Fixed denture adjacency evaluation method, device and system and storage medium

Abstract

The invention relates to the technical field of false tooth adjacency, and discloses a fixed false tooth adjacency evaluation method, device and system and a storage medium. According to the evaluation method, adjacent force dynamic data are collected in real time through an MEMS piezoresistive sensor, laser scanning is synchronously adopted to obtain the three-dimensional shape of a contact surface, mechanical data are input into a regression model to analyze the tightness and the stability, and the evaluation result is obtained. Geometric features of three-dimensional data are extracted through a 3D convolutional neural network, finally, multi-modal analysis results are fused to generate an evaluation report containing contact quality multi-dimensional indexes, and the device comprises a data acquisition module, an intelligent analysis module and a data output module. By adopting multi-modal data fusion and an intelligent algorithm, fixed denture contact surface morphological mechanics synchronous analysis and dynamic monitoring are realized, quantitative evaluation indexes are generated through an automatic process, subjective judgment and static detection limitations of a traditional method are overcome, and adjacency quality evaluation precision and clinical efficiency are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of denture adjacency, and in particular to a method, device, system and storage medium for evaluating fixed denture adjacency. Background Art

[0002] Fixed denture restoration is a core treatment method in the field of oral rehabilitation. The contact quality between the adjacent surfaces and natural teeth directly affects the long-term stability of the restoration and the patient's oral health. Traditional clinical evaluation mainly relies on the doctor's visual inspection, articulating paper staining and manual probe palpation, supplemented by two-dimensional imaging examinations. Although these methods can preliminarily determine the contact tightness and morphological adaptability, they are limited by subjective experience and low-dimensional data collection capabilities, making it difficult to achieve accurate quantification of the mechanical state and geometric characteristics of the contact surface. With the popularization of digital dental technology, three-dimensional scanning, pressure sensing and other equipment have gradually been applied in clinical practice, but they mostly remain at the level of single-point data collection or static analysis, and have not yet formed a systematic dynamic evaluation system.

[0003] In existing technologies, detection methods based on a single modality have significant limitations: contact surface morphology detection equipment (such as intraoral scanners) can obtain high-precision three-dimensional models, but cannot simultaneously reflect the mechanical distribution during actual occlusion; although pressure sensing devices can measure the magnitude of adjacent forces, they lack correlation analysis with the geometric characteristics of the contact surface. In addition, traditional dynamic monitoring mostly uses low-frequency sampling technology, which makes it difficult to capture key details such as the initial stress release of the restoration and the instantaneous overload during chewing movements. These technical fragmentations often lead to the contradictory phenomena of "qualified morphology but patient discomfort" or "mechanical compliance but rapid debonding" in clinical practice, exposing the inherent defects of the current evaluation system in the continuity of the time dimension and the collaborative analysis of multiple parameters.

[0004] The above problems seriously restrict the standardization process and long-term success rate of fixed denture restoration. In view of the shortcomings of the existing technology, the present invention proposes a method, device, system and storage medium for fixed denture proximal assessment. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a method, device, system and storage medium for fixed denture adjacency assessment, which solves the problem of inaccurate clinical judgment caused by the separation of contact surface morphology and mechanical state assessment in fixed denture restoration.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] A first aspect of the present invention provides a method for evaluating the proximity of fixed dentures, comprising the following steps:

[0008] S1, real-time acquisition of the contact force data between the fixed denture and the adjacent teeth using a MEMS piezoresistive array sensor, and acquisition of three-dimensional data of the contact surface using a 635nm laser scanner;

[0009] S2. Inputting the proximity force data into a regression analysis model and simultaneously inputting the three-dimensional contact surface data into a 3D convolutional neural network to extract features and generate quantitative evaluation results, wherein the quantitative evaluation results include: tightness evaluation, position evaluation, and shape and area evaluation;

[0010] S3. Generate an assessment report based on the quantitative assessment results and upload it to the cloud platform for storage via an encrypted transmission protocol.

[0011] Preferably, the step S1 includes:

[0012] S1.1. The smart sensor dental floss with a built-in ±0.01N sensitivity pressure sensor monitors the proximity force in real time, measures the pressure changes in the contact area, and generates a pressure distribution map and force change curve;

[0013] S1.2. The micro end-port scanning device obtains three-dimensional data of the contact surface through laser scanning or optical image capture with a resolution of 0.05mm, and calculates the position, shape and area of ​​the contact surface.

[0014] Preferably, the step S2 includes:

[0015] S2.1. Training a convolutional neural network model to convert the three-dimensional contact surface data into a 64×64×32 voxel matrix and extracting geometric features using a channel attention mechanism. The geometric features include contact surface accuracy, shape alignment, and surface curvature distribution.

[0016] S2.2. Based on the geometric features and the proximity force time series data, establish a proximity force dynamic regression model, and use an optimization algorithm to adjust the regression coefficient β to minimize the prediction error;

[0017] S2.3. Perform weighted fusion of the geometric features with the tightness index and stability coefficient output by the regression model to generate a comprehensive score, and determine whether the contact surface position meets the preset conditions.

[0018] Preferably, the optimization algorithm in step S2.2 is the Levenberg-Marquardt algorithm, and the error in step S2.2 is defined by the following formula:

[0019]

[0020] Among them, β is the regression coefficient vector, is the model prediction value, F i is the measured adjacency force value at the i-th time point, and N is the total number of data sampling points.

[0021] Preferably, the preset conditions in step S2.3 are:

[0022] The contact point position satisfies:

[0023] Where x and y are the coordinate offsets of the contact point on the tooth cross section, z is the position along the long axis of the tooth, and H is the clinical crown height;

[0024] The contact area should be within the range of 1.5-2.0 mm in the anterior area. 2 , 2.0-3.0mm in the posterior area 2 , the contact force range is 1.0-2.5N.

[0025] A second aspect of the present invention provides a fixed denture proximal assessment device, which is applied to the above-mentioned fixed denture proximal assessment method, comprising:

[0026] The data acquisition module is equipped with a MEMS piezoresistive array sensor and a 635nm laser scanner to collect proximity force data and three-dimensional contact surface data in real time;

[0027] an intelligent analysis module, the input end of which is connected to the output end of the data acquisition module, and which includes a 3D-CNN processor and a Levenberg-Marquardt optimizer, and is used to perform feature extraction and mechanical analysis on the proximity force data and the three-dimensional contact surface data to generate a quantitative evaluation result;

[0028] The data output module has an input end connected to the output end of the intelligent analysis module, and is used to generate an evaluation report based on the quantitative evaluation results and transmit it to the cloud platform for storage.

[0029] Preferably, the intelligent analysis module includes:

[0030] Model training unit: Build a convolutional neural network architecture based on voxelized 3D data to extract contact surface geometric features;

[0031] Feature extraction unit: identifies irregular areas and alignment deviations on the contact surface through multi-scale curvature analysis;

[0032] Mechanical analysis unit: optimize the parameters of the dynamic adjacent force model and evaluate the tightness and stability of the contact force;

[0033] Comprehensive decision-making unit: Determines adjacency quality compliance based on preset location thresholds and area standards.

[0034] Preferably, the data acquisition module includes:

[0035] The pressure sensing unit monitors the dynamic pressure distribution between adjacent teeth in real time, and achieves ±0.01N sensitivity detection through MEMS piezoresistive array sensors;

[0036] The 3D scanning unit reconstructs the 3D topography of the contact surface with high precision, using a λ=635nm laser to scan at a 45° incident angle to generate point cloud data.

[0037] A third aspect of the present invention provides a fixed denture adjacency evaluation system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the fixed denture adjacency evaluation method as described above is executed.

[0038] A fourth aspect of the present invention provides a storage medium having a computer program stored thereon, wherein the computer program executes the fixed denture adjacency assessment method as described above when the computer program is run.

[0039] The present invention provides a method, device, system, and storage medium for evaluating the proximity of fixed dentures. The method has the following beneficial effects:

[0040] 1. The present invention integrates high-precision sensing, three-dimensional scanning and deep learning algorithms to synchronously analyze the morphological characteristics and mechanical state of the contact surface, solving the problem of contradictory conclusions caused by the separation of morphological detection and mechanical evaluation in traditional methods. Existing technologies can only measure geometric parameters or the size of adjacent forces separately and cannot correlate the relationship between the two. This solution uses cross-modal data fusion technology to achieve multi-dimensional joint diagnosis of contact quality for the first time.

[0041] 2. Based on the feature extraction of convolutional neural networks and quantitative calculation of regression models, the system automatically generates objective scores for indicators such as contact surface accuracy and tightness. Compared with manual measurement that relies on the doctor's experience, this technical solution avoids human visual errors and differences in operating techniques, making the evaluation results of different medical institutions and different operators repeatable and comparable.

[0042] 3. The present invention adopts high-frequency data acquisition and time series analysis algorithms to capture the changing trend of adjacent forces during the insertion and occlusion of fixed dentures in real time. Traditional static detection methods can only obtain instantaneous state data, while this solution uses continuous monitoring technology to effectively identify dynamic problems such as abnormal stress release and occlusal force fluctuations, providing complete process data support for clinical adjustments.

[0043] 4. Through an end-to-end automated processing architecture, the present invention integrates three-dimensional scanning, mechanical testing, and data analysis into a single workflow, and directly outputs a visual evaluation report. Compared with the complex process of existing technologies that require step-by-step operation of multiple devices and manual integration of data, this solution greatly reduces the operating threshold and improves diagnosis and treatment efficiency, and is particularly suitable for standardized applications in primary medical institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flow chart of the evaluation method of the present invention;

[0045] Figure 2 It is a process framework diagram of the device of the present invention;

[0046] Figure 3 Schematic diagram of the system structure diagram of the present invention.

[0047] Among them, 40, fixed denture proximity evaluation system; 41, processor; 42, memory; 43, storage medium. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0049] Please see the attached Figure 1 The embodiment of the present invention provides a method for evaluating the proximity of fixed dentures, comprising the following steps:

[0050] S1, real-time acquisition of the contact force data between the fixed denture and the adjacent teeth using a MEMS piezoresistive array sensor, and acquisition of three-dimensional data of the contact surface using a 635nm laser scanner;

[0051] Step S1.1 monitors the proximity force in real time using a smart sensor dental floss with a built-in ±0.01N sensitivity pressure sensor, including the following implementation process:

[0052] Physical Structure: The smart sensor dental floss consists of a pressure sensor, a signal conditioning unit, and a wireless transmission unit. The pressure sensor consists of a 5×5 array of MEMS piezoresistive sensors, with 0.5mm spacing between adjacent sensors. These sensors are connected to the operational amplifier of the signal conditioning unit via a flexible circuit. The wireless transmission unit integrates a Bluetooth 5.0 module for communication with the main control board.

[0053] Signal conversion and processing:

[0054] Mechanical signal conversion: The sensor converts the adjacent force F(t) into a voltage signal:

[0055] V(t)=200·F(t)+ε(t) (unit: mV);

[0056] in is Gaussian white noise.

[0057] Noise reduction processing: The signal conditioning unit uses a Butterworth low-pass filter to eliminate high-frequency noise. Its transfer function is:

[0058] (s is a complex frequency variable);

[0059] The filtered signal is discretized at a sampling rate of 100 Hz to generate a digital sequence {F i |i=1,2,...,N}.

[0060] Pressure distribution map generation: Divide the contact area into 0.1mm×0.1mm grids and calculate the pressure at each grid point by bilinear interpolation:

[0061]

[0062] Among them, F k is the measurement value of four adjacent sensors, w k is the distance weight coefficient.

[0063] The pressure distribution map accurately displays the force distribution in the contact area between the denture and adjacent teeth, reflecting the magnitude and uniformity of the contact force. This is crucial for assessing the tightness and uniformity of the contact area. By analyzing the pressure distribution map, the doctor can determine whether the fixed denture is in good contact with the adjacent teeth and whether there are areas of excessive or insufficient pressure.

[0064] Strength change curve construction: Time series data {F i} Perform cubic spline interpolation to generate the continuous function F(t) and its first-order derivative:

[0065] (Unit: N / s);

[0066] in, is the instantaneous rate of change of the adjacent force with time (i.e., the first-order derivative); F(t+0.01) is the measured value of the adjacent force at 0.01 seconds after time t; F(t-0.01) is the measured value of the adjacent force at 0.01 seconds before time t; 0.01 is the time step (i.e., time interval), corresponding to the sampling period of 100 Hz sampling rate; 0.02 is the total span of the time window (i.e., the total duration of 0.01 seconds before and after).

[0067] The force curve records the temporal trend of contact forces, reflecting the dynamic evolution of interproximal forces. This is crucial for assessing the stability of the contact area and the retention of fixed dentures. The force curve helps clinicians understand how interproximal areas behave under varying forces and whether there are any potential contact issues or other potential problems.

[0068] Step S1.2 acquires three-dimensional data by laser scanning with a resolution of 0.05 mm, including the following implementation process:

[0069] Physical Structure: The micro-end-port scanning device consists of a laser transmitter, an optical receiver, and a motion control unit. The laser transmitter uses a 635nm semiconductor laser with a pulse frequency of 1MHz; the optical receiver integrates a CMOS sensor with a pixel size of 1.4μm; and the motion control unit uses a stepper motor to drive the scanning head to rotate (0-180°).

[0070] Laser scanning technology can generate detailed three-dimensional point cloud data on the contact surface, providing the geometric shape and precise position of the contact surface. The high penetration of lasers ensures the acquisition of high-quality data in complex oral environments, and the micro-end-mouth scanning device can be flexibly operated even in confined spaces. Optical imaging technology uses a high-definition probe to capture images of the contact surface and performs pixel-level image processing to obtain detailed information such as the position, shape, and area of ​​the contact surface. These image data are converted into quantifiable three-dimensional data through image processing algorithms, ensuring high resolution and high accuracy of the contact surface data.

[0071] 3D point cloud generation: Calculate laser ranging values ​​using the time-of-flight method:

[0072]

[0073] Where Δt is the time difference between the transmitted and received pulses, and the scanning accuracy is ±0.02mm.

[0074] Coordinate transformation and reconstruction: The point cloud (x′, y′, z′) in the local coordinate system is transformed into the global coordinate system through the rotation matrix R and the translation vector T:

[0075]

[0076] Where R is a 3×3 rotation matrix, T=[t x ,t y ,t z ] T is the translation vector, which is pre-calibrated using a calibration plate.

[0077] Contact surface feature calculation:

[0078] Contact area: Calculate the surface area based on the Delaunay triangulation algorithm:

[0079]

[0080] Where A is the total area of ​​the contact surface (unit: mm 2 ); M is the total number of triangles generated by the Delaunay triangulation algorithm; v1, v2, and v3 are the coordinates of the three vertices of a single triangle (unit: mm), which belong to points in the 3D point cloud data; (v2-v1)×(v3-v1) is a vector cross product operation, and the result is a vector; is the normalization coefficient.

[0081] The standard for the anterior area is 1.5-2.0mm 2 , 2.0-3.0mm in the posterior area 2 .

[0082] Position deviation: contact surface center point (x c ,y c ,z c ) and the theoretical position (x0, y0, z0) must satisfy the following Euclidean distance:

[0083]

[0084] Where H is the clinical crown height, and the contact point should be located between the adjacent gingival 1 / 3 and the middle 1 / 3 (0.3H≤z c ≤0.5H).

[0085] S2. Inputting the proximity force data into a regression analysis model and simultaneously inputting the three-dimensional contact surface data into a 3D convolutional neural network to extract features and generate quantitative evaluation results, wherein the quantitative evaluation results include: tightness evaluation, position evaluation, and shape and area evaluation;

[0086] Data preprocessing and model training:

[0087] Voxelization of 3D data:

[0088] The three-dimensional point cloud data of the contact surface between the fixed denture and the adjacent teeth were obtained by a micro-end-mouth scanning device, and the point cloud was converted into a 64×64×32 voxel matrix using a voxelization algorithm. The voxel resolution was 0.05mm×0.05mm×0.05mm, and the value of each voxel was defined as:

[0089]

[0090] This step converts the raw scan data into a structured 3D matrix, providing a standardized format for input to the subsequent convolutional neural network (CNN). The voxel resolution (0.05mm) is set based on clinical needs to ensure that micron-level geometric deviations of the contact surface can be captured.

[0091] Data arrangement optimization:

[0092] Use genetic algorithms to optimize data arrangement, reduce the similarity of data with different labels and enhance the relevance of data of the same type. The objective function is:

[0093]

[0094] Among them, S inter is the cosine similarity of different label matrices, S intrais the similarity of the same label matrix, N is the total number of samples in the dataset, M i is the matrix representation of the i-th sample. After optimization, the discrimination between different categories of data is improved by 15%-20%.

[0095] By optimizing data arrangement and enhancing the internal consistency of similar data, the efficiency of CNN training is improved. This step is directly related to the accuracy of CNN in subsequent steps because the optimized data distribution is more conducive to feature extraction.

[0096] Logistic regression model construction:

[0097] Based on the pressure distribution map in the historical dataset of fixed denture proximal relationships, the target influencing factors were screened:

[0098] Factor screening condition: frequency of occurrence of pressure area f k ≥20% and overlap with clinical assessment results k ≥85%.

[0099] Model construction: The association between contiguity and clinical qualification rate was established through logistic regression model:

[0100] (Regularization coefficient λ = 0.01);

[0101] Where p is the probability of qualified adjacent fixed dentures, is the logarithmic probability, β0 is the intercept term of the regression model, β k is the kth independent variable F k The regression coefficient is the random error term

[0102] The target influencing factors (such as the specific pressure area value F k ) will serve as input variables for the dynamic regression model in the following steps to ensure the clinical relevance of the mechanical analysis.

[0103] Contact surface feature extraction:

[0104] 3D Convolutional Neural Network (CNN) Architecture:

[0105] The 3DResNet-18 network with 4 convolutional layers is used. The input is a 64×64×32 voxel matrix and the output is a 128-dimensional geometric feature vector G = (G1, G2, G3). Specifically, it includes:

[0106] Contact surface accuracy G1: Calculate the average absolute error between the contact surface position and the reference position (unit: mm):

[0107]

[0108] Among them, xi is the actual three-dimensional coordinate of the i-th sampling point, x ref is the theoretical reference position of the contact surface, |x i -x ref | is the Euclidean distance deviation between the i-th sampling point and the reference position.

[0109] Alignment G2: Calculate the contact surface angle deviation (unit: °) by using the normal vector angle:

[0110]

[0111] Where n1 is the actual normal vector of the fixed denture contact surface, n2 is the theoretical normal vector of the adjacent tooth contact surface, n1·n2 is the dot product of the two normal vectors, and ||n1|| and ||n2|| are the moduli (norms) of the normal vectors.

[0112] Irregularity G3: Statistical percentage of non-planar triangles (%):

[0113]

[0114] CNN directly extracts geometric features through the voxel matrix, and the design of its network structure (such as ResNet-18) takes the gradient vanishing problem into consideration to ensure the effective transmission of deep features.

[0115] Channel Attention Module:

[0116] Embedding the channel attention mechanism in CNN, the weight calculation is:

[0117]

[0118] Among them, σ is the Sigmoid function, H = 64, W = 64, and D = 32 are the feature map sizes.

[0119] The channel attention module dynamically adjusts the channel weights according to the spatial distribution of the feature map, for example, enhancing the response of the edge area of ​​the contact surface, thereby improving the sensitivity of position evaluation.

[0120] Dynamic regression modeling of adjacency forces:

[0121] Dynamic regression model construction:

[0122] Expand the adjacent force prediction model based on the cubic B-spline basis function:

[0123]

[0124] Among them, B k (t) is the cubic B-spline basis function (number of nodes K = 15), β k is the regression coefficient.

[0125] The choice of cubic B-spline basis function (rather than polynomial or Fourier basis) is more suitable for describing the dynamic changes of adjacent forces due to its local support and smoothness, avoiding overfitting.

[0126] Levenberg-Marquardt optimization algorithm:

[0127] Optimize the regression coefficients by the error function defined in the claims:

[0128]

[0129] Iterative update formula:

[0130] β (n+1) =β (n) -(J T J+λI) -1 J T r;

[0131] Among them, J is the Jacobian matrix, and the element J ik =B k (t i ); λ is the damping factor (initial value 0.001, dynamically adjusted); r is the residual vector β is the regression coefficient vector, and its dimension is determined by the number of nodes k of the cubic B-spline basis function, that is, β=(β1,β2,…,β K );F i is the measured adjacent force value at the i-th time point; β (n) , β (n+1) is the regression coefficient vector of the nth and n+1th iterations; J T is the transpose of the Jacobian matrix, with dimensions K×N; I is the identity matrix, with dimensions K×K.

[0132] The Levenberg-Marquardt algorithm combines the advantages of gradient descent and Gauss-Newton method. Based on the screened factors, it quickly converges to the optimal solution to ensure the reliability of the tightness index S.

[0133] Output indicator calculation:

[0134] Tightness index S: the average value of the predicted adjacent force (unit N / mm 2 ):

[0135]

[0136] Stability coefficient C: standard deviation of the rate of change of adjacent forces (unit: N / s):

[0137]

[0138] in, At time point t i The change rate of the adjacent force at ; μ is the average value of the change rate of the adjacent force; is the deviation of the rate of change at a single time point from the average value.

[0139] The calculation of S and C depends directly on the optimized regression coefficient β * Its physical meaning is the mean value and fluctuation degree of contact force, which provides mechanical quantitative indicators for comprehensive scoring.

[0140] Comprehensive assessment and judgment:

[0141] Weighted fusion and score generation:

[0142] The geometric features and mechanical indicators are combined according to the claim weights to generate a comprehensive score:

[0143] Q=0.4G1+0.3S+0.2C+0.1(1-G3);

[0144] The weight distribution (40% for geometric accuracy and 50% for mechanical indicators) is based on the conclusions of clinical studies to ensure that the score reflects both morphological and functional adaptability.

[0145] Preset standard judgment:

[0146] Adjacent force range:

[0147] Anterior teeth area: 1.0N≤F avg ≤2.0N;

[0148] Posterior tooth area: 1.5N≤F avg ≤2.5N;

[0149] Among them, F avg is the average value of the adjacent forces.

[0150] Contact location:

[0151]

[0152] Where H is the clinical crown height (8 mm for anterior teeth and 10 mm for posterior teeth), x and y are the coordinate offsets of the contact point on the tooth cross section, and z is the position along the long axis of the tooth.

[0153] Contact area:

[0154] Anterior teeth: 1.5-2.0mm 2 ;

[0155] Posterior area: 2.0-3.0mm 2 .

[0156] The judgment criteria are derived from clinical research in the Journal of Dental Research and form a closed-loop verification with geometric features (G1, G2, G3) and mechanical indicators (S, C).

[0157] S3. Generate an assessment report based on the quantitative assessment results and upload it to the cloud platform for storage via an encrypted transmission protocol.

[0158] Assessment report generation and structuring:

[0159] First, the quantitative evaluation results (tightness index S, position deviation Δ, contact area A, and comprehensive score Q) output from step S2 are integrated according to a preset template. The template uses JSON format and contains the following fields:

[0160] Tightness assessment: Numerical field "tightness":{"value":1.8,"unit":"N / mm 2 "};

[0161] Position evaluation: coordinate field "position":{"x":0.1,"y":-0.05,"z":3.0,"H":8};

[0162] Shape and area evaluation: "area":{"value":1.9,"unit":"mm 2 "}.

[0163] Exemplarily, data serialization is achieved through Python's json library to generate a standardized report file (extension .repjson).

[0164] Encrypted transmission protocol implementation:

[0165] The report file is encrypted using the AES-256 encryption algorithm, and the key is transmitted using RSA-2048 asymmetric encryption. The encryption process includes:

[0166] Key generation: Randomly generate a 32-byte symmetric key KsymKsym.

[0167] Data encryption: The encryption function is:

[0168] C=AES.encrypt(M,K sym ,mode=GCM);

[0169] Among them, M is the report plaintext, C is the ciphertext, and the GCM mode provides integrity verification.

[0170] Key encapsulation: using cloud platform public key PK cloud Encryption K sym :

[0171] E key =RSA.encrypt(K sym ,PK cloud );

[0172] Secure transmission and cloud storage:

[0173] Upload encrypted data packets via HTTPS protocol (TLS1.3) {C,E key The transmission process satisfies:

[0174] Data sharding: When the file size exceeds 1MB, it is transmitted in 512KB fragments. The fragment index field "chunk_index": 2 / 5.

[0175] Retransmission mechanism: If ACK is not returned within 500ms, resuming the transmission is triggered.

[0176] The cloud platform storage uses a distributed architecture (such as HDFS), with a data redundancy strategy of three copies. The storage path is generated by hashing the patient ID and timestamp:

[0177] Path=" / data / "+SHA256(PID∥timestamp)[0:8].

[0178] The fixed denture proximal assessment device described below and the fixed denture proximal assessment method described above may refer to each other.

[0179] Please see the attached Figure 2 A fixed denture proximal assessment device, used in the above-mentioned fixed denture proximal assessment method, comprises:

[0180] The data acquisition module is equipped with a MEMS piezoresistive array sensor and a 635nm laser scanner to collect proximity force data and three-dimensional contact surface data in real time;

[0181] The intelligent analysis module, whose input end is connected to the output end of the data acquisition module, contains a 3D-CNN processor and a Levenberg-Marquardt optimizer, which is used to extract features and perform mechanical analysis on the proximity force data and the three-dimensional contact surface data to generate quantitative evaluation results;

[0182] The data output module, whose input end is connected to the output end of the intelligent analysis module, is used to generate an evaluation report based on the quantitative evaluation results and transmit it to the cloud platform for storage.

[0183] Intelligent analysis modules include:

[0184] Model training unit: Build a convolutional neural network architecture based on voxelized 3D data to extract contact surface geometric features;

[0185] Feature extraction unit: identifies irregular areas and alignment deviations on the contact surface through multi-scale curvature analysis;

[0186] Mechanical analysis unit: optimize the parameters of the dynamic adjacent force model and evaluate the tightness and stability of the contact force;

[0187] Comprehensive decision-making unit: Determines adjacency quality compliance based on preset location thresholds and area standards.

[0188] The data acquisition module includes:

[0189] The pressure sensing unit monitors the dynamic pressure distribution between adjacent teeth in real time, and achieves ±0.01N sensitivity detection through MEMS piezoresistive array sensors;

[0190] The 3D scanning unit reconstructs the 3D topography of the contact surface with high precision, using a λ=635nm laser to scan at a 45° incident angle to generate point cloud data.

[0191] The device of this embodiment can be used to execute the above method embodiment, and its principles and technical effects are similar, so they will not be repeated here.

[0192] Please see the attached Figure 3 The present invention also provides a fixed denture adjacency evaluation system 40, comprising: a memory 41 and a processor 42, wherein the memory 42 stores a computer program executed by the processor 41, and the computer program executes the above method when executed by the processor 41.

[0193] The present invention further provides a storage medium 43 on which a computer program is stored. When the computer program is run by the processor 41 , the above method is executed.

[0194] Among them, the storage medium 43 can 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.

[0195] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating the proximity of fixed dentures, characterized in that: The following steps are involved: S1, real-time acquisition of the contact force data between the fixed denture and the adjacent teeth using a MEMS piezoresistive array sensor, and acquisition of three-dimensional data of the contact surface using a 635nm laser scanner; S2. Inputting the proximity force data into a regression analysis model and simultaneously inputting the three-dimensional contact surface data into a 3D convolutional neural network to extract features and generate quantitative evaluation results, wherein the quantitative evaluation results include: tightness evaluation, position evaluation, and shape and area evaluation; S3. Generate an assessment report based on the quantitative assessment results and upload it to the cloud platform for storage via an encrypted transmission protocol.

2. The method for evaluating fixed denture proximities according to claim 1, wherein: The step S1 comprises: S1.

1. The smart sensor dental floss with a built-in ±0.01N sensitivity pressure sensor monitors the proximity force in real time, measures the pressure changes in the contact area, and generates a pressure distribution map and force change curve; S1.

2. The micro end-port scanning device obtains three-dimensional data of the contact surface through laser scanning or optical image capture with a resolution of 0.05mm, and calculates the position, shape and area of ​​the contact surface.

3. The method for evaluating fixed denture proximal connections according to claim 1, wherein: The step S2 comprises: S2.

1. Training a convolutional neural network model to convert the three-dimensional contact surface data into a 64×64×32 voxel matrix and extracting geometric features using a channel attention mechanism. The geometric features include contact surface accuracy, shape alignment, and surface curvature distribution. S2.

2. Based on the geometric features and the proximity force time series data, establish a proximity force dynamic regression model, and use an optimization algorithm to adjust the regression coefficient β to minimize the prediction error; S2.

3. Perform weighted fusion of the geometric features with the tightness index and stability coefficient output by the regression model to generate a comprehensive score, and determine whether the contact surface position meets the preset conditions.

4. The method for evaluating fixed denture proximal connections according to claim 3, wherein: The optimization algorithm in step S2.2 is the Levenberg-Marquardt algorithm, and the error in step S2.2 is defined by the following formula: Among them, β is the regression coefficient vector, is the model prediction value, F i is the measured adjacency force value at the i-th time point, and N is the total number of data sampling points.

5. The method for evaluating fixed denture proximal connections according to claim 3, wherein: The preset conditions in step S2.3 are: The contact point position satisfies: Where x and y are the coordinate offsets of the contact point on the tooth cross section, z is the position along the long axis of the tooth, and H is the clinical crown height; The contact area should be within the range of 1.5-2.0 mm in the anterior area. 2 , 2.0-3.0mm in the posterior area 2 , the contact force range is 1.0-2.5N.

6. The fixed denture proximal assessment device according to claim 1, characterized in that , a method for evaluating the proximity of fixed dentures as described in any one of claims 1 to 5 above, comprising: The data acquisition module is equipped with a MEMS piezoresistive array sensor and a 635nm laser scanner to collect proximity force data and three-dimensional contact surface data in real time; an intelligent analysis module, the input end of which is connected to the output end of the data acquisition module, and which includes a 3D-CNN processor and a Levenberg-Marquardt optimizer, and is used to perform feature extraction and mechanical analysis on the proximity force data and the three-dimensional contact surface data to generate a quantitative evaluation result; The data output module has an input end connected to the output end of the intelligent analysis module, and is used to generate an evaluation report based on the quantitative evaluation results and transmit it to the cloud platform for storage.

7. The fixed denture proximal assessment device according to claim 6, characterized in that: The intelligent analysis module includes: Model training unit: Build a convolutional neural network architecture based on voxelized 3D data to extract contact surface geometric features; Feature extraction unit: identifies irregular areas and alignment deviations on the contact surface through multi-scale curvature analysis; Mechanical analysis unit: optimize the parameters of the dynamic adjacent force model and evaluate the tightness and stability of the contact force; Comprehensive decision-making unit: Determines adjacency quality compliance based on preset location thresholds and area standards.

8. The fixed denture proximal assessment device according to claim 6, characterized in that: The data acquisition module includes: The pressure sensing unit monitors the dynamic pressure distribution between adjacent teeth in real time, and achieves ±0.01N sensitivity detection through MEMS piezoresistive array sensors; The 3D scanning unit reconstructs the 3D topography of the contact surface with high precision, using a λ=635nm laser to scan at a 45° incident angle to generate point cloud data.

9. A fixed denture proximal assessment system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the fixed denture proximal assessment method according to any one of claims 1 to 5 is executed.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when running, executes the fixed denture adjacency assessment method according to any one of claims 1 to 5.

Images