An additive manufacturing part screening analysis method and system for orthopedic infections

Abstract

The application provides a kind of additive manufacturing piece screening analysis method and system for orthopedic infection, it is related to additive manufacturing defect screening technical field.The method includes collecting object manufacturing piece historical screening data, carries out screening clustering analysis for object type, forms object type screening clustering data;According to object type screening clustering data, screening index extraction is carried out for object type, and object type screening index data is formed;Target manufacturing piece manufacturing result data is obtained, and screening analysis is carried out in combination with object type screening index data, and target object screening result data is formed.The method carries out reasonable quality control to the supplied manufacturing piece, effectively ensures that the manufacturing piece provided to patient has good quality, avoids the case that manufacturing piece occurs orthopedic infection in a short time after being implanted into human body.

Description

Technical Field

[0001] This invention relates to the field of additive manufacturing defect screening technology, and more specifically, to a screening and analysis method and system for additive manufacturing parts targeting orthopedic infections. Background Technology

[0002] With social development and advancements in science and technology, the manufacturing methods of medical devices have undergone revolutionary changes. Additive manufacturing is increasingly being used to produce implantable devices in orthopedics, meeting growing demand and improving quality. However, due to existing limitations in additive manufacturing technology, implantable devices still possess certain defects, which often determine the risk of orthopedic infections within a short period of use. For individual patients, the quality of the implanted device determines the success of the surgery and whether it will cause more serious or secondary injuries.

[0003] Therefore, quality control of additively manufactured implantable devices is particularly important for medical institutions. Currently, most quality control methods focus on controlling the supply chain, prioritizing well-known or reputable suppliers. However, this approach has limited quality control capabilities and cannot achieve accurate quality management and assurance for each implantable device.

[0004] Therefore, designing a screening and analysis method and system for additive manufacturing parts for orthopedic infections, and effectively ensuring the quality of the parts supplied to patients by reasonable quality control, thereby avoiding orthopedic infections occurring shortly after implantation, is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of this invention is to provide a method for screening and analyzing additively manufactured parts (ADMs) for orthopedic infections. This method involves clustering ADMs already implanted in patients based on part type to group usage data for the same type. Then, based on this clustered data, the method extracts and filters part types to form characteristic indicators that fully reflect the rapid occurrence of orthopedic infections due to part defects. This allows for reasonable quality screening when providing similar parts to patients, ensuring good implantation results and preventing rapid orthopedic infections. Compared to defect control based on the additive manufacturing technology itself, this method provides another dimension of quality assurance for implanted ADMs through reasonable quality screening and control, effectively improving the usage effect of the parts. Furthermore, even with the same supplier, it improves the quality of products supplied to medical institutions, making it an effective pre-sales quality control measure.

[0006] The present invention also aims to provide a screening and analysis system for additively manufactured parts targeting orthopedic infections. This system acquires data related to orthopedic infections in implanted parts through a data acquisition unit, and uses a cluster analysis unit to cluster data by part type. Based on this, an indicator extraction unit uses the clustered data to establish a correlation between defect characteristic parameters of the parts and the duration of orthopedic infections. Finally, a screening analysis unit, combined with this correlation, monitors the quality of products provided by suppliers, thereby ensuring the quality of products supplied by medical institutions. The different functional units are interconnected, forming a system for quality control of manufactured parts, which is a crucial material basis for achieving quality control of manufactured parts.

[0007] In a first aspect, the present invention provides a method for screening and analyzing additively manufactured parts for orthopedic infections, comprising: collecting historical screening data of target manufactured parts, performing screening cluster analysis based on target type to form target type screening cluster data; extracting screening indicators based on target type according to the target type screening cluster data to form target type screening indicator data; obtaining manufacturing result data of target manufactured parts, and performing screening analysis in conjunction with the target type screening indicator data to form target target screening result data.

[0008] In this invention, the method clusters the usage data of additively manufactured parts already implanted in patients based on part type. Then, based on the clustered data, it filters and extracts characteristic indicators that fully reflect the potential for rapid orthopedic infections due to part defects. This allows for reasonable quality screening when providing similar parts to patients, ensuring good implantation results and preventing rapid orthopedic infections. Compared to defect control based on additive manufacturing technology itself, this method provides a new dimension of quality assurance for implanted additively manufactured parts through reasonable quality screening and control, effectively improving the performance of the parts. Furthermore, even with the same supplier, it improves the quality of products supplied to medical institutions, making it an effective pre-sales quality control measure.

[0009] One possible implementation involves collecting historical screening data of manufactured objects and performing effect cluster analysis based on object type to form object type screening cluster data. This includes: extracting shape information of different manufactured objects from the historical screening data to form object manufacturing object shape information; performing analogical cluster analysis based on the object manufacturing object shape information on different manufactured objects in the historical screening data to form object manufacturing object cluster data corresponding to different object manufacturing object types; and extracting usage result data from the historical screening data of different object manufacturing objects to form corresponding object type screening cluster data.

[0010] In this invention, the cluster analysis of the usage results of the manufactured parts mainly considers two aspects. Firstly, the manufactured parts in the cluster should have a clear distinction at the implantation location; that is, manufactured parts at different implantation locations are of different types. After all, for human bones, different locations have different shapes and functions, thus the corresponding manufactured parts implanted also have significant differences. This difference affects the distribution of defects in the manufactured parts during production, and consequently affects the probability of orthopedic infections due to defects after implantation. Secondly, even manufactured parts implanted at the same location can differ due to different patient conditions. This difference manifests in customized treatment for different patients, and customized treatment also leads to different defect distributions in the manufactured parts, which also needs to be considered during clustering. This application completes the clustering process by using the shape information of the implanted manufactured parts as a reference for shape-based comparative clustering. Shape features can fully reflect the differences in manufactured parts at different locations and the differences in the same location due to customization, effectively ensuring the accuracy and rationality of the clustering.

[0011] As one possible implementation, analogical clustering analysis based on the shape information of different object manufacturing parts is performed on different object manufacturing parts in the historical screening data of object manufacturing parts to form object manufacturing part cluster data corresponding to different object manufacturing part types. This includes: extracting the shape information of one object manufacturing part as the basic shape information for clustering, and scaling and comparing it with the shape information of other object manufacturing parts one by one; if the shape of the object manufacturing part corresponding to the basic shape information of the clustering is completely superimposed on the shape of the object manufacturing part being compared after scaling, then the object manufacturing part being compared and... The extracted object manufacturing parts are determined to be of the same type. If the shape of the object manufacturing part corresponding to the basic shape information of the cluster does not completely overlap with the shape of the object manufacturing part being compared after scaling, but only a single size adjustment exists, then the object manufacturing part being compared and the extracted object manufacturing part are determined to be of the same type. After completing the comparative clustering based on the basic shape information, the extraction of the basic shape information of the cluster and the corresponding comparative clustering are repeated for the remaining different object manufacturing parts until the cluster analysis of all object manufacturing parts is completed. All object manufacturing parts clustered by different basic shape information are determined as the corresponding object manufacturing part cluster data.

[0012] In this invention, comparative clustering based on the shape information of manufactured parts mainly uses a scaling comparison method to determine whether there are essential differences in the shape of different manufactured parts. These essential differences primarily involve changes in shape structure. Proportional scaling changes and single dimensional changes, such as increasing or decreasing the dimension of a structure along a straight line, do not substantially affect the defect distribution of the manufactured parts. It can be understood that a linear increase or decrease in dimension simply increases production material and is unlikely to produce a substantial change in the distribution of defects. For example, for a cylindrical part that is inherently straight, simply increasing or decreasing the axial length without changing the diameter, or simply increasing the diameter without changing the axial length, will not change the defect distribution characteristics and will not fundamentally alter its impact on the probability of orthopedic infections. However, if the corner radius of a manufactured part changes, the shape of the part connected to the corner will increase or decrease non-linearly. This change essentially alters the shape structure and will affect the defect distribution characteristics. This comparison method allows for rapid clustering while effectively ensuring that the manufactured parts in the cluster have essentially the same defect distribution.

[0013] One possible implementation involves filtering and clustering data based on object type, extracting usage features specific to each object type, and forming object type filtering index data. This includes: dividing different object components within the different object type filtering clusters into regions based on shape features to form object shape segmentation data; determining the usage infection duration and infection occurrence area from implantation to orthopedic infection for different object components within the different object type filtering clusters; grouping usage result data for different object components with the same infection occurrence area within the different object type filtering clusters to form different object type regional infection data groups; extracting usage features based on the usage infection duration of different object components within the different object type regional infection data groups within the different object type filtering clusters to form corresponding object type infection group index data; and aggregating the different object type infection group index data from the different object type filtering clusters to form corresponding object type filtering index data.

[0014] In this invention, the extraction of usage features from clustered data primarily focuses on the correlation between defects in the manufactured parts themselves and the effective usage time of the manufactured parts. It is understood that after implantation, the manufactured parts may develop orthopedic infections at specific points in time due to environmental factors and inherent defects. Because the environmental factors involved in the use of the manufactured parts vary significantly depending on the patient's physical condition and activity level, the impact on orthopedic infections can differ, making reasonable correlation analysis difficult. However, this impact is generally controllable and limited. Therefore, although this application only considers the correlation between the defects in the manufactured parts themselves and the occurrence of orthopedic infections, the influence of environmental factors can be reasonably analyzed and processed during the analysis to reduce its impact on the correlation analysis. Of course, even within the same clustered data, different regions of the manufactured parts may exhibit different defect conditions, resulting in different regions initially causing orthopedic infections. If the analysis is performed directly without considering the location region, the extracted feature information will not be representative. After all, even with the same additive manufacturing parameters, defects in bending and non-bending areas differ, leading to varying probabilities of orthopedic infections. Therefore, before analysis, it's necessary to classify based on the location of infection to ensure the extracted feature data is accurate and reasonably representative.

[0015] One possible implementation involves filtering different object manufacturing parts from clustered data of different object types, performing shape feature-based region division, and forming object shape division data. This includes: for different object manufacturing parts in the object type-filtered clustered data, marking the shape dimensions and boundary points according to the corresponding object manufacturing part shape information, and determining all shape dimension boundary points and shape dimension lines; for different object manufacturing parts, connecting all shape dimension boundary points in pairs to form different boundary lines; for different object manufacturing parts, splitting the shape body according to different boundary lines and different shape dimension lines to form different shape body regions; and for different object manufacturing parts, mapping the same regions of different object manufacturing parts according to the dimension lines and boundary points involved in the different shape body regions, and determining the same shape body regions on different object manufacturing parts.

[0016] In this invention, the part is divided into regions to ensure that the impact of defects on orthopedic infections varies across different shaped regions during feature extraction. For a manufactured part, if the shape is simple and regular, the distribution and characteristics of defects are generally consistent, such as in rectangles, cylinders, and spheres. However, if the shape is complex, defects will exhibit different distributions and characteristic variations in different regions. These different regions can be visually reflected in the external dimensions, such as regions with bending radii. The external dimensions are based on the two endpoints of the bending edge's arc, encompassing the entire region corresponding to the arc. However, simply using external dimensions as a reference would lead to ambiguity in the internal division of the part. Therefore, lines are formed within the shape by connecting the boundary points of the shape dimensions. The entire shape is then divided into different sub-shapes using planes passing through these lines and the shape dimension lines. These sub-shapes map the regions corresponding to the shape dimensions and define the boundaries of the internal regions of the shape, ensuring reasonable region division and matching of the corresponding feature analysis positions. In addition, considering that although different objects under clustered data may have similar shapes and sizes, they may not be completely identical due to variations in a single dimension, the differentiation of the same region on different objects can be achieved by numbering and labeling dimension lines, boundary lines, and boundary points. As long as the numbering of all boundary lines and boundary points of the sub-shapes on different objects is matched one by one, it can be determined that the sub-shapes on two different objects belong to the same region.

[0017] As one possible implementation, different object type regions within clustered data are selected for infection. Usage features are extracted based on the usage infection duration of different manufactured parts within each data group, forming corresponding object type infection group indicator data. This includes: selecting different object type regions within clustered data for different object types and obtaining defect feature parameters corresponding to different manufactured parts. Where m represents the number of different object manufacturing parts in the object type region infection data group, and n represents the number of different defect feature parameters; for different object manufacturing parts in the object type region infection data group, according to the corresponding different defect feature parameters and duration of infection Correlation analysis of infection impact was conducted to determine the correlation screening formula for infection data groups of different object types in different regions. .

[0018] In this invention, the extraction of feature data is mainly used to obtain the correlation between the parameter information of the defect features in the characterizing area and the duration of orthopedic infection in that area of ​​the manufactured part. Only by determining this correlation can the quality screening of the subsequently supplied manufactured parts be achieved, and the quality of the products can be controlled from the process of product use quality, thereby improving the quality of service. To establish correlations, the first step is to extract characteristic parameters of defects from different manufactured parts. These parameters primarily quantify the characteristics of defects, including but not limited to the difference between theoretical and actual density, gap ratio, shrinkage rate, roughness, and geometric tolerances. The difference between theoretical and actual density quantifies the defect space generated during actual production within an average volume. The gap ratio characterizes the spatial proportion of the defect space, the shrinkage rate reflects the degree of influence of the defect space on the overall volume, roughness reflects the average size of the defect space, and geometric tolerances also reflect the size of the defect space from another dimensional dimension. These characteristic parameters can be obtained non-destructively or non-invasively, and most of them are parameters that must be inspected during the manufacturing process. Medical institutions can quickly obtain these parameters for correlation analysis based on the production inspection data after receiving the supplied products. After obtaining these characteristic parameters of constant defects, a correlation formula between the defect and the duration of orthopedic infection can be established and analyzed. Ultimately, this allows for the formation of information on the duration of orthopedic infection based on defect characteristic parameters, providing important reference information for medical institutions to conduct quality supervision of manufactured parts supplied by suppliers.

[0019] As one possible implementation, different manufactured objects in the object type region infection data group are processed according to their corresponding different defect characteristic parameters. and duration of infection Correlation analysis of infection impact was conducted to determine the correlation screening formula for infection data groups of different object types in different regions. This includes: randomly dividing the different object manufacturing parts in the object type region infection data group into an in-group parsing data part and an in-group adjustment data part, wherein the number of object manufacturing parts in the in-group parsing data part is not less than the number of object type region infection correlation screening parts. The total number of constants to be parsed in the data; for the parsed data portion within the group, arbitrarily extract different object manufacturing parts with the same number as the total number of constants to be parsed, and based on the different defect characteristic parameters of the object manufacturing parts. and duration of infection Screening for infection correlation between object type and region The constant to be parsed is parsed; an error tolerance limit is set. Screening for infection correlation of parsed object type regions Based on the group adjustment data section, the following adjustment analysis is performed: arbitrarily select different defect characteristic parameters corresponding to the manufactured parts in the group adjustment data section. Screening based on the correlation between the infection type and the region of the object Determine the corresponding theoretical infection duration If the following conditions are met on any three consecutive extracted object manufacturing parts: Then, the screening method for the correlation between the infection of the object type region is... If the desired shape is not met in any of the three extracted consecutive object manufacturing parts, then... Then, based on three randomly extracted object manufacturing parts, a screening method is used to determine the correlation between the infection of the object type region. Adjustments are made, and the non-repetitive arbitrary extraction and verification analysis is repeated until all three arbitrarily extracted manufactured objects meet the requirements. Then, the screening method for the correlation between the infection of the object type region is... To finalize the design.

[0020] In this invention, the screening formula required for correlation analysis is achieved by substituting the characteristic parameters and infection duration of different object data in the data set to complete the analysis of the constant term in the formula. Of course, each analysis only needs to extract data of the same number of object manufacturing parts as the total number of constant terms. Therefore, the analyzed screening formula is entirely determined by the data of these arbitrarily extracted manufacturing parts. However, such analysis still has a certain degree of individuality, meaning it may only be applicable to the extracted object manufacturing parts. To improve the generality of the screening formula, this application classifies the object manufacturing part data within the group, using one category for analysis and another for adjusting and verifying the accuracy of the analyzed screening formula. The error tolerance limit can be set according to the actual situation, while the verification requirement is to ensure that the prediction accuracy for three consecutive object manufacturing parts extracted in the verification data reaches the limit value. This randomness in data extraction greatly improves the applicability of the adjusted screening formula. The number of consecutively satisfied conditions for verification can also be determined according to the actual situation.

[0021] As one possible implementation, for the parsed data within the group, arbitrarily extract different object manufacturing parts with the same number as the total number of constants to be parsed, including: based on the infection duration used in the parsed data within the group. The maximum and minimum values ​​were used to determine the maximum infection time span within the group. ; Determine any point in time within the time span to ensure that the maximum infection time span within the group begins from that determined point in time. Continuous time length obtained within satisfy: ,in, This indicates the minimum allowed duration percentage; within the obtained continuous time length, using two time endpoints as a benchmark, the total number including both time endpoints is determined to be equal to the object type region infection correlation screening formula. The time point when the total number of constants to be parsed is recorded and marked as the extraction time point; the infection duration is extracted from the parsed data within the group. The object manufacturing part closest to the corresponding extraction time point; all extracted object manufacturing parts are identified as the filtering criteria for the infection correlation of the parsed object type region. Object manufacturing parts.

[0022] In this invention, the object manufacturing parts in the group-interpreted data section are arbitrarily extracted. To ensure that the extracted manufacturing part data can maximize the generality of the filtering method and reduce the workload of subsequent adjustments using the group-interpreted data section, the extracted object manufacturing parts need to have data with a certain time span. This reduces the likelihood that the analytical filtering method is only applicable to a specific usage infection period. The minimum allowed time span percentage can be set according to the actual situation. The determined extraction time points can be evenly distributed across the determined time span or randomly determined, as long as they are representative of the time span.

[0023] One possible implementation involves acquiring manufacturing result data of the target manufactured part, combining it with object type screening index data for monitoring and analysis, and forming target object screening result data. This includes: extracting the corresponding shape information of the target manufactured part based on its manufacturing result data; scaling and comparing the basic shape information of clusters in different object manufactured part clustering data based on the target manufactured part shape information to determine the type of the target manufactured part, and labeling the object type screening index data of the corresponding type of object type screening clustering data as target comparison feature data; extracting different target shape regions of the target manufactured part and different target defect feature parameters corresponding to the target shape regions based on the manufacturing result data of the target manufactured part; and for different target shape regions of the target manufactured part, screening based on the correlation between the object type regions of the same shape regions in the target comparison feature data. Based on the different target defect characteristic parameters of the target shape area, the target predicted usage time corresponding to the target shape area is determined; according to the target predicted usage time corresponding to different target shape areas of the target manufactured part, the shortest target predicted usage time is determined as the target part's predicted usage time; the target part's predicted usage time is analyzed, and if the target part's predicted usage time is not greater than the regulatory screening time threshold, the target manufactured part is marked as a regulatory non-conforming part, otherwise the target manufactured part is marked as a regulatory conforming part.

[0024] In the present invention, the quality supervision of the target manufactured part is to predict the usage duration of different shaped body regions by obtaining the usage feature data of object manufactured parts of the same type as the target manufactured part, and then take the shortest usage duration as the service life duration of the target manufactured part, and compare it with the duration requirement set by the quality supervision. Only when it is not less than this requirement can it be shown that the quality of the target manufactured part is qualified. In this way, although the manufacturing technology of the manufactured part itself is not improved to eliminate defects, medical institutions can achieve the screening of high-quality products through reasonable quality supervision of the products supplied by suppliers, avoiding rapid orthopedic infections caused by product defects. The supervision screening duration threshold can be set according to the actual situation.

[0025] In a second aspect, the present invention provides an additive manufacturing part screening and analysis system for orthopedic infections, including: a data acquisition unit for collecting historical screening data of object manufactured parts and manufacturing result data of the target manufactured part; a clustering analysis unit for performing effect clustering analysis on the historical screening data of object manufactured parts collected by the data acquisition unit for the object type to form object type screening clustering data; an index extraction unit for extracting usage features for the object type from the object type screening clustering data formed by the clustering analysis unit to form object type screening index data; a screening and analysis unit for monitoring and analyzing the manufacturing result data of the target manufactured part obtained by the data acquisition unit in combination with the object type screening index data formed by the index extraction unit to form target object screening result data.

[0026] In the present invention, the system obtains data information related to orthopedic infections of the manufactured parts implanted in patients through the data acquisition unit, and uses the clustering analysis unit to complete data clustering for the manufactured part type. On this basis, the index extraction unit establishes a correlation relationship between the defect feature parameters of the manufactured part and the orthopedic infection duration using the clustering data, and then uses the screening and analysis unit to combine the correlation relationship to achieve the quality supervision of the products provided by the supplier, achieving the effect of ensuring the quality of the products provided by the medical structure. Different functional units are interconnected to form a system for controlling the quality of manufactured part products, which is an important material basis for realizing the quality control of manufactured parts.

[0027] The beneficial effects of an additive manufacturing part screening and analysis method and system for orthopedic infections provided by the present invention are as follows: This method clusters the usage data of additively manufactured parts already implanted in patients based on part type, thus clustering the usage data of the same type of part. Then, based on the clustered data, it filters and extracts characteristic indicators that fully reflect the potential for rapid orthopedic infections due to part defects. This allows for reasonable quality screening when providing similar parts to patients, ensuring good implantation results and preventing rapid orthopedic infections. Compared to defect control based on additive manufacturing technology itself, this approach provides a more comprehensive quality assurance for implanted additively manufactured parts through reasonable quality screening and control, effectively improving the usage effect of the parts. Furthermore, even with the same supplier, it enhances the quality of products supplied to medical institutions, making it an effective pre-sales quality control method.

[0028] This system acquires data related to orthopedic infections of implanted manufactured parts through a data acquisition unit, and uses a cluster analysis unit to cluster data by manufactured part type. Based on this, an indicator extraction unit uses the clustered data to establish the correlation between manufactured part defect characteristic parameters and the duration of orthopedic infections. Finally, a screening analysis unit, combined with the correlation, monitors the quality of products provided by suppliers, thereby ensuring the quality of products supplied by medical institutions. These interconnected functional units form a system for quality control of manufactured parts, providing a crucial material foundation for effective quality management. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 A flowchart illustrating the steps of an additive manufacturing part screening and analysis method for orthopedic infections provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of an additive manufacturing part screening and analysis system for orthopedic infections provided in an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the present invention will now be described with reference to the accompanying drawings in the embodiments of the present invention.

[0032] With social development and advancements in science and technology, the manufacturing methods of medical devices have undergone revolutionary changes. Additive manufacturing is increasingly being used to produce implantable devices in orthopedics, meeting growing demand and improving quality. However, due to existing limitations in additive manufacturing technology, implantable devices still possess certain defects, which often determine the risk of orthopedic infections within a short period of use. For individual patients, the quality of the implanted device determines the success of the surgery and whether it will cause more serious or secondary injuries.

[0033] Therefore, quality control of additively manufactured implantable devices is particularly important for medical institutions. Currently, most quality control methods focus on controlling the supply chain, prioritizing well-known or reputable suppliers. However, this approach has limited quality control capabilities and cannot achieve accurate quality management and assurance for each implantable device.

[0034] refer to Figures 1-2 This invention provides a method for screening and analyzing additively manufactured parts (ADMs) for orthopedic infections. This method clusters the usage data of ADMs already implanted in patients based on part type, and then filters and extracts characteristic indicators that fully reflect the rapid occurrence of orthopedic infections due to part defects. This allows for reasonable quality screening when providing similar ADMs to patients, ensuring good implantation results and preventing rapid orthopedic infections. Compared to defect control based on additive manufacturing technology itself, this method provides another dimension of quality assurance for implanted ADMs through reasonable quality screening and control, effectively improving the usage effect of the parts. Furthermore, even with the same supplier, it improves the quality of products supplied to medical institutions, serving as an effective pre-sales quality control measure.

[0035] A screening and analysis method for additively manufactured parts targeting orthopedic infections specifically includes the following steps: S1: Collect historical screening data of manufactured objects, perform screening cluster analysis based on object type, and form object type screening cluster data.

[0036] Collect historical screening data of manufactured objects and perform screening cluster analysis based on object type to form object type screening cluster data. This includes: extracting shape information of different manufactured objects from the historical screening data to form object manufacturing object shape information; performing analogical cluster analysis based on the object manufacturing object shape information for different manufactured objects in the historical screening data to form object manufacturing object cluster data corresponding to different object manufacturing object types; and extracting usage result data from the historical screening data of object manufacturing objects based on the different object manufacturing object cluster data to form corresponding object type screening cluster data.

[0037] Cluster analysis of the usage results of manufactured parts mainly considers two aspects. Firstly, the manufactured parts in the cluster should have a clear distinction at the implantation location; that is, manufactured parts at different implantation locations are of different types. After all, the shape and function of different locations in the human skeleton are different, thus the corresponding manufactured parts implanted will also have significant differences. This difference affects the distribution of defects in the manufactured parts during production, and consequently affects the probability of orthopedic infections due to defects after implantation. Secondly, even manufactured parts implanted at the same location may differ due to different patient conditions. This difference reflects the customized treatment for different patients, and customized treatment will also lead to different defect distributions in the manufactured parts, which also needs to be considered during clustering. This application completes the clustering process by using the shape information of the implanted manufactured parts as a reference for shape-based comparative clustering. Shape features can fully reflect the differences between manufactured parts in different locations and the differences in the same location due to customization, effectively ensuring the accuracy and rationality of the clustering.

[0038] Analogical clustering analysis based on the shape information of different manufactured parts is performed on different manufactured parts in the historical screening data of manufactured parts, forming cluster data of manufactured parts corresponding to different manufactured part types. This includes: extracting the shape information of any one manufactured part as the basic shape information for clustering, and scaling and comparing it with the shape information of other manufactured parts one by one; if the shape of the manufactured part corresponding to the basic shape information of the clustering completely overlaps with the shape of the compared manufactured part after scaling, then the compared manufactured part and the extracted manufactured part are considered to be clustered. The components are identified as manufacturing parts of the same type. If the shape of the object manufacturing part corresponding to the cluster basic shape information does not completely overlap with the shape of the object manufacturing part being compared after scaling, but only a single size adjustment exists, then the object manufacturing part being compared and the extracted object manufacturing part are identified as manufacturing parts of the same type. After completing the comparative clustering based on the cluster basic shape information, the extraction of the cluster basic shape information and the corresponding comparative clustering are repeated for the remaining different object manufacturing parts until the cluster analysis of all object manufacturing parts is completed. All object manufacturing parts clustered by different cluster basic shape information are identified as the corresponding object manufacturing part cluster data.

[0039] Comparative clustering based on the shape information of manufactured parts primarily uses scaling comparison to determine whether there are essential differences in the shape of different manufactured parts. These essential differences mainly involve changes in shape structure. Proportional scaling changes and single dimensional changes, such as increasing or decreasing the dimension of a structure along a straight line, do not substantially affect the defect distribution of the manufactured parts. This is understandable; a linear increase or decrease in dimension simply increases production material and is unlikely to cause a substantial change in the distribution of defects. For example, for a cylindrical part that is inherently straight, simply increasing or decreasing the axial length while keeping the diameter unchanged, or simply increasing the diameter while keeping the axial length unchanged, will not change the defect distribution characteristics and will not fundamentally alter its impact on the probability of orthopedic infections. However, if the corner radius of a manufactured part changes, the shape of the part connected to the corner will increase or decrease non-linearly. This change essentially alters the shape structure and will affect the defect distribution characteristics. This comparative method allows for rapid clustering while effectively ensuring that the manufactured parts in the cluster have essentially the same defect distribution.

[0040] S2: Filter clustered data according to object type, extract filtering indicators for object type, and form object type filtering indicator data.

[0041] The data is clustered according to object type, and screening indicators are extracted for each object type to form object type screening indicator data. This includes: dividing different object components in different object type clusters into regions based on shape features to form object shape division data; determining the usage infection duration and infection occurrence area from implantation to orthopedic infection for different object components in different object type clusters; grouping the usage result data of different object components with the same infection occurrence area into different object type regional infection data groups; extracting usage features based on the usage infection duration of different object components in different object type regional infection data groups to form corresponding object type infection group indicator data; and aggregating the different object type infection group indicator data from different object type clusters to form corresponding object type screening indicator data.

[0042] The extraction of usage features from clustered data primarily focuses on the correlation between defects in the manufactured parts themselves and the effective usage time of the manufactured parts. It is understandable that, after implantation, the manufactured parts may develop orthopedic infections at specific points in time due to environmental factors and inherent defects. Because the environmental factors involved in the use of the manufactured parts vary significantly depending on the patient's physical condition and activity level, the impact on orthopedic infections can differ, making reasonable correlation analysis difficult. However, overall, this impact is controllable and limited. Therefore, although this application only considers the correlation between the defects in the manufactured parts themselves and the occurrence of orthopedic infections, the influence of environmental factors can be reasonably analyzed and processed during the analysis to reduce its impact on the correlation analysis. Of course, even within the same cluster of data, the defect conditions in different locations of manufactured parts may differ, resulting in different locations where orthopedic infections initially occur. If the analysis is performed directly without considering the location region, the extracted feature information will not be representative. After all, even with the same additive manufacturing parameters, defects in bending and non-bending areas differ, leading to varying probabilities of orthopedic infections. Therefore, before analysis, it's necessary to classify based on the location of infection to ensure the extracted feature data is accurate and reasonably representative.

[0043] Different object manufacturing parts in the clustered data of different object types are selected, and region division based on shape features is performed to form object shape division data. This includes: for different object manufacturing parts in the clustered data of object types, according to the shape information of the corresponding object manufacturing parts, the dimension lines and boundary points of the shape dimensions are marked to determine all the dimension boundary points and dimension lines; for different object manufacturing parts, all dimension boundary points are connected in pairs to form different boundary lines; for different object manufacturing parts, the shape is split according to the different boundary lines and different dimension lines to form different shape regions; for different object manufacturing parts, the same region is mapped according to the dimension lines and boundary points involved in the different shape regions to determine the same shape regions on different object manufacturing parts.

[0044] Dividing the manufactured part into regions ensures that the impact of defects on orthopedic infections varies across different shaped regions during feature extraction. For a manufactured part with a simple and regular shape, the distribution and characteristics of defects are generally consistent, such as in rectangles, cylinders, and spheres. However, for complex shapes, defects will exhibit different distributions and characteristics in different regions. These different regions are visually reflected in the external dimensions, such as regions with bending radii. The external dimensions are based on the two endpoints of the bending radius, encompassing the entire region corresponding to the radius. However, simply using external dimensions as a reference would lead to ambiguity in the internal division of the manufactured part. Therefore, connecting the boundary points of the shape dimensions creates lines within the shape, and the entire shape is divided into different sub-shapes using planes passing through these lines and shape dimension lines. These sub-shapes map the regions corresponding to the shape dimensions and define the boundaries of the internal regions of the shape, ensuring reasonable region division and matching the location of corresponding feature analyses. In addition, considering that although different objects under clustered data may have similar shapes and sizes, they may not be completely identical due to variations in a single dimension, the differentiation of the same region on different objects can be achieved by numbering and labeling dimension lines, boundary lines, and boundary points. As long as the numbering of all boundary lines and boundary points of the sub-shapes on different objects is matched one by one, it can be determined that the sub-shapes on two different objects belong to the same region.

[0045] For different object types, clustered data groups of infection regions are selected. Based on the usage infection duration of different manufactured parts within these data groups, usage features are extracted to form corresponding object type infection group index data. This includes: selecting clustered data groups of infection regions of different object types and obtaining defect feature parameters corresponding to different manufactured parts. Where m represents the number of different object manufacturing parts in the object type region infection data group, and n represents the number of different defect feature parameters; for different object manufacturing parts in the object type region infection data group, according to the corresponding different defect feature parameters and duration of infection Correlation analysis of infection impact was conducted to determine the correlation screening formula for infection data groups of different object types in different regions. .

[0046] The extraction of feature data primarily aims to obtain the correlation between parameter information representing defect features within a region and the duration of orthopedic infection in that region of the manufactured part. Only by determining this correlation can the quality screening of subsequently supplied manufactured parts be achieved, controlling product quality from the product usage process and improving service quality. For correlation analysis, the first step is to extract feature parameters related to defects on different manufactured parts. These parameters mainly quantify the characteristics of defects, including but not limited to the difference between theoretical and actual density, gap ratio, shrinkage rate, roughness, and geometric tolerances. The difference between theoretical and actual density quantifies the defect space generated during actual production at an average volume. The gap ratio characterizes the spatial proportion of the defect space, the shrinkage rate reflects the degree of influence of the defect space on the overall volume, roughness reflects the average size of the defect space, and geometric tolerances also reflect the size of the defect space from another dimensional dimension. These feature parameters can be obtained non-destructively or non-invasively, and most of these parameters are data that must be inspected when the manufactured parts leave the factory. After receiving the supplied products, medical institutions only need to quickly obtain the data based on the production inspection data for correlation analysis. After obtaining the characteristic parameters of these constant defects, a correlation formula with the duration of orthopedic infection can be established and analyzed. Ultimately, information on the duration of orthopedic infection based on defect characteristic parameters can be formed, providing important reference information for medical institutions to conduct quality supervision of manufactured parts supplied by suppliers.

[0047] For different manufactured parts in the object type region infection data group, based on the corresponding different defect characteristic parameters and duration of infection Correlation analysis of infection impact was conducted to determine the correlation screening formula for infection data groups of different object types in different regions. This includes: randomly dividing the different object manufacturing parts in the object type region infection data group into an in-group parsing data part and an in-group adjustment data part, wherein the number of object manufacturing parts in the in-group parsing data part is not less than the number of object type region infection correlation screening parts. The total number of constants to be parsed in the data; for the parsed data portion within the group, arbitrarily extract different object manufacturing parts with the same number as the total number of constants to be parsed, and based on the different defect characteristic parameters of the object manufacturing parts. and duration of infection Screening for infection correlation between object type and region The constant to be parsed is parsed; an error tolerance limit is set. Screening for infection correlation of parsed object type regions Based on the group adjustment data section, the following adjustment analysis is performed: arbitrarily select different defect characteristic parameters corresponding to the manufactured parts in the group adjustment data section. Screening based on the correlation between the infection type and the region of the object Determine the corresponding theoretical infection duration If the following conditions are met on any three consecutive extracted object manufacturing parts: Then, the screening method for the correlation between the infection of the object type region is... If the desired shape is not met in any of the three extracted consecutive object manufacturing parts, then... Then, based on three randomly extracted object manufacturing parts, a screening method is used to determine the correlation between the infection of the object type region. Adjustments are made, and the non-repetitive arbitrary extraction and verification analysis is repeated until all three arbitrarily extracted manufactured objects meet the requirements. Then, the screening method for the correlation between the infection of the object type region is... To finalize the design.

[0048] The screening formula required for correlation analysis is achieved by substituting the characteristic parameters and infection duration of different object data in the data set to analyze the constant term in the formula. Of course, each analysis only needs to extract data of the same number of object components as the total number of constant terms. Therefore, the analyzed screening formula is entirely determined by the data of these arbitrarily extracted components. However, such analysis still has a certain degree of individuality, meaning it may only be applicable to the extracted object components. To improve the generality of the screening formula, this application classifies the object component data within the group: one category is used for analysis, and the other is used to adjust and verify the accuracy of the analyzed screening formula. The allowable error limit can be set according to the actual situation, while the verification requirement is to ensure that the prediction accuracy for three consecutive extracted object components in the verification data reaches the limit. This randomness in data extraction greatly improves the applicability of the adjusted screening formula. The number of consecutively satisfied verification conditions can also be determined according to the actual situation.

[0049] For the parsed data within the group, arbitrarily extract different object manufacturing parts whose number is the same as the total number of constants to be parsed, including: based on the infection duration used in the parsed data within the group. The maximum and minimum values ​​were used to determine the maximum infection time span within the group. ; Determine any point in time within the time span to ensure that the maximum infection time span within the group begins from that determined point in time. Continuous time length obtained within satisfy: ,in, This indicates the minimum allowed duration percentage; within the obtained continuous time length, using two time endpoints as a benchmark, the total number including both time endpoints is determined to be equal to the object type region infection correlation screening formula. The time point when the total number of constants to be parsed is recorded and marked as the extraction time point; the infection duration is extracted from the parsed data within the group. The object manufacturing part closest to the corresponding extraction time point; all extracted object manufacturing parts are identified as the filtering criteria for the infection correlation of the parsed object type region. Object manufacturing parts.

[0050] Arbitrarily extract the manufactured parts from the parsed data section within the group. To ensure that the extracted manufactured part data can maximize the generality of the filtering method and reduce the workload of subsequent adjustments using the group's adjustment data section, the extracted manufactured parts need to have data spanning a certain time period. This reduces the likelihood that the parsed filtering method is only applicable to a specific usage infection period. The minimum allowed duration percentage can be set according to the actual situation. The determined extraction time points can be evenly distributed across the determined time span or randomly selected, as long as they are representative of the time span.

[0051] S3: Obtain the manufacturing result data of the target manufactured part, and perform screening analysis in combination with the object type screening index data to form the target object screening result data.

[0052] The process involves acquiring manufacturing result data for the target manufactured part, combining it with object type screening index data for filtering analysis, and forming target object screening result data. This includes: extracting the corresponding shape information of the target manufactured part based on its manufacturing result data; scaling and comparing the basic shape information of clusters in different object manufactured part clustering data based on the target manufactured part shape information to determine the type of the target manufactured part, and labeling the object type screening index data of the corresponding object type screening clustering data as target comparison feature data; extracting different target shape regions of the target manufactured part and the different target defect feature parameters corresponding to the target shape regions based on the manufacturing result data of the target manufactured part; and for different target shape regions of the target manufactured part, screening based on the correlation between the object type regions of the same shape regions in the target comparison feature data. Based on the different target defect characteristic parameters of the target shape area, the target predicted usage time corresponding to the target shape area is determined; according to the target predicted usage time corresponding to different target shape areas of the target manufactured part, the shortest target predicted usage time is determined as the target part's predicted usage time; the target part's predicted usage time is analyzed, and if the target part's predicted usage time is not greater than the regulatory screening time threshold, the target manufactured part is marked as a regulatory non-conforming part, otherwise the target manufactured part is marked as a regulatory conforming part.

[0053] The quality supervision of the target manufactured part is to predict the usage duration of different shaped body regions by obtaining the usage characteristic data of object manufactured parts of the same type as the target manufactured part, and then take the shortest usage duration as the service life duration of the target manufactured part, and compare it with the duration requirement set by the quality supervision. Only when it is not less than this requirement can it be shown that the quality of the target manufactured part is qualified. In this way, although the manufacturing technology of the manufactured part itself is not improved to eliminate defects, medical institutions can achieve the screening of high-quality products through reasonable quality supervision of the products supplied by suppliers, avoiding rapid orthopedic infections caused by product defects. The supervision screening duration threshold can be set according to the actual situation.

[0054] The present invention also provides an additive manufacturing part screening and analysis system for orthopedic infections, which includes: a data acquisition unit for collecting historical screening data of object manufactured parts and manufacturing result data of the target manufactured part; a clustering analysis unit for performing effect clustering analysis on the historical screening data of object manufactured parts collected by the data acquisition unit for object types to form object type screening clustering data; an index extraction unit for extracting usage characteristics for object types from the object type screening clustering data formed by the clustering analysis unit to form object type screening index data; a screening analysis unit for monitoring and analyzing the manufacturing result data of the target manufactured part obtained by the data acquisition unit in combination with the object type screening index data formed by the index extraction unit to form target object screening result data.

[0055] This system obtains data information related to orthopedic infections of the manufactured parts implanted in patients through the data acquisition unit, and uses the clustering analysis unit to complete data clustering for the manufactured part types. On this basis, the index extraction unit establishes a correlation relationship between the defect characteristic parameters of the manufactured parts and the orthopedic infection duration using the clustering data, and then uses the screening analysis unit to combine the correlation relationship to achieve the quality supervision of the products provided by suppliers, achieving the effect of ensuring the quality of the products provided by medical institutions. Different functional units are interconnected to form a system for controlling the quality of manufactured part products, which is an important material basis for realizing quality control of manufactured parts.

[0056] In summary, the beneficial effects of an additive manufacturing part screening and analysis method and system for orthopedic infections provided by the embodiments of the present invention are as follows: This method clusters the usage data of additively manufactured parts already implanted in patients based on part type, thus clustering the usage data of the same type of part. Then, based on the clustered data, it filters and extracts characteristic indicators that fully reflect the potential for rapid orthopedic infections due to part defects. This allows for reasonable quality screening when providing similar parts to patients, ensuring good implantation results and preventing rapid orthopedic infections. Compared to defect control based on additive manufacturing technology itself, this approach provides a more comprehensive quality assurance for implanted additively manufactured parts through reasonable quality screening and control, effectively improving the usage effect of the parts. Furthermore, even with the same supplier, it enhances the quality of products supplied to medical institutions, making it an effective pre-sales quality control method.

[0057] This system acquires data related to orthopedic infections of implanted manufactured parts through a data acquisition unit, and uses a cluster analysis unit to cluster data by manufactured part type. Based on this, an indicator extraction unit uses the clustered data to establish the correlation between manufactured part defect characteristic parameters and the duration of orthopedic infections. Finally, a screening analysis unit, combined with the correlation, monitors the quality of products provided by suppliers, thereby ensuring the quality of products supplied by medical institutions. These interconnected functional units form a system for quality control of manufactured parts, providing a crucial material foundation for effective quality management.

[0058] In the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In the specific implementation process, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. At the same time, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0059] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be repeated here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In the specific implementation process, the required indication method can be selected according to specific needs. This application embodiment does not limit the selected indication method; therefore, the indication methods involved in this application embodiment should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0060] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this application embodiment. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0061] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This application does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or communication device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0062] The “protocol” mentioned in this application embodiment may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to future communication systems. This application embodiment does not specifically limit this.

[0063] In the embodiments of this application, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0064] In the description of the embodiments of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of this application, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate that something is being used as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0065] It should be understood that the processor in the embodiments of this application can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0066] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0067] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0068] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0069] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0070] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0071] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0072] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0074] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0075] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0076] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0077] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for screening and analyzing additively manufactured parts for orthopedic infections, characterized in that, include: Collect historical screening data of manufactured parts, perform screening cluster analysis based on object type, and generate object type screening cluster data: By filtering the historical data of the manufactured objects, shape information of different manufactured objects is extracted to form the shape information of the manufactured objects; Perform analogical clustering analysis based on the shape information of the object manufacturing parts on different object manufacturing parts in the historical screening data of the object manufacturing parts to form object manufacturing part clustering data corresponding to different object manufacturing part types; Based on the clustering data of different object manufacturing parts, the usage result data in the historical screening data of the object manufacturing parts is extracted to form the corresponding object type screening clustering data. Based on the object type, cluster data is filtered, and filtering indicators for object type are extracted to form object type filtering indicator data: Different object manufacturing parts in the cluster data are filtered for different object types, and region division is performed based on shape features to form object shape division data; Different object manufacturing parts in the cluster data are filtered for different object types to determine the usage and infection duration from implantation to the occurrence of orthopedic infection and the infection location. Cluster data are filtered for different object types, and the usage result data of different object manufacturing parts with the same infection occurrence area are grouped to form different object type area infection data groups; For different object types, different object type regions are clustered in the data to filter infection data groups. Based on the usage infection duration corresponding to different object manufacturing parts in the data group, the filtering indicators are extracted to form the corresponding object type infection group indicator data. The data is used to filter and cluster different object types in the data to form corresponding object type filtering index data. Obtain the manufacturing result data of the target manufactured part, and perform filtering analysis in conjunction with the object type filtering index data to form target object filtering result data: Based on the manufacturing result data of the target manufactured part, extract the corresponding shape information of the target manufactured part; Based on the target manufactured part shape information, the cluster basic shape information in different target manufactured part clustering data is scaled and compared to determine the type of the target manufactured part, and the object type screening index data of the corresponding type of object type screening clustering data is labeled as the target comparison feature data; Based on the manufacturing result data of the target manufactured part, extract different target shape regions of the target manufactured part and different target defect feature parameters corresponding to the target shape regions; For different target shape regions of the target manufactured part, a correlation-based filtering method is used based on the object type region infection of the corresponding same shape region in the feature data. And different target defect feature parameters of the target shape region, determine the target prediction usage time corresponding to the target shape region; Based on the target predicted usage time corresponding to different target shape regions of the target manufactured part, the shortest target predicted usage time is determined as the target part usage predicted time; The predicted usage time of the target part is analyzed. If the predicted usage time of the target part is not greater than the regulatory screening time threshold, the target manufactured part is marked as a regulatory non-compliant part; otherwise, the target manufactured part is marked as a regulatory compliant part.

2. The method for screening and analyzing additively manufactured parts for orthopedic infections according to claim 1, characterized in that, The step of performing analogical clustering analysis based on the shape information of different manufactured objects in the historical screening data of the manufactured objects to form cluster data of manufactured objects corresponding to different types of manufactured objects includes: For the shape information of different manufactured objects, the shape information of one manufactured object is arbitrarily extracted as the basic shape information for clustering, and then scaled and compared with the shape information of other manufactured objects one by one. If the shape of the object manufacturing part corresponding to the clustering basic shape information completely overlaps with the shape of the object manufacturing part being compared through scaling, then the object manufacturing part being compared and the extracted object manufacturing part are determined to be manufacturing parts of the same type. If the shape of the object manufacturing part corresponding to the clustering basic shape information does not completely overlap with the shape of the object manufacturing part being compared after being scaled proportionally, but there is only a single size adjustment, then the object manufacturing part being compared and the extracted object manufacturing part are determined to be the same type of manufacturing part. After completing the comparative clustering based on the basic shape information, the extraction of basic shape information and the corresponding comparative clustering are repeated for the remaining different object manufacturing parts until the clustering analysis of all the object manufacturing parts is completed. All the object manufacturing parts clustered by different clustering basic shape information are identified as the corresponding object manufacturing part clustering data.

3. The method for screening and analyzing additively manufactured parts for orthopedic infections according to claim 2, characterized in that, The step of filtering and clustering different object manufacturing parts in the data for different object types, and performing region division based on shape features to form object shape division data includes: Different manufactured parts of the object are selected from the cluster data of the object type. Based on the shape information of the corresponding manufactured parts, the dimension lines and boundary points of the shape are marked to determine all the dimension boundary points and dimension lines. For different manufactured parts, connect all the boundary points of the external dimensions in pairs to form different boundary lines; For different manufactured objects, the shape body is divided according to different dividing lines and different outer dimension lines to form different shape body regions; For different manufactured objects, based on the dimension lines and boundary points involved in different shaped body regions, the same region mapping is performed on different manufactured objects to determine the same shaped body regions on different manufactured objects.

4. The method for screening and analyzing additively manufactured parts for orthopedic infections according to claim 3, characterized in that, The step of filtering and clustering different object type infection data groups in the data for different object types involves extracting screening indicators based on the usage infection duration corresponding to different object manufacturing parts in the data group, forming corresponding object type infection group indicator data, including: By filtering and clustering data for different object types, infection data groups of different object type regions are obtained, and defect feature parameters corresponding to different object manufactured parts are acquired. , where m represents the number of different object manufacturing parts in the object type region infection data group, and n represents the number of different defect feature parameters; For different manufactured objects in the infected data group of the object type region, according to the corresponding different defect feature parameters and the duration of infection. Correlation analysis of infection impact was conducted to determine the correlation screening formula for infection data groups of the specified object type regions. .

5. The method for screening and analyzing additively manufactured parts for orthopedic infections according to claim 4, characterized in that, The different manufactured objects in the infected data group of the object type region are classified according to their corresponding different defect feature parameters. and the duration of infection. Correlation analysis of infection impact was conducted to determine the correlation screening formula for infection data groups of the specified object type regions. ,include: The different object manufacturing parts in the object type region infection data group are randomly divided into an in-group parsing data part and an in-group adjustment data part, wherein the number of object manufacturing parts in the in-group parsing data part is not less than the number of object type region infection correlation screening parts. The total number of constants to be resolved in the file; For the parsed data portion within the group, arbitrarily extract different object manufacturing parts with the same number as the total number of constants to be parsed, and based on the different defect feature parameters of the object manufacturing parts... and the duration of infection. Screening for infection correlation in the region of the object type The constant to be parsed is parsed. Set the error tolerance limit value The parsed object type region infection correlation screening formula Based on the adjusted data within the group, the following adjustment analysis was performed: Arbitrarily select different defect feature parameters corresponding to the manufactured object in the adjustment data section within the group. Based on the object type, a region infection correlation screening method is used. Determine the corresponding theoretical infection duration If the following conditions are met in any three consecutive extracted object manufacturing parts: Then, the filtering formula for the infection correlation of the object type region is... If the desired shape is not met in any three consecutive extracted object manufacturing parts, then... Then, based on three randomly extracted object manufacturing parts, a screening formula is used to determine the infection correlation of the object type region. Adjustments are made, and non-repetitive arbitrary extraction and verification analysis is repeated until three consecutive extracted object manufacturing parts all satisfy the requirements. Then, the filtering formula for the infection correlation of the object type region is... To finalize the design.

6. The method for screening and analyzing additively manufactured parts for orthopedic infections according to claim 5, characterized in that, The step of extracting, arbitrarily, different object manufacturing parts from the parsed data portion of the group, with the same number as the total number of constants to be parsed, includes: Based on the infection duration described in the group's internal analysis data. The maximum and minimum values ​​were used to determine the maximum infection time span within the group. ; Determine any point in time within the time span to ensure that the maximum infection time span within the group begins from that determined point in time. Continuous time length obtained within satisfy: ,in, Indicates the minimum allowed duration percentage; Within the acquired continuous time span, using two time endpoints as a baseline, determine the total number of regions containing both time endpoints that equals the infection correlation screening formula for the object type. The time point at which the total number of constants to be parsed is described in the text is marked as the extraction time point; Extract the infection duration from the parsed data section within the group. The object manufacturing part that is closest to the extraction time point; All extracted object manufacturing parts were identified as samples for analyzing the infection correlation of the object type region. The object manufacturing part.

7. A screening and analysis system for additively manufactured parts targeting orthopedic infections, employing the screening and analysis method for additively manufactured parts targeting orthopedic infections as described in any one of claims 1-6, characterized in that, include: The data acquisition unit is used to collect historical screening data of the target manufactured parts and manufacturing result data of the target manufactured parts; The clustering analysis unit is used to perform clustering analysis on the historical screening data of manufactured parts collected by the data acquisition unit based on the object type, and to form object type screening clustering data. The indicator extraction unit is used to extract the usage features of the object type from the cluster data formed by the cluster analysis unit, and form object type screening indicator data. The screening and analysis unit is used to monitor and analyze the manufacturing result data of the target manufactured parts acquired by the data acquisition unit, combined with the object type screening index data formed by the index extraction unit, to form target object screening result data.

Images