Non-invasive life data monitoring method and system based on intelligent tooth socket

Abstract

The invention relates to a non-invasive life data monitoring method and system based on an intelligent tooth socket, and belongs to the technical field of health monitoring. The method comprises the following steps: acquiring non-invasive life data, obtaining non-invasive life quantification data according to the non-invasive life data, and constructing a multi-modal non-invasive life monitoring set according to the non-invasive life quantification data; according to the multi-modal non-invasive life monitoring set, obtaining a tooth pathological model through chewing and occlusion dynamic simulation; non-invasive life real-time monitoring data is obtained, a tooth pathology label is obtained through the tooth pathology model according to the non-invasive life real-time monitoring data, an orthodontic personalized correction scheme and a health intervention strategy are generated according to the tooth pathology label, and the tooth health condition is accurately recognized. Therefore, the chewing habit of the user is improved, and occurrence and development of oral diseases are prevented.

Description

Technical Field

[0001] The present invention belongs to the field of health monitoring technology, and in particular relates to a non-invasive life data monitoring method and system based on smart braces. Background Art

[0002] With the development of smart medical care and personalized health management, traditional braces have gradually revealed their limitations in functionality and applicability, and are unable to meet the high standards of modern orthodontic treatment and dental pathology prediction.

[0003] Existing technologies have obvious limitations in the field of chewing behavior analysis: traditional bite analyzers can only measure static bite force and cannot effectively correlate dynamic chewing behavior with pathological development, leading to the neglect of dynamic processes; clinical diagnosis is highly dependent on the doctor's experience, making the quantitative assessment of early lesions such as enamel microcracks difficult and lacking objectivity; in addition, existing AI models are mainly based on data correlation during analysis and fail to deeply integrate biomechanical mechanisms, resulting in blurred causal relationships, limiting the model's explanatory power and application depth.

[0004] As people's health awareness increases, the application of smart wearable devices for health monitoring is becoming increasingly widespread. As an emerging wearable device, smart braces offer advantages such as close contact with the mouth, discreet wear, high comfort, and no impact on daily activities. They provide new insights into non-invasive vital data monitoring. However, how to leverage advanced technologies to achieve real-time monitoring of smart braces, accurately predict dental conditions, and generate personalized orthodontic treatment recommendations has become a pressing technical challenge. Summary of the Invention

[0005] In order to solve the above problems existing in the prior art, the present invention proposes a non-invasive vital data monitoring method and system based on smart braces.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A non-invasive life data monitoring method based on smart braces, characterized by comprising: Acquiring non-invasive life data, obtaining non-invasive life quantification data based on the non-invasive life data, and constructing a multimodal non-invasive life monitoring set based on the non-invasive life quantification data; Obtaining a dental pathology model through chewing and occlusion dynamic simulation according to the multimodal non-invasive life monitoring set; Acquire non-invasive real-time life monitoring data, obtain dental pathology labels through the dental pathology model based on the non-invasive real-time life monitoring data, and generate an orthodontic personalized correction plan and health intervention strategy based on the dental pathology labels.

[0007] Preferably, the construction process of the multi-modal non-invasive vital monitoring set comprises: obtaining non-invasive vital denoising data according to the non-invasive vital data; obtaining non-invasive vital quantification data according to the non-invasive vital denoising data; obtaining a multi-modal non-invasive vital monitoring set through intelligent labeling of masticatory pathology labels according to the non-invasive vital quantification data.

[0008] Preferably, the modeling process of the dental pathology model comprises: generating a masticatory efficiency coefficient through dynamic optical flow feature extraction according to the multi-modal non-invasive vital monitoring set; obtaining a bilateral occlusal symmetry index through occlusal reverse modeling according to the multi-modal non-invasive vital monitoring set; obtaining a cross-modal feature tensor through dental pathology semantic embedding according to the masticatory efficiency coefficient and the bilateral occlusal symmetry index; obtaining a dental pathology model through a multi-modal graph neural network according to the cross-modal feature tensor.

[0009] Preferably, the mathematical expression of the masticatory efficiency coefficient is: , wherein CEI is the masticatory efficiency coefficient, v t is the bolus fragment motion vector, ||.||2 is the L2 norm, ΔS t is the bolus surface area change, E is the masticatory muscle energy consumption, T is the masticatory cycle, and t is the current time.

[0010] Preferably, the mathematical expression of the bilateral occlusal symmetry index is: , wherein OAI is the bilateral occlusal symmetry index, F L is the left occlusal force vector, F R is the right occlusal force vector, ||.||1 is the L1 norm, and max(F L , F R ) is the bilateral maximum occlusal force scalar value.

[0011] Preferably, the construction process of the dental pathology model comprises: obtaining a cross-modal correlation strength through node definition and edge weight training according to the cross-modal feature tensor; obtaining a biomechanical feature coupling coefficient through biomechanical feature time-varying regulation according to the cross-modal correlation strength; a preset tooth biomechanics topology matrix, updating the preset tooth biomechanics topology matrix according to the biomechanics feature coupling coefficient to obtain a tooth biomechanics topology update matrix; obtaining a tooth pathology label through iterative training according to the tooth biomechanics topology update matrix.

[0012] Preferably, the mathematical expression of the time-varying regulation of the biomechanics feature is: wherein A ij is the biomechanics feature coupling coefficient between the sample of the chewing efficiency mode i and the sample of the bilateral occlusion symmetry mode j, exp(.) is an exponential function, N is the total number of samples of the multi-modal non-invasive life monitoring set, S ij is the correlation strength between the sample of the chewing efficiency mode i and the sample of the bilateral occlusion symmetry mode k, S ik is the correlation strength between the sample of the chewing efficiency mode i and the sample of the bilateral occlusion symmetry mode k.

[0013] A non-invasive life data monitoring system based on an intelligent mouthguard, applied to the non-invasive life data monitoring method described above, comprising a multi-modal non-invasive life monitoring set construction module, a tooth pathology model construction module, and a tooth correction intervention module. The multi-modal non-invasive life monitoring set construction module is used to obtain non-invasive life data, obtain non-invasive life quantitative data according to the non-invasive life data, and construct a multi-modal non-invasive life monitoring set according to the non-invasive life quantitative data. The tooth pathology model construction module is used to obtain a tooth pathology model through chewing occlusion dynamic simulation according to the multi-modal non-invasive life monitoring set. The tooth correction intervention module is used to obtain non-invasive life real-time monitoring data, obtain a tooth pathology label through the tooth pathology model according to the non-invasive life real-time monitoring data, and generate an orthodontic personalized correction scheme and a health intervention strategy according to the tooth pathology label.

[0014] A non-invasive life data monitoring system based on an intelligent mouthguard is applied to an intelligent mouthguard. The intelligent mouthguard can capture physiological dynamic data in the oral cavity in real time and output a tooth pathology label through a tooth pathology model. An orthodontic personalized correction scheme and a health intervention strategy are generated according to the tooth pathology label. At the same time, the intelligent mouthguard is also provided with a positioning function, which can connect an APP Bluetooth to position the current position of the mouthguard and upload the monitored non-invasive life data to a client.

[0015] ​An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the above non-invasive vital data monitoring method when executing the computer program.

[0016] A storage medium comprising computer executable instructions for implementing the above non-invasive vital data monitoring method when executed by a computer processor.

[0017] The beneficial effects of the present application are: By obtaining non-invasive vital data and obtaining non-invasive vital quantitative data through data preprocessing, the consistency and comparability of the data are improved, which helps to improve the accuracy and reliability of subsequent analysis, and the multi-modal non-invasive vital monitoring set is constructed according to the non-invasive vital quantitative data, which helps to comprehensively and carefully understand the user's chewing behavior, more comprehensively reveals the user's dental condition, provides rich basic data for subsequent analysis and treatment, and provides support for the construction of dental pathology model.

[0018] The dental pathology model is obtained through chewing occlusion dynamic simulation, which helps to more accurately identify and predict dental diseases; the chewing efficiency coefficient is generated through dynamic optical flow feature extraction, which can quantify the user's chewing efficiency, providing an objective measurement means for evaluating chewing function and oral health; the bilateral occlusion symmetry index is obtained through occlusion reverse modeling, which helps to identify and analyze occlusion asymmetry problems; the cross-modal feature tensor is obtained through dental pathology semantic embedding, which realizes effective fusion between different monitoring data modalities, and improves the diagnostic accuracy of the dental pathology model.

[0019] Through the combination of non-invasive vital real-time monitoring data and dental pathology model, the dental pathology label can be generated in real time, and the user is provided with instant intelligent reminders, which helps to improve the user's chewing habits; the orthodontic personalized treatment health suggestion is generated according to the dental pathology label, which helps to improve the treatment effect, shorten the treatment cycle and reduce the treatment cost; through intelligent reminders and personalized treatment suggestions, it helps to prevent the occurrence and development of dental diseases and improve the patient's dental health condition. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to facilitate the understanding of those skilled in the art, the present application will be further described below with reference to the accompanying drawings.

[0021] Figure 1 A flowchart of a non-invasive vital data monitoring method based on an intelligent dental brace according to the present application. DETAILED DESCRIPTION

[0022] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined inventive purpose, the specific embodiments, structures, features and effects thereof according to the present application are described in detail below in combination with the drawings and preferred embodiments.

[0023] Please refer to Figure 1 A non-invasive life data monitoring method based on an intelligent mouthguard, comprising: S1: acquiring non-invasive life data, the non-invasive life data comprising bolus breaking morphology data, saliva fluid dynamics data, masticatory muscle group activity signals, occlusal surface three-dimensional topography data, and occlusal contact pressure distribution data; S2: obtaining non-invasive life quantitative data from the non-invasive life data through data preprocessing, and constructing a multi-modal non-invasive life monitoring set according to the non-invasive life quantitative data; S3: obtaining a dental pathology model from the multi-modal non-invasive life monitoring set through masticatory occlusion dynamic simulation; S4: acquiring non-invasive life real-time monitoring data, obtaining a dental pathology label from the dental pathology model according to the non-invasive life real-time monitoring data, and generating an orthodontic personalized treatment plan and a health intervention strategy according to the dental pathology label.

[0024] In the present embodiment, the acquisition of non-invasive life data is implemented by the following steps: The non-invasive life data is acquired by the built-in sensors of the intelligent mouthguard, which include a high-speed camera, an electromyography sensor, a 3D structured light scanning sensor, and a nano piezoelectric sensitive sensor. S101: obtaining bolus breaking morphology data and saliva fluid dynamics data through dynamic image capture by the high-speed camera; S102: collecting masticatory muscle group activity signals by the electromyography sensor; S103: acquiring occlusal surface three-dimensional topography data by the 3D structured light scanning sensor; S104: acquiring occlusal contact pressure distribution data by the nano piezoelectric sensitive sensor; It should be noted that the non-invasive life data is sampled at a fixed time interval and transmitted to a remote intelligent mouthguard data processing center in real time through the built-in Bluetooth for storage.

[0025] In the present embodiment, the non-invasive life quantitative data obtained from the non-invasive life data through data preprocessing, and the multi-modal non-invasive life monitoring set constructed according to the non-invasive life quantitative data are implemented by the following steps: S201: obtaining non-invasive life denoising data from the non-invasive life data through filtering and denoising; S202: obtaining non-invasive life quantitative data through dimension standardization processing according to the non-invasive life denoising data; S203: obtaining a multi-modal non-invasive life monitoring set through intelligent labeling of chewing pathological labels according to the non-invasive life quantitative data.

[0026] The intelligent labeling of the chewing pathological labels labels the dental pathological labels including caries labels, periodontitis labels, normal labels, and other inflammation labels through clinical data.

[0027] In the embodiment, the dental pathological model is obtained through chewing occlusion dynamic simulation according to the multi-modal non-invasive life monitoring set by the following steps: S301: generating a chewing efficiency index through dynamic optical flow feature extraction according to the multi-modal non-invasive life monitoring set; The mathematical expression of the chewing efficiency index is: , Wherein, CEI is the chewing efficiency index, v t is a food bolus fragment movement vector, ||.||2 is an L2 norm, ΔS t is a food bolus surface area change, E is chewing muscle energy consumption, T is a chewing cycle, and t is a current time.

[0028] The chewing efficiency index is a quantification of the mechanical efficiency of food crushing under unit energy consumption. The food bolus fragment movement vector is the instantaneous movement speed of the food fragments at the current time of chewing, which can reflect the dynamic characteristics of the food being squeezed and cut during chewing. The food bolus surface area change is the total surface area change of the food at the current time of chewing t relative to the previous time of chewing t−1, which is used to represent the degree of food crushing. The chewing muscle energy consumption is the total biomechanical energy consumed by the chewing muscles in completing a chewing cycle; the total chewing cycle time is the duration of a single chewing action, which is obtained by marking the start and end points of chewing through a high-speed camera.

[0029] The mathematical expression of the chewing muscle energy consumption is: , Wherein, E is the chewing muscle energy consumption, R is an electromyography power conversion coefficient, α is a muscle mechanical efficiency, EMG i (t) is the i-th block muscle chewing activity signal.

[0030] In this embodiment, the total time of a single chewing cycle is T = 0.8, 1000 frames of data are collected per second, and a total of 800 frames are collected. Three time points (t1 = 0.1s, t2 = 0.4s, and t3 = 0.7s) are selected. The L2 norm of the motion vector of the food bolus fragment and the change in the food bolus surface area at time t1 are 0.25 m / s and 2.5×10 −5 m 2 The L2 norm of the motion vector of the food bolus fragment and the change in the surface area of ​​the food bolus at time t2 are 0.38 m / s and 5.0×10 −5 m 2 The L2 norm of the motion vector of the food bolus fragment and the change in the surface area of ​​the food bolus at time t3 are 0.12 m / s and 1.2×10 −5 m 2 , the energy consumption of the masticatory muscles is 0.35J, and the chewing efficiency coefficient is calculated to be 0.076.

[0031] S302: Obtaining a bilateral occlusal symmetry index through occlusal inverse modeling according to the multimodal non-invasive life monitoring set; The mathematical expression of the bilateral occlusal symmetry index is: , Among them, OAI is the bilateral occlusal symmetry index, F L is the left bite force vector, F R is the right bite force vector, ||.||1 is the L1 norm, max(F L ,F R ) is the scalar value of the maximum bilateral bite force.

[0032] In this embodiment, the left bite force vector F L is [10,20,30], the right bite force vector F R is [15,25,35], the difference F between the bite force vectors on both sides L −F R is [−5,−5,−5], the L1 norm of the difference between the bite force vectors on both sides is 15, the L1 norm of the left bite force vector is 60, and the L1 norm of the right bite force vector is 75, then max(F L ,F R ) is 75, and the bilateral occlusal symmetry index is calculated to be 0.2.

[0033] It should be noted that the left occlusal force vector is the resultant force vector of the occlusal contact points of the left teeth, and the right occlusal force vector is the resultant force vector of the occlusal contact points of the right teeth; compared with the L2 norm, the L1 norm is more sensitive to local force differences and is suitable for detecting local occlusal overload, such as abnormal contact of a single tooth.

[0034] S303: obtaining a cross-modal feature tensor through dental pathology semantic embedding according to the masticatory efficiency coefficient and the bilateral occlusion symmetry index; Specifically, the dental pathology label is encoded into a 128-dimensional vector, and a cross-modal feature tensor is constructed through label-feature association according to the masticatory efficiency coefficient and the bilateral occlusion symmetry index.

[0035] S304: obtaining a dental pathology model through a multi-modal graph neural network according to the cross-modal feature tensor.

[0036] S304-1: obtaining a cross-modal correlation strength through node definition and edge weight training according to the cross-modal feature tensor; The node definition is a preset cross-modal feature node, and the preset cross-modal feature node includes a masticatory efficiency node, a bilateral occlusion symmetry node, and a dental pathology label node. The dental pathology label node is obtained through edge weight training of the masticatory efficiency node and the bilateral occlusion symmetry node to obtain a cross-modal correlation strength. The mathematical expression of the edge weight training is: , Wherein, W ij is a cross-modal correlation strength, S is a Sigmoid activation function, b is a bias term, W a is a learnable weight matrix, h i is a masticatory efficiency node, h j is a bilateral occlusion symmetry node.

[0037] S304-2: obtaining a biomechanical feature coupling coefficient through biomechanical feature time-varying regulation according to the cross-modal correlation strength; The mathematical expression of the biomechanical feature time-varying regulation is: , Wherein, A ij is a biomechanical feature coupling coefficient between a masticatory efficiency modal i sample and a bilateral occlusion symmetry modal j sample, exp(.) is an exponential function, N is the total number of samples in a multi-modal non-invasive life monitoring set, S ij is a correlation strength between the masticatory efficiency modal i sample and the bilateral occlusion symmetry modal k sample, S ik is a correlation strength between the masticatory efficiency modal i sample and the bilateral occlusion symmetry modal k sample.

[0038] S304-3: presetting a dental biomechanics topology matrix, updating the preset dental biomechanics topology matrix according to the biomechanical feature coupling coefficient to obtain a dental biomechanics topology update matrix; S304-4: updating the matrix according to the dental biomechanics topology to obtain a dental pathology label through iterative training.

[0039] In the embodiment, the structure of the multi-modal graph neural network includes a local adjacency interaction GNN layer, a cross-jaw mechanical coupling GNN layer, and a pathology prototype matching GNN layer, the biomechanics feature coupling mechanism is embedded between the GNN layers, and iterative training is performed until a preset number of iterations is reached. In order to prevent overfitting during training, feature masks and edge weight Dropout are added to ensure that the model can learn more robust and generalizable features.

[0040] A non-invasive vital data monitoring system based on an intelligent mouthguard includes a multi-modal non-invasive vital monitoring set construction module, a dental pathology model construction module, and a dental correction intervention module. The multi-modal non-invasive vital monitoring set construction module is used to obtain non-invasive vital data, obtain non-invasive vital quantitative data according to the non-invasive vital data, and construct a multi-modal non-invasive vital monitoring set according to the non-invasive vital quantitative data. The dental pathology model construction module is used to obtain a dental pathology model through mastication occlusion dynamic simulation according to the multi-modal non-invasive vital monitoring set. The dental correction intervention module is used to obtain non-invasive vital real-time monitoring data, obtain a dental pathology label through the dental pathology model according to the non-invasive vital real-time monitoring data, and generate an orthodontic personalized correction scheme and a health intervention strategy according to the dental pathology label.

[0041] In the embodiment, the intelligent mouthguard uses a medical-grade nanocomposite resin matrix, embeds a hollow grid cavity, has a U-shaped occlusal tray shape, covers the upper and lower dental arches, and the non-invasive vital data monitoring system of the intelligent mouthguard is highly integrated in the matrix, and includes the following key components: a multi-modal sensor group composed of a high-speed miniature camera, an electromyographic sensor, a 3D structured light scanning sensor, and a nanometer piezoelectric sensitive sensor; the core of a main control PCB is a d microcontroller equipped with a DSP instruction set and a radio frequency module, which is responsible for real-time fusion processing of multi-source sensor data, dynamic baseline calibration algorithm execution, and wireless data transmission through a low-power Bluetooth module, and a positioning system is deployed on the main control PCB, which can transmit position information to a client in real time.

[0042] The computer storage medium of the embodiments of the present application can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0043] The computer-readable signal medium can include a data signal propagated in baseband or propagated as a carrier wave, in which the computer-readable program code is contained. Such propagated data signal can take a variety of forms, including but not limited to electro-magnetic, optical or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium that is not a storage medium and that can be used to carry or propagate program code that is used by or in connection with an instruction execution system, apparatus, or device.

[0044] The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire line, optical fiber, RF, etc., or any suitable combination of the above. The computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as "C" or the like. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0045] The above merely describes the preferred embodiments of the present application, and is not intended to limit the present application in any form. Although the present application has been disclosed with the preferred embodiments as above, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the above disclosed technical content to obtain equivalent embodiments with equivalent changes, as long as the changes or modifications do not deviate from the technical solution of the present application. Any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application still belongs to the scope of the technical solution of the present application.

Claims

1. A non-invasive life data monitoring method based on smart braces, characterized in that: include: Acquiring non-invasive life data, obtaining non-invasive life quantification data based on the non-invasive life data, and constructing a multimodal non-invasive life monitoring set based on the non-invasive life quantification data; Obtaining a dental pathology model through chewing and occlusion dynamic simulation according to the multimodal non-invasive life monitoring set; Acquire non-invasive real-time life monitoring data, obtain dental pathology labels through the dental pathology model based on the non-invasive real-time life monitoring data, and generate an orthodontic personalized correction plan and health intervention strategy based on the dental pathology labels.

2. The non-invasive life data monitoring method according to claim 1, characterized in that: The construction process of the multimodal non-invasive life monitoring set includes: Obtaining non-invasive life denoising data according to the non-invasive life data; Obtaining non-invasive life quantization data according to the non-invasive life denoising data; A multimodal non-invasive life monitoring set is obtained based on the non-invasive life quantification data through intelligent annotation of chewing pathology labels.

3. The non-invasive life data monitoring method according to claim 1, characterized in that: The modeling process of the dental pathology model includes: generating a chewing efficiency coefficient by extracting dynamic optical flow features based on the multimodal non-invasive life monitoring set; Obtaining a bilateral occlusal symmetry index through occlusal inverse modeling based on the multimodal non-invasive vital monitoring set; Obtaining a cross-modal feature tensor based on the masticatory efficiency coefficient and the bilateral occlusal symmetry index through dental pathology semantic embedding; A dental pathology model is obtained through a multimodal graph neural network based on the cross-modal feature tensor.

4. The non-invasive life data monitoring method according to claim 3, characterized in that: The mathematical expression of the chewing efficiency coefficient is: ， Among them, CEI is the chewing efficiency coefficient, v t is the motion vector of the food pellet fragment, ||.||2 is the L2 norm, ΔS t is the change in the surface area of ​​the food bolus, E is the energy consumption of the masticatory muscles, T is the chewing cycle, and t is the current moment.

5. The non-invasive life data monitoring method according to claim 3, characterized in that: The mathematical expression of the bilateral occlusal symmetry index is: ， Among them, OAI is the bilateral occlusal symmetry index, F L is the left bite force vector, F R is the right bite force vector, ||.||1 is the L1 norm, max(F L ,F R ) is the scalar value of the maximum bilateral bite force.

6. The non-invasive life data monitoring method according to claim 3, characterized in that: The process of constructing the dental pathology model includes: Obtaining cross-modal association strength through node definition and edge weight training according to the cross-modal feature tensor; Obtaining a biomechanical characteristic coupling coefficient through time-varying regulation of the biomechanical characteristics according to the cross-modal correlation strength; Preset a tooth biomechanical topology matrix, and update the preset tooth biomechanical topology matrix according to the biomechanical characteristic coupling coefficient to obtain a tooth biomechanical topology update matrix; The tooth pathology label is obtained by iterative training based on the tooth biomechanical topology update matrix.

7. The non-invasive life data monitoring method according to claim 6, characterized in that: The mathematical expression for the time-varying regulation of the biomechanical characteristics is: ， Among them, A ij is the biomechanical characteristic coupling coefficient between the chewing efficiency modality i sample and the bilateral occlusal symmetry modality j sample, exp(.) is the exponential function, N is the total number of samples in the multimodal non-invasive life monitoring set, S ij is the correlation strength between the chewing efficiency modality i sample and the bilateral occlusal symmetry modality k sample, S ik is the correlation strength between the chewing efficiency modality i sample and the bilateral occlusal symmetry modality k sample.

8. A non-invasive vital data monitoring system based on smart braces, applied to the non-invasive vital data monitoring method according to any one of claims 1 to 7, characterized in that: It includes a multimodal non-invasive life monitoring set construction module, a dental pathology model construction module, and a dental orthodontic intervention module; The multimodal non-invasive life monitoring set construction module is used to obtain non-invasive life data, obtain non-invasive life quantification data based on the non-invasive life data, and construct a multimodal non-invasive life monitoring set based on the non-invasive life quantification data; The dental pathology model construction module is used to obtain a dental pathology model through chewing and occlusion dynamic simulation according to the multimodal non-invasive life monitoring set; The dental orthodontic intervention module is used to obtain non-invasive real-time life monitoring data, obtain dental pathology labels through the dental pathology model based on the non-invasive real-time life monitoring data, and generate personalized orthodontic treatment plans and health intervention strategies based on the dental pathology labels.

9. The non-invasive life data monitoring system according to claim 8, characterized in that: The system is applied to smart braces, which can capture physiological dynamic data in the oral cavity in real time and output dental pathology labels through a dental pathology model, and generate personalized orthodontic treatment plans and health intervention strategies based on the dental pathology labels; at the same time, the smart braces are also equipped with a positioning function, which can connect to the APP Bluetooth to locate the current position of the braces and upload the monitored non-invasive life data to the client.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the non-invasive vital data monitoring method according to any one of claims 1 to 7 is implemented.

11. A storage medium containing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, the computer executable instructions are used to perform the non-invasive vital data monitoring method according to any one of claims 1 to 7.

Images