However, since multi-dimensional data often contains redundant or noisy information, this information will affect the accuracy and efficiency of subsequent analysis if it is not processed. By performing redundancy reduction processing on the data set and removing irrelevant or repeated parts, the remaining data is made more compact and effective, avoiding the waste of computing resources and improving the speed and accuracy of data processing. At this time, the data set still has calibration deviations caused by different sources and different formats. The data is standardized by unified scale and reference to ensure that all data are consistent in the same dimension, reduce the potential risks caused by data errors, and improve the reliability of subsequent data analysis. After redundancy reduction and calibration, the data set is standardized to ensure that each dimension of the data set can be compared horizontally, thereby providing more accurate input for the construction of the model. Standardization also effectively avoids the influence of different data ranges on the analysis results, further improving the integration and applicability of the data. Finally, the processed data sets are divided into static and dynamic multidimensional processing data sets, which respectively represent the static characteristics (such as size and shape) and dynamic characteristics (such as pressure changes when worn and breathing airflow) in the design of respiratory masks. This classification process can better support subsequent personalized modeling and optimization, ensuring that the mask design not only meets the stable structural requirements in actual use, but also can adapt to the dynamic changes during user use.

[0008] Preferably, step S2 comprises the following steps: Step S21: performing static multi-dimensional data linkage on the static multi-dimensional processed data set to generate static multi-dimensional linkage data, wherein the respiratory mask multi-dimensional processed data set includes facial geometric feature data, bone structure data and fit data; Step S22: performing a data set evaluation on the dynamic multi-dimensional processing data set to generate dynamic multi-dimensional evaluation data, wherein the dynamic multi-dimensional processing data set includes mask deformation data, respiratory airflow change data and pressure distribution data; Step S23: Perform finite element model set analysis based on static multi-dimensional linkage data to generate a user wearing demand portrait model; dynamically adjust the wearing scenario of the user wearing demand portrait model according to the dynamic multi-dimensional scoring data to generate a user personalized portrait model.

[0009] The present invention conducts static multi-dimensional data linkage on static multi-dimensional processing data sets, combines facial geometric feature data, bone structure data and fit data, and reveals the relationship between mask design elements through linkage analysis. This linkage processing not only optimizes the fit between the mask and the facial morphology, but also provides a scientific basis for the comfort and wearing effect of the mask, ensuring that the design of the mask can adapt to the facial features of different users and improve the wearing comfort and sealing. By evaluating the dynamic multi-dimensional processing data set, combining the mask deformation data, respiratory airflow change data and pressure distribution data, the dynamic performance of the mask during the wearing process is quantitatively analyzed. The dynamic evaluation data can accurately reflect the changes between the mask and the respiratory airflow and the facial contact surface during the wearing process, thereby providing a more accurate adjustment basis for the design, ensuring the performance and comfort of the mask in different usage scenarios. Based on the static multi-dimensional linkage data, a finite element model set analysis is performed, combined with the user's facial data and wearing requirements, and a user wearing requirement portrait model is generated by simulating different wearing scenarios. This process effectively converts static data into dynamic wearing requirements, revealing the differentiated needs of different users during the wearing process. At the same time, based on dynamic multi-dimensional scoring data, the wearing demand portrait model is dynamically adjusted, so that the generated user personalized portrait model can reflect the changes in user needs in different wearing scenarios in real time, further improving the fit and comfort of the mask. This series of data analysis and model adjustment not only provides an accurate basis for the personalized design of the mask, but also provides a quantitative optimization solution for the user's wearing experience. Through this innovative process, a high degree of matching between mask design and user needs can be achieved, effectively improving the user's wearing experience and the overall performance of the product.

[0010] Preferably, step S21 includes the following steps: Step S211: docking the facial geometry feature data and the bone structure data in a coordinate system space to generate facial geometry-bone structure space coordinate data; Step S212: calibrate the key bone positions of the facial geometry-bone structure spatial coordinate data to generate facial geometry-bone structure calibration data; perform contour area division based on the facial geometry-bone structure calibration data to generate facial geometry-bone region data; perform feature deviation search processing on the facial geometry-bone region data to generate facial geometry-bone region feature deviation data; Step S213: performing point cloud distance evaluation matching on the facial geometry feature data and the bone structure data based on the facial geometry-bone area feature deviation data to generate facial geometry-bone point cloud matching data; performing fit quantization processing on the facial geometry-bone point cloud matching data and the fit data to generate facial fit quantization data; Step S214: integrating the facial geometry-bone structure spatial coordinate data, the facial geometry-bone region feature deviation data and the facial fit quantification data into a multidimensional data set to generate static multidimensional linkage data.

[0011] The present invention generates facial geometry-bone structure space coordinate data by docking the facial geometry feature data with the bone structure data in the coordinate system space. This process ensures that the various geometric features of the face and the bone structure are uniformly analyzed in the same coordinate system, laying a foundation for the subsequent adaptability analysis. The facial geometry-bone structure calibration data is generated by calibrating the key bone positions of the facial geometry-bone structure space coordinate data. This step not only accurately calibrates the bone feature positions of the face, but also divides the facial contour area based on these data to generate facial geometry-bone area data, thereby helping to accurately identify and analyze the structural features of each area of ​​the face. The facial geometry-bone area feature deviation data is generated by performing feature deviation search processing on the facial geometry-bone area data. This process effectively finds the difference between the facial geometry and the bone structure, providing important information for the subsequent adaptation optimization. The facial geometry-bone point cloud matching data is generated by performing point cloud distance evaluation matching on the facial geometry data and the bone structure data based on the facial geometry-bone area feature deviation data. The core of this step is to quantify the adaptability of the facial geometry and the bone structure through the point cloud matching technology, thereby providing key data for the precise design of the mask. In addition, the facial geometry-bone point cloud matching data is combined with the fit data to perform fit quantification processing to generate facial fit quantification data. This step accurately quantifies the fit between the mask and the face, providing data support for subsequent optimization and personalized design. By integrating the facial geometry-bone structure spatial coordinate data, facial geometry-bone regional feature deviation data, and facial fit quantification data into a multidimensional data set, static multidimensional linkage data is generated. This integration not only enhances the connectivity between the various data dimensions, but also provides a high-dimensional comprehensive data set for further analysis, modeling, and optimization, ensuring the accurate adaptation of the mask design in multiple dimensions. Through this systematic multidimensional data processing process, the personalization and adaptation accuracy of the mask design can be significantly improved, thereby providing users with a higher level of wearing comfort and more accurate mask matching.

[0012] Preferably, step S22 includes the following steps: Step S221: performing mask fitting edge gap detection on the mask deformation data to generate mask edge gap detection data; performing mask fitting contour compression detection on the mask deformation data to generate mask contour compression detection data; performing mask fitting comfort evaluation based on the mask edge gap detection data and the mask contour compression detection data to generate mask comfort evaluation data; Step S222: Generate a gas flow path for the respiratory airflow change data to generate a mask respiratory gas flow path; perform resistance eddy current detection on the respiratory airflow change data to generate mask respiratory eddy current detection data; perform airflow stability evaluation on the mask respiratory gas flow path based on the mask respiratory eddy current detection data to generate mask respiratory airflow evaluation data; Step S223: performing uniformity analysis on the pressure distribution data to generate mask pressure uniformity data; performing comfort evaluation on the mask pressure uniformity data using a preset pressure threshold to generate mask comfort evaluation data; Step S224: Perform personalized and overall evaluation on the mask comfort evaluation data, the mask breathing airflow evaluation data, and the mask comfort evaluation data to generate dynamic multi-dimensional evaluation data.

[0013] The present invention generates facial geometry-bone structure space coordinate data by docking the facial geometry feature data with the bone structure data in the coordinate system space. This process ensures that the various geometric features of the face and the bone structure are uniformly analyzed in the same coordinate system, laying a foundation for the subsequent adaptability analysis. The facial geometry-bone structure calibration data is generated by calibrating the key bone positions of the facial geometry-bone structure space coordinate data. This step not only accurately calibrates the bone feature positions of the face, but also divides the facial contour area based on these data to generate facial geometry-bone area data, thereby helping to accurately identify and analyze the structural features of each area of ​​the face. The facial geometry-bone area feature deviation data is generated by performing feature deviation search processing on the facial geometry-bone area data. This process effectively finds the difference between the facial geometry and the bone structure, providing important information for the subsequent adaptation optimization. The facial geometry-bone point cloud matching data is generated by performing point cloud distance evaluation matching on the facial geometry data and the bone structure data based on the facial geometry-bone area feature deviation data. The core of this step is to quantify the adaptability of the facial geometry and the bone structure through the point cloud matching technology, thereby providing key data for the precise design of the mask. In addition, the facial geometry-bone point cloud matching data is combined with the fit data to perform fit quantification processing to generate facial fit quantification data. This step accurately quantifies the fit between the mask and the face, providing data support for subsequent optimization and personalized design. By integrating the facial geometry-bone structure spatial coordinate data, facial geometry-bone regional feature deviation data, and facial fit quantification data into a multidimensional data set, static multidimensional linkage data is generated. This integration not only enhances the connectivity between the various data dimensions, but also provides a high-dimensional comprehensive data set for further analysis, modeling, and optimization, ensuring the accurate adaptation of the mask design in multiple dimensions. Through this systematic multidimensional data processing process, the personalization and adaptation accuracy of the mask design can be significantly improved, thereby providing users with a higher level of wearing comfort and more accurate mask matching.

[0014] Preferably, step S3 comprises the following steps: Step S31: Acquire real-time user facial scanning data; Step S32: Supplementing the user personalized portrait model with three-dimensional personalized model data based on the real-time user facial scanning data to generate three-dimensional personalized user facial data; Step S33: construct a three-dimensional breathing mask personalized model based on the personalized user facial data and the user personalized portrait model to generate a personalized three-dimensional breathing mask model.

[0015] The present invention captures the geometric shape, bone structure and skin feature details of the user's face in real time by acquiring real-time user facial scanning data, ensuring accurate recording of the user's facial features. This data collection process provides the most basic and accurate data support for subsequent personalized modeling, and can accurately reflect the facial differences of users. Next, step S32 generates three-dimensional personalized user facial data by supplementing the user's personalized portrait model with three-dimensional personalized model data based on real-time facial scanning data. In this process, the original facial scanning data is intelligently integrated with the existing personalized portrait model, so that the facial features of each user are described more comprehensively and three-dimensionally. Through this supplement, the model can more accurately reflect the specific needs of the user's face, thereby providing more refined parameter support for the design of personalized breathing masks. A three-dimensional breathing mask personalized model is constructed according to the personalized user facial data and the user's personalized portrait model, and a three-dimensional breathing mask model that meets the user's unique facial features is generated. In this process, the design elements of the mask's shape, size, and structure are accurately adjusted to match the user's facial features to the greatest extent. Through refined 3D modeling, not only is the comfortable fit of the mask structure guaranteed, but also the optimization of airtightness and airflow during wearing. This series of precise processes greatly improves the personalized customization capabilities of the respiratory mask, ensuring that users can obtain a more comfortable, practical and physiologically appropriate mask design. Through this innovative method, the blindness and roughness of traditional respiratory mask design methods are effectively avoided, providing users with more scientific and personalized products, significantly improving the wearing comfort and functionality of the mask.

[0016] Preferably, step S33 includes the following steps: Step S331: using a data fusion algorithm to combine personalized user facial data and a personalized user portrait model to generate personalized integrated data for a respiratory mask; Step S332: Perform preliminary three-dimensional breathing mask modeling on the personalized integrated data of the breathing mask to generate a preliminary three-dimensional breathing mask model; Step S333: performing pressure distribution on the preliminary model of the three-dimensional breathing mask to generate a three-dimensional breathing mask pressure distribution model; performing finite element fit analysis based on the three-dimensional breathing mask pressure distribution model to generate a three-dimensional breathing mask fit model; performing personalized dynamic parameter adjustment on the three-dimensional breathing mask fit model based on the dynamic multi-dimensional scoring data to generate a personalized three-dimensional breathing mask model.

[0017] The present invention combines personalized user facial data with the personalized user portrait model through a data fusion algorithm to generate personalized integrated data of the breathing mask. The data fusion process fully considers the geometric morphology, bone structure and wearing requirements of the user's face, ensuring that each parameter of the personalized portrait model can be accurately mapped to the specific features of the user's face. This integrated data not only improves the accuracy of the personalized model, but also provides a solid foundation for subsequent three-dimensional modeling. Based on the integrated data, preliminary modeling of the three-dimensional breathing mask is performed to generate a preliminary model of the three-dimensional breathing mask. This preliminary model realizes the virtual construction of the mask structure, considers the geometric relationship between the facial features and the mask contact area, and provides preliminary guarantees for the fit and comfort of the mask. However, only the preliminary model is not enough to ensure the best fitting effect in actual use. The pressure distribution of the three-dimensional breathing mask preliminary model is further distributed to generate a three-dimensional breathing mask pressure distribution model. The pressure distribution model can accurately predict the comfort and stability under different wearing conditions by accurately simulating the stress conditions of each area of ​​the mask, avoiding facial discomfort or functional failure caused by pressure concentration. Furthermore, a three-dimensional respiratory mask fit model was generated by performing finite element fit analysis on the pressure distribution model. This fit analysis can deeply evaluate the stress distribution, material deformation and adaptability of the contact surface of the mask when worn, ensuring that the mask can maintain an ideal fit and performance in a dynamic use environment. Finally, the three-dimensional respiratory mask fit model was personalized and dynamically adjusted based on the dynamic multidimensional scoring data to generate a personalized three-dimensional model of the respiratory mask. This adjustment process is based on real-time feedback and dynamic scoring data to ensure the best fit of the mask in different wearing scenarios, and through continuous optimization, the balance between mask comfort and functionality is achieved. Through this series of high-precision data processing steps, the respiratory mask can not only be personalized according to the unique facial features of each user, but also ensure the best comfort and functionality during the actual wearing process, thereby effectively improving the user's wearing experience.

[0018] Preferably, step S4 comprises the following steps: Step S41: performing a comprehensive evaluation of model generation on the personalized three-dimensional model of the breathing mask to generate comprehensive evaluation data of the three-dimensional model of the breathing mask; Step S42: constructing a model report based on the comprehensive evaluation data of the breathing mask three-dimensional model, and generating a breathing mask model generation report; Step S43: using visualization technology to perform data chart visualization analysis on the respiratory mask model generation report, generating a respiratory mask visualization chart, thereby completing the three-dimensional model generation operation of the respiratory mask.

[0019] The present invention generates comprehensive evaluation data of the three-dimensional model of the breathing mask by comprehensively evaluating the personalized three-dimensional model of the breathing mask. This comprehensive evaluation not only integrates the data of the geometric characteristics, pressure distribution, fit, and airflow path of the mask in multiple dimensions, but also takes into account the dynamic adaptability and comfort of the model in actual use. This comprehensive evaluation can comprehensively detect the performance of the mask in various wearing scenarios, and provide data support for subsequent adjustment and optimization. A model report is constructed based on the comprehensive evaluation data of the three-dimensional model of the breathing mask, and a breathing mask model generation report is generated. The report records in detail each key parameter, test data, and evaluation results in the mask design process, forming a standard document for further analysis and modification. The model report not only provides a basis for targeted improvements for the design team, but also provides users with transparency and reliability analysis of the mask design. The generation of this report provides data support to ensure that the mask can meet personalized needs in actual wearing, and reduces the adaptation problems caused by the lack of data evaluation in the traditional design process. By using visualization technology to visualize the data chart of the breathing mask model generation report, a visualization chart of the breathing mask is generated. Visual charts present complex evaluation data in the form of graphs and charts, helping the design team and users to more intuitively understand the pros and cons and adaptability of the mask design. The chart provides a clearer reference for subsequent optimization work, making the mask design process not only more efficient, but also able to be quickly adjusted based on user feedback. Through this series of precise evaluations and visual analyses, the invention effectively avoids the problems of poor information transmission and design blind spots in traditional designs, greatly improves the design efficiency and accuracy of respiratory masks, and brings users more personalized and high-quality products that meet usage needs.

[0020] In this specification, a three-dimensional model generation system of a breathing mask is provided, which is used to execute the above-mentioned three-dimensional model generation method of the breathing mask, and the three-dimensional model generation system of the breathing mask includes: The data acquisition and preprocessing module is used to obtain a multi-dimensional original data set of the breathing mask; perform data preprocessing on the multi-dimensional original data set of the breathing mask to generate a multi-dimensional processed data set of the breathing mask; The data linkage and modeling module is used to perform static multidimensional data linkage on the multidimensional processing data set of the respiratory mask to generate static multidimensional linkage data; perform data set scoring on the multidimensional processing data set of the respiratory mask to generate dynamic multidimensional scoring data; perform personalized modeling based on the static multidimensional linkage data and the dynamic multidimensional scoring data to generate a user personalized portrait model; The facial data collection and personalized modeling module is used to obtain real-time user facial scanning data; based on the real-time user facial scanning data, the user personalized portrait model is supplemented with three-dimensional personalized model data to generate a personalized three-dimensional model of the breathing mask; The report generation and model output module is used to construct a model report based on the personalized three-dimensional model of the breathing mask, generate a breathing mask model generation report, and thus complete the three-dimensional model generation operation of the breathing mask.

[0021] The beneficial effect of the present invention is that by obtaining a multidimensional raw data set of a respiratory mask and performing data preprocessing on it, the raw data can be effectively cleaned and standardized, thereby improving the quality and reliability of the data and laying a solid foundation for subsequent modeling and analysis. The multidimensional processed data set after data preprocessing provides a unified and structured basis for further static linkage and dynamic scoring analysis, ensuring the consistency and operability of the data in the subsequent process. In the static multidimensional data linkage stage, by performing linkage analysis on different dimensions of the data, the relationship between various design elements can be revealed, providing a theoretical basis for the design optimization of the respiratory mask. In addition, the generation of dynamic scoring data enables the mask design to meet user needs more accurately by evaluating the fitness and performance of each design dimension in real time. The personalized modeling stage combines static and dynamic data to tailor a personalized mask model for each user, thereby achieving more efficient matching and better wearing comfort. By obtaining real-time user facial scanning data and combining the user's personalized portrait model for three-dimensional supplementation, the accurate matching of the mask can be achieved in details, further improving the wearing comfort and sealing. Finally, the generated report based on the personalized three-dimensional mask model can not only comprehensively summarize the design and effect of the mask, but also provide a scientific basis for subsequent production links, ensuring the improvement of production efficiency and product quality. Through this innovative process, the design accuracy and user satisfaction of the respiratory mask can be significantly improved, thereby providing users with a customized and personalized wearing experience. Therefore, the present invention solves the problems of lack of personalization and insufficient adaptability in the design of traditional respiratory masks by combining the static linkage and dynamic scoring of multi-dimensional data, improves the accuracy and comfort of the mask design, and significantly improves the user experience and product performance.

[0022] The present invention also provides a computer-readable storage medium storing a computer program, wherein the computer program is used to execute the three-dimensional model generating method. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic flowchart of steps of a method for generating a three-dimensional model of a breathing mask; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. Figure 4 for Figure 1Detailed implementation steps of step S4 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0024] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0026] It should be understood that although the terms "first", "second", etc. are used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly a second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0027] To achieve this, please refer to Figures 1 to 4 , a method for generating a three-dimensional model of a breathing mask, the method comprising the following steps: Step S1: obtaining a multidimensional original data set of a respiratory mask; performing data preprocessing on the multidimensional original data set of the respiratory mask to generate a multidimensional processed data set of the respiratory mask; Step S2: performing static multidimensional data linkage on the multidimensional processing data set of the respiratory mask to generate static multidimensional linkage data; performing data set scoring on the multidimensional processing data set of the respiratory mask to generate dynamic multidimensional scoring data; performing personalized modeling based on the static multidimensional linkage data and the dynamic multidimensional scoring data to generate a user personalized portrait model; Step S3: acquiring real-time user facial scanning data; supplementing the user personalized portrait model with three-dimensional personalized model data based on the real-time user facial scanning data to generate a personalized three-dimensional model of the breathing mask; Step S4: construct a model report based on the personalized three-dimensional model of the breathing mask, generate a breathing mask model generation report, and thus complete the three-dimensional model generation operation of the breathing mask.

[0028] The beneficial effect of the present invention is that by obtaining a multidimensional raw data set of a respiratory mask and performing data preprocessing on it, the raw data can be effectively cleaned and standardized, thereby improving the quality and reliability of the data and laying a solid foundation for subsequent modeling and analysis. The multidimensional processed data set after data preprocessing provides a unified and structured basis for further static linkage and dynamic scoring analysis, ensuring the consistency and operability of the data in the subsequent process. In the static multidimensional data linkage stage, by performing linkage analysis on different dimensions of the data, the relationship between various design elements can be revealed, providing a theoretical basis for the design optimization of the respiratory mask. In addition, the generation of dynamic scoring data enables the mask design to meet user needs more accurately by evaluating the fitness and performance of each design dimension in real time. The personalized modeling stage combines static and dynamic data to tailor a personalized mask model for each user, thereby achieving more efficient matching and better wearing comfort. By obtaining real-time user facial scanning data and combining the user's personalized portrait model for three-dimensional supplementation, the accurate matching of the mask can be achieved in details, further improving the wearing comfort and sealing. Finally, the generated report based on the personalized three-dimensional mask model can not only comprehensively summarize the design and effect of the mask, but also provide a scientific basis for subsequent production links, ensuring the improvement of production efficiency and product quality. Through this innovative process, the design accuracy and user satisfaction of the respiratory mask can be significantly improved, thereby providing users with a customized and personalized wearing experience. Therefore, the present invention solves the problems of lack of personalization and insufficient adaptability in the design of traditional respiratory masks by combining the static linkage and dynamic scoring of multi-dimensional data, improves the accuracy and comfort of the mask design, and significantly improves the user experience and product performance.

[0029] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of a process flow of a method for generating a three-dimensional model of a breathing mask according to the present invention. In this example, the method for generating a three-dimensional model of a breathing mask includes the following steps: Step S1: obtaining a multidimensional original data set of a respiratory mask; performing data preprocessing on the multidimensional original data set of the respiratory mask to generate a multidimensional processed data set of the respiratory mask; In an embodiment of the present invention, the multi-dimensional raw data set of the respiratory mask is obtained by collecting raw data related to the respiratory mask from multiple sources, including but not limited to the geometric characteristics, material properties, wearing comfort, pressure distribution, respiratory airflow changes, and deformation data of the mask. These data come from multiple channels such as sensors, simulation tests of masks, user feedback, and facial scanning, and have multi-dimensional and multi-level complexity. In order to ensure the availability and accuracy of the data, a series of data cleaning and standardization processes are performed in the data preprocessing stage, including data redundancy removal, noise filtering, and missing value filling, so as to convert the raw data into a format that can be further analyzed and used. Through these processes, redundant information can be removed, outliers can be eliminated, and gaps in the data can be filled, thereby improving the integrity and reliability of the data. In addition, data preprocessing also includes normalizing and standardizing data of different dimensions so that they can be effectively fused and compared within the same data framework. In this process, the missing data are repaired by appropriate algorithms such as mean filling, interpolation, or machine learning methods, and the scale conversion of various types of data is performed so that the data has a unified dimension or metric.

[0030] Step S2: performing static multidimensional data linkage on the multidimensional processing data set of the respiratory mask to generate static multidimensional linkage data; performing data set scoring on the multidimensional processing data set of the respiratory mask to generate dynamic multidimensional scoring data; performing personalized modeling based on the static multidimensional linkage data and the dynamic multidimensional scoring data to generate a user personalized portrait model; In an embodiment of the present invention, data fusion and association technology are used to match and associate different data dimensions (such as facial geometric features, material properties, fit, and pressure distribution) in a multidimensional processing data set in space and time. By defining appropriate data association rules and algorithms (such as similarity measurement, cluster analysis, and principal component analysis), the data of each dimension are merged in the same coordinate system or data framework to reveal the inherent connection and interaction between them. Static multidimensional data linkage can reveal the comprehensive performance of mask design under different wearing conditions, help identify the key factors in mask design and their impact on comfort and adaptability. Then, in the data set scoring stage, the static multidimensional data is scored by using a multidimensional scoring system (such as a weighted scoring model, a Bayesian scoring method, or a fuzzy logic scoring system) to generate dynamic multidimensional scoring data. This process quantitatively scores multiple functional dimensions of the mask, combines the user's actual wearing needs, dynamic changes in airflow, and pressure distribution factors, and analyzes the performance of the mask under different conditions to generate a set of comprehensive scoring systems for specific user needs. These scores not only consider static factors, but also reflect dynamic changes in real time, thereby providing more targeted evaluation results. Based on static multi-dimensional linkage data and dynamic multi-dimensional scoring data, personalized modeling is performed to generate a personalized user portrait model. This process combines the aforementioned scoring data with linkage data, uses machine learning algorithms (such as decision trees, support vector machines, neural networks) for modeling, matches user personalized needs with design parameters, and generates an accurate personalized portrait model.

[0031] Step S3: acquiring real-time user facial scanning data; supplementing the user personalized portrait model with three-dimensional personalized model data based on the real-time user facial scanning data to generate a personalized three-dimensional model of the breathing mask; In an embodiment of the present invention, facial data is collected by a high-precision three-dimensional scanner or other facial recognition technology equipment (such as laser scanning, structured light or optical imaging). These devices can capture the subtle geometric features of the user's face, including facial contours, bone structure, soft tissue morphology, and specific facial biomarkers (such as eyes, nose bridge, and chin key points). The scanned data is presented in the form of a point cloud, and each point contains position coordinates (x, y, z) and facial surface normal information, so as to obtain an accurate model of the three-dimensional facial structure. These data are represented by a high-density three-dimensional coordinate point set, with high resolution and high spatial accuracy, and can truly reproduce the user's facial morphology. The user's personalized portrait model is supplemented with three-dimensional personalized model data based on real-time user facial scanning data. This step involves data fusion of facial scanning data with previously generated personalized portrait models, with the purpose of further supplementing and refining the detailed information of the personalized portrait model. Through data fusion algorithms (such as Kalman filtering, data interpolation, and weighted averaging), data from different sources (such as historical data, user basic portraits, and real-time facial scanning data) are comprehensively processed to generate more accurate and detailed personalized user facial three-dimensional data. In this process, by extracting and matching the features of the scan data and supplementing the facial detail information in the user portrait model, not only the accuracy of the facial model is improved, but also the personalized adaptation capability is further enhanced. Based on the real-time personalized facial data and the optimized user portrait model, a personalized 3D model of the breathing mask is generated. This process involves matching the user's 3D facial scan data with the design parameters of the mask, and using computer-aided design (CAD) software or finite element analysis (FEA) methods to model the personalized mask. Specifically, an accurate 3D breathing mask model is generated based on the user's facial features, the mask's fitting area, and the comfort requirements.

[0032] Step S4: construct a model report based on the personalized three-dimensional model of the breathing mask, generate a breathing mask model generation report, and thus complete the three-dimensional model generation operation of the breathing mask.

[0033] In an embodiment of the present invention, a personalized three-dimensional model of a respiratory mask is created by computer-aided design (CAD) software or a digital modeling tool. The model not only contains geometric information of the mask, but also includes the adaptability, comfort and functional analysis results that match the user's facial data. On this basis, the first step in constructing a model report is to conduct an in-depth analysis of the key elements of the structure, shape, size, contact surface, airflow path, and pressure distribution of the three-dimensional model. The structure and stress analysis of the three-dimensional model of the mask is performed by finite element analysis (FEA) to evaluate the deformation, contact pressure and comfort of the model when worn. This process evaluates the physical properties and comfort of the mask by decomposing the model into multiple finite units and performing mechanical calculations on each unit to ensure its stability and comfort in actual use. Secondly, a dynamic analysis of the airflow path of the mask is performed based on the simulation of respiratory airflow to evaluate the stability, resistance and uniformity of the airflow, especially how to ensure unimpeded gas flow when the user breathes. In this process, the airflow is simulated by the computational fluid dynamics (CFD) method to ensure the uniformity and comfort of the airflow distribution and generate relevant airflow model data. The construction of the mask model report also needs to include evaluation data related to the personalized needs of the user. For example, through the fit analysis with the user's facial structure, the report will detail the area where the mask contacts the user's face, the distribution of contact pressure, and potential fit issues, and generate corresponding comfort scores and fit evaluations. These data not only evaluate whether the design of the mask meets the user's personalized needs from a geometric morphological level, but also cover multiple aspects of comfort, functionality, and physiological fit. By integrating all analysis data, the report will systematically present the performance evaluation, fit results, airflow analysis, and comfort score information of the mask model.

[0034] Preferably, step S1 comprises the following steps: Step S11: Acquire a multi-dimensional original data set of a respiratory mask; Step S12: performing data redundancy reduction processing on the multidimensional original data set of the breathing mask to generate a multidimensional redundancy reduced data set of the breathing mask; performing data set calibration on the multidimensional redundancy reduced data set of the breathing mask to generate a multidimensional calibration data set of the breathing mask; Step S13: performing data set standardization processing on the respiratory mask multidimensional calibration data set to generate a respiratory mask multidimensional processing data set, wherein the respiratory mask multidimensional processing data set includes a static multidimensional processing data set and a dynamic multidimensional processing data set.

[0035] In an embodiment of the present invention, a multidimensional raw data set of a respiratory mask is obtained, and data is collected by various sensors, measuring devices, and 3D scanners, covering the geometry, structure, fit, airflow path, and pressure distribution of the mask. Multidimensional data. These data are collected from multiple data sources, including the appearance data of the mask, material performance data, and facial feature data of the wearer. The acquired raw data is often high-dimensional and has multiple attributes. Therefore, the accuracy and consistency of the data are the prerequisites for ensuring the effect of subsequent analysis. The original data set is subjected to redundancy reduction processing, the purpose of which is to eliminate redundant and repeated data points to reduce the noise and redundancy of the data and ensure the simplicity and efficiency of the data set. This process involves data deduplication, feature selection or dimensionality reduction techniques, such as principal component analysis (PCA) or independent component analysis (ICA), which reduces and compresses the data to remove irrelevant or highly correlated data variables, thereby improving the efficiency and accuracy of data analysis. Subsequently, the data set after redundancy reduction is calibrated. Calibration refers to the accuracy adjustment and consistency correction of the data to ensure that the differences between various data sources or measurement methods do not affect the final analysis results. Calibration can ensure the temporal and spatial consistency of data through data fusion technology, sensor calibration, and time synchronization methods. Standardization is performed on the data set that has been redundancy-reduced and calibrated. Standardization is a key step in data preprocessing. Its purpose is to convert data of different dimensions or different ranges into a unified standard form, thereby eliminating the impact of inconsistent dimensions on the analysis results. Common standardization techniques include Z-score standardization and minimum-maximum normalization, which ensure that data is compared and processed within the same scale range by scaling the data proportionally.

[0036] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: performing static multi-dimensional data linkage on the static multi-dimensional processed data set to generate static multi-dimensional linkage data, wherein the respiratory mask multi-dimensional processed data set includes facial geometric feature data, bone structure data and fit data; Step S22: performing a data set evaluation on the dynamic multi-dimensional processing data set to generate dynamic multi-dimensional evaluation data, wherein the dynamic multi-dimensional processing data set includes mask deformation data, respiratory airflow change data and pressure distribution data; Step S23: Perform finite element model set analysis based on static multi-dimensional linkage data to generate a user wearing demand portrait model; dynamically adjust the wearing scenario of the user wearing demand portrait model according to the dynamic multi-dimensional scoring data to generate a user personalized portrait model.

[0037] In the embodiment of the present invention, the technical means for linking static multidimensional data to static multidimensional processing data sets mainly utilizes multidimensional data fusion and spatial mapping methods. The static data sets include facial geometric feature data, bone structure data and fit data. There is a certain correlation between these data. Through spatial docking and feature fusion technology, different types of data can be effectively combined to generate static multidimensional linkage data. Specifically, facial geometric feature data and bone structure data can be spatially docked through coordinate system conversion to form a unified three-dimensional coordinate space, thereby realizing the linkage between different data dimensions. At the same time, fit data can be matched with geometric morphology data to further improve the fit between the mask and the user's face. Data fusion technology, such as weighted averaging, Kalman filtering, and particle filtering, can be used to find the best combination method between multiple data sources to ensure the accuracy and consistency of data. The technical means for data evaluation for dynamic multidimensional processing data sets mainly evaluates the validity and stability of dynamic data through data analysis and modeling methods. The dynamic data set includes mask deformation data, respiratory airflow change data, and pressure distribution data. These data reflect the dynamic performance of the mask during wearing. Through data evaluation, potential quality problems and comfort differences can be identified. The mask deformation data is monitored in real time by strain sensors or pressure sensors, and the adaptability of the mask to the face can be determined by deformation analysis; the respiratory airflow change data can be used to evaluate whether the airflow is smooth, whether there are eddies or excessive resistance, through flow sensors or airflow path detection; the pressure distribution data is collected by pressure sensors to evaluate whether the pressure is evenly distributed to ensure comfort and effectiveness when wearing. Dynamic evaluation data helps to identify potential risks of discomfort or substandard functions, and provide data support for subsequent personalized adjustments. Finite element model set analysis is performed based on static multi-dimensional linkage data to generate a user wearing demand portrait model. Finite element analysis (FEA) is a numerical calculation technology that solves complex geometric shapes by decomposing them into small, simple elements. In this process, finite element analysis can be applied to the design and optimization of respiratory masks to simulate the mechanical response and deformation behavior of the mask when it contacts the user's face, so as to accurately predict the comfort, adaptability and stress concentration areas during wearing. Based on static multi-dimensional linkage data, finite element analysis can perform virtual simulation of the mask to generate a portrait model that meets the wearing requirements. On this basis, the wearing demand portrait is dynamically adjusted according to the dynamic multi-dimensional scoring data.

[0038] Preferably, step S21 includes the following steps: Step S211: docking the facial geometry feature data and the bone structure data in a coordinate system space to generate facial geometry-bone structure space coordinate data; Step S212: calibrate the key bone positions of the facial geometry-bone structure spatial coordinate data to generate facial geometry-bone structure calibration data; perform contour area division based on the facial geometry-bone structure calibration data to generate facial geometry-bone region data; perform feature deviation search processing on the facial geometry-bone region data to generate facial geometry-bone region feature deviation data; Step S213: performing point cloud distance evaluation matching on the facial geometry feature data and the bone structure data based on the facial geometry-bone area feature deviation data to generate facial geometry-bone point cloud matching data; performing fit quantization processing on the facial geometry-bone point cloud matching data and the fit data to generate facial fit quantization data; Step S214: integrating the facial geometry-bone structure spatial coordinate data, the facial geometry-bone region feature deviation data and the facial fit quantification data into a multidimensional data set to generate static multidimensional linkage data.

[0039] In an embodiment of the present invention, the coordinate system space docking of facial geometric feature data and bone structure data is achieved through coordinate transformation technology. Facial geometric feature data is obtained through three-dimensional scanning technology and represents the surface morphology of the face; while bone structure data is obtained through medical imaging technology (such as CT or MRI) and represents the spatial position of facial bones. In order to combine these two data from different sources, it is necessary to dock the coordinate systems, that is, to unify the spatial coordinates of the two into the same coordinate system, thereby forming facial geometry-bone structure space coordinate data. This process relies on spatial transformation algorithms in computer vision, such as affine transformation, rigid transformation or non-rigid transformation, which can accurately align facial geometry data with bone data. The key bone position calibration of facial geometry-bone structure space coordinate data is achieved through a bone calibration algorithm. This calibration process mainly involves identifying the key bone positions of the face in the docked data, such as the important bone features of the zygomatic bone and mandible. The calibration of these key positions is of great significance for subsequent regional division and feature deviation analysis. Bone position calibration is completed by image-based positioning technology, such as active contour model (ActiveContour Model) or annotation technology in machine learning. After calibration, the facial geometry-bone structure data can be used to divide the facial contour area and generate facial geometry-bone area data. Based on the facial geometry-bone area data, step S212 further performs feature deviation search processing. This process identifies inconsistencies and errors in the data by calculating the deviation value between the facial geometry and the bone area. The feature deviation search uses a distance measurement algorithm (such as Euclidean distance, cosine similarity) to compare the morphological differences between different areas, thereby generating facial geometry-bone area feature deviation data. Based on the facial geometry-bone area feature deviation data, point cloud distance evaluation matching is further performed. Point cloud matching is a method for evaluating the matching degree of facial geometry and bone point cloud data by comparing the distance between the two. The point cloud data is obtained by laser scanning or structured light scanning and contains the spatial coordinates of each point on the face. Through a point cloud matching algorithm, such as the ICP (Iterative Closest Point) algorithm, the matching accuracy between the facial geometry and the bone structure can be calculated, thereby generating facial geometry-bone point cloud matching data. Then, these data are combined with the fit data to perform fit quantification processing to quantify the fit degree of the mask contact with the face. The fit can be calculated by calculating the contact area between the mask surface and the facial contour, or by evaluating the pressure distribution. All generated data (facial geometry-bone structure spatial coordinate data, facial geometry-bone area feature deviation data, facial fit quantification data) will be integrated into a multidimensional data set.This integration process uses data fusion techniques, such as principal component analysis (PCA) or multidimensional scaling (MDS), to merge multiple data sources into a unified, multidimensional model through dimensionality reduction or cluster analysis, thereby generating static multidimensional linkage data.

[0040] Preferably, step S22 includes the following steps: Step S221: performing mask fitting edge gap detection on the mask deformation data to generate mask edge gap detection data; performing mask fitting contour compression detection on the mask deformation data to generate mask contour compression detection data; performing mask fitting comfort evaluation based on the mask edge gap detection data and the mask contour compression detection data to generate mask comfort evaluation data; Step S222: Generate a gas flow path for the respiratory airflow change data to generate a mask respiratory gas flow path; perform resistance eddy current detection on the respiratory airflow change data to generate mask respiratory eddy current detection data; perform airflow stability evaluation on the mask respiratory gas flow path based on the mask respiratory eddy current detection data to generate mask respiratory airflow evaluation data; Step S223: performing uniformity analysis on the pressure distribution data to generate mask pressure uniformity data; performing comfort evaluation on the mask pressure uniformity data using a preset pressure threshold to generate mask comfort evaluation data; Step S224: Perform personalized and overall evaluation on the mask comfort evaluation data, the mask breathing airflow evaluation data, and the mask comfort evaluation data to generate dynamic multi-dimensional evaluation data.

[0041] In an embodiment of the present invention, the processing of the mask deformation data is performed by a deformation analysis algorithm. The mask deformation data comes from three-dimensional scanning or mechanical simulation, which describes the geometric changes of the mask under different wearing conditions. Through edge gap detection based on deformation data, the size of the gap between the mask and the face contact edge can be analyzed to identify the sealing problem. The edge gap detection method can use an edge detection algorithm or a threshold segmentation technique in image processing to further generate mask edge gap detection data. On this basis, the compression detection of the mask fitting contour analyzes the pressure of the mask and the facial contour in the deformation data, calculates the compression area using a mechanical analysis method (such as contact force analysis or finite element analysis), and generates mask contour compression detection data. Based on these two test data, the comfort evaluation data can be obtained by constructing a mathematical model, combining the comprehensive evaluation of the gap size and the pressure force, and obtaining the user's wearing comfort score. The respiratory airflow change data mainly involves the generation and stability evaluation of the airflow path. The generation of the airflow path is achieved through fluid dynamics simulation (CFD), and the path of the respiratory airflow flow is constructed according to the change of the airflow inside the mask. These paths can not only reflect the airflow distribution in the mask, but also help evaluate the efficiency of airflow flow. The respiratory vortex detection analyzes the kinetic energy and pressure distribution of the airflow, uses turbulence detection algorithms (such as the Reynolds stress model or vortex analysis method) to identify the vortex area in the airflow, and generates mask respiratory vortex detection data. On this basis, the stability of the airflow path is evaluated based on the vortex data, and the mask respiratory airflow evaluation data is generated by combining the speed, direction and stability indicators of the airflow. The processing of pressure distribution data is intended to ensure that the mask can evenly distribute pressure when worn to avoid local excessive compression or discomfort. Pressure uniformity analysis performs statistical and distribution analysis on the pressure data of different areas inside the mask, and uses data fitting or cluster analysis algorithms to determine the uniformity of pressure distribution. The generated mask pressure uniformity data can provide a quantitative indicator of the pressure distribution state. On this basis, the preset pressure thresholds are used for comfort evaluation, and the comfort score of the mask wearing is calculated based on these thresholds and combined with the uniformity data. The setting of the pressure threshold is based on clinical research or ergonomic data to ensure that the mask can provide reasonable comfort when worn. The mask comfort assessment data, respiratory airflow assessment data and pressure uniformity data are comprehensively analyzed to generate dynamic multidimensional assessment data. The generation of multidimensional assessment data relies on data fusion algorithms, such as principal component analysis (PCA) or multivariate regression analysis, to integrate each independent assessment dimension into a comprehensive score that can fully reflect the performance of the mask under different wearing conditions.

[0042] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: Acquire real-time user facial scanning data; Step S32: Supplementing the user personalized portrait model with three-dimensional personalized model data based on the real-time user facial scanning data to generate three-dimensional personalized user facial data; Step S33: construct a three-dimensional breathing mask personalized model based on the personalized user facial data and the user personalized portrait model to generate a personalized three-dimensional breathing mask model.

[0043] In the embodiment of the present invention, a modern three-dimensional scanner or a depth camera can be used to collect the geometric feature data of the user's face in real time and generate a fine three-dimensional facial model. These facial data include facial contour, skin color, bone structure and facial detail information, which provide a basis for subsequent personalized modeling. In this process, facial data acquisition adopts laser scanning, structured light scanning or stereo vision technology, which can efficiently and accurately capture the three-dimensional form of the user's face and form point cloud data containing the detailed shape and size of each facial area. The personalized portrait model already contains the user's basic physiological information, such as age, gender, and facial features, but these data are often more abstract and general. By fusing the real-time facial scanning data with the personalized portrait data, the user's facial geometric feature data can be accurately supplemented to the personalized portrait model through data docking algorithms (such as feature matching, point cloud registration or least squares fitting). At this time, based on the refined three-dimensional data of the user's face, the facial details that are not carefully expressed in the original portrait model can be supplemented to form more accurate personalized facial data. A three-dimensional mask model is generated by a modeling algorithm (such as finite element modeling, geometric modeling or surface fitting technology). During this process, by analyzing the detailed scanning data of the user's face and using spatial mapping and parametric modeling technology, the breathing mask that contacts the user's face can be accurately designed based on the user's facial features (such as the geometric information of the face shape, cheekbones, nose bridge, and chin area).

[0044] Preferably, step S33 includes the following steps: Step S331: using a data fusion algorithm to combine personalized user facial data and a personalized user portrait model to generate personalized integrated data for a respiratory mask; Step S332: Perform preliminary three-dimensional breathing mask modeling on the personalized integrated data of the breathing mask to generate a preliminary three-dimensional breathing mask model; Step S333: performing pressure distribution on the preliminary model of the three-dimensional breathing mask to generate a three-dimensional breathing mask pressure distribution model; performing finite element fit analysis based on the three-dimensional breathing mask pressure distribution model to generate a three-dimensional breathing mask fit model; performing personalized dynamic parameter adjustment on the three-dimensional breathing mask fit model based on the dynamic multi-dimensional scoring data to generate a personalized three-dimensional breathing mask model.

[0045] In an embodiment of the present invention, the personalized user facial data includes facial geometric features, bone structure, and facial expression information, while the personalized portrait model includes the user's basic physiological information and wearing requirements data. Through a data fusion algorithm (for example, a method based on weighted average, Kalman filtering, or collaborative filtering), the information of the two is integrated to generate a personalized integrated data set that fully reflects the user's facial features and requirements. The data set contains refined three-dimensional data of the user's face and personalized wearing requirements, providing sufficient data support for subsequent modeling and optimization. Computer-aided design (CAD) and parametric modeling methods are used to construct a preliminary model of a three-dimensional breathing mask that conforms to the user's facial contour and morphology. This modeling process uses the finite element method (FEM) for meshing processing, which can accurately represent the contact area, fit, and force between the mask and the user's face in three-dimensional space, laying the foundation for subsequent fit analysis. By calculating the pressure change after the respiratory airflow contacts the mask surface, a pressure distribution model of each area of ​​the mask during wearing is generated. Then, based on the pressure distribution model, a "finite element fit analysis" is performed to evaluate the fit of the mask in the contact area with the user's face. Finite element analysis can accurately simulate the deformation and stress distribution of the mask under different usage conditions (such as changes in facial expressions and breathing pressure), so as to judge the comfort and fit of the mask. Finally, based on dynamic multidimensional scoring data (for example, comfort score, breathing flow score), the mask is "personalized dynamic parameter adjustment". These dynamic scoring data are derived from real-time monitoring and analysis of the user's wearing conditions. By adjusting the parameters of the model (such as the fit of the mask, pressure distribution, and breathing flow path), a personalized three-dimensional model of the breathing mask that best suits the user is generated.

[0046] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes: Step S41: performing a comprehensive evaluation of model generation on the personalized three-dimensional model of the breathing mask to generate comprehensive evaluation data of the three-dimensional model of the breathing mask; Step S42: constructing a model report based on the comprehensive evaluation data of the breathing mask three-dimensional model, and generating a breathing mask model generation report; Step S43: using visualization technology to perform data chart visualization analysis on the respiratory mask model generation report, generating a respiratory mask visualization chart, thereby completing the three-dimensional model generation operation of the respiratory mask.

[0047] In an embodiment of the present invention, the comprehensive evaluation is based on multiple evaluation dimensions, including but not limited to comfort, adaptability, airflow patency, and material performance. In this process, the evaluation indicators are compared with the preset standards, and the evaluation data generated is comprehensively calculated using weighted average, correlation analysis, or multidimensional scaling evaluation methods. These evaluation data cover the adaptability, breathing fluency, and comfort of the mask, providing data support for subsequent report generation. Through the analysis of the comprehensive evaluation data, key indicators and decision-making basis are screened out, and this information is organized into a structured data report. The report construction process automatically integrates the evaluation results, charts, and explanatory texts with the help of data processing tools (such as Excel, Pandas library in Python) to form a systematic report file, which systematically presents the various evaluation indicators, performance analysis, and optimization suggestions of the respiratory mask model. The core technical means of this process are data aggregation, information organization, and automatic report generation technology, which ensure the integrity and accuracy of the report content. By using data visualization tools (such as Tableau, Power BI, Matplotlib), complex evaluation data is converted into easy-to-understand charts and dynamic graphics. This process not only includes basic bar charts, line charts and pie charts, but also more complex presentation methods such as 3D visualization, heat maps and airflow simulation to show the model’s behavior under different conditions, such as airflow distribution and mask pressure changes.

[0048] In this specification, a three-dimensional model generation system of a breathing mask is provided, which is used to execute the above-mentioned three-dimensional model generation method of the breathing mask, and the three-dimensional model generation system of the breathing mask includes: The data acquisition and preprocessing module is used to obtain a multi-dimensional original data set of the breathing mask; perform data preprocessing on the multi-dimensional original data set of the breathing mask to generate a multi-dimensional processed data set of the breathing mask; The data linkage and modeling module is used to perform static multidimensional data linkage on the multidimensional processing data set of the respiratory mask to generate static multidimensional linkage data; perform data set scoring on the multidimensional processing data set of the respiratory mask to generate dynamic multidimensional scoring data; perform personalized modeling based on the static multidimensional linkage data and the dynamic multidimensional scoring data to generate a user personalized portrait model; The facial data collection and personalized modeling module is used to obtain real-time user facial scanning data; based on the real-time user facial scanning data, the user personalized portrait model is supplemented with three-dimensional personalized model data to generate a personalized three-dimensional model of the breathing mask; The report generation and model output module is used to construct a model report based on the personalized three-dimensional model of the breathing mask, generate a breathing mask model generation report, and thus complete the three-dimensional model generation operation of the breathing mask.

[0049] The present invention also provides a computer-readable storage medium storing a computer program, which implements the above-mentioned method for generating a three-dimensional model of a breathing mask when executed.

[0050] The beneficial effect of the present invention is that by obtaining a multidimensional raw data set of a respiratory mask and performing data preprocessing on it, the raw data can be effectively cleaned and standardized, thereby improving the quality and reliability of the data and laying a solid foundation for subsequent modeling and analysis. The multidimensional processed data set after data preprocessing provides a unified and structured basis for further static linkage and dynamic scoring analysis, ensuring the consistency and operability of the data in the subsequent process. In the static multidimensional data linkage stage, by performing linkage analysis on different dimensions of the data, the relationship between various design elements can be revealed, providing a theoretical basis for the design optimization of the respiratory mask. In addition, the generation of dynamic scoring data enables the mask design to meet user needs more accurately by evaluating the fitness and performance of each design dimension in real time. The personalized modeling stage combines static and dynamic data to tailor a personalized mask model for each user, thereby achieving more efficient matching and better wearing comfort. By obtaining real-time user facial scanning data and combining the user's personalized portrait model for three-dimensional supplementation, the accurate matching of the mask can be achieved in details, further improving the wearing comfort and sealing. Finally, the generated report based on the personalized three-dimensional mask model can not only comprehensively summarize the design and effect of the mask, but also provide a scientific basis for subsequent production links, ensuring the improvement of production efficiency and product quality. Through this innovative process, the design accuracy and user satisfaction of the respiratory mask can be significantly improved, thereby providing users with a customized and personalized wearing experience. Therefore, the present invention solves the problems of lack of personalization and insufficient adaptability in the design of traditional respiratory masks by combining the static linkage and dynamic scoring of multi-dimensional data, improves the accuracy and comfort of the mask design, and significantly improves the user experience and product performance.

[0051] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points of view, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the same elements of the application documents are included in the present invention.

[0052] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for generating a three-dimensional model of a breathing mask, characterized in that: The following steps are involved: Step S1: obtaining a multidimensional original data set of a respiratory mask; performing data preprocessing on the multidimensional original data set of the respiratory mask to generate a multidimensional processed data set of the respiratory mask; Step S2: performing static multidimensional data linkage on the multidimensional processed data set of the breathing mask to generate static multidimensional linkage data; performing data set scoring on the multidimensional processed data set of the breathing mask to generate dynamic multidimensional scoring data; Personalized modeling is performed based on static multi-dimensional linkage data and dynamic multi-dimensional scoring data to generate a user personalized portrait model; Step S3: acquiring real-time user facial scanning data; supplementing the user personalized portrait model with three-dimensional personalized model data based on the real-time user facial scanning data to generate a personalized three-dimensional model of the breathing mask; Step S4: construct a model report based on the personalized three-dimensional model of the breathing mask, generate a breathing mask model generation report, and thus complete the three-dimensional model generation operation of the breathing mask.

2. The method for generating a three-dimensional model of a breathing mask according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire a multi-dimensional original data set of a respiratory mask; Step S12: performing data redundancy reduction processing on the multidimensional original data set of the breathing mask to generate a multidimensional redundancy reduced data set of the breathing mask; performing data set calibration on the multidimensional redundancy reduced data set of the breathing mask to generate a multidimensional calibration data set of the breathing mask; Step S13: performing data set standardization processing on the respiratory mask multidimensional calibration data set to generate a respiratory mask multidimensional processing data set, wherein the respiratory mask multidimensional processing data set includes a static multidimensional processing data set and a dynamic multidimensional processing data set.

3. The method for generating a three-dimensional model of a breathing mask according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing static multi-dimensional data linkage on the static multi-dimensional processed data set to generate static multi-dimensional linkage data, wherein the respiratory mask multi-dimensional processed data set includes facial geometric feature data, bone structure data and fit data; Step S22: performing a data set evaluation on the dynamic multi-dimensional processing data set to generate dynamic multi-dimensional evaluation data, wherein the dynamic multi-dimensional processing data set includes mask deformation data, respiratory airflow change data and pressure distribution data; Step S23: Perform finite element model set analysis based on static multi-dimensional linkage data to generate a user wearing demand portrait model; dynamically adjust the wearing scenario of the user wearing demand portrait model according to the dynamic multi-dimensional scoring data to generate a user personalized portrait model.

4. The method for generating a three-dimensional model of a breathing mask according to claim 3, characterized in that: Step S21 includes the following steps: Step S211: docking the facial geometry feature data and the bone structure data in a coordinate system space to generate facial geometry-bone structure space coordinate data; Step S212: calibrate the key bone positions of the facial geometry-bone structure spatial coordinate data to generate facial geometry-bone structure calibration data; perform contour area division based on the facial geometry-bone structure calibration data to generate facial geometry-bone region data; perform feature deviation search processing on the facial geometry-bone region data to generate facial geometry-bone region feature deviation data; Step S213: performing point cloud distance evaluation matching on the facial geometry feature data and the bone structure data based on the facial geometry-bone area feature deviation data to generate facial geometry-bone point cloud matching data; performing fit quantization processing on the facial geometry-bone point cloud matching data and the fit data to generate facial fit quantization data; Step S214: integrating the facial geometry-bone structure spatial coordinate data, the facial geometry-bone region feature deviation data and the facial fit quantification data into a multidimensional data set to generate static multidimensional linkage data.

5. The method for generating a three-dimensional model of a breathing mask according to claim 3, characterized in that: Step S22 includes the following steps: Step S221: performing mask fitting edge gap detection on the mask deformation data to generate mask edge gap detection data; performing mask fitting contour compression detection on the mask deformation data to generate mask contour compression detection data; performing mask fitting comfort evaluation based on the mask edge gap detection data and the mask contour compression detection data to generate mask comfort evaluation data; Step S222: Generate a gas flow path for the respiratory airflow change data to generate a mask respiratory gas flow path; perform resistance eddy current detection on the respiratory airflow change data to generate mask respiratory eddy current detection data; perform airflow stability evaluation on the mask respiratory gas flow path based on the mask respiratory eddy current detection data to generate mask respiratory airflow evaluation data; Step S223: performing uniformity analysis on the pressure distribution data to generate mask pressure uniformity data; performing comfort evaluation on the mask pressure uniformity data using a preset pressure threshold to generate mask comfort evaluation data; Step S224: Perform personalized and overall evaluation on the mask comfort evaluation data, the mask breathing airflow evaluation data, and the mask comfort evaluation data to generate dynamic multi-dimensional evaluation data.

6. The method for generating a three-dimensional model of a breathing mask according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Acquire real-time user facial scanning data; Step S32: Supplementing the user personalized portrait model with three-dimensional personalized model data based on the real-time user facial scanning data to generate three-dimensional personalized user facial data; Step S33: construct a three-dimensional breathing mask personalized model based on the personalized user facial data and the user personalized portrait model to generate a personalized three-dimensional breathing mask model.

7. The method for generating a three-dimensional model of a breathing mask according to claim 6, characterized in that: Step S33 includes the following steps: Step S331: using a data fusion algorithm to combine personalized user facial data and a personalized user portrait model to generate personalized integrated data for a respiratory mask; Step S332: Perform preliminary three-dimensional breathing mask modeling on the personalized integrated data of the breathing mask to generate a preliminary three-dimensional breathing mask model; Step S333: performing pressure distribution on the preliminary model of the three-dimensional breathing mask to generate a three-dimensional breathing mask pressure distribution model; performing finite element fit analysis based on the three-dimensional breathing mask pressure distribution model to generate a three-dimensional breathing mask fit model; performing personalized dynamic parameter adjustment on the three-dimensional breathing mask fit model based on the dynamic multi-dimensional scoring data to generate a personalized three-dimensional breathing mask model.

8. The method for generating a three-dimensional model of a breathing mask according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing a comprehensive evaluation of model generation on the personalized three-dimensional model of the breathing mask to generate comprehensive evaluation data of the three-dimensional model of the breathing mask; Step S42: constructing a model report based on the comprehensive evaluation data of the breathing mask three-dimensional model, and generating a breathing mask model generation report; Step S43: using visualization technology to perform data chart visualization analysis on the respiratory mask model generation report, generating a respiratory mask visualization chart, thereby completing the three-dimensional model generation operation of the respiratory mask.

9. A three-dimensional model generation system for a breathing mask, characterized in that: For executing the method for generating a three-dimensional model of a breathing mask as claimed in claim 1, the three-dimensional model generating system of the breathing mask comprises: The data acquisition and preprocessing module is used to obtain a multi-dimensional original data set of the breathing mask; perform data preprocessing on the multi-dimensional original data set of the breathing mask to generate a multi-dimensional processed data set of the breathing mask; The data linkage and modeling module is used to perform static multidimensional data linkage on the multidimensional processing data set of the respiratory mask to generate static multidimensional linkage data; perform data set scoring on the multidimensional processing data set of the respiratory mask to generate dynamic multidimensional scoring data; perform personalized modeling based on the static multidimensional linkage data and the dynamic multidimensional scoring data to generate a user personalized portrait model; The facial data collection and personalized modeling module is used to obtain real-time user facial scanning data; based on the real-time user facial scanning data, the user personalized portrait model is supplemented with three-dimensional personalized model data to generate a personalized three-dimensional model of the breathing mask; The report generation and model output module is used to construct a model report based on the personalized three-dimensional model of the breathing mask, generate a breathing mask model generation report, and thus complete the three-dimensional model generation operation of the breathing mask.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the method for generating a three-dimensional model of a respiratory mask according to any one of claims 1 to 8 is implemented.

Images