A method and device for oral gas detection for children

Abstract

The present invention discloses an oral gas detection method and device for children. The method includes: obtaining an oral gas detection information set of children with different types of health status information; the oral gas detection information set includes a number of oral gas detection information corresponding to each type of health status information; the oral gas detection information includes a hydrogen sulfide content sequence value, a methanethiol content sequence value, and a dimethyl sulfide content sequence value; performing correlation analysis processing on the health status information and the oral gas detection information set to obtain a gas correlation model; analyzing the components of the collected oral gas of children to obtain gas component detection result information; using the gas correlation model to perform identification processing on the gas component detection result information to obtain children's health status information. The present invention realizes the accurate detection of children's physical status through the full detection and feature extraction of children's oral gas information.

Description

Technical Field

[0001] The present invention relates to the fields of oral cavity detection and medical big data processing, and particularly to an oral gas detection method and device for children. Background Art

[0002] Bad breath is a common clinical phenomenon, with an incidence rate of about 30% in children. The main possible reasons are problems in the oral cavity itself, such as dental caries, dental plaque, food residues, etc. In addition, tonsil stones in the otolaryngology department, foreign bodies in the nasal cavity (such as rubber, pen caps, small toys, etc. accidentally entering the nasal cavity of children and not being removed in time, resulting in infection over time), sinusitis, etc. may also cause bad breath. Gastrointestinal reasons also account for a small part, such as indigestion or foods with peculiar odors, causing oral odor through belching and other forms. From the perspective of the components of the odor, they are mainly some sulfides. Specifically, the sulfide components contained in the odors in different positions such as the oral cavity, nasal cavity, pharynx, and stomach are different. Generally speaking, the oral gas of children contains rich information on health status and physical condition. How to effectively detect and extract the features of children's oral gas information to achieve the detection of children's physical condition is an important problem to be solved. Summary of the Invention

[0003] The present invention mainly solves the problem of how to effectively detect and extract the features of children's oral gas information to achieve the detection of children's physical condition, and discloses an oral gas detection method and device for children.

[0004] In the first aspect of the embodiments of the present application, an oral gas detection method for children is disclosed, including:

[0005] S1, obtaining a set of oral gas detection information of children with different types of health status information; the set of oral gas detection information includes several oral gas detection information corresponding to each type of health status information; the oral gas detection information includes hydrogen sulfide content sequence values, methanethiol content sequence values, and dimethyl sulfide content sequence values;

[0006] S2, performing correlation analysis processing on the health status information and the set of oral gas detection information to obtain a gas correlation model;

[0007] S3, performing component analysis on the collected oral gas of children to obtain gas component detection result information;

[0008] S4, using the gas correlation model to perform identification processing on the gas component detection result information to obtain children's health status information.

[0009] Performing correlation analysis and processing on the set of the health status information and the oral gas detection information to obtain a gas correlation model, including:

[0010] S21, respectively performing preprocessing on the health status information and the set of oral gas detection information to obtain preprocessed health status information and a set of preprocessed oral gas detection information;

[0011] S22, representing all types of health status information as state vectors; representing the set of preprocessed oral gas detection information corresponding to each type of health status information as a corresponding gas detection matrix; the elements of the state vector being the encoded values of each type of health status information;

[0012] S23, performing data reduction processing on the gas detection matrices corresponding to all types of health status information to obtain data reduction matrices;

[0013] S24, using the data reduction matrix to perform transformation processing on the gas detection matrix corresponding to each type of health status information to obtain a corresponding reduced-dimension gas detection matrix; the reduced-dimension gas detection matrix including reduced-dimension gas detection vectors;

[0014] S25, performing state estimation processing on the state vectors and the reduced-dimension gas detection matrices corresponding to all types of health status information to obtain state estimation vectors;

[0015] S26, constructing a gas correlation model by using the reduced-dimension gas detection matrix and the state estimation vectors.

[0016] Respectively performing preprocessing on the health status information and the set of oral gas detection information to obtain preprocessed health status information and a set of preprocessed oral gas detection information, including:

[0017] S211, respectively performing normalization processing on the health status information and the set of oral gas detection information to obtain preprocessed health status information and a set of normalized oral gas detection information;

[0018] S212, respectively performing boundary check processing on the preprocessed health status information and the set of normalized oral gas detection information to obtain a set of preprocessed oral gas detection information.

[0019] Respectively performing boundary check processing on the preprocessed health status information and the set of normalized oral gas detection information to obtain a set of preprocessed oral gas detection information, including:

[0020] For the set of normalized oral gas detection information corresponding to all types of health status information, taking the data value of each type of data in the oral gas detection information as the dependent variable and the corresponding health status information of the data as the independent variable, perform autoregressive-moving average modeling on the dependent variable and the independent variable to obtain the regression model of the type of data respectively;

[0021] Using the regression model, perform calculation processing on the independent variable to obtain the regression data value;

[0022] Determine whether the absolute value of the difference between the regression data value and the corresponding dependent variable value is greater than the set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the set of normalized oral gas detection information, and if it is less than or equal to the first regression discrimination threshold, do not process the data.

[0023] The state estimation processing of the state vector and the reduced-dimensional gas detection matrix corresponding to all types of health status information to obtain a state estimation vector includes:

[0024] Using the state vector and the reduced-dimensional gas detection matrix corresponding to all types of health status information, construct an estimation error model;

[0025] Solve the estimation error model to obtain a state estimation vector.

[0026] The estimation error model includes:

[0027]

[0028] v T ·v = 1,

[0029] where v is the state estimation vector, v is a column vector of dimension 2, a k is the k-th element of the state vector and also the encoding value of the k-th type of health status information, r i k is the i-th row vector of the reduced-dimensional gas detection matrix corresponding to the k-th type of health status information, P is the number of types of health status information, and N is the row dimension of the reduced-dimensional gas detection matrix.

[0030] The gas association model includes:

[0031] Using the data reduction matrix, multiply it with the preprocessed oral gas detection information to obtain a reduced-dimensional gas detection vector;

[0032] Using the state estimation vector, multiply it with the reduced-dimensional gas detection vector to obtain a child health status estimation value;

[0033] Round the estimated value of the child's health status to obtain the child's health status value;

[0034] Determine the corresponding child health status information according to the child health status value.

[0035] In the second aspect of the embodiments of the present application, an oral gas detection device for children is disclosed. The device includes:

[0036] A memory storing executable program code;

[0037] A processor coupled to the memory;

[0038] The processor calls the executable program code stored in the memory and executes the above-mentioned oral gas detection method for children.

[0039] In the third aspect of the embodiments of the present application, a computer-readable storage medium is disclosed. The computer-readable storage medium stores computer instructions, which are used to execute the above-mentioned oral gas detection method for children when called by a computer.

[0040] In the fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed. The information data processing terminal is used to implement the above-mentioned oral gas detection method for children.

[0041] The beneficial effects of the present invention are as follows:

[0042] With the device of the present invention, a child blows air into the gas collection device on an empty stomach in the morning, and the reagent (or other measurement methods) in the device can measure the content of certain target gases. By extracting and correlating the physical characteristics of children and the characteristics of the exhaled components, the present invention establishes a gas correlation model, and through effective and sufficient detection and feature extraction of children's oral gas information, accurate detection of children's physical conditions is achieved.

[0043] The present invention establishes a state vector, performs state estimation processing on the state vector and the reduced-dimension gas detection matrix corresponding to all types of health status information, obtains a state estimation vector, reduces the detection complexity, effectively suppresses noise and interference in the collected information, and improves the detection accuracy. Description of the Drawings

[0044] Figure 1 It is a flowchart of the implementation of the method of the present invention. Detailed Embodiments

[0045] To better understand the content of the present invention, an embodiment is given here.

[0046] Figure 1 It is a flowchart of the implementation of the method of the present invention.

[0047] Regarding the problem of how to effectively detect and extract the characteristics of children's oral gas information to achieve the detection of children's physical conditions, the present invention discloses an oral gas detection method and device for children.

[0048] In the first aspect of the embodiments of the present application, an oral gas detection method for children is disclosed, including:

[0049] S1, obtaining a set of oral gas detection information of children with different types of health status information; the set of oral gas detection information includes several oral gas detection information corresponding to each type of health status information; the oral gas detection information includes hydrogen sulfide content sequence values, methanethiol content sequence values, and dimethyl sulfide content sequence values;

[0050] S2, performing correlation analysis processing on the health status information and the set of oral gas detection information to obtain a gas correlation model;

[0051] S3, performing component analysis on the collected children's oral gas to obtain gas component detection result information;

[0052] S4, using the gas correlation model to perform identification processing on the gas component detection result information to obtain children's health status information;

[0053] The performing correlation analysis processing on the health status information and the set of oral gas detection information to obtain a gas correlation model includes:

[0054] S21, respectively performing preprocessing on the health status information and the set of oral gas detection information to obtain preprocessed health status information and a preprocessed set of oral gas detection information;

[0055] S22, representing all types of health status information as state vectors; representing the preprocessed set of oral gas detection information corresponding to each type of health status information as a corresponding gas detection matrix; the elements of the state vector are the coding values of each type of health status information;

[0056] S23, performing data reduction processing on the gas detection matrices corresponding to all types of health status information to obtain a data reduction matrix;

[0057] S24, using the data reduction matrix to perform transformation processing on the gas detection matrix corresponding to each type of health status information to obtain a corresponding reduced-dimensional gas detection matrix; the reduced-dimensional gas detection matrix includes reduced-dimensional gas detection vectors;

[0058] S25. Perform state estimation processing on the state vector and the reduced-dimension gas detection matrices corresponding to all types of health state information to obtain a state estimation vector.

[0059] S26. Use the reduced-dimension gas detection matrix and the state estimation vector to construct a gas correlation model.

[0060] The preprocessing of the health state information and the set of oral gas detection information respectively to obtain preprocessed health state information and a set of preprocessed oral gas detection information includes:

[0061] S211. Perform normalization processing on the health state information and the set of oral gas detection information respectively to obtain preprocessed health state information and a set of normalized oral gas detection information.

[0062] S212. Perform boundary check processing on the preprocessed health state information and the set of normalized oral gas detection information respectively to obtain a set of preprocessed oral gas detection information.

[0063] The performing boundary check processing on the preprocessed health state information and the set of normalized oral gas detection information respectively to obtain a set of preprocessed oral gas detection information includes:

[0064] For the set of normalized oral gas detection information corresponding to all types of health state information, taking the data value of each type of data in the oral gas detection information as the dependent variable and the corresponding health state information of the data as the independent variable, perform autoregressive-moving average modeling on the dependent variable and the independent variable to respectively obtain the regression models for the type of data.

[0065] Use the regression model to perform calculation processing on the independent variable to obtain a regression data value.

[0066] Determine 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, delete the data from the set of normalized oral gas detection information, and if it is less than or equal to the first regression discrimination threshold, do not process the data.

[0067] The value of the first regression discrimination threshold can be 5.

[0068] The performing state estimation processing on the state vector and the reduced-dimension gas detection matrices corresponding to all types of health state information to obtain a state estimation vector includes:

[0069] Use the state vector and the reduced-dimension gas detection matrices corresponding to all types of health state information to construct an estimation error model.

[0070] Solve the estimation error model to obtain the state estimation vector.

[0071] The estimation error model includes:

[0072]

[0073] v T ·v = 1,

[0074] where v is the state estimation vector, v is a column vector with a dimension of 2, a k is the k-th element of the state vector and also the coding value of the health state information of the k-th type, r i k is the i-th row vector of the dimensionality reduction gas detection matrix corresponding to the health state information of the k-th type, P is the number of types of health state information, and N is the row dimension of the dimensionality reduction gas detection matrix.

[0075] The gas association model includes:

[0076] Multiply the data reduction matrix by the preprocessed oral gas detection information to obtain a dimensionality reduction gas detection vector;

[0077] Multiply the state estimation vector by the dimensionality reduction gas detection vector to obtain a child health state estimation value;

[0078] Round the child health state estimation value to obtain a child health state value;

[0079] Determine the corresponding child health state information according to the child health state value.

[0080] Perform data reduction processing on the gas detection matrices corresponding to all types of health state information to obtain a data reduction matrix, which is to use the principal component analysis method to perform principal component extraction processing on the gas detection matrix, and use the obtained principal component extraction matrix as the data reduction matrix; the dimension of the data reduction matrix is 3 rows and 2 columns. Data reduction processing can adopt the feature reduction algorithm.

[0081] The data reduction matrix is used to implement data reduction processing on data.

[0082] The autoregressive-moving average modeling can adopt the ARMA method.

[0083] All oral gas detection information of the same type of health state information is represented as the corresponding oral graph

[0084] The health status information includes the encoding value 1 of the first health status information, the encoding value 2 of the second health status information, the encoding value 3 of the third health status information, and the encoding value 4 of the fourth health status information; the first health status information may be completely healthy; the second health status information may be oral health problems or diet - related factors; the third health status information may be digestive system health problems or lifestyle issues; the third health status information may be genetic factors.

[0085] Determining the corresponding child health status information according to the child health status value is a process of reverse decoding based on the encoding value of the health status information to determine the corresponding health status information according to the composition of the health status information.

[0086] The collected oral gas of children is realized by using a gas chromatograph; the gas component detection result information includes hydrogen sulfide content, methanethiol content, and dimethyl sulfide content.

[0087] The health status information is digital encoding information for different health status types of children.

[0088] In this method, after executing S23 and before executing S24 to obtain the data reduction matrix, it further includes optimizing the data reduction matrix and using the optimized data reduction matrix in S24.

[0089] The optimization process includes:

[0090] Calculating the cross - correlation matrix of all row vectors of the obtained data reduction matrix;

[0091] Performing decomposition processing on the cross - correlation matrix to obtain the eigenmatrix;

[0092] The calculation expression of the decomposition processing is:

[0093] Y = UAV,

[0094] where U is the left decomposition matrix, A is the eigenmatrix, V is the right decomposition matrix, both U and V are orthogonal matrices, and A is a diagonal matrix; the decomposition processing can adopt QR decomposition processing.

[0095] Multiplying the left decomposition matrix by the data reduction matrix to obtain the optimized data reduction matrix.

[0096] In the second aspect of the embodiments of the present application, an oral gas detection device for children is disclosed. The device includes:

[0097] A memory storing executable program code;

[0098] A processor coupled to the memory;

[0099] The processor calls the executable program code stored in the memory and executes the oral gas detection method for children.

[0100] In a third aspect of the embodiments of the present application, a computer-readable storage medium is disclosed. The computer-readable storage medium stores computer instructions, which are used to execute the oral gas detection method for children when called by a computer.

[0101] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed. The information data processing terminal is used to implement the oral gas detection method for children.

[0102] The above are only the embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for detecting oral gas for children, characterized in that: include: S1, obtaining a set of oral gas detection information of children who have obtained different types of health status information; the set of oral gas detection information includes a number of oral gas detection information corresponding to each type of health status information; the oral gas detection information includes a sequence value of hydrogen sulfide content, a sequence value of methyl mercaptan content, and a sequence value of dimethyl sulfide content; S2, performing correlation analysis on the health status information and the oral gas detection information set to obtain a gas correlation model; S3, analyzing the components of the collected oral gas of the child to obtain gas component detection result information; S4, using the gas association model to identify and process the gas component detection result information to obtain the child's health status information; The correlating analysis and processing of the health status information and the oral gas detection information set to obtain a gas correlation model includes: S21, preprocessing the health status information and the oral gas detection information set respectively to obtain preprocessed health status information and preprocessed oral gas detection information set; S22, representing all types of health status information as a state vector; representing a set of pre-processed oral gas detection information corresponding to each type of health status information as a corresponding gas detection matrix; the elements of the state vector are the encoding values ​​of each type of health status information; S23, performing data reduction processing on the gas detection matrices corresponding to all types of health status information to obtain a data reduction matrix; S24, using a data reduction matrix, transforming a gas detection matrix corresponding to each type of health status information to obtain a corresponding reduced-dimensionality gas detection matrix; the reduced-dimensionality gas detection matrix includes a reduced-dimensionality gas detection vector; S25, performing state estimation processing on the state vector and the reduced-dimensional gas detection matrix corresponding to all types of health status information to obtain a state estimation vector; S26, constructing a gas correlation model using the reduced-dimensional gas detection matrix and the state estimation vector.

2. The oral gas detection method for children according to claim 1, characterized in that: The preprocessing of the health status information and the oral gas detection information set to obtain preprocessed health status information and preprocessed oral gas detection information set includes: S211, normalizing the health status information and the oral gas detection information set respectively to obtain pre-processed health status information and a normalized oral gas detection information set; S212, performing boundary check processing on the pre-processed health status information and the normalized oral gas detection information set respectively to obtain a pre-processed oral gas detection information set.

3. The method for detecting oral gas for children according to claim 2, characterized in that: The pre-processed health status information and the normalized oral gas detection information set are subjected to boundary check processing respectively to obtain the pre-processed oral gas detection information set, including: For the normalized oral gas detection information set corresponding to all types of health status information, the data value of each type of oral gas detection information is taken as the dependent variable, and the corresponding health status information of the data is taken as the independent variable. The dependent variable and the independent variable are subjected to autoregression-sliding average modeling to obtain the regression model of the data of the type; Using the regression model, the independent variable is calculated to obtain regression data values; Determine 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, delete the data from the normalized oral gas detection information set; if it is less than or equal to the first regression discrimination threshold, do not process the data.

4. The method for detecting oral gas for children according to claim 3, characterized in that: The state estimation process is performed on the state vector and the reduced-dimensional gas detection matrix corresponding to all types of health status information to obtain the state estimation vector, including: An estimation error model is constructed using the reduced-dimensional gas detection matrix corresponding to the state vector and all types of health status information; The estimation error model is solved to obtain a state estimation vector.

5. The method for detecting oral gas for children according to claim 4, characterized in that: The estimation error model comprises: v T ·v=1, Among them, v is the state estimation vector, v is a column vector with dimension 2, and a k is the kth element of the state vector, and is also the encoding value of the kth type of health status information, r i k is the i-th row vector of the reduced-dimensionality gas detection matrix corresponding to the k-th type of health status information, P is the number of types of health status information, and N is the row dimension of the reduced-dimensionality gas detection matrix.

6. The method for detecting oral gas for children according to claim 3, characterized in that: The gas correlation model comprises: The data reduction matrix is ​​used to multiply the preprocessed oral gas detection information to obtain a dimension-reduced gas detection vector; The state estimation vector is used to multiply the dimension-reduced gas detection vector to obtain the estimated value of the child's health state; Rounding the estimated value of the child's health status to obtain a child's health status value; According to the child health status value, the corresponding child health status information is determined.

7. An oral gas detection device for children, 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 oral gas detection method for children according to any one of claims 1 to 6.

8. A computer storable medium, characterized in that: The computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the oral gas detection method for children according to any one of claims 1 to 6.

9. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the oral gas detection method for children according to any one of claims 1 to 6.

Images