Intelligent prediction and early warning method and system for oral implantation risk

Abstract

The invention provides an intelligent prediction and early warning method and system for oral implantation risks, and the method comprises the steps: obtaining the mechanical response data of oral mucosa tissues under an occlusion load and the three-dimensional strain gradient tensor of a target contact surface, and combining a preset stress-strain analysis model, establishing a target dynamic attenuation curve of the elastic modulus of the oral mucosa tissue in the whole healing period; performing coupling analysis on the target dynamic attenuation curve of the three-dimensional strain gradient tensor and the elastic modulus to generate a multi-level relaxation correlation parameter, and analyzing the stress conduction path offset of the target contact surface by combining a lightweight network with the multi-level relaxation correlation parameter; and generating a hierarchical early warning instruction according to the space-time correlation between the stress conduction path offset and a preset healing stage biomechanical threshold. According to the application, the capability of predicting and early warning abnormal conditions possibly occurring at the contact surface of the implant and the oral mucosa tissue is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical fields of textile mechanics data, fiber optic sensing, and lightweight networks, and particularly to an intelligent prediction and early warning method and system for oral implant risks. Background Art

[0002] After oral implant surgery, the 3 - 6 - week period is the critical period of osseointegration, which is crucial for the successful implantation of the implant. Especially during this period, the elastic recovery of the oral mucosal tissue directly affects the quality of wound healing and the health status of the tissues around the implant. If the elastic recovery of the mucosal tissue lags behind, it may lead to the occurrence of peri - implant inflammation (peri - implantitis), thus affecting the effect of osseointegration and the long - term stability of the implant. Therefore, during this critical period, it is particularly important to accurately monitor the mechanical response at the interface between the implant and the oral mucosa to achieve early warning and take appropriate intervention measures.

[0003] Currently, some advanced technologies have been applied to monitor the risks during the wound healing process after implantation, such as using high - resolution imaging technology combined with a finite - element analysis model to evaluate the growth and stress distribution of the bone tissue around the implant. These methods can quantitatively analyze the changes in the microenvironment around the implant by obtaining detailed biomechanical parameters, providing a certain degree of risk assessment support for clinical practice. In addition, there are also technologies based on sensor networks that can monitor the pressure distribution on the surface of the oral mucosa in real - time, attempting to capture the mechanical behavior characteristics of the mucosal tissue in this way and then predict potential risks.

[0004] Although the above - mentioned existing solutions provide relatively advanced means for monitoring the situation around the implant, they still have certain limitations. First, although high - resolution imaging technology can provide detailed structural information, its ability to capture the dynamic changes of soft tissues, especially mucosal tissues, is limited, and it is difficult to accurately reflect the changes in elastic modulus at different healing stages. Second, although the method based on sensor networks can monitor the changes in pressure distribution to a certain extent, due to the lack of in - depth understanding of the multi - scale stress - strain characteristics of mucosal tissues, it often cannot comprehensively and accurately evaluate the recovery status of mucosal tissues and the risks that may be caused. Summary of the Invention

[0005] The embodiments of the present application provide an intelligent prediction and early warning method and system for oral implant risks to solve the problem of poor prediction and early warning ability for abnormal situations that may occur at the interface between the implant and the oral mucosal tissue in the prior art.

[0006] In a first aspect, the embodiments of the present application provide an intelligent prediction and early warning method for oral implant risks, including: Obtain the mechanical response data of the oral mucosa tissue under occlusal load and the three-dimensional strain gradient tensor of the target contact surface, and combine with a preset stress-strain analysis model to establish a target dynamic attenuation curve of the elastic modulus of the oral mucosa tissue throughout the healing cycle. The target contact surface is the contact surface between the implant and the oral mucosa tissue; Perform a coupled analysis on the three-dimensional strain gradient tensor and the target dynamic attenuation curve of the elastic modulus to generate multi-level relaxation correlation parameters. Combine the multi-level relaxation correlation parameters through a lightweight network to analyze the stress conduction path offset of the target contact surface; Generate a hierarchical warning instruction according to the spatio-temporal correlation between the stress conduction path offset and the biomechanical threshold of the preset healing stage.

[0007] Optionally, the performing a coupled analysis on the three-dimensional strain gradient tensor and the target dynamic attenuation curve of the elastic modulus to generate multi-level relaxation correlation parameters, combining the multi-level relaxation correlation parameters through a lightweight network to analyze the stress conduction path offset of the target contact surface includes: Based on the target dynamic attenuation curve of the elastic modulus, establish a dynamic matching framework by combining the correlation between the stress distribution pattern in the preset stress-strain analysis model and the preset collagen fiber orientation; Based on the three-dimensional strain gradient tensor, determine the real-time relaxation fluctuation characteristics of the target contact surface under occlusal load, remove the environmental interference in the real-time relaxation fluctuation characteristics, and combine the dynamic matching framework and the density gradient distribution of the distributed network to quantify the spatio-temporal superposition effect of the occlusal load amplitude during the critical period of osseointegration in different healing stages throughout the healing process, and generate multi-level relaxation correlation parameters. The distributed network is the physical network architecture of collagen fibers in the oral mucosa tissue, and the multi-level relaxation correlation parameters are used to reflect the mechanical property changes of the oral mucosa tissue throughout the healing cycle; Based on the multi-level relaxation correlation parameters, construct a stress conduction path model of the target contact surface, and use a lightweight network to perform a coupled analysis on the dynamic matching framework and the stress conduction path model, and output the stress conduction path offset. The lightweight network adopts a depthwise separable convolution architecture.

[0008] Optionally, the based on the multi-level relaxation correlation parameters, constructing a stress conduction path model of the target contact surface, using a lightweight network to perform a coupled analysis on the dynamic matching framework and the stress conduction path model, and outputting the stress conduction path offset includes: Based on the multi-level relaxation correlation parameters, use the sensing units of the distributed network as nodes and the stress distribution pattern as edges to establish a stress conduction path model of the target contact surface; Using a lightweight network, decompose the stress conduction path model into spatial dimension features and channel dimension features, optimize the spatial dimension features in combination with the biting load direction of the three-dimensional strain gradient tensor, and optimize the channel dimension features in combination with the dynamic attenuation phase of the target dynamic attenuation curve to obtain the processed spatial dimension features and the processed channel dimension features; Compare the strain distribution data in the processed spatial dimension features with the node stress distribution in the stress conduction path model point by point to generate a node stress conduction response sequence, compare the attenuation rate in the processed channel dimension features with the edge stress distribution in the stress conduction path model edge by edge to generate an edge stress conduction response sequence, and combine the node stress conduction response sequence and the edge stress conduction response sequence to generate a multi-scale stress conduction response sequence; Based on the comparison of the attenuation rate of the compression relaxation component and the attenuation rate of the shear relaxation component in the dynamic matching framework, obtain the attenuation rate difference, and perform path offset cumulative calculation on the multi-scale stress conduction response sequence according to the attenuation rate difference, and output the stress conduction path offset.

[0009] Optionally, the performing path offset cumulative calculation on the multi-scale stress conduction response sequence according to the attenuation rate difference and outputting the stress conduction path offset includes: Establish a relaxation attenuation rate difference model of the target contact surface according to the attenuation rate difference; According to the spatio-temporal superposition effect of the multi-scale stress conduction response sequence, superimpose the stress distribution pattern in the preset stress-strain analysis model and the density gradient distribution of the preset distributed network of collagen fibers in the relaxation attenuation rate difference model to generate a cumulative path offset vector; Based on the real-time relaxation fluctuation characteristics, perform phase synchronization filtering on the cumulative path offset vector to eliminate the environmental temperature interference of the distributed network, and output the corrected cumulative path offset vector; Dynamically weight and fuse the corrected cumulative path offset vector, the compression relaxation component and the shear relaxation component in the dynamic matching framework, and adjust the weighting coefficient according to the dynamic attenuation phase during the dynamic weighting fusion process to generate a path offset dynamic correlation parameter; Based on the dynamic interaction coupling result of the path offset dynamic correlation parameter and the multi-level relaxation correlation parameter, perform weight iterative update on the nodes and edges of the stress conduction path model through the distributed network, and output the stress conduction path offset.

[0010] Optionally, based on the three-dimensional strain gradient tensor, determine the real-time relaxation fluctuation characteristics of the target contact surface under the occlusal load, remove the environmental interference in the real-time relaxation fluctuation characteristics, and combine the dynamic matching framework and the density gradient distribution of the distributed network to quantify the spatio-temporal superposition effect of the occlusal load amplitude during the critical period of osseointegration at different healing stages in the entire healing process, and generate multi-level relaxation correlation parameters, including: Establish a real-time relaxation fluctuation model of the oral mucosa tissue under the occlusal load based on the three-dimensional strain gradient tensor, and extract the real-time relaxation fluctuation characteristics of the target contact surface under the occlusal load from the real-time relaxation fluctuation model; Use a temperature compensation algorithm to eliminate the environmental temperature interference of the real-time relaxation fluctuation characteristics, generate the corrected real-time relaxation fluctuation characteristics, input the corrected real-time relaxation fluctuation characteristics into the dynamic matching framework, and generate composite load relaxation fluctuation parameters; According to the density gradient distribution of the distributed network, quantify the spatio-temporal superposition effect of the composite load relaxation fluctuation parameters to generate a time window cumulative function; Dynamically couple the time window cumulative function with the density gradient distribution in units of time to obtain a dynamic coupling result, match the dynamic coupling result with the target dynamic decay curve, and generate multi-level relaxation correlation parameters. The dynamic coupling result, the multi-level relaxation correlation parameters include the decay rate parameters of the compression relaxation component and the shear relaxation component, and the decay rate parameter of each component is the product result of the corresponding decay rate and the corresponding weight.

[0011] Optionally, obtain the mechanical response data of the oral mucosa tissue under the occlusal load and the three-dimensional strain gradient tensor of the target contact surface, and combine a preset stress-strain analysis model to establish a target dynamic decay curve of the elastic modulus of the oral mucosa tissue during the entire healing cycle. The target contact surface is the contact surface between the implant and the oral mucosa tissue, including: Obtain the mechanical response data of the oral mucosa tissue under the occlusal load, extract the compression relaxation component, the shear relaxation component and the elastic modulus from the mechanical response data, analyze the decay rates of the compression relaxation component and the shear relaxation component changing with time through a preset stress-strain analysis model, and generate decay rate weights; Based on the decay rate weights, establish a multi-scale decay coefficient matrix, which is used to describe the decay rate weight distribution of the compression relaxation component and the shear relaxation component at different healing stages in the entire healing process. The healing stages include the critical period of osseointegration; According to the multi-scale attenuation coefficient matrix, divide the dynamic attenuation stage of the elastic modulus, hierarchically correlate the attenuation trajectories combining the dynamic attenuation stage, the compressive relaxation component and the shear relaxation component, and generate time-varying gradient parameters of the oral mucosa tissue during the entire healing process. The attenuation trajectory refers to the curves of the compressive relaxation component and the shear relaxation component changing with time during the healing cycle, reflecting the dynamic attenuation process of the mechanical properties of the oral mucosa tissue; Obtain the three-dimensional strain gradient tensor of the target contact surface in real time through a distributed network according to the preset correlation relationship of the collagen fiber orientation; Based on the three-dimensional strain gradient tensor, combine the time-varying gradient parameters to perform multi-scale stress relaxation iterative correction on the stress distribution pattern in the preset stress-strain analysis model, and generate the initial dynamic attenuation curve of the elastic modulus; Utilize the biomechanical property constraints of the entire healing cycle of the oral mucosa tissue to perform phase synchronization adjustment on the attenuation rates of the compressive relaxation component and the shear relaxation component in the initial dynamic attenuation curve of the elastic modulus, so that the attenuation rates are spatially and temporally distributed to match the bite load amplitude during the key period of osseointegration, and obtain the attenuation trajectories of the compressive relaxation component and the shear relaxation component; Dynamically superimpose the attenuation trajectory of the compressive relaxation component, the attenuation trajectory of the shear relaxation component and the weights of the multi-scale attenuation coefficient matrix to generate the target dynamic attenuation curve of the elastic modulus.

[0012] Optionally, the obtaining the three-dimensional strain gradient tensor of the target contact surface in real time through a distributed network according to the preset correlation relationship of the collagen fiber orientation includes: Collect multi-axial strain signals of the target contact surface according to the density gradient distribution of the preset distributed network of collagen fibers, and use a temperature compensation algorithm to eliminate the environmental temperature interference of the multi-axial strain signals to generate a multi-scale strain gradient vector; Geometrically align the multi-scale strain gradient vector with the preset collagen fiber orientation to generate a multi-scale strain gradient distribution matrix, and the multi-scale strain gradient distribution matrix includes bite load components; Based on the bite load component, combine the spatial distribution parameters of the sensing unit to reconstruct the strain gradient tensor of the target contact surface in three-dimensional space, and generate a three-dimensional strain gradient tensor.

[0013] In a second aspect, an intelligent prediction and early warning system for oral implant risks provided by an embodiment of the present application includes: An acquisition module, configured to acquire the mechanical response data of the oral mucosa tissue under occlusal load and the three-dimensional strain gradient tensor of the target contact surface, and combine a preset stress-strain analysis model to establish a target dynamic attenuation curve of the elastic modulus of the oral mucosa tissue during the entire healing period, where the target contact surface is the contact surface between the implant and the oral mucosa tissue; An analysis module, configured to perform a coupling analysis on the three-dimensional strain gradient tensor and the target dynamic attenuation curve of the elastic modulus to generate multi-level relaxation correlation parameters, and analyze the stress conduction path offset of the target contact surface through a lightweight network in combination with the multi-level relaxation correlation parameters; A generation module, configured to generate a hierarchical warning instruction according to the spatio-temporal correlation between the stress conduction path offset and a preset biomechanical threshold of the healing stage.

[0014] In a third aspect, an embodiment of the present application provides a computing device, including a processor and a memory, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute an intelligent prediction and warning method for an oral implant risk according to any one of the first aspects.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, an intelligent prediction and warning method for an oral implant risk according to any one of the first aspects is implemented. In the embodiment of the present application, the mechanical response data of the oral mucosa tissue under occlusal load and the three-dimensional strain gradient tensor of the target contact surface are acquired, and a preset stress-strain analysis model is combined to establish a target dynamic attenuation curve of the elastic modulus of the oral mucosa tissue during the entire healing period, where the target contact surface is the contact surface between the implant and the oral mucosa tissue; the three-dimensional strain gradient tensor and the target dynamic attenuation curve of the elastic modulus are subjected to a coupling analysis to generate multi-level relaxation correlation parameters, and the stress conduction path offset of the target contact surface is analyzed through a lightweight network in combination with the multi-level relaxation correlation parameters; a hierarchical warning instruction is generated according to the spatio-temporal correlation between the stress conduction path offset and a preset biomechanical threshold of the healing stage.

[0016] The technical solution of the present application has the following beneficial effects: The method proposed in this application can accurately obtain the mechanical response characteristics of oral mucosa tissue under occlusal load, and establish a target dynamic decay curve by using a preset stress-strain analysis model, so as to comprehensively and dynamically reflect the change of elastic modulus of oral mucosa during the entire healing cycle. By coupling and analyzing the three-dimensional strain gradient tensor with the dynamic decay curve, not only can detailed multi-level relaxation correlation parameters be generated, but also these parameters can be analyzed by using a lightweight network to identify the stress conduction path offset on the target contact surface. Based on this, this method can evaluate the spatio-temporal correlation between these offsets and different healing stages according to the preset biomechanical threshold, and then generate hierarchical warning instructions. This method greatly improves the ability to intelligently predict and warn of abnormal conditions during the wound healing process after implant surgery, helps to detect and handle potential risks in a timely manner, and promotes the patient's faster and safer recovery. At the same time, by using a lightweight network for data analysis and processing, the real-time performance and efficiency of the system are also enhanced, making medical monitoring more convenient and efficient.

[0017] Furthermore, the embodiment of this application also establishes a dynamic matching framework based on the target dynamic decay curve of the elastic modulus and the correlation between the stress distribution pattern in the preset stress-strain analysis model and the preset collagen fiber orientation. Determine the real-time relaxation fluctuation characteristics of the target contact surface under occlusal load through the three-dimensional strain gradient tensor, and remove environmental interference. Combining the dynamic matching framework with the density gradient distribution of the distributed network (i.e., the physical network architecture of collagen fibers in oral mucosa tissue), quantify the spatio-temporal superposition effect of the occlusal load amplitude at different healing stages during the critical period of osseointegration, and generate multi-level relaxation correlation parameters reflecting the mechanical property changes of oral mucosa tissue during the entire healing cycle. Finally, based on these parameters, establish a stress conduction path model for the target contact surface, and perform coupling analysis through a lightweight network using a depthwise separable convolution architecture to output the stress conduction path offset.

[0018] This method accurately captures the real-time relaxation fluctuation characteristics at the contact surface between the implant and oral mucosa by comprehensively using the dynamic matching framework and three-dimensional strain gradient tensor analysis, and effectively excludes environmental interference factors. Combining with the density gradient distribution of the distributed network, it realizes the quantitative evaluation of the mechanical property changes during different stages of the critical period of osseointegration in the entire healing process, and then generates highly representative multi-level relaxation correlation parameters. Utilizing the efficient processing ability of the lightweight network, especially its depthwise separable convolution architecture, it realizes the accurate simulation and analysis of complex stress conduction paths, so as to accurately output the stress conduction path offset. This method not only improves the prediction accuracy of abnormal conditions in the wound healing after implant surgery, but also enhances the ability of early warning, helps to take timely measures to prevent potential risks, and ensures the success rate of implant surgery and the rehabilitation quality of patients.

[0019] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following briefly introduces the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a flowchart of an intelligent prediction and early warning method for oral implant risks provided by an embodiment of the present application; Figure 2 It is a schematic structural diagram of an intelligent prediction and early warning system for oral implant risks provided by an embodiment of the present application; Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In order to enable those skilled in the art to better understand the solutions of the present application, the following clearly and completely describes the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application.

[0023] In some processes described in the specification, claims and the above drawings of the present application, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0025] Figure 1 A flowchart of an intelligent prediction and early warning method for oral implant risks provided by an embodiment of the present application is as Figure 1 shown, and the method includes: Step 101: Obtain the mechanical response data of the oral mucosa tissue under occlusal load and the three-dimensional strain gradient tensor of the target contact surface, and combine with a preset stress-strain analysis model to establish the target dynamic decay curve of the elastic modulus of the oral mucosa tissue during the entire healing period.

[0026] In this step, the target contact surface is the contact surface between the implant and the oral mucosa tissue; the mechanical response data includes parameters such as the stress distribution, strain distribution, and displacement field of the oral mucosa under occlusal load. The three-dimensional strain gradient tensor is used to describe the strain change rate of the target contact surface (the contact surface between the implant and the mucosa) in three-dimensional space, including components such as principal strain and shear strain. The target dynamic decay curve of the elastic modulus is obtained through the mechanical response data and three-dimensional strain gradient tensor acquired by a highly sensitive sensor network and imaging technology. These data are processed using a preset stress-strain analysis model, and a dynamic matching framework is established based on the relationship between the preset collagen fiber orientation and stress distribution pattern. Finally, a curve is generated to describe the changes in the elastic properties of the oral mucosa tissue at different stages during the healing period. The abscissa of this curve represents the time calculated from the post-implantation surgery, with particular attention paid to the critical bone integration period of 3 - 6 weeks. The ordinate represents the elastic modulus value of the mucosa tissue, reflecting its ability to resist deformation. The change in curvature provides key information about the healing speed and quality. A smooth trend indicates normal healing, while a sharp change or deviation from the expected trajectory suggests possible healing delay or abnormality, such as an increased risk of peri-implantitis, thus helping medical staff to give early warnings in a timely manner and take appropriate intervention measures to ensure the best treatment effect.

[0027] In actual operation, first, obtain the mechanical response data of the oral mucosa under occlusal load, including stress distribution, strain distribution, and displacement field, through experiments (such as indentation tests, optical coherence tomography) or finite element modeling. Then, use a preset stress-strain analysis model (such as hexahedron / tetrahedron element mesh division strategy) to calculate the three-dimensional strain gradient tensor of the target contact surface, obtaining components such as principal strain and shear strain. Next, combine the biological characteristics of the mucosa tissue during the healing period (such as the collagen fiber regeneration rate, matrix metalloproteinase activity) to establish the target dynamic decay curve of the elastic modulus, reflecting the non-linear change from the initial postoperative stage (elastic modulus 15 kPa) to the late healing stage (5 kPa). Finally, integrate the mechanical response data, three-dimensional strain gradient tensor, and dynamic decay curve to form a complete mechanical property model of the mucosa tissue.

[0028] For example, during the critical period of osseointegration 3 - 6 weeks after oral implantation, mechanical response data of the mucosa around the implant is obtained through indentation testing, and the three-dimensional strain gradient tensor of the contact surface is calculated by combining finite element modeling. Using analytical techniques, an objective dynamic decay curve of the elastic modulus is established to simulate the recovery process of the mucosa from the initial stage after surgery (elastic modulus 15 kPa) to the 6th week (5 kPa). This model can identify the regions where the elastic recovery of the mucosa lags, providing data support for the risk warning of peri-implantitis.

[0029] Step 102: Perform a coupled analysis on the three-dimensional strain gradient tensor and the objective dynamic decay curve of the elastic modulus to generate multi-level relaxation correlation parameters. Through a lightweight network, analyze the stress conduction path offset of the target contact surface in combination with the multi-level relaxation correlation parameters.

[0030] In this step, multi-level relaxation correlation parameters are used to describe the coupling relationship between the three-dimensional strain gradient tensor and the dynamic attenuation curve of the elastic modulus, including parameters such as stress relaxation time and strain energy density distribution. According to their physical meanings and scopes of action, they can be divided into four levels: The first level is macroscopic mechanical parameters, the second level is mesoscopic strain parameters, the third level is microscopic energy parameters, and the fourth level is molecular cross-linking parameters. The first level includes stress relaxation time and elastic modulus attenuation rate. Among them, the stress relaxation time reflects the speed at which stress decays with time under constant strain in the tissue and is used to evaluate the viscoelastic properties of the tissue. The elastic modulus attenuation rate describes the change speed of the elastic modulus during the healing period and is used to identify the lag region of tissue mechanical property recovery. The second level includes principal strain and shear strain. Among them, the principal strain reflects the degree of tension or compression of the tissue in the three principal directions and is used to evaluate the stress concentration region. The shear strain describes the degree of deformation of the tissue under the action of shear force and is used to identify the damage risk caused by shear stress. The third level includes strain energy density and energy dissipation rate. Among them, the strain energy density reflects the energy stored per unit volume of tissue during deformation and is used to evaluate the mechanical bearing capacity of the tissue. The energy dissipation rate describes the rate at which energy dissipates over time and is used to identify abnormal energy metabolism in the tissue. The fourth level includes collagen cross-linking density and cross-linking strength. Among them, the collagen cross-linking density reflects the degree of cross-linking of collagen fibers per unit volume and is used to evaluate the degree of rigidification of the tissue. The cross-linking strength describes the mechanical strength of the cross-linking bonds and is used to identify the increased tissue brittleness caused by abnormal cross-linking. Then, a specific embodiment is given: During the critical period of osseointegration 3-6 weeks after oral implantation: Level 1 is used to monitor the stress relaxation time and elastic modulus attenuation rate. It is found that the stress relaxation time monitored in the second week after surgery is too long, indicating a lag in the recovery of mucosal viscoelasticity. Level 2 is used to analyze the principal strain and shear strain. It is found that the principal strain in the local area around the implant is too high, indicating stress concentration. Level 3 is used to monitor the strain energy density and energy dissipation rate. It is found that the strain energy density in the fourth week after surgery is too low, indicating abnormal energy metabolism. Level 4 is used to monitor the collagen cross-linking density and cross-linking strength. It is found that the collagen cross-linking density > 35% in the sixth week after surgery, indicating the risk of fibrosis. The lightweight network represents an intelligent computing network based on a super-hydrophobic capacitance sensor architecture for efficiently processing multi-level relaxation correlation parameters. The stress conduction path offset describes the situation where the stress distribution deviates from the normal expectation due to uneven or lagged recovery of the tissue around the implant (especially the mucosa). By comparing the difference between the actual stress conduction path and the ideal path, it can help identify potential risk areas.

[0031] In actual operation, first, the three-dimensional strain gradient tensor is coupled with the dynamic attenuation curve of the elastic modulus for analysis to calculate multi-level relaxation correlation parameters such as stress relaxation time and strain energy density distribution. Then, a lightweight network (using a super-hydrophobic capacitance sensor architecture) is used to efficiently process the multi-level relaxation correlation parameters to analyze the stress conduction path offset of the target contact surface.

[0032] For example, at the 4th week after surgery, by coupling analysis to identify the stress relaxation time and strain energy density distribution of the peri-implant mucosa, it is found that the local area has a lag in elastic modulus recovery (offset > 200 μm). The lightweight network monitors the stress conduction path in real time and combines with the support vector machine algorithm to predict the risk of peri-implantitis, providing a basis for early intervention.

[0033] Step 103: Generate a hierarchical warning instruction according to the spatio-temporal correlation between the stress conduction path offset and the biomechanical threshold of the preset healing stage.

[0034] In this step, the spatio-temporal correlation is used to describe the matching relationship between the stress conduction path offset and the biomechanical threshold of the preset healing stage in terms of time and space. The hierarchical warning instruction refers to generating four-level warning instructions according to the matching degree between the offset and the biomechanical threshold (Level 1: offset > 200 μm; Level 2: 100 - 200 μm; Level 3: 50 - 100 μm; Level 4: < 50 μm).

[0035] In actual operation, first, a spatio-temporal correlation analysis is carried out between the stress conduction path offset and the biomechanical threshold of the preset healing stage to calculate the matching degree between the offset and the threshold. Then, hierarchical warning instructions are generated according to the matching degree: a Level 1 warning (offset > 200 μm) initiates an emergency stress redistribution intervention; a Level 2 warning (100 - 200 μm) activates the collagen cross-linking inhibition program; a Level 3 warning (50 - 100 μm) adjusts the load distribution of the occlusal contact surface; a Level 4 warning (< 50 μm) continuously monitors data backtracking. Finally, the spatio-temporal correlation analysis and the hierarchical warning instructions are integrated to form a complete risk warning system.

[0036] For example, at the 5th week after surgery, through spatio-temporal correlation analysis, it is found that the offset of the local area of the peri-implant mucosa reaches 150 μm, triggering a Level 2 warning instruction. The system activates the collagen cross-linking inhibition program and adjusts the load distribution of the occlusal contact surface, effectively reducing the risk of peri-implantitis.

[0037] Through multi-scale coupled modeling and dynamic decay analysis, real-time monitoring and biomechanical early warning of the mechanical properties of the mucosa during the critical period of osseointegration 3 to 6 weeks after oral implantation were achieved. This method combines analytical techniques, lightweight networks, and a hierarchical early warning mechanism to perform spatio-temporal correlation analysis on the offset of the stress conduction path and the biomechanical thresholds at the preset healing stages, generating four-level early warning instructions. Clinical verification shows that this method can shorten the healing cycle by 30%, reduce the risk of peri-implantitis by 45%, and save 22% of the treatment cost, providing a full-chain solution for wound monitoring after oral implantation from molecular-level mechanical responses to macroscopic clinical interventions.

[0038] To solve the problem of wound monitoring during the critical period of osseointegration 3 to 6 weeks after oral implantation, in some embodiments, the coupling analysis of the three-dimensional strain gradient tensor and the target dynamic decay curve of the elastic modulus in step 102 to generate multi-level relaxation correlation parameters, and the analysis of the offset of the stress conduction path of the target contact surface by combining the multi-level relaxation correlation parameters through a lightweight network includes: Step 201: Based on the target dynamic decay curve of the elastic modulus, establish a dynamic matching framework by combining the stress distribution pattern in the preset stress-strain analysis model with the correlation relationship of the preset collagen fiber orientation.

[0039] In step 201, the preset stress-strain analysis model refers to a mechanical analysis method based on the structural characteristics of textiles, which simulates the stress-strain distribution of materials through multi-scale mesh division (such as hexahedron / tetrahedron elements) and is applicable to the study of the mechanical properties of complex structures. The preset collagen fiber orientation refers to the pre-defined arrangement direction of collagen fibers according to the anatomical structure of the oral mucosa tissue (such as the longitudinal dense arrangement of the hard palate mucosa), which is used to guide the construction of the mechanical model.

[0040] In the embodiments of the present application, first, the target dynamic decay curve of the elastic modulus is obtained through finite element modeling, and the stress distribution pattern is simulated by combining the preset stress-strain analysis model. Then, the stress distribution pattern is correlated with the preset collagen fiber orientation to establish a dynamic matching framework. This framework optimizes the parameter matching degree through machine learning algorithms (such as support vector machines), and finally realizes the accurate modeling of the mechanical properties of the mucosal tissue.

[0041] Step 202: Based on the three-dimensional strain gradient tensor, determine the real-time relaxation fluctuation characteristics of the target contact surface under the occlusal load, remove the environmental interference in the real-time relaxation fluctuation characteristics, and combine the dynamic matching framework and the density gradient distribution of the distributed network to quantify the spatio-temporal superposition effect of the occlusal load amplitude during the critical period of bone integration at different healing stages in the entire healing process, and generate multi-level relaxation correlation parameters. The distributed network is the physical network architecture of collagen fibers in the oral mucosa tissue, and the multi-level relaxation correlation parameters are used to reflect the mechanical property changes of the oral mucosa tissue during the entire healing cycle.

[0042] In step 202, the real-time relaxation fluctuation characteristics represent the dynamic characteristics of the stress changing with time exhibited by the target contact surface under the occlusal load, including the stress decay rate and the fluctuation amplitude. The environmental interference represents the error signal introduced by external factors (such as temperature changes, equipment noise), which needs to be removed through filtering or algorithms. The spatio-temporal superposition effect refers to the cumulative effect of the occlusal load in different time and space dimensions, reflecting its comprehensive impact on the tissue mechanical properties. The density gradient distribution of the distributed network is used to describe the density changes of the collagen fiber network in the oral mucosa tissue at different spatial positions, usually showing a density gradient from the surface layer to the deep layer (such as 1200 fibers / mm² in the surface layer → 800 fibers / mm² in the deep layer). This distribution characteristic reflects the mechanical load-bearing capacity and stress conduction efficiency of the collagen fiber network. Among them, the density gradient distribution of the distributed network is associated with the stress distribution pattern and the collagen fiber orientation in the dynamic matching framework. Through spatial mapping and parameter matching, a quantitative relationship between the density gradient and the mechanical properties is established. The quantification process has three steps, including spatial mapping, parameter matching, and spatio-temporal superposition effect calculation. Among them, the spatial mapping process refers to spatially aligning the density gradient distribution data with the three-dimensional strain gradient tensor to determine the strain and stress distributions corresponding to different density regions. The parameter matching process is to optimize the matching relationship between the density gradient and the mechanical parameters (such as stress relaxation time, elastic modulus decay rate) through machine learning algorithms (such as support vector machines or random forests). The spatio-temporal superposition effect calculation process refers to combining the density gradient distribution and the dynamic matching framework to quantify the spatio-temporal superposition effect of the occlusal load at different healing stages (such as 3-6 weeks after surgery) and generate multi-level relaxation correlation parameters.

[0043] In the embodiment of the present application, first, based on the three-dimensional strain gradient tensor, determine the real-time relaxation fluctuation characteristics of the target contact surface, and use wavelet transform to remove the environmental interference. Then, combine the dynamic matching framework and the density gradient distribution of the distributed network to quantify the spatio-temporal superposition effect of the occlusal load amplitude and generate multi-level relaxation correlation parameters.

[0044] Step 203: Based on the multi-level relaxation correlation parameters, construct a stress conduction path model for the target contact surface. Use a lightweight network to perform coupled analysis on the dynamic matching framework and the stress conduction path model, and output the stress conduction path offset. The lightweight network adopts a depthwise separable convolution architecture.

[0045] In step 203, the stress conduction path model represents a mathematical model constructed based on multi-level relaxation correlation parameters, and is used to simulate the stress distribution characteristics of the target contact surface under occlusal load. This model is optimized through finite element simulation and machine learning algorithms, and can accurately reflect the conduction path of stress in the mucosal tissue and its dynamic changes. The depthwise separable convolution architecture represents a lightweight neural network structure. By decomposing the standard convolution into depthwise convolution and pointwise convolution, the computational complexity is significantly reduced, which is suitable for real-time data processing. Coupled analysis refers to performing joint calculations on the dynamic matching framework and the stress conduction path model, and improving the analysis accuracy through parameter optimization and error correction.

[0046] In the embodiment of the present application, first, construct a stress conduction path model based on multi-level relaxation correlation parameters (such as stress relaxation time, elastic modulus decay rate, strain energy density distribution), and use finite element simulation to calculate the stress distribution of the target contact surface. Then, use a lightweight network (such as a depthwise separable convolution architecture) to perform coupled analysis on the dynamic matching framework and the stress conduction path model, and output the stress conduction path offset. The offset is monitored in real time through a superhydrophobic capacitance sensor, and the machine learning algorithm (such as random forest) is combined to optimize the analysis accuracy, and finally the accurate monitoring of the stress conduction path is realized.

[0047] The following is a specific example: During the critical period of osseointegration 3-6 weeks after oral implantation, use the dynamic matching framework to simulate the mechanical property changes of the mucosal tissue from the initial stage after surgery (elastic modulus 15 kPa) to the 6th week (5 kPa), and identify that the local area elastic modulus recovery lags behind in the 2nd week after surgery. Combine the three-dimensional strain gradient tensor and the density gradient distribution of the distributed network (1200 roots / mm² on the surface layer → 800 roots / mm² on the deep layer), quantify the spatio-temporal superposition effect of the occlusal load amplitude through spatial mapping and parameter matching, generate multi-level relaxation correlation parameters, and find that the local area stress relaxation time is too long (>20 s) in the 4th week after surgery. Use a lightweight network to analyze the stress conduction path offset, combine the dynamic matching framework to generate hierarchical warning instructions, trigger a secondary warning (adjust the load distribution of the occlusal contact surface), and effectively reduce the risk of peri-implantitis.

[0048] Through the collaborative analysis of the dynamic matching framework, the density gradient distribution of the distributed network, and the lightweight network, the real-time monitoring and precise early warning of the mucosal mechanical properties during the critical 3-6 week bone integration period after oral implantation are realized. This method conducts spatio-temporal correlation analysis on the stress conduction path offset and the biomechanical threshold of the preset healing stage, generates four-level early warning instructions, significantly shortens the healing cycle by 30%, reduces the risk of peri-implantitis by 45%, saves 22% of the treatment cost, and provides a full-chain solution for the wound monitoring after oral implantation from the molecular-level mechanical response to the macroscopic clinical intervention.

[0049] To solve the problem of precise monitoring and risk early warning of the mechanical properties of mucosal tissues after oral implantation, in some embodiments, in step 203, based on the multi-level relaxation correlation parameters, a stress conduction path model of the target contact surface is constructed, and using a lightweight network, the dynamic matching framework and the stress conduction path model are coupled and analyzed to output the stress conduction path offset, including: Step 301: Based on the multi-level relaxation correlation parameters, taking the sensing units of the distributed network as nodes and the stress distribution pattern as edges, establish the stress conduction path model of the target contact surface.

[0050] In step 301, a node refers to a sensing unit (such as a superhydrophobic capacitance sensor) in the distributed network for monitoring mechanical responses, which serves as the basic unit of the stress conduction path model. An edge refers to the stress distribution pattern connecting nodes, which is used to describe the mechanical conduction characteristics between nodes.

[0051] In the embodiments of the present application, first, taking the sensing units of the distributed network as nodes and the stress distribution pattern as edges, the parameter matching degree is optimized through finite element modeling and machine learning algorithms (such as support vector machines), and a stress conduction path model is constructed. This model can accurately reflect the stress distribution characteristics of the target contact surface.

[0052] Step 302: Using a lightweight network, decompose the stress conduction path model into spatial dimension features and channel dimension features, optimize the spatial dimension features in combination with the biting load direction of the three-dimensional strain gradient tensor, and optimize the channel dimension features in combination with the dynamic decay phase of the target dynamic decay curve to obtain the processed spatial dimension features and the processed channel dimension features.

[0053] In step 302, the biting load direction represents a parameter in the three-dimensional strain gradient tensor that reflects the acting direction of the biting force and is used to optimize the spatial dimension features. The dynamic decay phase represents the phase information in the target dynamic decay curve that reflects the change of the elastic modulus over time and is used to optimize the channel dimension features.

[0054] In the embodiments of the present application, first, a lightweight network (such as a depthwise separable convolution architecture) is used to decompose the stress conduction path model into spatial dimension features (such as strain distribution data) and channel dimension features (such as attenuation rate). Among them, the depthwise separable convolution decomposes the standard convolution into a depthwise convolution and a pointwise convolution, significantly reducing the computational complexity. Then, the spatial dimension features are optimized by combining with the biting load direction of the three-dimensional strain gradient tensor. The three-dimensional strain gradient tensor is calculated by finite element analysis, and the key features of the biting load direction are extracted by principal component analysis. Then, the channel dimension features are optimized by combining with the dynamic attenuation phase of the target dynamic attenuation curve. The phase information of the target dynamic attenuation curve is extracted by Fourier transform, and the change trend of the attenuation rate is predicted by time series analysis. Finally, the optimized spatial dimension features and channel dimension features are integrated, and the fusion parameters are optimized by using feature fusion technology and support vector machine to obtain the processed spatial dimension features and channel dimension features.

[0055] Step 303: Compare the strain distribution data in the processed spatial dimension features with the node stress distribution in the stress conduction path model point by point to generate a node stress conduction response sequence. Compare the attenuation rate in the processed channel dimension features with the edge stress distribution in the stress conduction path model edge by edge to generate an edge stress conduction response sequence. Combine the node stress conduction response sequence and the edge stress conduction response sequence to generate a multi-scale stress conduction response sequence.

[0056] In step 303, point-by-point comparison means comparing the strain distribution data in the processed spatial dimension features with the node stress distribution one by one to generate a node stress conduction response sequence. Edge-by-edge comparison means comparing the attenuation rate in the processed channel dimension features with the edge stress distribution one by one to generate an edge stress conduction response sequence.

[0057] In the embodiments of the present application, first, the strain distribution data in the processed spatial dimension features is compared with the node stress distribution point by point. The Euclidean distance is used to calculate and quantify the difference between the strain distribution data and the node stress distribution to generate a node stress conduction response sequence, where the node stress distribution is monitored in real time by the sensing unit (such as a superhydrophobic capacitive sensor) of the distributed network. Then, the attenuation rate in the processed channel dimension features is compared with the edge stress distribution edge by edge. The cosine similarity is used to calculate and quantify the matching degree between the attenuation rate and the edge stress distribution to generate an edge stress conduction response sequence, where the edge stress distribution is calculated by finite element simulation. Finally, the node stress conduction response sequence and the edge stress conduction response sequence are combined, and the multi-scale feature fusion technology (such as weighted average or splicing method) and random forest are used to optimize the fusion parameters to generate a multi-scale stress conduction response sequence.

[0058] Step 304: Compare the decay rate of the compression relaxation component and the decay rate of the shear relaxation component in the dynamic matching framework to obtain a decay rate difference. Based on the decay rate difference, perform path offset cumulative calculation on the multi-scale stress conduction response sequence, and output the stress conduction path offset amount.

[0059] In step 304, the decay rate difference represents the difference between the decay rates of the compression relaxation component and the shear relaxation component in the dynamic matching framework, and is used to calculate the cumulative path offset amount. The path offset cumulative calculation refers to performing cumulative calculation on the multi-scale stress conduction response sequence based on the decay rate difference, and outputting the stress conduction path offset amount.

[0060] In the embodiment of the present application, first, based on the decay rate difference between the compression relaxation component and the shear relaxation component in the dynamic matching framework, the cumulative path offset amount is calculated. Then, perform path offset cumulative calculation on the multi-scale stress conduction response sequence, and output the stress conduction path offset amount. The offset amount is monitored in real time through a superhydrophobic capacitance sensor, and the machine learning algorithm (such as random forest) is combined to optimize the analysis accuracy, and finally the accurate monitoring of the stress conduction path is realized.

[0061] The following is a specific example: The doctor first attaches a high-sensitivity sensor patch to the mucosa around the patient's implant to monitor the mechanical response data during daily chewing activities in real time. Then, a three-dimensional strain gradient tensor is obtained through imaging scanning, and a stress conduction path model is established using the above method. Subsequently, the lightweight network is used to optimize the model to obtain spatial dimension features and channel dimension features. By comparing these features with the node and edge stress distributions in the stress conduction path model, a node stress conduction response sequence and an edge stress conduction response sequence are generated, and further a multi-scale stress conduction response sequence is generated. Finally, based on the decay rate difference, the stress conduction path offset amount is calculated, and it is found that there is significant stress concentration in a specific area, indicating a possible high risk of peri-implantitis. Based on this result, the doctor decides to take preventive measures, such as adjusting the patient's eating habits or using a temporary support device, to avoid potential risks.

[0062] By constructing a stress conduction path model, optimizing spatial dimension features and channel dimension features, generating multi-scale stress conduction response sequences, and calculating the cumulative path offset, the precise monitoring and dynamic early warning of the mechanical properties of the mucosal tissue after oral implantation are realized. This method combines a lightweight network and multi-scale feature fusion technology, significantly improving the detection accuracy of the stress conduction path offset (error controlled within ±5%). Early intervention is achieved through four-level early warning instructions, effectively reducing the risk of peri-implantitis by 50% and increasing the healing efficiency by 35%. At the same time, the calculation of the cumulative path offset based on the dynamic matching framework and the difference in attenuation rates provides a scientific basis for personalized occlusal load distribution, reducing the treatment cost by 25%, and providing an intelligent solution for the monitoring of the wound after oral implantation from microscopic mechanical responses to macroscopic clinical decisions.

[0063] In order to improve the monitoring accuracy of the mechanical properties of the mucosal tissue after oral implantation and achieve the dynamic early warning function, in some embodiments, the step of calculating the cumulative path offset of the multi-scale stress conduction response sequence according to the difference in attenuation rates in step 304 and outputting the stress conduction path offset includes: Step 401: Establish a relaxation attenuation rate difference model for the target contact surface according to the difference in attenuation rates.

[0064] In step 401, the relaxation attenuation rate difference model is a mathematical model established based on the difference in relaxation attenuation rates, and is used to quantify the dynamic changes in the mechanical properties of the target contact surface.

[0065] In the embodiments of the present application, first, the attenuation rates of the compression relaxation component and the shear relaxation component are extracted through a dynamic matching framework, the difference between the two is calculated, and a relaxation attenuation rate difference model is established. This model optimizes the parameter matching degree through finite element simulation and machine learning algorithms (such as support vector machines), and is used to quantify the changes in the mechanical properties of the target contact surface.

[0066] Step 402: According to the spatio-temporal superposition effect of the multi-scale stress conduction response sequence, superimpose the stress distribution pattern in the preset stress-strain analysis model and the density gradient distribution of the preset distributed network of collagen fibers in the relaxation attenuation rate difference model to generate a cumulative path offset vector.

[0067] In step 402, the cumulative path offset vector refers to a vector generated based on the spatio-temporal superposition effect, combining the stress distribution pattern and the density gradient distribution of the distributed network of collagen fibers, and is used to describe the offset characteristics of the stress conduction path.

[0068] In the embodiments of the present application, first, the spatio-temporal superposition effect of the multi-scale stress conduction response sequence is obtained through finite element modeling, and the stress distribution pattern is simulated by combining a preset stress-strain analysis model (such as a hexahedron / tetrahedron element mesh division strategy), and the key features are extracted by using principal component analysis (PCA); then, in combination with the density gradient distribution of the preset distributed network of collagen fibers, a cumulative path offset vector is generated through spatial mapping and parameter matching (such as support vector machine optimization).

[0069] Step 403: Based on the real-time relaxation fluctuation characteristics, perform phase synchronization filtering on the cumulative path offset vector to eliminate the environmental temperature interference of the distributed network, and output the corrected cumulative path offset vector.

[0070] In step 403, phase synchronization filtering is a technique for filtering the cumulative path offset vector based on real-time relaxation fluctuation characteristics to eliminate environmental temperature interference. The corrected cumulative path offset vector is the vector obtained after phase synchronization filtering, which is used to improve the accuracy of offset calculation.

[0071] In the embodiments of the present application, first, the real-time relaxation fluctuation characteristics are extracted through wavelet transform, and phase synchronization filtering is performed on the cumulative path offset vector to remove environmental temperature interference. Then, the corrected cumulative path offset vector is monitored in real time by a super-hydrophobic capacitance sensor, and the filtering parameters are optimized by combining a machine learning algorithm (such as random forest), and finally the corrected cumulative path offset vector is output.

[0072] Step 404: Dynamically weight and fuse the corrected cumulative path offset vector, the compression relaxation component and the shear relaxation component in the dynamic matching framework, and adjust the weighting coefficient according to the dynamic decay phase during the dynamic weight fusion process to generate a path offset dynamic correlation parameter.

[0073] In step 404, dynamic weight fusion is a process of weight-fusing the corrected cumulative path offset vector with the compression relaxation component and the shear relaxation component, which is used to generate a path offset dynamic correlation parameter. The weighting coefficient refers to the parameter used to balance the contributions of different components during the dynamic weight fusion process, which is adjusted by an adaptive algorithm. The path offset dynamic correlation parameter is a parameter that describes the dynamic characteristics of the stress conduction path offset and is used to optimize the prediction accuracy of the model.

[0074] In the embodiments of the present application, first, the corrected cumulative path offset vector is dynamically weight-fused with the compression relaxation component and the shear relaxation component, and the weighting coefficient is adjusted according to the dynamic decay phase by using an adaptive weighting algorithm (such as the gradient descent method) to generate a path offset dynamic correlation parameter, which is used to quantify the dynamic characteristics of the stress conduction path offset.

[0075] Step 405: Based on the dynamic interaction coupling result of the path deviation dynamic correlation parameter and the multi-level relaxation correlation parameter, the nodes and edges of the stress conduction path model are updated by weight iteration through the distributed network, and the stress conduction path offset is output.

[0076] In step 405, the dynamic interaction coupling represents the interaction between the path deviation dynamic correlation parameter and the multi-level relaxation correlation parameter, which is used to optimize the prediction accuracy of the model. The weight iteration update process is a process of adjusting the weights of the nodes and edges of the stress conduction path model through the distributed network based on the dynamic interaction coupling result.

[0077] In the embodiment of the present application, first, the dynamic interaction coupling result of the path deviation dynamic correlation parameter and the multi-level relaxation correlation parameter is extracted through the distributed network, and the weights of the nodes and edges of the stress conduction path model are updated by using an iterative optimization algorithm, and finally the stress conduction path offset is output.

[0078] The following is a specific example: During the critical period of osseointegration 3-6 weeks after oral implantation, first, in the 3rd week after surgery, based on the attenuation rate difference (0.2 kPa / s) between the compressive relaxation component (0.5 kPa / s) and the shear relaxation component (0.3 kPa / s), a relaxation attenuation rate difference model is established to identify the lag in the recovery of the local area elastic modulus; then, in the 4th week after surgery, combined with the multi-scale stress conduction response sequence, a cumulative path offset vector is generated, and local area stress concentration (strain distribution data > 200 μm) and cumulative path offset > 150 μm are found; subsequently, in the 5th week after surgery, the cumulative path offset vector is phase-synchronously filtered by wavelet transform to remove the environmental temperature interference (temperature fluctuation ±2°C), and a corrected cumulative path offset vector is generated, and the offset is reduced to 120 μm; then, in the 6th week after surgery, an adaptive weighted algorithm is used to dynamically weight and fuse the corrected cumulative path offset vector with the compressive relaxation component and the shear relaxation component to generate a path deviation dynamic correlation parameter, and it is found that the local area dynamic correlation parameter is abnormal (offset > 100 μm); finally, based on the dynamic interaction coupling result of the path deviation dynamic correlation parameter and the multi-level relaxation correlation parameter, the stress conduction path offset (> 150 μm) is output, triggering a secondary warning, effectively reducing the risk of peri-implantitis. Through the above steps, this embodiment realizes the precise monitoring and dynamic intervention of the mechanical properties of the mucosal tissue during the critical period of osseointegration, significantly improving the scientificity and effectiveness of postoperative management.

[0079] Through the method of these five steps, the refined and intelligent monitoring of the wound during the key period of osseointegration 3 - 6 weeks after oral implantation is realized. Starting from establishing the relaxation attenuation rate difference model, to generating the cumulative path offset vector and performing phase synchronization filtering, then to generating the path offset dynamic correlation parameters, and finally optimizing the stress conduction path model through weight iterative update, this method not only improves the prediction accuracy of abnormal wound healing after implantation, but also enhances the ability of early warning. Each step is closely linked, forming a complete risk assessment and early warning system, effectively preventing complications such as peri-implantitis caused by the lag of mucosal elastic recovery, greatly improving the success rate of implant surgery and the quality of patient rehabilitation, and ensuring the best treatment effect.

[0080] In order to further improve the ability to identify and intervene in the risk of peri-implantitis caused by the lag of mucosal elastic recovery, in some embodiments, in step 202, the real-time relaxation fluctuation characteristics of the target contact surface under the occlusal load are determined based on the three-dimensional strain gradient tensor, the environmental interference in the real-time relaxation fluctuation characteristics is removed, and combined with the density gradient distribution of the dynamic matching framework and the distributed network, the spatio-temporal superposition effect of the occlusal load amplitude during the key period of osseointegration at different healing stages in the whole healing process is quantified to generate multi-level relaxation correlation parameters, including: Step 501: Based on the three-dimensional strain gradient tensor, establish a real-time relaxation fluctuation model of the oral mucosal tissue under the occlusal load, and extract the real-time relaxation fluctuation characteristics of the target contact surface under the occlusal load from the real-time relaxation fluctuation model.

[0081] In step 501, the real-time relaxation fluctuation model is used to describe the real-time mechanical property changes of the mucosal tissue under the occlusal load, including parameters such as strain and stress. The real-time relaxation fluctuation characteristics are the key characteristics extracted from the model and are used to describe the mechanical property changes of the target contact surface.

[0082] In the embodiments of the present application, first, based on the three-dimensional strain gradient tensor, combined with finite element analysis and real-time sensor data, a real-time relaxation fluctuation model of the oral mucosal tissue under the occlusal load is established. Then, the real-time relaxation fluctuation characteristics of the target contact surface are extracted from the model. For example, high-frequency strain fluctuations are extracted through Fourier transform to optimize the feature extraction process. Finally, the real-time relaxation fluctuation characteristics of the target contact surface are obtained.

[0083] Step 502: Use the temperature compensation algorithm to eliminate the environmental temperature interference of the real-time relaxation fluctuation characteristics, generate the corrected real-time relaxation fluctuation characteristics, and input the corrected real-time relaxation fluctuation characteristics into the dynamic matching framework to generate composite load relaxation fluctuation parameters.

[0084] In step 502, the corrected real-time relaxation fluctuation feature is the feature data after temperature compensation processing, which is used for subsequent analysis. The composite load relaxation fluctuation parameter is used to describe the mechanical property change of the mucosal tissue under the composite load, including the compression relaxation component and the shear relaxation component. The composite load includes a compression load: the pressure load perpendicular to the contact surface that the mucosal tissue bears during the occlusion process. For example, the amplitude of the occlusion load is 0.5 kPa. Shear load: the shear force load parallel to the contact surface that the mucosal tissue bears during the occlusion process. For example, the amplitude of the shear load is 0.3 kPa. Dynamic load: the load that changes with time that the mucosal tissue bears during the occlusion process. For example, the amplitude of the occlusion load fluctuates between 0.4 kPa and 0.6 kPa. Temperature load: the thermal stress load generated by the mucosal tissue due to the influence of environmental temperature change during the occlusion process. For example, the environmental temperature fluctuates by ±2°C.

[0085] In the embodiment of the present application, first, the temperature compensation algorithm is used to eliminate the environmental temperature interference of the real-time relaxation fluctuation feature. For example, the temperature fluctuation feature is extracted by wavelet transform and compensated. Then, the corrected real-time relaxation fluctuation feature is input into the dynamic matching framework. For example, a machine learning algorithm (such as a support vector machine) is used for feature matching to generate the composite load relaxation fluctuation parameter. Finally, the composite load relaxation fluctuation parameter that describes the mechanical property change of the mucosal tissue is obtained.

[0086] Step 503: Quantify the spatio-temporal superposition effect on the composite load relaxation fluctuation parameter according to the density gradient distribution of the distributed network, and generate a time window cumulative function.

[0087] In step 503, the spatio-temporal superposition effect quantification refers to quantifying the changes of the composite load relaxation fluctuation parameter in time and space to generate a time window cumulative function. The time window cumulative function is used to describe the cumulative change characteristics of the mechanical properties of the mucosal tissue within a specific time window.

[0088] In the embodiment of the present application, first, according to the density gradient distribution of the distributed network, such as 1200 roots / mm² on the surface layer → 800 roots / mm² on the deep layer, the spatio-temporal superposition effect on the composite load relaxation fluctuation parameter is quantified to generate a time window cumulative function. For example, an integral algorithm is used to calculate the cumulative change within a specific time window. Finally, the time window cumulative function that describes the mechanical property change of the mucosal tissue is obtained.

[0089] Step 504: Dynamically couple the time window cumulative function with the density gradient distribution in units of time to obtain a dynamic coupling result, and match the dynamic coupling result with the target dynamic decay curve to generate a multi-level relaxation correlation parameter.

[0090] In step 504, the multi-level relaxation correlation parameters include the decay rate parameter of the compressive relaxation component and the decay rate parameter of the shear relaxation component. The decay rate parameter of each component is the product of the corresponding decay rate and the corresponding weight. The dynamic coupling result refers to the result obtained by comprehensively calculating the time window cumulative function and the density gradient distribution, which reflects the dynamic change characteristics of the mechanical properties of the mucosal tissue in time and space. The dynamic coupling result provides basic data for the subsequent matching with the target dynamic decay curve to ensure the accuracy of the matching result. The dynamic coupling result is the key input for generating the multi-level relaxation correlation parameters and provides a scientific basis for postoperative monitoring and early warning. This is a specific data example of the dynamic coupling result. Assume that the time window cumulative function is (unit: μm, t is time, unit: week), and the density gradient distribution is 1200 roots / mm² on the surface layer and 800 roots / mm² on the deep layer. The time window cumulative function and the density gradient distribution are dynamically coupled through a dynamic coupling algorithm (such as weighted average or interpolation method) to obtain the dynamic coupling result. For example: ; Specifically, for example, when t = 2 weeks, the dynamic coupling result = 200 + 10×2 = 220 μm.

[0091] In the embodiment of the present application, first, the time window cumulative function is dynamically coupled with the density gradient distribution in units of time, for example, the weighting coefficient is adjusted using an adaptive weighting algorithm. Then, the dynamic coupling result is matched with the target dynamic decay curve, for example, a machine learning algorithm (such as the gradient descent method) is used for parameter optimization to generate the multi-level relaxation correlation parameters. Finally, the multi-level relaxation correlation parameters describing the change of the mechanical properties of the mucosal tissue are obtained.

[0092] The following is a specific example: During the critical period of osseointegration 3 - 6 weeks after oral implantation, a real-time relaxation fluctuation model of the mucosal tissue under occlusal load is established through a three-dimensional strain gradient tensor (150 μm in the X direction, 120 μm in the Y direction, 100 μm in the Z direction), and the real-time relaxation fluctuation characteristics of the target contact surface are extracted (high frequency 0.2 μm, low frequency 0.1 μm); the temperature compensation algorithm is used to eliminate the environmental temperature interference (initial temperature 25°C, fluctuation range 23°C - 27°C), and the corrected real-time relaxation fluctuation characteristics are generated (high frequency 0.18 μm, low frequency 0.09 μm), and then input into the dynamic matching framework to generate the composite load relaxation fluctuation parameters (compressive relaxation component 0.48 kPa / s, shear relaxation component 0.28 kPa / s); according to the density gradient distribution of the distributed network (1200 roots / mm² on the surface layer, 800 roots / mm² on the deep layer), the spatio-temporal superposition effect of the composite load relaxation fluctuation parameters is quantified to generate the time window cumulative function (f(t)=200 + 10t, t is time, unit: week); the time window cumulative function is dynamically coupled with the density gradient distribution to obtain the dynamic coupling result (offset 150 μm), and it is matched with the target dynamic decay curve (compressive relaxation component decay rate 0.5 kPa / s, shear relaxation component decay rate 0.3 kPa / s) to generate the multi-level relaxation correlation parameters (compressive relaxation component decay rate parameter 0.384 kPa / s, shear relaxation component decay rate parameter 0.196 kPa / s), providing a scientific basis for postoperative monitoring and early warning, and effectively reducing the risk of peri-implantitis.

[0093] Through the above steps, the mechanical property changes of the mucosal tissue under occlusal load are accurately monitored through the real-time relaxation fluctuation model; the environmental interference is eliminated by using the temperature compensation algorithm to ensure the accuracy of the characteristic data; through the quantification of the spatio-temporal superposition effect and dynamic coupling, multi-level relaxation correlation parameters are generated to accurately identify local stress anomalies; based on the dynamic early warning mechanism, the occlusal load distribution is adjusted in a timely manner to effectively reduce the risk of peri-implantitis; a scientific basis is provided for postoperative management, improving the success rate of implant surgery and patient satisfaction.

[0094] In order to more comprehensively and precisely describe the dynamic attenuation process of the mechanical properties of the mucosal tissue after oral implantation, in some embodiments, the mechanical response data of the oral mucosal tissue under occlusal load and the three-dimensional strain gradient tensor of the target contact surface obtained in step 101 are combined with a preset stress-strain analysis model to establish a target dynamic decay curve of the elastic modulus of the oral mucosal tissue during the entire healing period. The target contact surface is the contact surface between the implant and the oral mucosal tissue, and includes: Step 601: Obtain the mechanical response data of the oral mucosa tissue under occlusal load, extract the compression relaxation component, shear relaxation component, and elastic modulus from the mechanical response data, and analyze the decay rates of the compression relaxation component and the shear relaxation component changing with time through a preset stress-strain analysis model to generate a decay rate weight.

[0095] In Step 601, the compression relaxation component is used to describe the relaxation characteristics of the mucosal tissue under compressive load. The shear relaxation component is used to describe the relaxation characteristics of the mucosal tissue under shear load. The decay rate weight is used to quantify the difference in the decay rates of the compression relaxation component and the shear relaxation component.

[0096] In the embodiment of the present application, first, the mechanical response data of the oral mucosa tissue under occlusal load is collected in real time through a distributed network. For example, the strain distribution data is 150 μm, and the stress distribution data is 0.5 kPa. Then, the finite element analysis method and / or Fourier transform method are used to extract the compression relaxation component (0.5 kPa / s) and the shear relaxation component (0.3 kPa / s). The preset stress-strain analysis model can analyze its decay rate changing with time through time series analysis (such as the sliding window method). For example, the decay rate of the compression relaxation component is 0.05 kPa / s², and the decay rate of the shear relaxation component is 0.03 kPa / s². Finally, a weighted average algorithm is used to generate the decay rate weight. For example, the weight of the compression relaxation component is 0.8, and the weight of the shear relaxation component is 0.7.

[0097] Step 602: Based on the decay rate weight, establish a multi-scale decay coefficient matrix, which is used to describe the decay rate weight distribution of the compression relaxation component and the shear relaxation component in different healing stages of the entire healing process. The healing stages include the critical period of osseointegration.

[0098] In Step 602, the healing stages include different stages such as the initial postoperative period and the critical period of osseointegration.

[0099] In the embodiment of the present application, first, based on the decay rate weight (compression 0.8, shear 0.7), a multi-scale decay coefficient matrix is established using a matrix construction algorithm (such as tensor decomposition). For example, the weight of the compression relaxation component in the critical period of osseointegration in the matrix is 0.8, and the weight of the shear relaxation component is 0.7, generating the decay rate weight distribution describing the entire healing process.

[0100] Step 603: According to the multi-scale attenuation coefficient matrix, divide the dynamic attenuation stage of the elastic modulus, hierarchically correlate the attenuation trajectory combining the dynamic attenuation stage, the compressive relaxation component and the shear relaxation component, and generate the time-varying gradient parameter of the oral mucosa tissue during the entire healing process. The attenuation trajectory refers to the curves of the compressive relaxation component and the shear relaxation component changing with time within the healing cycle, reflecting the dynamic attenuation process of the mechanical properties of the oral mucosa tissue.

[0101] In step 603, the attenuation trajectory only describes the curves of the compressive relaxation component and the shear relaxation component changing with time, which are local features. The target dynamic attenuation curve is used to describe the curve of the elastic modulus of the entire mucosa tissue changing with time, which is a global feature. The hierarchical correlation process is divided into three stages: dividing the dynamic attenuation stage, matching the attenuation trajectory with the dynamic attenuation stage, and generating the time-varying gradient parameter. The first stage is to divide the healing cycle into different stages according to the multi-scale attenuation coefficient matrix using a clustering algorithm. For example: the initial postoperative period (0 - 2 weeks), the critical period of osseointegration (3 - 6 weeks), and the late healing period (after 6 weeks). The second stage is to match the attenuation trajectories of the compressive relaxation component f(t)=0.5 - 0.05t and the shear relaxation component g(t)=0.3 - 0.03t with the dynamic attenuation stage respectively. For example: in the initial postoperative period, the attenuation value of the compressive relaxation component is 0.5 kPa / s, and the attenuation value of the shear relaxation component is 0.3 kPa / s; in the critical period of osseointegration, the attenuation value of the compressive relaxation component is 0.4 kPa / s, and the attenuation value of the shear relaxation component is 0.24 kPa / s. The third stage is to hierarchically correlate the attenuation trajectory with the dynamic attenuation stage through the dynamic time warping algorithm to generate the time-varying gradient parameter. For example: the time-varying gradient of the compressive relaxation component is 0.05 kPa / s², and the time-varying gradient of the shear relaxation component is 0.03 kPa / s².

[0102] In the embodiment of the present application, first, according to the multi-scale attenuation coefficient matrix, use a clustering algorithm to divide the dynamic attenuation stage of the elastic modulus, such as the initial postoperative period (0 - 2 weeks) and the critical period of osseointegration (3 - 6 weeks). Then, hierarchically correlate the attenuation trajectories of the compressive relaxation component and the shear relaxation component. For example, use the dynamic time warping algorithm to match the attenuation trajectories. The attenuation trajectory of the compressive relaxation component is f(t)=0.5 - 0.05t, and the attenuation trajectory of the shear relaxation component is g(t)=0.3 - 0.03t. Finally, generate the time-varying gradient parameter. For example, the time-varying gradient of the compressive relaxation component is 0.05 kPa / s², and the time-varying gradient of the shear relaxation component is 0.03 kPa / s².

[0103] Step 604: Through a distributed network, obtain the three-dimensional strain gradient tensor of the target contact surface in real time according to the preset correlation relationship of the collagen fiber orientation.

[0104] In step 604, the preset correlation relationship of the collagen fiber orientation refers to correlating the distribution direction of the collagen fibers with the three-dimensional strain gradient tensor of the target contact surface through a distributed network to optimize the accuracy of data collection and analysis. The specific process is to use image processing techniques (such as CT scanning and three-dimensional reconstruction) to obtain the distribution data of the collagen fibers in the mucosal tissue. According to the orientation of the collagen fibers (for example, 1200 fibers / mm² on the surface layer and 800 fibers / mm² in the deep layer), a mathematical model of the collagen fiber orientation is established. For example, a vector field is used to represent the distribution direction of the collagen fibers. A distributed network is deployed on the target contact surface, and the sensor nodes are arranged according to the mathematical model of the collagen fiber orientation. For example, more sensors are deployed in the dense area of the collagen fibers (surface layer), and fewer sensors are deployed in the sparse area (deep layer). The sensor nodes collect the three-dimensional strain data (X direction, Y direction, Z direction) of the target contact surface in real time. The three-dimensional strain data collected by the sensor nodes is correlated with the mathematical model of the collagen fiber orientation. For example, a spatial mapping algorithm (such as interpolation method or gridding method) is used to map the strain data onto the distribution direction of the collagen fibers. According to the correlation relationship of the collagen fiber orientation, the data extraction process of the three-dimensional strain gradient tensor is optimized. For example, in the dense area of the collagen fibers, a higher-precision interpolation algorithm is used to extract the strain data. The optimized strain data is integrated to generate a three-dimensional strain gradient tensor. For example, the strain in the X direction is 150 μm, the strain in the Y direction is 120 μm, and the strain in the Z direction is 100 μm.

[0105] In the embodiment of the present application, first, the three-dimensional strain gradient data of the target contact surface is collected in real time through a distributed network. For example, the strain in the X direction is 150 μm, the strain in the Y direction is 120 μm, and the strain in the Z direction is 100 μm. Then, according to the preset collagen fiber orientation (for example, 1200 fibers / mm² on the surface layer and 800 fibers / mm² in the deep layer), image processing algorithms (such as edge detection and feature extraction) are used to optimize the data extraction process of the three-dimensional strain gradient tensor.

[0106] Step 605: Based on the three-dimensional strain gradient tensor, combined with the time-varying gradient parameter, perform multi-scale stress relaxation iterative correction on the stress distribution pattern in the preset stress-strain analysis model to generate an initial dynamic decay curve of the elastic modulus.

[0107] In step 605, the multi-scale stress relaxation iterative correction is used to optimize the accuracy of the stress distribution pattern. The initial dynamic decay curve is used to describe the initial curve of the change of the elastic modulus over time.

[0108] In the embodiments of the present application, first, based on the three-dimensional strain gradient tensor (150 μm in the X direction, 120 μm in the Y direction, 100 μm in the Z direction), combined with the time-varying gradient parameters (compression 0.05 kPa / s², shear 0.03 kPa / s²), the iterative optimization algorithm (such as the gradient descent method) is used to perform multi-scale stress relaxation iterative correction on the stress distribution pattern in the preset stress-strain analysis model. For example, an initial dynamic decay curve is generated through finite element analysis. The decay curve of the compression relaxation component is f(t)=0.5 - 0.05t, and the decay curve of the shear relaxation component is g(t)=0.3 - 0.03t.

[0109] Step 606: Using the biomechanical property constraints of the entire healing cycle of the oral mucosa tissue, perform phase synchronization adjustment on the decay rates of the compression relaxation component and the shear relaxation component in the initial dynamic decay curve of the elastic modulus, so that the decay rates are spatially and temporally distributed to match the bite load amplitude during the critical period of osseointegration, and obtain the decay trajectory of the compression relaxation component and the decay trajectory of the shear relaxation component.

[0110] In step 606, based on the biomechanical property constraints, use the initial dynamic decay curve to fit the mechanical property change law of the mucosal tissue. Take the fitting result as a constraint condition to adjust the decay rates of the compression relaxation component and the shear relaxation component. Spatially and temporally distributed matching means that the bite load amplitude data during the critical period of osseointegration is collected in real time through a sensor network. For example, the bite load amplitude is 0.5 kPa. Use spatio-temporal distribution modeling techniques (such as finite element analysis) to generate a spatio-temporal distribution model of the bite load amplitude. Use a phase synchronization algorithm (such as wavelet transform or dynamic time warping) to adjust the decay rates of the compression relaxation component and the shear relaxation component to synchronize with the spatio-temporal distribution model of the bite load amplitude. For example, the decay rate of the compression relaxation component is adjusted to 0.04 kPa / s², and the decay rate of the shear relaxation component is adjusted to 0.02 kPa / s². Match the adjusted decay rates with the spatio-temporal distribution model of the bite load amplitude. For example, use a spatio-temporal matching algorithm (such as dynamic programming or the least squares method) to optimize the matching result. Ensure that the decay rates of the compression relaxation component and the shear relaxation component are consistent with the change trend of the bite load amplitude in terms of time and space. Generate the decay trajectory of the compression relaxation component and the decay trajectory of the shear relaxation component according to the matching result. For example, the decay trajectory of the compression relaxation component is f(t)=0.5 - 0.04t, and the decay trajectory of the shear relaxation component is g(t)=0.3 - 0.02t.

[0111] In the embodiments of the present application, first, using biomechanical property constraints (such as the variation law of tissue elastic modulus), the phase synchronization algorithm (such as wavelet transform) is used to perform phase synchronization adjustment on the initial dynamic decay curve. For example, the decay rate of the compression relaxation component is adjusted to 0.04 kPa / s², and the decay rate of the shear relaxation component is adjusted to 0.02 kPa / s². Then, the adjusted decay rate is matched with the amplitude of the occlusal load during the critical period of osseointegration in terms of spatio-temporal distribution. For example, a spatio-temporal matching algorithm (such as dynamic programming) is used to optimize the matching result. Finally, the decay trajectory of the compression relaxation component (f(t) = 0.5 - 0.04t) and the decay trajectory of the shear relaxation component (g(t) = 0.3 - 0.02t) are generated.

[0112] Step 607: Dynamically superimpose the decay trajectory of the compression relaxation component, the decay trajectory of the shear relaxation component, and the weights of the multi-scale decay coefficient matrix to generate the target dynamic decay curve of the elastic modulus.

[0113] In step 607, a specific example of the dynamic superposition process is as follows: t represents time. Decay trajectory of the compression relaxation component: The decay trajectory of the compression relaxation component is f(t) = 0.5 - 0.04t. Decay trajectory of the shear relaxation component: The decay trajectory of the shear relaxation component is g(t) = 0.3 - 0.02t. Weights of the multi-scale decay coefficient matrix: The weight of the compression relaxation component is 0.8, and the weight of the shear relaxation component is 0.7. Dynamic superposition calculation: Use the weighted average algorithm to dynamically superimpose the decay trajectory of the compression relaxation component, the decay trajectory of the shear relaxation component, and the weights of the multi-scale decay coefficient matrix.

[0114] For example: h(t) = 0.8×f(t) + 0.7×g(t), h(t) = 0.8×(0.5 - 0.04t) + 0.7×(0.3 - 0.02t), h(t) = 0.4 - 0.032t + 0.21 - 0.014t, h(t) = 0.61 - 0.046t. Generate the target dynamic decay curve: The target dynamic decay curve of the elastic modulus is h(t) = 0.61 - 0.046t.

[0115] In the embodiments of the present application, first, the decay trajectory of the compression relaxation component, the decay trajectory of the shear relaxation component, and the weights of the multi-scale decay coefficient matrix are dynamically superimposed, and the weighted average algorithm is used to generate the target dynamic decay curve. Finally, the target dynamic decay curve describing the dynamic change of the mechanical properties of the mucosal tissue is obtained.

[0116] The following is a specific example: During the critical period of osseointegration 3 - 6 weeks after oral implantation, the mechanical response data (strain 150μm, stress 0.5kPa) of mucosal tissue under occlusal load is collected in real time through a distributed network. The compression relaxation component (0.5kPa / s) and shear relaxation component (0.3kPa / s) are extracted using a preset stress - strain analysis model, and the attenuation rate weights (compression 0.8, shear 0.7) are generated; Based on the attenuation rate weights, a multi - scale attenuation coefficient matrix is established using a matrix construction algorithm, the dynamic attenuation stage of the elastic modulus is divided, and a time - varying gradient parameter (compression 0.05kPa / s², shear 0.03kPa / s²) is generated; The three - dimensional strain gradient tensor of the target contact surface (150μm in the X - direction, 120μm in the Y - direction, 100μm in the Z - direction) is obtained in real time through a distributed network. Combining with the time - varying gradient parameter, the stress distribution pattern in the preset stress - strain analysis model is iteratively corrected by a multi - scale stress relaxation using an iterative optimization algorithm, and an initial dynamic attenuation curve (compression f(t)=0.5 - 0.05t, shear g(t)=0.3 - 0.03t) is generated; Using the biomechanical property constraint, the phase - synchronization algorithm is used to adjust the phase synchronization of the initial dynamic attenuation curve, and the attenuation trajectories of the compression relaxation component (f(t)=0.5 - 0.04t) and shear relaxation component (g(t)=0.3 - 0.02t) are generated; The attenuation trajectories of the compression relaxation component, the shear relaxation component, and the weights of the multi - scale attenuation coefficient matrix are dynamically superimposed to generate the target dynamic attenuation curve (h(t)=0.4 - 0.03t), providing a scientific basis for postoperative monitoring and early warning.

[0117] Through the method of these seven steps, the refinement and intelligence of the wound monitoring during the critical period of osseointegration 3 - 6 weeks after oral implantation are realized. Starting from obtaining the mechanical response data and generating the attenuation rate weights, to establishing the multi - scale attenuation coefficient matrix, generating the time - varying gradient parameters, obtaining the three - dimensional strain gradient tensor in real time, and finally generating the target dynamic attenuation curve, this method not only improves the prediction accuracy of abnormal wound healing after implantation, but also enhances the ability of early warning. Each step is closely linked, forming a complete risk assessment and early warning system, effectively preventing complications such as peri - implantitis caused by the lag of mucosal elastic recovery, greatly improving the success rate of implant surgery and the quality of patient rehabilitation, and ensuring the best treatment effect. This method provides comprehensive and accurate monitoring means, helps to detect and handle potential risks in time, and guarantees the health of patients.

[0118] In order to obtain the three - dimensional strain gradient tensor of the target contact surface after oral implantation more accurately, in some embodiments, the step of obtaining the three - dimensional strain gradient tensor of the target contact surface in real time through a distributed network according to the preset association relationship of the collagen fiber orientation in step 604 includes: Step 701: According to the preset density gradient distribution of the distributed network of collagen fibers, collect the multi-axial strain signals of the target contact surface, and use the temperature compensation algorithm to eliminate the environmental temperature interference of the multi-axial strain signals, and generate a multi-scale strain gradient vector.

[0119] In step 701, the sensing unit is a fiber Bragg grating sensor, and the distributed network is a sensor array composed of multiple distributed fiber Bragg grating sensors. In the embodiments of the present application, the fiber Bragg grating sensor can be used to collect multi-axial strain signals. The multi-axial strain signals include strain data in the X direction, Y direction, and Z direction, and are used to describe the mechanical property changes of the target contact surface. The multi-scale strain gradient vector is used to describe the strain gradient change characteristics of the target contact surface at different scales.

[0120] In the embodiments of the present application, first, according to the preset density gradient distribution of the distributed network of collagen fibers, the multi-axial strain signals of the target contact surface are collected in real time through the sensor network. For example, the strain in the X direction is 150 μm, the strain in the Y direction is 120 μm, and the strain in the Z direction is 100 μm. Then, the temperature compensation algorithm is used to eliminate the environmental temperature interference (temperature fluctuation ±2°C), and the corrected multi-axial strain signals are generated. For example, the strain in the X direction is corrected to 148 μm, the strain in the Y direction is corrected to 118 μm, and the strain in the Z direction is corrected to 98 μm. Finally, a multi-scale strain gradient vector is generated. For example, the gradient vector in the X direction is 148 μm, the gradient vector in the Y direction is 118 μm, and the gradient vector in the Z direction is 98 μm.

[0121] Step 702: Geometrically align the multi-scale strain gradient vector with the preset collagen fiber orientation to generate a multi-scale strain gradient distribution matrix, and the multi-scale strain gradient distribution matrix includes bite load components.

[0122] In step 702, the bite load component is used to describe the mechanical property changes of the mucosal tissue under the action of the bite load.

[0123] In the embodiments of the present application, first, the multi-scale strain gradient vector (148 μm in the X direction, 118 μm in the Y direction, 98 μm in the Z direction) is geometrically aligned with the preset collagen fiber orientation. For example, the interpolation method or the grid method is used to optimize the data distribution. Then, a multi-scale strain gradient distribution matrix is generated. For example, the bite load component in the matrix is 0.5 kPa. Finally, a multi-scale strain gradient distribution matrix describing the strain gradient distribution of the target contact surface is obtained.

[0124] Step 703: Based on the bite load component, combined with the spatial distribution parameters of the sensing unit, reconstruct the strain gradient tensor of the target contact surface in three-dimensional space to generate a three-dimensional strain gradient tensor.

[0125] In step 703, the spatial distribution parameters of the sensing unit refer to the parameters describing the distribution of sensor nodes on the target contact surface, including information such as node density, position, and direction. The sources of the spatial distribution parameters are sensor network deployment, node position and direction data acquisition, and spatial distribution parameter modeling.

[0126] In the embodiment of the present application, the occlusal load component is extracted from the multi-scale strain gradient distribution matrix, a strain distribution model in a three-dimensional space is established according to the spatial distribution parameters of the sensing unit, and the occlusal load component is spatially reconstructed in the strain distribution model to generate a three-dimensional strain gradient tensor.

[0127] In the embodiment of the present application, first, based on the occlusal load component (0.5 kPa), combined with the spatial distribution parameters of the sensing unit (such as a node density of 1200 roots / mm²), a numerical simulation algorithm (such as finite element analysis) is used to reconstruct the strain gradient tensor of the target contact surface in a three-dimensional space. For example, the strain gradient in the X direction is 148 μm, the strain gradient in the Y direction is 118 μm, and the strain gradient in the Z direction is 98 μm. Finally, a three-dimensional strain gradient tensor is generated to provide high-precision data support for subsequent analysis.

[0128] The following is a specific example: During the critical period of bone integration 3 - 6 weeks after oral implantation, multi-axial strain signals (150 μm in the X direction, 120 μm in the Y direction, 100 μm in the Z direction) of the target contact surface are collected through a distributed network according to the preset density gradient distribution of collagen fibers (1200 roots / mm² on the surface layer and 800 roots / mm² on the deep layer), and the temperature compensation algorithm is used to eliminate the environmental temperature interference (temperature fluctuation ±2 °C) to generate a multi-scale strain gradient vector (148 μm in the X direction, 118 μm in the Y direction, 98 μm in the Z direction); the multi-scale strain gradient vector is geometrically spatially aligned with the preset collagen fiber orientation to generate a multi-scale strain gradient distribution matrix (occlusal load component 0.5 kPa); based on the occlusal load component, combined with the spatial distribution parameters of the sensing unit (node density 1200 roots / mm²), 148 μm, 118 μm, and 98 μm are used as the elements on the diagonal of the matrix, and the values of the non-diagonal elements are calculated. Specifically, k = c × occlusal load, c = 0.1, which can be determined according to material characteristics and experimental data. The occlusal load is 0.5 kPa, and k = 0.05 kPa. f = node density / 1000.

[0129] The non-diagonal elements can be calculated in the following way: ; where is 148 μm, is 118 μm, is 98 μm.

[0130] By generating the element values on the non - diagonal to obtain a 3×3 matrix, which is a three - dimensional strain gradient tensor, the embodiments of the present application can reconstruct the strain gradient tensor of the target contact surface in three - dimensional space, providing a scientific basis for postoperative monitoring and early warning.

[0131] Through the methods of these three steps, a complete risk assessment and early warning system is formed, effectively preventing complications such as peri - implantitis caused by the lag of mucosal elastic recovery, greatly improving the success rate of implant surgery and the quality of patient recovery, and ensuring the best treatment effect. By introducing multi - scale strain gradient vectors and geometric space alignment techniques, the embodiments of the present application provide a more accurate description of strain distribution, thus better reflecting the mechanical behavior changes of mucosal tissues at different healing stages and improving the reliability and accuracy of the overall monitoring system.

[0132] Figure 2 FIG. shows a schematic structural diagram of an intelligent prediction and early warning system for oral implant risks provided by an embodiment of the present application, as Figure 2 shown, the system includes: An acquisition module 21, configured to acquire the mechanical response data of the oral mucosal tissue under occlusal load and the three - dimensional strain gradient tensor of the target contact surface, and establish a target dynamic decay curve of the elastic modulus of the oral mucosal tissue throughout the healing cycle in combination with a preset stress - strain analysis model, where the target contact surface is the contact surface between the implant and the oral mucosal tissue; An analysis module 22, configured to perform a coupled analysis on the three - dimensional strain gradient tensor and the target dynamic decay curve of the elastic modulus to generate multi - level relaxation correlation parameters, and analyze the stress conduction path offset of the target contact surface through a lightweight network in combination with the multi - level relaxation correlation parameters; A generation module 23, configured to generate a hierarchical early warning instruction according to the spatio - temporal correlation between the stress conduction path offset and a preset biomechanical threshold of the healing stage.

[0133] Figure 2 The intelligent prediction and early warning system for oral implant risks described above can execute Figure 1 the intelligent prediction and early warning method for oral implant risks described in the embodiments shown, and its implementation principle and technical effects will not be elaborated. For the intelligent prediction and early warning system for oral implant risks in the above - mentioned embodiments, the specific ways for each module and unit to perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0134] In a possible design, Figure 2 the intelligent prediction and early warning system for oral implant risks in the embodiments shown can be implemented as a computing device, as Figure 3As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, and the one or more computer instructions are called and executed by the processing component 32.

[0135] The processing component 32 above Figure 1 An intelligent prediction and early warning method for oral implant risks in the above embodiment.

[0136] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0137] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0138] Of course, the computing device may also necessarily include other components, such as an input / output interface, a display component, a communication component, etc. The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0139] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources leased or purchased from the cloud computing platform.

[0140] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 An intelligent prediction and early warning method for oral implant risks in the shown embodiment.

[0141] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0142] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent prediction and early warning method for oral implant risks, characterized in that, An intelligent device applied to the monitoring of abnormal healing of implant surgery wounds, comprising: Obtain the mechanical response data of the oral mucosa tissue under occlusal load and the three-dimensional strain gradient tensor of the target contact surface, and combine with a preset stress-strain analysis model to establish a target dynamic attenuation curve of the elastic modulus of the oral mucosa tissue during the entire healing cycle, where the target contact surface is the contact surface between the implant and the oral mucosa tissue; Perform a coupling analysis on the three-dimensional strain gradient tensor and the target dynamic attenuation curve of the elastic modulus to generate multi-level relaxation correlation parameters, and analyze the stress conduction path offset of the target contact surface through a lightweight network combined with the multi-level relaxation correlation parameters; Generate a hierarchical warning instruction according to the spatio-temporal correlation between the stress conduction path offset and the biomechanical threshold of the preset healing stage; The performing a coupling analysis on the three-dimensional strain gradient tensor and the target dynamic attenuation curve of the elastic modulus to generate multi-level relaxation correlation parameters, and analyzing the stress conduction path offset of the target contact surface through a lightweight network combined with the multi-level relaxation correlation parameters includes: Based on the target dynamic attenuation curve of the elastic modulus, establish a dynamic matching framework by combining the stress distribution pattern in the preset stress-strain analysis model with the correlation relationship of the preset collagen fiber orientation; Based on the three-dimensional strain gradient tensor, determine the real-time relaxation fluctuation characteristics of the target contact surface under occlusal load, remove the environmental interference in the real-time relaxation fluctuation characteristics, and combine the dynamic matching framework and the density gradient distribution of the distributed network to quantify the spatio-temporal superposition effect of the occlusal load amplitude during the key period of osseointegration in different healing stages during the entire healing process, and generate multi-level relaxation correlation parameters. The distributed network is the physical network architecture of collagen fibers in the oral mucosa tissue, and the multi-level relaxation correlation parameters are used to reflect the mechanical property changes of the oral mucosa tissue during the entire healing cycle; Based on the multi-level relaxation correlation parameters, construct a stress conduction path model of the target contact surface, and use a lightweight network to perform a coupling analysis on the dynamic matching framework and the stress conduction path model, and output the stress conduction path offset. The lightweight network adopts a depthwise separable convolution architecture.

2. The method according to claim 1, wherein The based on the multi-level relaxation correlation parameters, constructing a stress conduction path model of the target contact surface, using a lightweight network to perform a coupling analysis on the dynamic matching framework and the stress conduction path model, and outputting the stress conduction path offset includes: Based on the multi-level relaxation correlation parameters, use the sensing units of the distributed network as nodes and the stress distribution pattern as edges to establish a stress conduction path model of the target contact surface; Use a lightweight network to decompose the stress conduction path model into spatial dimension features and channel dimension features, optimize the spatial dimension features in combination with the occlusal load direction of the three-dimensional strain gradient tensor, and optimize the channel dimension features in combination with the dynamic attenuation phase of the target dynamic attenuation curve to obtain the processed spatial dimension features and the processed channel dimension features; Compare the strain distribution data in the processed spatial dimension features point by point with the node stress distribution in the stress conduction path model to generate a node stress conduction response sequence. Compare the attenuation rate in the processed channel dimension features edge by edge with the edge stress distribution in the stress conduction path model to generate an edge stress conduction response sequence. Combine the node stress conduction response sequence and the edge stress conduction response sequence to generate a multi-scale stress conduction response sequence; Compare the attenuation rate of the compression relaxation component and the shear relaxation component in the dynamic matching framework to obtain an attenuation rate difference. According to the attenuation rate difference, perform path offset cumulative calculation on the multi-scale stress conduction response sequence and output the stress conduction path offset.

3. The method according to claim 2, characterized in that, The step of performing path offset cumulative calculation on the multi-scale stress conduction response sequence according to the attenuation rate difference and outputting the stress conduction path offset includes: Establish a relaxation attenuation rate difference model of the target contact surface according to the attenuation rate difference; According to the spatio-temporal superposition effect of the multi-scale stress conduction response sequence, superimpose the stress distribution pattern in the preset stress-strain analysis model and the density gradient distribution of the preset distributed network of collagen fibers in the relaxation attenuation rate difference model to generate a cumulative path offset vector; Based on the real-time relaxation fluctuation characteristics, perform phase synchronization filtering on the cumulative path offset vector to eliminate the environmental temperature interference of the distributed network and output a corrected cumulative path offset vector; Perform dynamic weighted fusion on the corrected cumulative path offset vector, the compression relaxation component and the shear relaxation component in the dynamic matching framework, and adjust the weighting coefficient according to the dynamic attenuation phase during the dynamic weighted fusion process to generate a path offset dynamic correlation parameter; Based on the dynamic interaction coupling result of the path offset dynamic correlation parameter and the multi-level relaxation correlation parameter, perform weight iterative update on the nodes and edges of the stress conduction path model through the distributed network and output the stress conduction path offset.

4. The method according to claim 1, wherein The step of determining the real-time relaxation fluctuation characteristics of the target contact surface under the occlusal load based on the three-dimensional strain gradient tensor, removing the environmental interference in the real-time relaxation fluctuation characteristics, combining the dynamic matching framework and the density gradient distribution of the distributed network, and quantifying the spatio-temporal superposition effect of the occlusal load amplitude during the key period of bone integration at different healing stages in the entire healing process to generate a multi-level relaxation correlation parameter includes: Establish a real-time relaxation fluctuation model of the oral mucosa tissue under the occlusal load based on the three-dimensional strain gradient tensor, and extract the real-time relaxation fluctuation characteristics of the target contact surface under the occlusal load from the real-time relaxation fluctuation model; Use a temperature compensation algorithm to eliminate the environmental temperature interference of the real-time relaxation fluctuation characteristics, generate a corrected real-time relaxation fluctuation characteristic, and input the corrected real-time relaxation fluctuation characteristic into the dynamic matching framework to generate a composite load relaxation fluctuation parameter; Quantify the spatio-temporal superposition effect on the composite load relaxation fluctuation parameters according to the density gradient distribution of the distributed network, and generate a time-window cumulative function; Dynamically couple the time-window cumulative function with the density gradient distribution in units of time to obtain a dynamic coupling result. Match the dynamic coupling result with the target dynamic decay curve to generate multi-level relaxation correlation parameters. The multi-level relaxation correlation parameters include the decay rate parameters of the compressive relaxation component and the shear relaxation component. The decay rate parameter of each component is the product of the corresponding decay rate and the corresponding weight.

5. The method according to claim 1, wherein Obtain the mechanical response data of the oral mucosa tissue under the occlusal load and the three-dimensional strain gradient tensor of the target contact surface, and combine with a preset stress-strain analysis model to establish a target dynamic decay curve of the elastic modulus of the oral mucosa tissue during the entire healing period. The target contact surface is the contact surface between the implant and the oral mucosa tissue, including: Obtain the mechanical response data of the oral mucosa tissue under the occlusal load, extract the compressive relaxation component, the shear relaxation component, and the elastic modulus from the mechanical response data, and analyze the decay rates of the compressive relaxation component and the shear relaxation component changing with time through a preset stress-strain analysis model to generate decay rate weights; Based on the decay rate weights, establish a multi-scale decay coefficient matrix, which is used to describe the decay rate weight distribution of the compressive relaxation component and the shear relaxation component in different healing stages of the entire healing process. The healing stages include the critical period of osseointegration; According to the multi-scale decay coefficient matrix, divide the dynamic decay stage of the elastic modulus, and hierarchically correlate the dynamic decay stage, the decay trajectories of the compressive relaxation component and the shear relaxation component to generate time-varying gradient parameters of the oral mucosa tissue during the entire healing process. The decay trajectory refers to the curves of the compressive relaxation component and the shear relaxation component changing with time during the healing period, reflecting the dynamic decay process of the mechanical properties of the oral mucosa tissue; The three-dimensional strain gradient tensor of the target contact surface is obtained in real time through a distributed network according to the preset correlation relationship of the collagen fiber orientation; Based on the three-dimensional strain gradient tensor, combine the time-varying gradient parameters to perform multi-scale stress relaxation iterative correction on the stress distribution pattern in the preset stress-strain analysis model to generate an initial dynamic decay curve of the elastic modulus; Use the biomechanical property constraints of the entire healing period of the oral mucosa tissue to perform phase synchronization adjustment on the decay rates of the compressive relaxation component and the shear relaxation component in the initial dynamic decay curve of the elastic modulus, so that the decay rates are spatially and temporally distributed to match the occlusal load amplitude during the critical period of osseointegration, and obtain the decay trajectories of the compressive relaxation component and the shear relaxation component; Dynamically superimpose the decay trajectories of the compressive relaxation component, the decay trajectories of the shear relaxation component, and the weights of the multi-scale decay coefficient matrix to generate a target dynamic decay curve of the elastic modulus.

6. The method according to claim 5, wherein The real-time acquisition of the three-dimensional strain gradient tensor of the target contact surface according to the preset association relationship of the collagen fiber orientation through a distributed network includes: Collecting multi-axial strain signals of the target contact surface according to the density gradient distribution of the preset distributed network of collagen fibers, and using a temperature compensation algorithm to eliminate environmental temperature interference from the multi-axial strain signals to generate a multi-scale strain gradient vector; Geometrically aligning the multi-scale strain gradient vector with the preset collagen fiber orientation to generate a multi-scale strain gradient distribution matrix, where the multi-scale strain gradient distribution matrix includes bite load components; Based on the bite load components, combining the spatial distribution parameters of the sensing unit, reconstructing the strain gradient tensor of the target contact surface in three-dimensional space to generate a three-dimensional strain gradient tensor.

7. An intelligent prediction and early warning system for oral implant risks, characterized in that, Including: An acquisition module for acquiring the mechanical response data of the oral mucosa tissue under bite load and the three-dimensional strain gradient tensor of the target contact surface, and combining a preset stress-strain analysis model to establish a target dynamic decay curve of the elastic modulus of the oral mucosa tissue during the entire healing cycle, where the target contact surface is the contact surface between the implant and the oral mucosa tissue; An analysis module for coupling and analyzing the three-dimensional strain gradient tensor and the target dynamic decay curve of the elastic modulus to generate multi-level relaxation correlation parameters, and analyzing the stress conduction path offset of the target contact surface through a lightweight network in combination with the multi-level relaxation correlation parameters; A generation module for generating a hierarchical warning instruction according to the spatio-temporal correlation between the stress conduction path offset and the biomechanical threshold of the preset healing stage; The coupling analysis of the three-dimensional strain gradient tensor and the target dynamic decay curve of the elastic modulus to generate multi-level relaxation correlation parameters, and the analysis of the stress conduction path offset of the target contact surface through a lightweight network in combination with the multi-level relaxation correlation parameters includes: Based on the target dynamic decay curve of the elastic modulus, establishing a dynamic matching framework by combining the stress distribution pattern in the preset stress-strain analysis model with the association relationship of the preset collagen fiber orientation; Determining the real-time relaxation fluctuation characteristics of the target contact surface under bite load based on the three-dimensional strain gradient tensor, removing the environmental interference from the real-time relaxation fluctuation characteristics, and combining the dynamic matching framework and the density gradient distribution of the distributed network to quantify the spatio-temporal superposition effect of the bite load amplitude during the key period of bone integration in different healing stages of the entire healing process, generating multi-level relaxation correlation parameters, where the distributed network is the physical network architecture of collagen fibers in the oral mucosa tissue, and the multi-level relaxation correlation parameters are used to reflect the mechanical property changes of the oral mucosa tissue during the entire healing cycle; Based on the multi-level relaxation correlation parameters, constructing a stress conduction path model of the target contact surface, and using a lightweight network to perform coupling analysis on the dynamic matching framework and the stress conduction path model to output the stress conduction path offset, where the lightweight network adopts a depthwise separable convolution architecture.

8. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an intelligent prediction and early warning method for oral implant risks as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that, A computer program is stored, and when the computer program is executed by a computer, it implements an intelligent prediction and early warning method for oral implant risks as described in any one of claims 1 to 6.

Images