Health management method, system and equipment based on multi-dimensional detection and storage medium

Abstract

The invention discloses a health management method, system and device based on multi-dimensional detection and a storage medium, and the method comprises the steps: carrying out the traditional Chinese medicine constitution recognition, intelligent tongue diagnosis detection and meridian detection of a user, and obtaining a plurality of detection results of the physical condition of the user; fusing the multiple detection results by adopting a diagnosis fusion strategy to obtain a diagnosis result; and providing personalized health management suggestions for the user according to the diagnosis result. Multiple detection results of the physical condition of the user are obtained by carrying out multi-dimensional detection such as traditional Chinese medicine constitution, intelligent tongue diagnosis and meridian measurement on the user, the accuracy and pertinence of diagnosis are improved by carrying out fusion analysis on the multiple detection results, meanwhile, a fusion diagnosis technology is combined, and the diagnosis accuracy and pertinence are improved. According to the invention, personalized health suggestions and schemes can be provided according to specific conditions of the user, and compared with an existing health management system, the health management system has higher accuracy and pertinence, and more scientific and personalized health management services can be provided for the user.

Description

Technical Field

[0001] The present invention relates to a health management method, system, device and storage medium based on multi-dimensional detection, belonging to the clinical field of traditional Chinese medicine. Background Art

[0002] At present, there are some health management systems based on TCM constitution, intelligent tongue diagnosis, and meridian measurement, but most of these systems only analyze a certain detection technology, without combining multiple technologies, resulting in insufficient personalization. In addition, the existing health management systems also have problems such as inaccurate diagnosis results and lack of scientific basis. Therefore, the present invention aims to provide a comprehensive health management system and method based on TCM constitution, intelligent tongue diagnosis, and meridian measurement, which improves the accuracy of diagnosis results by integrating multiple detection technologies, and provides users with more personalized and scientific health management services.

[0003] There have been some relevant research results in the industry, such as health management systems based on TCM constitution theory, health management systems based on intelligent tongue diagnosis, and health management systems based on meridian measurement. However, these systems have the limitations of a single technology and cannot provide comprehensive health management services. At the same time, the existing health management systems also lack targeted diagnostic methods and cannot provide personalized health advice based on the specific circumstances of users. Summary of the invention

[0004] In view of this, the present invention provides a multi-dimensional health management method, system, computer device and storage medium, which improves the accuracy and pertinence of diagnosis by integrating and analyzing multiple test results. It also combines diagnostic fusion technology to provide personalized health advice and plans based on the user's specific circumstances.

[0005] The first object of the present invention is to provide a multi-dimensional health management method.

[0006] The second object of the present invention is to provide a multi-dimensional TCM constitution identification system.

[0007] A third object of the present invention is to provide a computer device.

[0008] A fourth object of the present invention is to provide a storage medium.

[0009] The first object of the present invention can be achieved by adopting the following technical solutions:

[0010] A health management method based on multi-dimensional detection, the method comprising:

[0011] Perform TCM constitution identification, intelligent tongue diagnosis and meridian detection on users to obtain various test results of users' physical conditions;

[0012] A diagnostic fusion strategy is used to fuse multiple test results to obtain a diagnostic result;

[0013] Provide users with personalized health management suggestions based on the diagnosis results.

[0014] Furthermore, the diagnostic fusion strategy is used to fuse multiple test results to obtain a diagnostic result, including:

[0015] The multiple detection results are input into a diagnosis fusion model, and feature-level fusion and decision-level fusion are performed on the multiple detection results to obtain a diagnosis result. The diagnosis fusion model includes a feature-level fusion part and a decision-level fusion part.

[0016] Furthermore, the feature-level fusion and decision-level fusion of the multiple detection results to obtain the diagnosis result include:

[0017] Through the fusion analysis of multiple test results, multiple sub-features are obtained, and a group of sub-features with a high correlation with the health status of traditional Chinese medicine are found;

[0018] Using the canonical association analysis theory, a group of sub-features are fused into a new feature as the TCM health status feature;

[0019] The characteristics of TCM health status are integrated into decision-making to obtain the diagnosis result.

[0020] Furthermore, the decision-making integration of the TCM health status characteristics to obtain the diagnosis result includes:

[0021] Multiple classifiers are used to identify the characteristics of TCM health status and obtain local recognition results;

[0022] Based on Bayesian theory and voting rules, the local recognition results are comprehensively analyzed to obtain the diagnosis results.

[0023] Furthermore, the basic characteristics of TCM constitution identification include constitution type, constitution definition and constitution cause.

[0024] Furthermore, the basic features of the intelligent tongue diagnosis include tongue coating, tongue color, tongue shape and tongue coating color.

[0025] Furthermore, the basic features of the meridian detection include main problem meridians, meridian reference values, meridian states, health items and meridian values.

[0026] The second object of the present invention can be achieved by adopting the following technical solutions:

[0027] A health management system based on multi-dimensional detection, the system comprising:

[0028] The detection module is used to identify the user's TCM constitution, perform intelligent tongue diagnosis and meridian detection, and obtain various test results of the user's physical condition;

[0029] A fusion module is used to fuse multiple test results using a diagnostic fusion strategy to obtain a diagnostic result;

[0030] The health management suggestion module is used to provide users with personalized health management suggestions based on the diagnosis results.

[0031] The third object of the present invention can be achieved by adopting the following technical solutions:

[0032] A computer device includes a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the above-mentioned health management method is implemented.

[0033] The fourth object of the present invention can be achieved by adopting the following technical solutions:

[0034] A storage medium stores a program, and when the program is executed by a processor, the above-mentioned health management method is implemented.

[0035] The present invention has the following beneficial effects compared with the prior art:

[0036] The present invention obtains multiple test results of the user's physical condition by performing multi-dimensional tests on the user's traditional Chinese medicine constitution, intelligent tongue diagnosis, meridian measurement, etc., and improves the accuracy and pertinence of the diagnosis through fusion analysis of multiple test results. At the same time, it also combines diagnostic fusion technology to provide personalized health advice and plans based on the user's specific situation. Compared with existing health management systems, the present invention has higher accuracy and pertinence, and can provide users with more scientific and personalized health management services. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0038] Figure 1 This is a flow chart of a health management method based on multi-dimensional detection according to Example 1 of the present invention.

[0039] Figure 2This is a schematic diagram of the principle of the diagnostic fusion model of Example 1 of the present invention.

[0040] Figure 3 This is a structural block diagram of a health management system based on multi-dimensional detection according to Example 2 of the present invention.

[0041] Figure 4 This is a structural block diagram of a computer device according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0043] Embodiment 1:

[0044] like Figure 1 As shown, this embodiment provides a health management method based on multi-dimensional detection, which uses traditional Chinese medicine constitution theory, intelligent tongue diagnosis technology and meridian measurement technology, combined with fusion diagnosis technology, to provide personalized health management services, specifically including the following steps:

[0045] S101, performing TCM constitution identification, intelligent tongue diagnosis and meridian detection on the user to obtain various test results of the user's physical condition.

[0046] In one embodiment, the basic features of TCM constitution identification include constitution type, constitution definition and constitution cause; the basic features of intelligent tongue diagnosis include tongue coating, tongue color, tongue shape and tongue coating color; the basic features of meridian detection include main problem meridians, meridian reference values, meridian status, health items and meridian values.

[0047] Meridian detection push method: http: / / aimed.jinhuatuo.com / aimed-api / (PUSH_URL_FROM_APP)

[0048] Tongue image detection interface: http: / / aimed.jinhuatuo.com / aimed-api / tongue / submit

[0049] Physical identification interface: http: / / aimed.jinhuatuo.com / aimed-api / physique / subject-commit

[0050] In one embodiment, through the detection of three dimensions of traditional Chinese medicine constitution, intelligent tongue diagnosis and meridians, various detection results of the user's physical condition are obtained as shown in Table 1 below.

[0051] Table 1 Multi-dimensional detection results

[0052]

[0053]

[0054]

[0055]

[0056]

[0057] S102. Using a diagnostic fusion strategy to fuse multiple test results to obtain a diagnostic result.

[0058] In one embodiment, the principle of the diagnostic fusion model is as follows Figure 2 As shown, the diagnosis fusion model includes a feature-level fusion part and a decision-level fusion part. Multiple test results are input into the diagnosis fusion model, and feature-level fusion and decision-level fusion are performed on the multiple test results to obtain a diagnosis result.

[0059] In one embodiment, multiple test results are fused at the feature level and the decision level, including: obtaining multiple sub-features through fusion analysis of the multiple test results, and finding a group of sub-features with a high correlation with the TCM health status; using the canonical association analysis theory, a group of sub-features are fused into a new feature as a TCM health status feature; and the TCM health status features are fused at the decision level to obtain a diagnosis result.

[0060] In one embodiment, based on the detection results of the three dimensions, a user health status vector H = [h1, h2, ..., h n ], where h i Represents different health indicators (different test results); Regarding physical identification, define the physical characteristic vector T = [t1, t2, ..., t k ], where t i ∈{0,1,...,m}, m is the number of constitution types; for tongue image detection, define the tongue image feature vector S = [s1,s2,s3,s4], where s1 is tongue coating, s2 is tongue color, s3 is tongue shape, and s4 is tongue coating color; for meridian detection, define the meridian feature vector M = [m1,m2,...,m l ], where m i Represents the state value of the i-th meridian.

[0061] In one embodiment, multiple sub-features are obtained by fusion analysis of multiple detection results, as follows:

[0062] 1) Feature integration: F = [T; S; M] / / feature concatenation.

[0063] 2) Use principal component analysis (PCA) for dimensionality reduction: F' = PCA (F) = W^T*F, where W is the eigenvector matrix.

[0064] In one embodiment, a group of sub-features with a high correlation with the health status of traditional Chinese medicine are found, as follows:

[0065] 1) It is necessary to calculate the correlation between each sub-feature and the target variable (health status in this embodiment). There are several commonly used methods:

[0066] a) Pearson Correlation Coefficient:

[0067] For continuous variables, the Pearson correlation coefficient can be used Where X is the feature and Y is the target variable.

[0068] b) Spearman's Rank Correlation Coefficient:

[0069] For nonlinear relationships or ordinal variables, the Spearman correlation coefficient ρ = 1-(6*Σd 2 ) / (n*(n 2 -1)), where d is the rank difference and n is the number of samples.

[0070] c) Mutual Information:

[0071] For categorical variables or nonlinear relationships, mutual information is a good choice, I(X;Y) = ΣΣp(x,y)*log(p(x,y) / (p(x)*p(y))).

[0072] 2) After calculating the correlation, you can select sub-features with higher correlation by the following method:

[0073] a) Threshold-based selection:

[0074] Set a threshold θ and select features that meet the following condition: |correlation(X,Y)|>θ. For example, you can set θ=0.5 and select features whose absolute value of the correlation coefficient is greater than 0.5.

[0075] b) Selection based on sorting:

[0076] Sort all features by their absolute value of relevance from large to small, and select the first k features. k can be set according to specific needs, for example, select the first 10 features.

[0077] c) Recursive Feature Elimination (RFE):

[0078] Train a model (such as linear regression or support vector machine), calculate the importance score for each feature, remove the least important features, and repeat until a preset number of features is reached

[0079] d) LASSO Regularization:

[0080] Use L1 regularized linear model for feature selection, min(||Y-Xβ|| 2 +λ||β||1), where λ is used to control the regularization strength. A larger λ will cause more features to be compressed to 0.

[0081] In one embodiment, sub-feature selection may be performed by combining multiple methods, as follows:

[0082] S1. Data preprocessing

[0083] Handle missing values; encode categorical variables (such as one-hot encoding); standardize or normalize continuous variables.

[0084] S2. Calculate the correlation

[0085] For continuous variables, Pearson correlation coefficient was calculated; for categorical variables, mutual information was calculated

[0086] S3. Preliminary feature screening

[0087] Set the threshold θ = 0.3; select features with an absolute correlation value greater than θ

[0088] S4. Recursive feature elimination

[0089] Use random forest as the basic model; the initial feature set is the result of S3; gradually delete the least important features until the number of features is reduced to a preset value (such as 20).

[0090] S5, LASSO regularization

[0091] Use cross validation to determine the optimal λ value; apply the LASSO model to further screen features

[0092] S6. Final feature set

[0093] Combining the results of RFE and LASSO, select the features retained by both methods; if the number of features is still too large, select the top k features based on the relevance ranking.

[0094] S7. Verification

[0095] Train the model using the selected feature subset; evaluate the model performance on the validation set; if the performance is not satisfactory, you can adjust the parameters of feature selection or try other methods.

[0096] In one embodiment, TCM health status features are subjected to decision fusion to obtain a diagnosis result, including: using multiple classifiers to identify TCM health status features to obtain local identification results; using Bayesian theory and voting rules to comprehensively analyze the local identification results to obtain a diagnosis result.

[0097] In one embodiment, multiple classifiers are used to identify the TCM health status features to obtain local recognition results as follows:

[0098] Construct a multi-classifier integration system as a diagnostic fusion model: C = {C1, C2, ..., C k}, where C i Represents a single classifier.

[0099] a. Decision tree based classifier: C1(F”) = DecisionTree(F”)

[0100] b. Support vector machine classifier: C2(F”) = SVM(F”)

[0101] c. Neural network classifier: C3(F”)=NeuralNetwork(F”)

[0102] In one embodiment, the local recognition results are comprehensively analyzed based on Bayesian theory and voting rules, as follows:

[0103] a. Bayesian fusion: P(ω|x)=Σ i P(ω|C i (x))*P(C i |x) / P(ω), where ω is the health status category and x is the input feature.

[0104] b. Weighted voting: y = argmax_ωΣ i w i *I(C i (x) = ω), where w i is the classifier weight, and I is the indicator function.

[0105] In one embodiment, the TCM health status features are fused for decision making to obtain a diagnosis result. The specific process is as follows:

[0106] 1) Data preparation

[0107] Suppose the TCM health status feature vector is X = [x1, x2, ..., x], where n is the number of features; the health status label is Y, which can be a discrete category (such as "healthy", "sub-healthy", "disease") or a continuous health index.

[0108] 2) Classifier selection

[0109] Select K different classifiers to form a classifier set C = {C1, C2, ..., C k}, Commonly used classifiers include: Decision Tree, Support Vector Machine (SVM), Random Forest, k-Nearest Neighbors (kNN), Naive Bayes, and Neural Network.

[0110] 3) Training process

[0111] For each classifier C i :

[0112] a) Data partitioning: Randomly divide the dataset into a training set (X_train, Y_train) and a validation set (X_val, Y_val).

[0113] b) Parameter optimization: Use grid search or random search to optimize hyperparameters, θ i * = argmax_θF(C i (X_val; θ), Y_val), where F is the performance evaluation function (such as accuracy, F1 score, etc.).

[0114] c) Model training: Use the optimized parameters to train the model on the training set. i *=C i (X_train,Y_train;θ i *).

[0115] 4) Identification process

[0116] For the new input feature X_new:

[0117] a) Individual classifier predictions:

[0118] For each classifier C i *, calculate its predicted result y i =C i *(X_new).

[0119] b) Integrated decision making:

[0120] Combine the results of individual classifiers according to different ensemble strategies:

[0121] Majority voting method (applicable to classification problems): y_pred = mode([y1,y2,...,y k ]);

[0122] Weighted voting method: y_pred = argmax_yΣ i w i *I(y i =y), where w i is the classifier C i The weight of can be determined based on its performance on the validation set.

[0123] Average method (applicable to regression problems): y_pred = (1 / K)*Σ i y i .

[0124] c) Training:

[0125] Train a meta-classifier M, taking the output of the individual classifiers as input, y_pred = M([y1,y2,...,y k ])

[0126] d) Performance evaluation:

[0127] Use the test set (X_test, Y_test) to evaluate the performance of the ensemble model:

[0128] For classification problems: calculate accuracy, precision, recall, F1 score, etc.

[0129] For regression problems: calculate mean square error (MSE), mean absolute error (MAE), etc.

[0130] 5) Model interpretation

[0131] To improve the interpretability of the model, the following methods can be used:

[0132] a) Feature Importance Analysis: For tree-based methods (such as random forests), the importance score of each feature is calculated.

[0133] b) SHAP (SHapley Additive exPlanations) value: calculates the contribution of each feature to the prediction result

[0134] c) Partial Dependence Plots: Analyze the impact of a single feature on the prediction results

[0135] 6) Dynamic Update

[0136] In order to adapt to the dynamic changes in health status, the model can be updated regularly using online learning methods:

[0137] a) Incremental learning: For classifiers that support incremental learning (such as some decision tree algorithms), new data is used for incremental updates.

[0138] b) Sliding window: Maintain a fixed-size training data window and periodically retrain the model with the latest data.

[0139] S103. Provide personalized health management suggestions to users based on the diagnosis results.

[0140] In one embodiment, the diagnosis result can be optimized first: introduce time series information and construct a dynamic Bayesian network P(H_t|H_{t-1},F”t)=P(H_t|H{t-1})*P(F”_t|H_t) / P(F”_t).

[0141] In one embodiment, the process of generating personalized health management suggestions is as follows:

[0142] Define the health management strategy space A = {a1, a2, ..., a m}, the goal is to find the optimal strategy a*=argmax_aQ(H,a).

[0143] a) Rule-based strategy generation: if condition(H) then a=a i .

[0144] b) Reinforcement learning optimization: Q(H,a)←Q(H,a)+α[R+γmax_a'Q(H',a')-Q(H,a)], where R is the reward function, α is the learning rate, and γ is the discount factor.

[0145] In one embodiment, continuous optimization may be performed:

[0146] a) Online Learning Updates: Where θ is the model parameter, η is the learning rate, and L is the loss function.

[0147] b) Transfer learning: θ_target=θ_source+Δθ, minimize L_target(θ_target)+λ||Δθ|| 2

[0148] c) Knowledge graph update: G = (V, E, R), where V is the vertex set (health concepts), E is the edge set (conceptual relations), and R is the relationship type set.

[0149] The following provides personalized health management suggestions for users based on the diagnosis results of two examples:

[0150] Example 1:

[0151] The diagnosis results show that the user has a yang deficiency constitution. Tongue examination shows that the tongue is pale, plump and tender with white fur. Meridian examination shows that the kidney meridian and spleen meridian are deficient in qi and blood. The health management suggestions given are:

[0152] 1) Dietary adjustment: It is recommended to eat more foods that warm and nourish Yang Qi, such as lamb, beef, chicken, etc., and at the same time eat an appropriate amount of ingredients that nourish Kidney Yin, such as black sesame and wolfberry.

[0153] 2) Exercise recommendations: It is advisable to do gentle exercise, such as Tai Chi, Ba Duan Jin, etc., to enhance physical fitness. Avoid strenuous exercise and prolonged exposure to cold environments.

[0154] 3) Acupoint massage: Massaging the Zusanli, Guanyuan, Mingmen and other acupoints every day can help regulate the spleen and stomach and warm and nourish the kidney yang.

[0155] 4) Chinese medicine conditioning: Under the guidance of a Chinese medicine practitioner, you can consider taking Chinese patent medicines such as Yougui Pills or Jinkui Shenqi Pills that warm and nourish the kidney yang.

[0156] 5) Daily routine: Maintain a regular schedule and avoid staying up late. It is recommended to go to bed before 11pm to conform to the law of the growth of Yang energy in the human body.

[0157] Example 2:

[0158] The diagnosis results show that the user has a damp-heat constitution. Tongue examination shows that the tongue is red with a greasy yellow coating. Meridian examination shows that the liver and gallbladder meridians have heat symptoms. The health management suggestions given are:

[0159] 1) Diet adjustment: It is recommended to eat a light diet and eat more foods that have the effect of clearing heat and removing dampness, such as mung beans, bitter melon, winter melon, etc. Reduce the intake of spicy, greasy, and sweet foods.

[0160] 2) Exercise suggestions: Aerobic exercise, such as jogging and swimming, can help to remove sweat and moisture. However, avoid strenuous exercise in hot and humid environments.

[0161] 3) Acupoint massage: Massage Yanglingquan, Sanyinjiao, Zusanli and other acupoints every day to help soothe the liver and gallbladder, clear away heat and dampness.

[0162] 4) Chinese medicine conditioning: Under the guidance of a Chinese medicine practitioner, you can consider taking Chinese patent medicines such as Longdan Xiegan Pills or Bixie Fenqing Pills that can clear away heat and dampness.

[0163] 5) Lifestyle habits: Maintain good emotional management and avoid being irritable and impatient; pay attention to keeping the environment ventilated and dry to reduce moisture.

[0164] It should be noted that although the method operations of the above embodiments are described in a specific order, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0165] Embodiment 2:

[0166] like Figure 3 As shown, this embodiment provides a health management system based on multi-dimensional detection, which includes a detection module 301, a fusion module 302 and a health management suggestion module 303. The specific description of each module is as follows:

[0167] The detection module 301 is used to perform TCM constitution identification, intelligent tongue diagnosis and meridian detection on the user, and obtain various detection results of the user's physical condition;

[0168] A fusion module 302 is used to fuse multiple test results using a diagnosis fusion strategy to obtain a diagnosis result;

[0169] The health management suggestion module 303 is used to provide personalized health management suggestions to the user according to the diagnosis results.

[0170] It should be noted that the system provided in this embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0171] Embodiment 3:

[0172] This embodiment provides a computer device, such as Figure 4 As shown, it includes a processor 402, a memory, an input device 403, a display device 404 and a network interface 405 connected through a system bus 401. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 406 and an internal memory 407. The non-volatile storage medium 406 stores an operating system, a computer program and a database. The internal memory 407 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the processor 402 executes the computer program stored in the memory, the health management method of the above-mentioned embodiment 1 is implemented as follows:

[0173] Conduct TCM constitution identification, intelligent tongue diagnosis and meridian detection on users to obtain multiple test results of the user's physical condition; use diagnostic fusion strategy to fuse multiple test results to obtain diagnostic results; and provide users with personalized health management suggestions based on the diagnostic results.

[0174] Embodiment 4:

[0175] This embodiment provides a storage medium, which is a computer-readable storage medium, storing a computer program. When the computer program is executed by a processor, the health management method of the above embodiment 1 is implemented as follows:

[0176] Conduct TCM constitution identification, intelligent tongue diagnosis and meridian detection on users to obtain multiple test results of the user's physical condition; use diagnostic fusion strategy to fuse multiple test results to obtain diagnostic results; and provide users with personalized health management suggestions based on the diagnostic results.

[0177] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0178] In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device, or device. In this embodiment, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium, which may send, propagate, or transmit a program used by or in combination with an instruction execution system, device, or device. The computer program contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0179] The computer readable storage medium can be written in one or more programming languages ​​or a combination thereof to execute the computer program of the present embodiment, and the programming language includes an object-oriented programming language, such as Java, Python, C++, and also includes a conventional procedural programming language, such as C language or a similar programming language. The program can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, 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 can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0180] To sum up, the present invention obtains multiple test results of the user's physical condition by performing multi-dimensional tests on the user's traditional Chinese medicine constitution, intelligent tongue diagnosis, meridian measurement, etc., and improves the accuracy and pertinence of the diagnosis through fusion analysis of multiple test results. At the same time, it also combines fusion diagnosis technology to provide personalized health advice and plans based on the user's specific situation. Compared with existing health management systems, the present invention has higher accuracy and pertinence, and can provide users with more scientific and personalized health management services.

[0181] The above description is only a preferred embodiment of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention.

Claims

1. A health management method based on multi-dimensional detection, characterized in that: The method comprises: Perform TCM constitution identification, intelligent tongue diagnosis and meridian detection on users to obtain various test results of users' physical conditions; A diagnostic fusion strategy is used to fuse multiple test results to obtain a diagnostic result; Provide users with personalized health management suggestions based on the diagnosis results.

2. The health management method according to claim 1, characterized in that: The diagnostic fusion strategy is used to fuse multiple test results to obtain a diagnostic result, including: The multiple detection results are input into a diagnosis fusion model, and feature-level fusion and decision-level fusion are performed on the multiple detection results to obtain a diagnosis result. The diagnosis fusion model includes a feature-level fusion part and a decision-level fusion part.

3. The health management method according to claim 2, characterized in that: The feature-level fusion and decision-level fusion of multiple detection results are performed to obtain a diagnosis result, including: Through the fusion analysis of multiple test results, multiple sub-features are obtained, and a group of sub-features with a high correlation with the health status of traditional Chinese medicine are found; Using the canonical association analysis theory, a group of sub-features are fused into a new feature as the TCM health status feature; The characteristics of TCM health status are integrated into decision-making to obtain the diagnosis result.

4. The health management method according to claim 3, characterized in that: The decision-making fusion of TCM health status characteristics to obtain a diagnosis result includes: Multiple classifiers are used to identify the characteristics of TCM health status and obtain local recognition results; Based on Bayesian theory and voting rules, the local recognition results are comprehensively analyzed to obtain the diagnosis results.

5. The health management method according to any one of claims 1 to 3, characterized in that: The basic characteristics of TCM constitution identification include constitution type, constitution definition and constitution causes.

6. The health management method according to any one of claims 1 to 3, characterized in that: The basic features detected by the intelligent tongue diagnosis include tongue coating, tongue color, tongue shape and tongue coating color.

7. The health management method according to any one of claims 1 to 3, characterized in that: The basic features of the meridian detection include main problem meridians, meridian reference values, meridian states, health items and meridian values.

8. A health management system based on multi-dimensional detection, characterized in that: The system comprises: The detection module is used to identify the user's TCM constitution, perform intelligent tongue diagnosis and meridian detection, and obtain various test results of the user's physical condition; A fusion module is used to fuse multiple test results using a diagnostic fusion strategy to obtain a diagnostic result; The health management suggestion module is used to provide users with personalized health management suggestions based on the diagnosis results.

9. A computer device comprising a processor and a memory for storing a program executable by the processor, characterized in that: When the processor executes the program stored in the memory, the health management method described in any one of claims 1 to 7 is implemented.

10. A storage medium storing a program, characterized in that: When the program is executed by a processor, the health management method described in any one of claims 1 to 7 is implemented.

Images