Tooth health condition assessment method and device based on multi-source information

Abstract

The invention discloses a tooth health condition assessment method and device based on multi-source information. The method comprises the following steps: acquiring a tooth image data set and a tooth index data set; the tooth image data set comprises tooth image data; the tooth index data set comprises a time sampling sequence of tooth indexes; the time sampling sequence comprises a plurality of acquisition values; preprocessing the tooth image data set and the tooth index data set to obtain a preprocessed data set; the preprocessing data set comprises a preprocessed tooth image data set and a tooth index data set; and performing evaluation processing on the preprocessed data set to obtain a tooth health condition evaluation value. According to the invention, the tooth health condition of the user is rapidly and accurately evaluated by using the obtained various multi-source tooth monitoring data.

Description

Technical Field

[0001] The present invention relates to the field of medical information processing, and in particular to a method and device for evaluating dental health status based on multi-source information. Background Art

[0002] At present, accurate assessment of the health status of teeth is an important prerequisite for good oral health care. The current determination of the health status of the oral cavity and teeth is mainly based on experience and observation. This method has problems such as limited observation information and prone to misjudgment.

[0003] In the past decade, with the rapid development of computer and electronic technology, with the help of computer imaging technology, such as X-ray, computer tomography CT and laser scanning, it is possible to obtain three-dimensional image data of teeth. At the same time, various dental health monitoring technologies have also been greatly enriched, and people can monitor the health of their teeth through a variety of dental health indicators.

[0004] How to use the various multi-source dental monitoring data obtained to quickly and accurately assess the user's dental health status is an issue that urgently needs to be addressed. Summary of the invention

[0005] With regard to how to utilize various types of multi-source dental monitoring data obtained to quickly and accurately evaluate the user's dental health status, the present invention discloses a dental health status evaluation method and device based on multi-source information.

[0006] In a first aspect of the embodiment of the present application, a method for evaluating dental health status based on multi-source information is disclosed, comprising:

[0007] S1, acquiring a tooth image data set and a tooth index data set; the tooth image data set includes tooth image data; the tooth index data set includes a time sampling sequence of tooth indexes; the time sampling sequence includes a plurality of acquisition values;

[0008] S2, preprocessing the tooth image dataset and the tooth index dataset to obtain a preprocessed dataset; the preprocessed dataset includes the preprocessed tooth image dataset and the tooth index dataset;

[0009] S3, evaluating the preprocessed data set to obtain a dental health status evaluation value.

[0010] The preprocessing of the tooth image dataset and the tooth index dataset to obtain a preprocessed dataset includes:

[0011] Performing noise reduction processing on the tooth image dataset and the tooth index dataset to obtain a noise reduction dataset;

[0012] Performing data cleaning processing on the noise reduction data set to obtain a first data set;

[0013] Anomaly detection processing is performed on the first data set to obtain a preprocessed data set.

[0014] The step of evaluating the preprocessed data set to obtain a dental health status evaluation value includes:

[0015] S31, using the trained tooth image evaluation model, processing the preprocessed tooth image data set to obtain a tooth image evaluation value;

[0016] S32, performing comprehensive evaluation processing on the preprocessed tooth index data set to obtain an index evaluation value;

[0017] S33, performing weighted sum processing on the tooth image evaluation value and the index evaluation value to obtain a tooth health status evaluation value.

[0018] The tooth image evaluation model includes a first convolution module, a second convolution module, a third convolution module, a fourth convolution module, a first fusion module, a second fusion module, a third fusion module, a first normalization module, a second normalization module, and a first activation module;

[0019] The input end of the first convolution module is used to receive dental image data, and the output end of the first convolution module is respectively connected to the input end of the first fusion module and the input end of the second fusion module; the output end of the first fusion module is connected to the input end of the third convolution module; the output end of the third convolution module is connected to the input end of the first normalization module; the output end of the first normalization module is connected to the input end of the third fusion module; the input end of the second convolution module is used to receive dental image data, and the output end of the second convolution module is respectively connected to the input end of the third fusion module and the input end of the first fusion module; the output end of the second fusion module is connected to the input end of the fourth convolution module; the output end of the fourth convolution module is connected to the input end of the second normalization module; the output end of the second normalization module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the input end of the first activation module; the output end of the first activation module is used to output a dental image evaluation value.

[0020] The comprehensive evaluation process of the preprocessed tooth index data set to obtain an index evaluation value includes:

[0021] S3201, representing the tooth index data set as an index matrix; the row vector of the index matrix is ​​a time sampling sequence of each tooth index;

[0022] S3202, decomposing the indicator matrix to obtain a characteristic matrix of the indicator matrix;

[0023] S3203, extracting the diagonal elements of the feature matrix to obtain a feature vector;

[0024] S3204, performing linear fitting processing on the elements and element sequence values ​​of the feature vector to obtain an approximation model;

[0025] S3205, obtaining the standard value of each tooth index;

[0026] S3206, for each time sampling sequence of a tooth index, calculating the absolute value of the difference between each collected value contained therein and the standard value of the tooth index; using the absolute value of the difference calculated for all collected values ​​of the time sampling sequence, constructing an offset sequence of the tooth index;

[0027] S3207, constructing an offset matrix using the offset sequences of all tooth indicators;

[0028] S3208, performing correlation calculation processing on the indicator matrix and the offset matrix to obtain a correlation vector;

[0029] S3209, for each tooth indicator offset sequence, find an element with a maximum value, determine the sequence number of the element in the offset sequence, and use it as the deviation sequence number of the tooth indicator;

[0030] S3210, using the approximation model, calculating and processing the deviation sequence values ​​of all tooth indicators to obtain an approximation sequence;

[0031] S3211, using the association vector as a weight sequence, performing weighted summation processing on the approximation sequence to obtain an indicator evaluation value.

[0032] The calculation expression of the decomposition process is:

[0033] A1=UAV,

[0034] Among them, U is the left decomposition matrix, A1 is the indicator matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix.

[0035] The calculation expression of the association calculation is:

[0036]

[0037] Among them, A1 ij is the element in the i-th row and j-th column of the indicator matrix A1, A2 ij is the element in the i-th row and j-th column of the offset matrix A2, pi is the i-th element of the association vector, and M2 is the column dimension of the indicator matrix.

[0038] In a second aspect of the embodiment of the present application, a device for evaluating dental health status based on multi-source information is disclosed, the device comprising:

[0039] A memory storing executable program code;

[0040] a processor coupled to the memory;

[0041] The processor calls the executable program code stored in the memory to execute the dental health status assessment method based on multi-source information.

[0042] In a third aspect of the embodiments of the present application, a computer storable medium is disclosed, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the method for evaluating dental health status based on multi-source information.

[0043] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, wherein the information data processing terminal is used to implement the dental health status assessment method based on multi-source information.

[0044] The beneficial effects of the present invention are:

[0045] The present invention first performs noise reduction, data cleaning and anomaly detection processing on the collected multi-source information, effectively filtering out noise and interference in the collected data, and ensuring the accuracy and consistency of the data source of health assessment.

[0046] The present invention adopts different evaluation and processing methods for different types of tooth collection data; the proposed deep learning model is used to evaluate and process the tooth image data; the indicator matrix and the offset matrix are constructed using the indicator data, and the proposed association calculation processing method is used to process the indicator matrix and the offset matrix to obtain the association vector; the association vector is used as a weight sequence to perform weighted summation processing on the approximation sequence to obtain the indicator evaluation value, thereby achieving effective extraction of the indicator health characteristics. Finally, the evaluation results of the two types of data, image and indicator, are fused using a fusion weighting method to obtain the final tooth health status evaluation result. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0048] In order to better understand the content of the present invention, an embodiment is given here.

[0049] Figure 1It is a flow chart for implementing the method of the present invention.

[0050] In a first aspect of the embodiment of the present application, a method for evaluating dental health status based on multi-source information is disclosed, comprising:

[0051] S1, acquiring a tooth image data set and a tooth index data set; the tooth image data set includes tooth image data; the tooth index data set includes a time sampling sequence of tooth indexes;

[0052] S2, preprocessing the tooth image dataset and the tooth index dataset to obtain a preprocessed dataset; the preprocessed dataset includes the preprocessed tooth image dataset and the tooth index dataset;

[0053] S3, evaluating the preprocessed data set to obtain a dental health status evaluation value;

[0054] The preprocessing of the tooth image dataset and the tooth index dataset to obtain a preprocessed dataset includes:

[0055] Performing noise reduction processing on the tooth image dataset and the tooth index dataset to obtain a noise reduction dataset;

[0056] Performing data cleaning processing on the noise reduction data set to obtain a first data set;

[0057] Performing anomaly detection processing on the first data set to obtain a preprocessed data set;

[0058] The first data set includes a tooth image data set and a tooth index data set after data cleaning.

[0059] The denoising data set includes a tooth image data set and a tooth index data set after denoising processing.

[0060] The step of evaluating the preprocessed data set to obtain a dental health status evaluation value includes:

[0061] S31, using the trained tooth image evaluation model, processing the preprocessed tooth image data set to obtain a tooth image evaluation value;

[0062] S32, performing comprehensive evaluation processing on the preprocessed tooth index data set to obtain an index evaluation value;

[0063] S33, performing weighted sum processing on the tooth image evaluation value and the index evaluation value to obtain a tooth health status evaluation value;

[0064] The tooth image evaluation model includes a first convolution module, a second convolution module, a third convolution module, a fourth convolution module, a first fusion module, a second fusion module, a third fusion module, a first normalization module, a second normalization module, and a first activation module;

[0065] The input end of the first convolution module is used to receive dental image data, and the output end of the first convolution module is respectively connected to the input end of the first fusion module and the input end of the second fusion module; the output end of the first fusion module is connected to the input end of the third convolution module; the output end of the third convolution module is connected to the input end of the first normalization module; the output end of the first normalization module is connected to the input end of the third fusion module; the input end of the second convolution module is used to receive dental image data, and the output end of the second convolution module is respectively connected to the input end of the third fusion module and the input end of the first fusion module; the output end of the second fusion module is connected to the input end of the fourth convolution module; the output end of the fourth convolution module is connected to the input end of the second normalization module; the output end of the second normalization module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the input end of the first activation module; the output end of the first activation module is used to output a dental image evaluation value.

[0066] The fusion module is constructed based on the concat operation in Python; the activation module is implemented based on the sigmoid, Tanh, or ReLU activation function.

[0067] The comprehensive evaluation process of the preprocessed tooth index data set to obtain an index evaluation value includes:

[0068] S3201, representing the tooth index data set as an index matrix; the row vector of the index matrix is ​​a time sampling sequence of each tooth index;

[0069] S3202, decomposing the indicator matrix to obtain a left decomposition matrix, a characteristic matrix, and a right decomposition matrix of the indicator matrix;

[0070] S3203, extracting the diagonal elements of the feature matrix to obtain a feature vector;

[0071] S3204, performing linear fitting processing on the elements and element sequence values ​​of the feature vector to obtain an approximation model;

[0072] S3205, obtaining the standard value of each tooth index;

[0073] S3206, for each time sampling sequence of a tooth index, calculating the absolute value of the difference between each element contained therein and the standard value corresponding to the tooth index; using the absolute values ​​of the differences calculated for all elements, constructing an offset sequence of the tooth index;

[0074] S3207, constructing an offset matrix using the offset sequences of all tooth indicators;

[0075] S3208, performing correlation calculation processing on the indicator matrix and the offset matrix to obtain a correlation vector;

[0076] S3209, for each tooth indicator offset sequence, find an element with a maximum value, determine the sequence number of the element in the offset sequence, and use it as the deviation sequence number of the tooth indicator;

[0077] S3210, using the approximation model, calculating and processing the deviation sequence values ​​of all tooth indicators to obtain an approximation sequence;

[0078] S3211, using the association vector as a weight sequence, performing weighted summation processing on the approximation sequence to obtain an indicator evaluation value.

[0079] The calculation expression of the decomposition process is:

[0080] A1=UAV,

[0081] Among them, U is the left decomposition matrix, A1 is the indicator matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix.

[0082] The calculation expression of the association calculation is:

[0083]

[0084] Among them, A1 ij is the element in the i-th row and j-th column of the indicator matrix A1, A2 ij is the element in the i-th row and j-th column of the offset matrix A2, p i is the i-th element of the association vector, and M is the column dimension of the indicator matrix.

[0085] The decomposition process can be implemented by using a matrix singular value decomposition algorithm.

[0086] The feature vector is represented as I a , I a =[λ1,λ2,…,λ N1 ], N1 is the number of elements contained in the eigenvector;

[0087] The linear fitting process uses the characteristic vector element serial number value Ix as a known independent variable and the characteristic vector element value as a known dependent variable, and constructs the curve to be approximated using the known independent variable and the known dependent variable, and uses the function approximation method to perform curve fitting on the curve to be approximated to obtain the approximation model f(Ix).

[0088] The curve fitting of the curve to be approximated by the function approximation method may be performed by using the best consistent linear approximation method. The approximation model f(Ix) is expressed as:

[0089] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α2(Ix) 2 +α1(Ix)+α0,

[0090] Wherein, P1 is the order of the approximation model f(Ix), α0, α1, α2, …, α P1 are the coefficients of the approximation model f(Ix);

[0091] The training process of the tooth image assessment model includes:

[0092] Acquire an evaluation knowledge training set; the evaluation knowledge training set includes tooth image data and corresponding evaluation values;

[0093] Initialize the number of training iterations;

[0094] The tooth image data in the evaluation knowledge training set is used as input data and input into the tooth image evaluation model; the evaluation value of the input data in the evaluation knowledge training set is used as label information;

[0095] Using the tooth image evaluation model, the input data is processed to obtain an evaluation index;

[0096] Performing difference calculation processing on the obtained evaluation index and label information to obtain a difference value;

[0097] Determine whether the difference value satisfies a convergence condition, and obtain a first determination result;

[0098] When the first judgment result is no, judging whether the training iteration number value is equal to the training number threshold, and obtaining a second judgment result;

[0099] When the second judgment result is no, determining that the model training state does not meet the training termination condition;

[0100] When the second judgment result is yes, determining that the model training state satisfies the training termination condition;

[0101] When the first judgment result is yes, determining that the model training state satisfies a training termination condition;

[0102] When the model training status does not meet the termination training condition, the parameter update model is used to update the parameters of the dental image evaluation model, and the training iteration number value is increased by 1, triggering the execution of inputting the dental image data in the evaluation knowledge training set as input data into the dental image evaluation model;

[0103] When the model training state satisfies the training termination condition, the training process of the tooth image evaluation model is completed to obtain a trained tooth image evaluation model.

[0104] The difference value satisfies the convergence condition, which means that the difference value is less than a preset convergence threshold; the difference value does not satisfy the convergence condition, which means that the difference value is not less than the preset convergence threshold.

[0105] The parameter updating model comprises:

[0106]

[0107] θ←θ+v;

[0108] In the formula, is the difference value obtained after the ith tooth image data in the evaluation knowledge training set is input into the tooth image evaluation model, v is the parameter update value, θ is the parameter of the tooth image evaluation model, η is the initial parameter learning rate, α is the momentum angle parameter, 0≤α≤π / 4, It means to find partial derivatives with respect to variable θ;

[0109] The tooth image data may be tooth three-dimensional point cloud data collected by laser radar, or computer tomography (CT) scan data, or

[0110] The noise reduction process can be implemented by using the DeNoise command in MATLAB.

[0111] The anomaly detection process includes:

[0112] For each type of data attribute of a data set, the data collection information of the data is used as an independent variable, and the data value of the data is used as a dependent variable, and autoregression-sliding average modeling is performed to obtain regression models of the data attributes of the type; the independent variables are calculated and processed using the regression model to obtain regression data values; it is determined whether the absolute value of the difference between the regression data value and the corresponding dependent variable value is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, the data is deleted from the data set; if it is less than or equal to the first regression discrimination threshold, the data is not processed;

[0113] Performing fusion processing on all data after anomaly detection in the data set to obtain a preprocessed data set;

[0114] The data cleaning process includes filling missing values, smoothing noise data, and smoothing or deleting outliers; the smoothed noise data is obtained by first determining the noise data, and then smoothing the noise data according to the data before and after the noise data; the noise data is a value whose value is less than the detection sensitivity of the sensor of the observed data, or greater than the measurement upper limit of the sensor of the observed data. The outlier point can be determined by the Kalman filter method. The filling value of the missing value can be determined by averaging the measured values ​​within a certain sampling interval before and after the missing value.

[0115] The tooth indicators of the tooth indicator data set include soft plaque index, tartar index, plaque index, gum index, gingival sulcus bleeding index, periodontal pocket depth, alveolar bone absorption degree and tooth mobility.

[0116] The tooth indexes of the tooth index data set are determined based on the indexes of general oral examination, and specifically include:

[0117] Periodontal probing examination: This is a basic method to check the health of periodontal tissues, usually performed using a conventional periodontal manual probe. The examination includes periodontal pocket depth, gingival bleeding, alveolar bone absorption, etc.

[0118] Oral hygiene index and related indices: These indices are used to measure oral hygiene status and include:

[0119] Debris Index (DI): evaluates the coverage area of ​​soft plaque on the tooth surface.

[0120] Calculus Index (CI): Assess the coverage of calculus above and below the gums.

[0121] Plaque Index (PLI): Assess the plaque status of the gingival margin and adjacent surfaces.

[0122] Gingival Index (GI): Assess the health of the gums, including inflammation, color changes, edema, etc.

[0123] Sulcus Bleeding Index (SBI): Assess gingival bleeding.

[0124] Specific examination indicators of periodontal disease: These indicators include the presence of tartar, gingival bleeding, periodontal pocket depth, degree of alveolar bone loss, and tooth mobility.

[0125] In a second aspect of the embodiment of the present application, a device for evaluating dental health status based on multi-source information is disclosed, the device comprising:

[0126] A memory storing executable program code;

[0127] a processor coupled to the memory;

[0128] The processor calls the executable program code stored in the memory to execute the dental health status assessment method based on multi-source information.

[0129] In a third aspect of the embodiments of the present application, a computer storable medium is disclosed, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the method for evaluating dental health status based on multi-source information.

[0130] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, wherein the information data processing terminal is used to implement the dental health status assessment method based on multi-source information.

[0131] The present invention first performs noise reduction, data cleaning and anomaly detection processing on the collected multi-source information, effectively filtering out noise and interference in the collected data, and ensuring the accuracy and consistency of the data source of health assessment.

[0132] The present invention adopts different evaluation and processing methods for different types of tooth collection data; the proposed deep learning model is used to evaluate and process the tooth image data; the indicator matrix and the offset matrix are constructed using the indicator data, and the proposed association calculation processing method is used to process the indicator matrix and the offset matrix to obtain the association vector; the association vector is used as a weight sequence to perform weighted summation processing on the approximation sequence to obtain the indicator evaluation value, thereby achieving effective extraction of the indicator health characteristics. Finally, the evaluation results of the two types of data, image and indicator, are fused using a fusion weighting method to obtain the final tooth health status evaluation result.

[0133] The dental health status assessment in the present invention includes: 1. Dentition integrity: whether there is an abnormal number of teeth, whether there are missing teeth. 2. Tooth arrangement: whether the dental arch is narrow, the dentition is crowded, the dentition is sparse, the overbite is deep, the overjet is deep, etc. 3. Tooth integrity: whether there are caries, wedge defects, residual roots and crowns, etc. 4. Periodontal health: whether the gums are red and swollen, whether the roots are exposed, etc.

[0134] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for evaluating dental health status based on multi-source information, characterized in that: include: S1, obtaining a tooth image data set and a tooth index data set; the tooth image data set includes tooth image data; The tooth index data set includes a time sampling sequence of tooth indexes; The time sampling sequence includes a plurality of acquisition values; S2, preprocessing the tooth image dataset and the tooth index dataset to obtain a preprocessed dataset; The preprocessed data set includes a preprocessed tooth image data set and a tooth index data set; S3, evaluating the preprocessed data set to obtain a dental health status evaluation value.

2. The method for evaluating dental health status based on multi-source information according to claim 1, characterized in that: The preprocessing of the tooth image dataset and the tooth index dataset to obtain a preprocessed dataset includes: Performing noise reduction processing on the tooth image dataset and the tooth index dataset to obtain a noise reduction dataset; Performing data cleaning processing on the noise reduction data set to obtain a first data set; Anomaly detection processing is performed on the first data set to obtain a preprocessed data set.

3. The method for evaluating dental health status based on multi-source information according to claim 1, characterized in that: The step of evaluating the preprocessed data set to obtain a dental health status evaluation value includes: S31, using the trained tooth image evaluation model, processing the preprocessed tooth image data set to obtain a tooth image evaluation value; S32, performing comprehensive evaluation processing on the preprocessed tooth index data set to obtain an index evaluation value; S33, performing weighted sum processing on the tooth image evaluation value and the index evaluation value to obtain a tooth health status evaluation value.

4. The method for evaluating dental health status based on multi-source information according to claim 3, characterized in that: The tooth image evaluation model includes a first convolution module, a second convolution module, a third convolution module, a fourth convolution module, a first fusion module, a second fusion module, a third fusion module, a first normalization module, a second normalization module, and a first activation module; The input end of the first convolution module is used to receive dental image data, and the output end of the first convolution module is respectively connected to the input end of the first fusion module and the input end of the second fusion module; the output end of the first fusion module is connected to the input end of the third convolution module; the output end of the third convolution module is connected to the input end of the first normalization module; the output end of the first normalization module is connected to the input end of the third fusion module; the input end of the second convolution module is used to receive dental image data, and the output end of the second convolution module is respectively connected to the input end of the third fusion module and the input end of the first fusion module; the output end of the second fusion module is connected to the input end of the fourth convolution module; the output end of the fourth convolution module is connected to the input end of the second normalization module; the output end of the second normalization module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the input end of the first activation module; the output end of the first activation module is used to output a dental image evaluation value.

5. The method for evaluating dental health status based on multi-source information according to claim 4, characterized in that: The comprehensive evaluation process of the preprocessed tooth index data set to obtain an index evaluation value includes: S3201, representing the tooth index data set as an index matrix; the row vector of the index matrix is ​​a time sampling sequence of each tooth index; S3202, decomposing the indicator matrix to obtain a characteristic matrix of the indicator matrix; S3203, extracting the diagonal elements of the feature matrix to obtain a feature vector; S3204, performing linear fitting processing on the elements and element sequence values ​​of the feature vector to obtain an approximation model; S3205, obtaining the standard value of each tooth index; S3206, for each time sampling sequence of a tooth index, calculating the absolute value of the difference between each collected value contained therein and the standard value of the tooth index; using the absolute value of the difference calculated for all collected values ​​of the time sampling sequence, constructing an offset sequence of the tooth index; S3207, constructing an offset matrix using the offset sequences of all tooth indicators; S3208, performing correlation calculation processing on the indicator matrix and the offset matrix to obtain a correlation vector; S3209, for each tooth indicator offset sequence, find an element with a maximum value, determine the sequence number of the element in the offset sequence, and use it as the deviation sequence number of the tooth indicator; S3210, using the approximation model, calculating and processing the deviation sequence values ​​of all tooth indicators to obtain an approximation sequence; S3211, using the association vector as a weight sequence, performing weighted summation processing on the approximation sequence to obtain an indicator evaluation value.

6. The method for evaluating dental health status based on multi-source information according to claim 5, characterized in that: The calculation expression of the decomposition process is: A1=UAV, Among them, U is the left decomposition matrix, A1 is the indicator matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix.

7. The method for evaluating dental health status based on multi-source information according to claim 5, characterized in that: The calculation expression of the association calculation is: Among them, A1 ij is the element in the i-th row and j-th column of the indicator matrix A1, A2 ij is the element in the i-th row and j-th column of the offset matrix A2, p i is the i-th element of the association vector, and M2 is the column dimension of the indicator matrix.

8. A dental health status assessment device based on multi-source information, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the dental health status assessment method based on multi-source information according to any one of claims 1 to 7.

9. A computer storable medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the dental health status assessment method based on multi-source information according to any one of claims 1 to 7.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the dental health status assessment method based on multi-source information as described in any one of claims 1 to 7.

Images