Traditional Chinese medicine constitution identification method, traditional Chinese medicine constitution identification device and computer readable storage medium

Abstract

The invention provides a traditional Chinese medicine constitution identification method, a traditional Chinese medicine constitution identification device and a computer readable storage medium. The traditional Chinese medicine constitution identification method comprises the steps that S1, optimized inquiry questions are obtained, and the optimized inquiry questions are optimized according to standard inquiry questions of a traditional Chinese medicine constitution standardization scale and based on a preset number of original inquiry data of the traditional Chinese medicine constitution standardization scale; s2, acquiring a tongue image of the user, and preliminarily determining a traditional Chinese medicine constitution identification type of the user based on the tongue image; s3, based on the preliminarily determined traditional Chinese medicine constitution identification type, determining personalized inquiry questions of the user; and S4, obtaining personalized inquiry data of the user for the personalized inquiry question, and determining the traditional Chinese medicine constitution identification type of the user again based on the personalized inquiry data. According to the traditional Chinese medicine constitution identification method, the inquiry questions are fewer and more personalized, the inquiry efficiency is improved, and the constitution identification accuracy and the user experience are improved.

Description

TECHNICAL FIELD

[0001] The present application generally relates to the technical field of data information processing, and particularly relates to a traditional Chinese medicine constitution identification method, a traditional Chinese medicine constitution identification device and a computer readable storage medium. BACKGROUND

[0002] Traditional Chinese medicine constitution is a kind of life phenomenon objectively existing in human body, and can identify sub-health state. Traditional Chinese medicine constitution is divided into normal constitution, Yin deficiency constitution, Yang deficiency constitution, Qi deficiency constitution, blood stasis constitution, phlegm-damp constitution, damp-heat constitution, Qi stagnation constitution and special constitution. The "Traditional Chinese Medicine Constitution Classification, Judgment Method and Judgment Standard" expounds the traditional Chinese medicine constitution identification based on the scale, which is divided into male, female, adult, old man and other problem types, and each person needs to do fixed 62 questions.

[0003] The Chinese patent document (application number: 202410827946.9) discloses a traditional Chinese medicine constitution identification method based on human three-dimensional reconstruction, which introduces three-dimensional reconstruction technology and machine learning algorithm. The patent points out that there are other identification methods besides the scale for constitution identification, and the disadvantage is that the constitution identification method of human three-dimensional reconstruction has not formed a consensus and standard.

[0004] The Chinese patent document (application number: 202410651399.3) discloses a traditional Chinese medicine constitution identification method, system, equipment and storage medium based on decision tree. The method comprises: acquiring data of traditional Chinese medicine constitution identification scale from multiple traditional Chinese medicine clinics; pre-processing the acquired data to obtain a pre-processed data set; based on the pre-processed data set, selecting a decision tree algorithm, constructing and training a decision tree model; inputting the feature data of the examinee into the trained decision tree model to determine the constitution type of the examinee; screening the items of the traditional Chinese medicine constitution identification scale to obtain key items; determining the mutual relationship between the items by analyzing the branches and nodes in the trained decision tree model; based on the screened key items and the mutual relationship between the items, simplifying the traditional Chinese medicine constitution identification scale and removing redundant items. The disadvantage of the patent is that the screened questionnaire is not personalized, and everyone does the scale questionnaire in the same way, which is not a personalized scale.

[0005] A Chinese patent document (application number: 201811454775.0) discloses a method and device for TCM constitution identification that combines inspection and questioning. The method includes the following steps: using a camera to take facial images and tongue coating images, identifying k (k<9) constitution types through inspection, and then inputting several constitution types into the questioning module. The questioning module obtains questions to be asked based on the k constitution types input. The subject answers these questions, and then obtains the final constitution type based on the answers. The device includes a liveness detector, a camera, a microphone, a speaker, a touch screen, an intelligent information processor, and a case database memory. The shortcoming of this patent is that the questioning consists of 62 questions, which is too many.

[0006] A Chinese patent document (application number: 202411164345.0) discloses a health management method, system, device, and storage medium based on multi-dimensional testing. The method includes: performing Traditional Chinese Medicine (TCM) constitution identification, intelligent tongue diagnosis, and meridian testing on a user to obtain multiple test results on the user's physical condition; using a diagnostic fusion strategy to fuse the multiple test results to obtain a diagnosis; and providing personalized health management recommendations to the user based on the diagnosis results. The patent's shortcomings are that the constitution identification consultation is not personalized, and the health tests do not target specific symptoms.

[0007] Therefore, the existing physical constitution identification methods have defects such as too many questions, the questions for each person are the same, not personalized questions, low consultation efficiency, low accuracy, and poor user experience.

[0008] The contents of the background technology section are merely the technologies known to the inventors and do not necessarily represent the existing technologies in this field. Summary of the Invention

[0009] In order to solve one or more problems in the prior art, the present invention provides a method for identifying constitution in Traditional Chinese Medicine, comprising:

[0010] S1: Obtaining optimized medical questionnaires, wherein the optimized medical questionnaires are optimized based on standard medical questionnaires of a standardized TCM constitution scale and a preset number of original medical questionnaire data of the standardized TCM constitution scale;

[0011] S2: Obtaining a tongue image of the user, and preliminarily determining the TCM constitution type of the user based on the tongue image;

[0012] S3: Determine personalized medical questions for the user based on the initially determined TCM constitution identification type; and

[0013] S4: Obtaining the user's personalized medical consultation data for the personalized medical consultation question, and re-determining the user's TCM constitution identification type based on the personalized medical consultation data.

[0014] Optionally, the optimized interrogation question is optimized by the following steps:

[0015] S11: determining first interrogation data of each TCM constitution based on the original interrogation data;

[0016] S12: preprocessing the first interrogation data, converting the first interrogation data into a point system to obtain second interrogation data; and

[0017] S13: performing cluster analysis on the second interrogation data based on a cluster algorithm, and determining an optimized interrogation question of each TCM constitution based on the cluster analysis result, wherein the number of the optimized interrogation question of each TCM constitution is less than the number of the standard interrogation question.

[0018] Preferably, the cluster algorithm comprises a K-means cluster algorithm, and step S13 comprises:

[0019] S131: randomly selecting K sample points as initial cluster center points, wherein K is equal to the number of the optimized interrogation question;

[0020] S132: calculating the distance from each sample point to each cluster center point based on the second interrogation data, and classifying it into the nearest cluster;

[0021] S133: recalculating the average value of the sample points of each cluster as a new cluster center point;

[0022] S134: repeating sub-steps S132-S133 until the cluster center points no longer change significantly or the preset number of iterations is reached; and

[0023] S135: taking the K questions closest to the cluster center points as the optimized interrogation question.

[0024] Optionally, step S2 comprises:

[0025] S21: converting the tongue image from an RGB color space to an LAB color space;

[0026] S22: determining the LAB value range of the tongue color based on the LAB color space; and

[0027] S23: preliminarily determining the TCM constitution identification type of the user based on the LAB value range.

[0028] Optionally, step S3 comprises: determining the personalized interrogation question of the user based on the preliminarily determined TCM constitution identification type and the corresponding optimized interrogation question.

[0029] Preferably, step S3 further comprises:

[0030] S31: determining personal information of the user, the personal information comprising age information, gender information and answer date information;

[0031] S32: respectively encoding the age information, the gender information and the answer date information to generate a user feature vector; and

[0032] S33: determining the personalized diagnosis question based on the user feature vector.

[0033] Preferably, the sub-step S32 comprises:

[0034] S321: encoding the age information based on a first mapping relationship between age intervals and discrete encoding values;

[0035] S322: encoding the gender information based on a mapping relationship between gender and binary encoding; and

[0036] S323: extracting day information of the answer date information, and encoding the answer date information based on a second mapping relationship between the day information and discrete encoding values.

[0037] Optionally, the step S3 further comprises:

[0038] S34: initializing weight values of the corresponding optimization diagnosis question in an age feature dimension, a gender feature dimension and an answer date feature dimension respectively to construct a question weight matrix.

[0039] Preferably, the step S3 further comprises:

[0040] S35: calculating a personalized score of the corresponding optimization diagnosis question based on the question weight matrix and the user feature vector; and

[0041] S36: sorting the corresponding optimization diagnosis question based on the personalized score to generate the personalized diagnosis question.

[0042] Optionally, the personalized score is calculated based on the following formula:

[0043]

[0044] wherein Scorei is a personalized score of an i-th question, Wij is a weight of the i-th question in a j-th feature dimension, and Fj is an encoding of the user in the j-th feature dimension.

[0045] Optionally, the step S4 comprises:

[0046] S41: converting the personalized diagnosis data into a point system; and

[0047] S42: Based on the personalized inquiry data of the integral system, the scores of the TCM constitution identification types preliminarily determined are respectively counted, and the TCM constitution identification type with the highest score is taken as the TCM constitution identification type of the user.

[0048] Optionally, the TCM constitution identification method further comprises: S5: acquiring an infrared image of the knee joint of the user, and identifying the muscle and bone state of the user based on the infrared image of the knee joint.

[0049] Preferably, the TCM constitution identification method further comprises: S6: outputting a conditioning suggestion based on the TCM constitution identification type and the muscle and bone state.

[0050] The application further provides a TCM constitution identification device, comprising:

[0051] a first image acquisition module configured to acquire a tongue image of a user; and

[0052] a processing module coupled to the first image acquisition module and configured to execute the TCM constitution identification method according to any one of the above.

[0053] Preferably, the TCM constitution identification device further comprises: a second image acquisition module coupled to the processing module and configured to acquire an infrared image of the knee joint of the user.

[0054] The application further provides a computer readable storage medium comprising computer executable instructions stored thereon, which, when executed by a processor, implement the TCM constitution identification method according to the above.

[0055] Compared with the prior art, the TCM constitution identification method of the application has fewer inquiry questions, the inquiry questions are more personalized, and the TCM constitution identification method is helpful to improve the inquiry efficiency, improve the constitution identification accuracy and improve the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will introduce the drawings used in the embodiments described in the embodiments by way of examples. The drawings in the following description are only some of the present disclosure, and those skilled in the art can also obtain other drawings according to the provided drawings without creating creative labor. The drawings are used to provide further understanding of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application, and do not constitute a limitation to the present application. In the drawings:

[0057] Figure 1 The flowchart of the TCM constitution identification method according to some embodiments of the present application is shown.

[0058] Figure 2An implementation procedure flowchart of optimizing an inquiry question according to some embodiments of the present application is shown.

[0059] Figure 3 A flowchart of step S13 according to some embodiments of the present application is shown.

[0060] Figure 4 A flowchart of sub-steps of step S2 according to some embodiments of the present application is shown.

[0061] Figure 5 A flowchart of sub-steps of step S3 according to some embodiments of the present application is shown.

[0062] Figure 6 A flowchart of sub-sub-steps of sub-step S32 according to some embodiments of the present application is shown.

[0063] Figure 7 A flowchart of sub-steps of step S4 according to some embodiments of the present application is shown.

[0064] Figure 8 A flowchart of a traditional Chinese medicine constitution identification method according to some embodiments of the present application is shown.

[0065] Figure 9 A schematic diagram of a traditional Chinese medicine constitution identification device according to some embodiments of the present application is shown. DETAILED DESCRIPTION

[0066] In the following, only certain exemplary embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present application. Therefore, the drawings and the description are considered to be exemplary in nature and not limiting.

[0067] In the description of the application, it is to be understood that the orientations or positional relationships indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the application and simplifying the description, and do not indicate or imply that the devices or elements indicated thereby must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the application. In addition, the terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated thereby. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the application, the meaning of "a plurality of" is two or more, unless otherwise explicitly specified and limited.

[0068] In the description of the application, it should be noted that, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting", "coupling" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected or can communicate with each other; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal communication or interaction relationship of two elements. For those skilled in the art, the specific meaning of the above terms in the application can be understood according to the specific circumstances.

[0069] In the present application, unless otherwise explicitly specified and limited, the first feature "above" or "below" the second feature can include that the first and second features are in direct contact, or that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, the first feature "above", "above" and "above" the second feature includes that the first feature is directly above and obliquely above the second feature, or only indicates that the horizontal height of the first feature is higher than that of the second feature. The first feature "below", "below" and "below" the second feature includes that the first feature is directly below and obliquely below the second feature, or only indicates that the horizontal height of the first feature is less than that of the second feature.

[0070] Many different embodiments or examples of the application are provided below to implement different structures of the application. For simplicity of the present application, the components and settings of the specific examples are described below. Of course, they are only examples and the purpose is not to limit the application. In addition, the application can refer to the same reference numerals and / or reference letters in different examples, and such repetition is for the purpose of simplification and clarity, which does not indicate the relationship between the various embodiments and / or settings discussed. In addition, the application provides examples of various specific processes and materials, but those skilled in the art can realize the application of other processes and / or the use of other materials.

[0071] The preferred embodiments of the application are described below in conjunction with the accompanying drawings, it should be understood that the preferred embodiments described herein are only used to illustrate and explain the application, and are not used to limit the application.

[0072] The application provides a traditional Chinese medicine constitution identification method. The traditional Chinese medicine constitution identification method of the application can be executed by a computer, a processing device, a processing module, a processor, etc. In other words, the traditional Chinese medicine constitution identification method of the application essentially belongs to an information processing method executed by a computer, etc.

[0073] In some embodiments, the computer, the processing device, the processing module, the processor, etc. can include processing circuitry, a central processing unit (CPU), a micro control unit (MCU), a graphic processing unit (GPU), a digital signal processor (DSP), other general-purpose processors, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a complex programmable logic device (CPLD) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0074] Compared with the prior art, the traditional Chinese medicine constitution identification method of the application has fewer interrogation questions and more personalized interrogation questions, which helps to improve the interrogation efficiency, improve the constitution identification accuracy and user experience. Details are introduced below.

[0075] Figure 1 A flowchart of a traditional Chinese medicine constitution identification method 10 according to some embodiments of the application is shown. As shown in FIG. 1, the traditional Chinese medicine constitution identification method 10 includes the following steps. Figure 1As shown, the traditional Chinese medicine constitution identification method 10 includes steps S1-S4. The following exemplary introduces the traditional Chinese medicine constitution identification method 10 with the processing module as the execution subject. It should be understood that the computer, processing device, processor and other execution subjects execute the traditional Chinese medicine constitution identification method 10 similarly.

[0076] In step S1, the optimized interrogation question is obtained. The optimized interrogation question can be stored in a storage module (not shown in the figure). The processing device can be communicatively connected to the storage module. When step S1 is executed, the processing module can obtain the optimized interrogation question from the storage module. For example, the processing module can obtain the optimized interrogation question from the storage module based on the input instruction of the user.

[0077] In some embodiments, the optimized interrogation question can be a standard interrogation question according to the traditional Chinese medicine constitution standardized scale, optimized based on a preset number of original interrogation data of the traditional Chinese medicine constitution standardized scale. The traditional Chinese medicine constitution is divided into nine types, including the balanced constitution, the yin deficiency constitution, the yang deficiency constitution, the qi deficiency constitution, the blood stasis constitution, the phlegm-damp constitution, the damp-heat constitution, the qi depression constitution and the special constitution. The classification, determination method and determination standard of traditional Chinese medicine constitution states that the constitution identification is based on the scale, and each person needs to answer 62 fixed questions. That is, the standard interrogation question of the traditional Chinese medicine constitution standardized scale includes 62 fixed questions, which has the problems of too many interrogation questions and the same interrogation for each person, thus resulting in low interrogation efficiency and poor user experience.

[0078] The present application improves the prior art. The processing module of the present application can optimize the standard interrogation question (62 questions) of the traditional Chinese medicine constitution standardized scale based on a preset number of original interrogation data (for example, including several hundred, several thousand or even tens of thousands of interrogation questions and answers of the aforementioned nine constitutions) of the traditional Chinese medicine constitution standardized scale, to obtain the optimized interrogation question. The present application simplifies the 62 standard interrogation questions of the nine constitutions into 27 optimized interrogation questions, and simplifies the 8 standard interrogation questions of each constitution into 3 optimized interrogation questions, which greatly reduces the interrogation questions, helps to improve the interrogation efficiency and enhance the user experience, and since the optimized interrogation question is optimized based on a preset number of original interrogation data of the traditional Chinese medicine constitution standardized scale, the accuracy of constitution identification can be ensured.

[0079] In some embodiments, in step S1, the optimized interrogation question can be optimized through steps S11-S13. The optimized interrogation question can be one of the steps of step S1. Figure 2 The implementation step flow diagram of the optimized interrogation question according to some embodiments of the present application is shown.

[0080] As Figure 2As shown, in step S11, the processing module can determine the first interrogation data of each TCM constitution based on the original interrogation data. The original interrogation data can be stored in the storage module. The processing module can obtain the original interrogation data from the storage module. Based on the original interrogation data, the processing module can determine the first interrogation data of each TCM constitution. The first interrogation data is 8 standard interrogation questions and their answer information of 9 TCM constitutions respectively. The answer information of each standard interrogation question includes “none”, “rarely”, “sometimes”, “often”, and “always”.

[0081] In some embodiments, the storage module can include a memory. The memory can be a software module, or a hardware module, or partially a software module and partially a hardware module. In some embodiments, the memory can include a random access memory (RAM) and / or a non-volatile memory (NVM). Further, the memory can include one or more of a phase-change random access memory (PRAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), and the like. In some embodiments, the memory can be a cloud memory.

[0082] In step S12, the processing module can preprocess the first interrogation data and convert the first interrogation data into a point system to obtain second interrogation data. For example, the processing module can convert the answer information of 8 standard interrogation questions of the first interrogation data of 9 TCM constitutions respectively from “none”, “rarely”, “sometimes”, “often”, and “always” to 1, 2, 3, 4, and 5 points respectively to obtain the second interrogation data. That is, in the first interrogation data, the representation form of the answer information of the standard interrogation questions is a frequency system, i.e., “none”, “rarely”, “sometimes”, “often”, and “always”. In the second interrogation data, the representation form of the answer information of the standard interrogation questions is a point system, i.e., 1, 2, 3, 4, and 5. The processing module converts the first interrogation data in the frequency system into the second interrogation data in the point system, which is convenient for subsequent processing.

[0083] Table 1 exemplarily shows the conversion relationship between the first interrogation data and the second interrogation data, but the present application is not limited thereto.

[0084] Table 1

[0085]

[0086] In step S13, the processing module can perform clustering analysis on the second inquiry data based on a clustering algorithm, and determine the optimized inquiry question for each TCM constitution based on the clustering analysis result. The number of the optimized inquiry question for each TCM constitution is less than the number of the standard inquiry question. The clustering algorithm includes but is not limited to K-means, hierarchical clustering, DBSCAN, spectral clustering, Gaussian mixture model, fuzzy C-means, K-medoids, Mean Shift, OPTICS BIRCH, and the like.

[0087] Hereinafter, step S13 is exemplarily introduced by taking the case that the processing module performs clustering analysis using K-means algorithm.

[0088] Figure 3 A flowchart showing the sub-steps of step S13 according to some embodiments of the present application is shown. As shown in FIG. 6, step S13 includes sub-steps S131-S135. Figure 3

[0089] Hereinafter, the case of Qi deficiency constitution (type B) is exemplarily introduced. It should be understood that the optimized inquiry question for each TCM constitution can be determined based on sub-steps S131-S135.

[0090] In sub-step S131, K sample points are randomly selected as initial cluster center points, and K is equal to the number of the optimized inquiry question. K is a positive integer.

[0091] For example, the number of the optimized inquiry question for Qi deficiency constitution (type B) is 3, and the processing module sets K=3. For another example, the number of the optimized inquiry question for Qi deficiency constitution (type B) is 4, and the processing module sets K=4. It should be understood that K is less than the number of the standard inquiry question, i.e., K<8.

[0092] Exemplarily, the processing module can randomly select 3 standard inquiry questions from the 8 standard inquiry questions for Qi deficiency constitution (type B), calculate the average value of the scores of the 3 randomly selected standard inquiry questions, and take the average value as the cluster center point, i.e., the initial cluster center point.

[0093] In sub-step S132, the distance between each sample point and each cluster center point is calculated based on the second inquiry data, and each sample point is classified into the nearest cluster.

[0094] For example, for the problem clustering of Qi deficiency constitution (type B), the processing module can calculate the distance between the score of each problem in the 8 standard inquiry questions and the initial cluster center point, and select the problem with the shortest distance as the core problem, i.e., belonging to this category. ​

[0095] Sub-step S133, recalculating the average value of the sample points of each cluster as a new cluster center point. That is, the processing module can recalculate the average value of the sample points of each cluster to update the cluster center point.

[0096] Sub-step S134, repeating sub-steps S132-S133 until the cluster center point no longer changes significantly or reaches a preset number of iterations. That is, the processing module can update the cluster center point through multiple iterations until the cluster center point no longer changes significantly or reaches a preset number of iterations, i.e., the iteration ends.

[0097] Sub-step S135, taking the K questions closest to the cluster center point as the optimized interrogation questions. When the iteration ends, the processing module can take the K questions corresponding to the integral closest to the cluster center point as the optimized interrogation questions.

[0098] For example, the 3 questions corresponding to the integral closest to the cluster center point are:

[0099] (1) Do you easily feel tired?

[0100] (2) Do you easily feel short of breath (shortness of breath, unable to catch breath)?

[0101] (3) Do you easily sweat when you move a little more?

[0102] Then the processing module can take these 3 questions as the optimized interrogation questions for Qi deficiency (type B). These 3 questions can be considered as the core questions of Qi deficiency (type B) and the interrogation questions that best represent Qi deficiency (type B).

[0103] Preferably, after the processing module determines the optimized interrogation questions for a certain TCM constitution, it can also evaluate the clustering results. For example, the processing module can calculate the variance of the questions within each cluster and the distance between the questions in different clusters to ensure that the variance is less than a variance threshold and the distance is less than a distance threshold, ensuring good clustering results and ensuring the reliability and accuracy of the optimized interrogation questions.

[0104] Table 2 exemplarily shows a comparison between the standard interrogation questions for Qi deficiency (type B) and the optimized interrogation questions determined based on the clustering algorithm. It should be noted that Table 2 is only exemplary and the present application is not limited thereto.

[0105] Table 2

[0106]

[0107] It should be understood that the optimization inquiry question of each TCM constitution can be determined based on the sub-steps S131-S135. Table 3 exemplarily shows the optimization inquiry question of 9 TCM constitutions determined based on the clustering algorithm. It should be noted that Table 3 is only exemplarily shown, and the present application is not limited thereto.

[0108] Table 3

[0109]

[0110]

[0111] Step S2, acquiring the tongue image of the user, and preliminarily determining the TCM constitution identification type of the user based on the tongue image. The tongue image of the user can be acquired by the first image acquisition module. The first image acquisition module can be a color camera, a color camera, or the like module or device. The first image acquisition module can be coupled to the processing module, and the two can communicate with each other. The processing module can acquire the tongue image of the user from the first image acquisition module. Based on the tongue image, the processing module can determine the color space. Based on the color space, the processing module can preliminarily determine the TCM constitution identification type of the user. When preliminarily determining the TCM constitution identification type, the processing module can determine several of the nine constitution types, such as three types, etc. Preliminarily determining the TCM constitution identification type is equivalent to roughly classifying the TCM constitution identification type of the user, that is, roughly determining several constitution types.

[0112] Figure 4 A flowchart showing the sub-steps of step S2 according to some embodiments of the present application is shown. As shown in Figure 4 Step S2 includes sub-steps S21-S23.

[0113] Sub-step S21, the processing module can convert the tongue image from the RGB color space to the LAB color space. Converting the tongue image to the LAB color space can reduce or even eliminate the noise influence of the ambient light, and taking advantage of the more accurate identification and classification of colors in the LAB color space can help to ensure the accuracy of the preliminary determination of the TCM constitution identification type of the user (i.e., the rough classification result).

[0114] Sub-step S22, based on the LAB color space, the processing module can determine the LAB value range of the tongue color. Table 4 exemplarily shows the correspondence between the LAB value range, the tongue color, and the constitution. It should be noted that Table 4 is only exemplarily shown, and the present application is not limited thereto. For example, the processing module can determine that the LAB range of the pale tongue color is [-, 100, 100]. For another example, the processing module can determine that the LAB range of the red tongue color is [-, 160, 134], etc.

[0115] Table 4

[0116] LAB range Tongue color Constitution 1 Constitution 2 Constitution 3 [-,100,100] Pale Qi deficiency constitution Yang deficiency constitution Balanced constitution [-,155,126] Light red Qi deficiency constitution Yang deficiency constitution Balanced constitution [-,160,134] Red Yin deficiency constitution Damp-heat constitution Qi stagnation constitution [-,166,149] Dark red Damp-heat constitution Qi stagnation constitution Blood stasis constitution [-,183,94] Light purple Phlegm-damp constitution Blood stasis constitution Special constitution [-,167,110] Purple Phlegm-damp constitution Blood stasis constitution Special constitution

[0117] In sub-step S23, based on the LAB value range, the processing module can preliminarily determine the TCM constitution identification type of the user. For example, if the LAB range of the tongue color is [-, 100, 100], the processing module can preliminarily determine three TCM constitution identification types of the user, which are qi deficiency constitution (constitution 1), yang deficiency constitution (constitution 2), and normal constitution (constitution 3). For another example, if the LAB range of the tongue color is [-, 160, 134], the processing module can preliminarily determine three TCM constitution identification types of the user, which are yin deficiency constitution (constitution 1), damp-heat constitution (constitution 2), and qi stagnation constitution (constitution 3), and so on. Based on the tongue image and the LAB color space, the TCM constitution identification type of the user is preliminarily determined, which takes into account the accuracy and personalization.

[0118] In step S3, based on the preliminarily determined TCM constitution identification type, the personalized interrogation question of the user is determined. For example, if the preliminarily determined TCM constitution identification type is qi deficiency constitution (constitution 1), yang deficiency constitution (constitution 2), and normal constitution (constitution 3), the processing module can determine the personalized interrogation question of the user based on these three constitution types.

[0119] In some embodiments, step S3 includes: based on the preliminarily determined TCM constitution identification type and the corresponding optimized interrogation question, determining the personalized interrogation question of the user. For example, if the preliminarily determined TCM constitution identification type is qi deficiency constitution (constitution 1), yang deficiency constitution (constitution 2), and normal constitution (constitution 3), based on the optimized interrogation question of the TCM constitution shown in Table 3, the processing module can determine three optimized interrogation questions corresponding to the three constitution types respectively, i.e., nine optimized interrogation questions. These nine questions can be used as the personalized interrogation question of the user. Table 5 exemplarily shows the personalized interrogation question corresponding to the preliminarily determined TCM constitution identification type. It should be noted that Table 5 is only exemplary, and the present application is not limited thereto.

[0120] Table 5

[0121]

[0122] Figure 5 A flowchart showing the sub-steps of step S3 according to some embodiments of the present application is shown. As shown in FIG. 6, step S3 includes sub-steps S31-S33. Figure 5

[0123] ​Sub-step S31, determine the personal information of the user, the personal information including age information, gender information and answering date information. For example, the user can input the personal information through the HMI, the HMI can communicate the personal information to the processing module, and the processing module can determine the personal information of the user through the HMI.

[0124] Sub-step S32, respectively encode the age information, the gender information and the answering date information to generate a user feature vector. For example, after the processing module determines the personal information of the user, the processing module can encode the age information, the gender information and the answering date information to generate a user feature vector.

[0125] Figure 6 A flowchart of sub-sub-steps of sub-step S32 according to some embodiments of the present application is shown. As shown in FIG. 6, sub-step S32 includes sub-sub-steps S321-S323. Figure 6

[0126] Sub-sub-step S321, encode the age information based on a first mapping relationship between age intervals and discrete coding values. For example, the processing module can divide the age of the user into several intervals (e.g., 0-17 years old, 18-59 years old, 60 years old and above), and respectively map them into discrete coding values (e.g., 0, 1, 2). Table 6 exemplarily shows the first mapping relationship between the age intervals and the discrete coding values. The first mapping relationship can be stored in the storage module, and the processing module can call the first mapping relationship to encode the age information. For example, the age of the user is 45 years old, and based on the first mapping relationship, the processing module can encode the age of the user as 1. For another example, the age of the user is 15 years old, and based on the first mapping relationship, the processing module can encode the age of the user as 0. It should be noted that the first mapping relationship presented in Table 6 is only exemplarily shown, and the present application is not limited thereto.

[0127] Table 6

[0128] User age interval 0-17 years old 18-59 years old 60 years old and above Discrete encoding value 0 1 2

[0129] Sub-sub-step S322, encode the gender information based on a mapping relationship between the gender information and binary coding. For example, the processing module can convert the gender information into binary coding, such as male coded as 0 and female coded as 1. Table 7 exemplarily shows the mapping relationship between the gender information and the binary coding. The mapping relationship can be stored in the storage module, and the processing module can call the mapping relationship to encode the gender information. For example, the gender of the user is male, and based on the mapping relationship, the processing module can encode the gender of the user as 0. For another example, the gender of the user is female, and based on the mapping relationship, the processing module can encode the gender of the user as 1. It should be noted that the mapping relationship presented in Table 7 is only exemplarily shown, and the present application is not limited thereto.

[0130] ​

[0131] User gender Male Female Binary encoding 0 1

[0132] In sub-step S323, day information of the answer date information is extracted, and the answer date information is encoded based on a second mapping relationship between the day information and discrete encoding values. For example, the processing module can extract the day (number) information of the answer date and encode it (e.g., 1-7 is encoded as 0, 8-14 is encoded as 1, 15-21 is encoded as 2, 22-28 is encoded as 3, and 29-31 is encoded as 4). Table 8 exemplarily shows the second mapping relationship between the day information and binary encoding. The second mapping relationship can be stored in the storage module, and the processing module can call the second mapping relationship to encode the answer date information. For example, the user's answer date is May 16, 2025. The processing module can extract the day information 16 of the answer date information, and based on the second mapping relationship, the answer date information can be encoded as 2. It should be noted that the second mapping relationship presented in Table 8 is only exemplarily shown, and the present application is not limited thereto.

[0133] Table 8

[0134] Day (number) information 1-7 8-14 15-21 22-28 29-31 Discrete encoding value 0 1 2 3 4

[0135] In sub-step S33, the personalized diagnosis question is determined based on the user feature vector. The processing module can combine the age, gender, and date encoding into a three-dimensional feature vector [age, gender, date] to generate the user feature vector. For example, the user is 45 years old, male, and the answer date is May 16, 2025. The processing module can encode the age as 1, the gender as 0, and the date as 2. The age is the first feature dimension, the gender is the second feature dimension, and the date is the third feature dimension, and the processing module can generate a three-dimensional feature vector [1, 0, 2]. The three-dimensional feature vector [1, 0, 2] can be used as the user feature vector. Based on the user feature vector, the personalized diagnosis question is determined, which further improves the accuracy and personalization.

[0136] In some embodiments, step S3 further comprises a sub-step S34 of initializing the weight values of the corresponding optimization interrogation questions in the age characteristic dimension, the gender characteristic dimension, and the answering date characteristic dimension respectively, and constructing a question weight matrix. Table 9 exemplarily shows the weight values of the nine optimization interrogation questions corresponding to the three initially determined Chinese constitution types in different characteristic dimensions (age, gender, date). For example, with reference to Table 9, for the constitution type initially determined as Qi deficiency constitution, the age weight of question 1 is 1.2, the gender weight is 0.8, and the date weight is 1.1; the age weight of question 2 is 0.9, the gender weight is 1.1, and the date weight is 0.7. It should be noted that the question weight matrix presented in Table 9 is only exemplarily shown, and the present application is not limited thereto.

[0137] Table 9

[0138]

[0139]

[0140] Preferably, step S3 further comprises sub-steps S35-S36. In sub-step S35, the personalized scores of the corresponding optimization interrogation questions are respectively calculated based on the question weight matrix and the user characteristic vector. For example, the processing module can calculate the personalized scores of the nine optimization interrogation questions based on the question weight matrix shown in Table 9 and the user characteristic vector [1, 0, 2] generated in Tables 6-8.

[0141] In some embodiments, the personalized score can be calculated based on the following formula:

[0142]

[0143] wherein Scorei is the personalized score of the i-th question, Wi,j is the weight of the i-th question in the j-th characteristic dimension, and Fj is the encoding of the user in the j-th characteristic dimension. i ij j

[0144] The personalized scores of the nine optimization interrogation questions are as follows:

[0145] Question 1: Score1=1.2×(1+1)+0.8×(0+1)+1.1×(2+1)=2.4+0.8+3.3=6.5.

[0146] Question 2: Score2=0.9×(1+1)+1.1×(0+1)+0.7×(2+1)=1.8+1.1+2.1=5.0.

[0147] ​​​Question 3: Score3 = 0.8x(1+1) + 1.2x(0+1) + 0.8x(2+1) = 1.6 + 1.2 + 2.4 = 5.2.

[0148] Question 4: Score4 = 1x(1+1) + 1.1x(0+1) + 0.9x(2+1) = 2 + 1.1 + 2.7 = 5.8.

[0149] Question 5: Score5 = 1.1x(1+1) + 1x(0+1) + 1x(2+1) = 2.2 + 1 + 3 = 6.2.

[0150] Question 6: Score6 = 1.2x(1+1) + 0.9x(0+1) + 1.1x(2+1) = 2.4 + 0.9 + 3.3 = 6.8.

[0151] Question 7: Score7 = 1x(1+1) + 1x(0+1) + 1.2x(2+1) = 2 + 1 + 3.6 = 6.6.

[0152] Question 8: Score8 = 0.9x(1+1) + 1.1x(0+1) + 0.9x(2+1) = 1.8 + 1.1 + 2.7 = 5.6.

[0153] Question 9: Score9 = 1.1x(1+1) + 0.8x(0+1) + 1.3x(2+1) = 2.2 + 0.8 + 3.9 = 6.9.

[0154] Sub-step S36, based on the personalized score, the corresponding optimized interrogation question is sorted to generate a personalized interrogation question.

[0155] For example, after the processing module calculates the personalized scores of the 9 optimized interrogation questions, the 9 questions (questions 1-9) can be sorted in descending order of the personalized scores (Score1-Score9). Based on the question sorting result, the personalized interrogation question of the user is generated, that is, [question 9, question 6, question 7, question 1, question 5, question 4, question 8, question 3, question 2]. By sorting the optimized interrogation questions to generate the personalized interrogation questions, the personalization is further improved.

[0156] Table 10 exemplarily shows the personalized interrogation questions generated based on the 9 optimized interrogation questions corresponding to the three preliminary determined Chinese medical constitution types. It should be noted that the personalized interrogation questions presented in Table 10 are only exemplary, and the present application is not limited thereto.

[0157] Table 10

[0158]

[0159] Step S4, obtaining the personalized interrogation data of the user for the personalized interrogation question, and determining the TCM constitution identification type of the user again based on the personalized interrogation data. In some embodiments, the processing module can be coupled to a human machine interface (HMI) to realize human-computer interaction. For example, after determining the personalized interrogation question of the user, the processing module can output the personalized interrogation question through the HMI, and the user can complete the personalized interrogation question through the HMI. The processing module can obtain the personalized interrogation data of the user for the personalized interrogation question through the HMI. Based on the personalized interrogation data, the processing module can determine the TCM constitution identification type of the user again. It should be noted that step S4 is different from step S3. In step S3, the processing module preliminarily determines several constitution types of the user (i.e., coarse classification type), while in step S4, the processing module determines one constitution type of the user (i.e., fine classification type). For example, the processing module preliminarily determines three constitution types of the user (e.g., qi deficiency constitution, yang deficiency constitution, and balanced constitution) in step S3, and the processing module obtains the personalized interrogation data of the user for nine personalized interrogation questions determined for the coarse classification type in step S4, and determines the TCM constitution identification type of the user (e.g., one of qi deficiency constitution, yang deficiency constitution, and balanced constitution) based on the personalized interrogation data.

[0160] Figure 7 A flowchart showing the sub-steps of step S4 according to some embodiments of the present application is shown. As shown, step S4 includes sub-steps S41 and S42. Figure 7

[0161] Sub-step S41, converting the personalized interrogation data into a point system. For example, the processing module can convert the personalized interrogation data from a frequency system (i.e., "none", "rarely", "sometimes", "often", "always") into a point system (i.e., 1, 2, 3, 4, 5). Sub-step S41 is similar to step S12.

[0162] Sub-step S42, respectively counting the scores of the TCM constitution identification types preliminarily determined based on the personalized interrogation data in the point system, and taking the TCM constitution identification type with the highest score as the TCM constitution identification type of the user. For example, the processing module can count the scores of qi deficiency constitution, yang deficiency constitution, and balanced constitution based on the user's answers to the nine personalized questions, each question being scored 1-5 points, and the processing module determines qi deficiency constitution as the TCM constitution identification type of the user if the score of qi deficiency constitution is the highest.

[0163] The TCM constitution identification method 10 of the present application can accurately, efficiently and reliably determine the TCM constitution identification type of the user through steps S1-S4, thereby enhancing the user experience.

[0164] ​In some embodiments, the TCM constitution identification method 10 further includes step S5. Step S5 may be performed after step S4.

[0165] Figure 8 FIG. 1 is a flow chart showing a method 10 for identifying TCM constitution according to some embodiments of the present invention. Figure 8 As shown, step S5, obtains an infrared image of the user's knee joint, and identifies the user's muscle and bone status based on the infrared image of the knee joint. For example, the second image acquisition module can acquire an infrared image of the user's knee joint, and preferably, an image of the exposed knee joint can be taken. The second image acquisition module can be a module or device such as an infrared camera, an infrared thermal imager, etc. The second image acquisition module can be coupled to the processing module, and the two can communicate with each other. The processing module can obtain the user's knee joint infrared image from the second image acquisition module. The processing module can analyze the infrared image of the knee joint through image processing and machine vision technology, analyze the temperature averages of multiple areas of the knee joint, and thus determine the user's muscle and bone status, such as analyzing the inflammation distribution of arthritis, the meridian blockage of arthritis, etc.

[0166] In some embodiments, the TCM constitution identification method 10 further includes step S6. Step S6 may be performed after step S5. Figure 8 As shown, step S6, based on the TCM constitution identification type and muscle and bone state, output conditioning suggestions. For example, 8 kinds of biased constitutions (i.e., the other 8 constitutions except the peaceful constitution) correspond to 8 kinds of exercise, physical therapy, diet, and constitution tea conditioning suggestions respectively. The processing module can output corresponding conditioning suggestions based on the user's TCM constitution identification type and muscle and bone state. For example, for users with Qi deficiency and inflammation distribution areas and relatively blocked meridians, the processing module can output conditioning suggestions such as drinking Qi deficiency conditioning tea and acupuncture points.

[0167] The TCM constitution identification method of the present invention has the advantages of fewer questions and more personalized questions, which helps to improve the efficiency of consultation, improve the accuracy of constitution identification, and improve user experience.

[0168] The present invention uses clustering algorithms such as k-means to optimize and simplify medical consultation questions, encodes questions based on user personal information, and combines the rough selection of physical constitution through tongue and face diagnosis to achieve personalized medical consultation, improve the efficiency of physical constitution classification, and stimulate users' enthusiasm for medical consultation.

[0169] Compared with traditional muscle and bone condition identification solutions, the present invention integrates infrared thermal imaging and constitution identification, which improves the accuracy and reliability of muscle and bone condition identification and conditioning recommendations. It is suitable for personalized Traditional Chinese Medicine constitution identification and conditioning for people with knee osteoarthritis, providing a more accurate, scientific, effective and reliable health conditioning solution for people with knee osteoarthritis.

[0170] The application further provides a Chinese medical constitution identification device. Figure 9 A schematic diagram of a Chinese medical constitution identification device 20 according to some embodiments of the application is shown. As shown, the Chinese medical constitution identification device 20 comprises a first image acquisition module 21 and a processing module 23. The first image acquisition module 21 can acquire a tongue image of a user. The processing module 23 is coupled to the first image acquisition module 21 and can perform the Chinese medical constitution identification method 10 as described above. Figure 9

[0171] Preferably, as shown, the Chinese medical constitution identification device 20 further comprises a second image acquisition module 22. The second image acquisition module 22 is coupled to the processing module 23 and can acquire an infrared image of a knee joint of the user. Although not shown in the figure, in some embodiments, the Chinese medical constitution identification device 20 can comprise a HMI coupled to the processing module 23 for human-machine interaction. In some embodiments, the Chinese medical constitution identification device 20 can comprise a storage module coupled to the processing module 23 for storing information such as standard interrogation questions, optimized interrogation questions, personalized interrogation questions, tongue images, infrared images of knee joints, etc. of the user. Figure 9

[0172] The Chinese medical constitution identification device of the application can achieve the same or similar technical effects as the Chinese medical constitution identification method. Details are not repeated here.

[0173] The application further provides a computer readable storage medium. The computer readable storage medium comprises computer executable instructions stored thereon, which, when executed by a processor, implement the Chinese medical constitution identification method 10 as described above.

[0174] The application can take the form of a computer program product embodied in one or more storage media having stored thereon computer readable code. The computer readable storage medium can be a permanent or non-permanent, removable or non-removable media, and can be implemented by any method or technology. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, PRAM, SRAM, DRAM, other types of RAM, ROM, EEPROM, flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital video disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0175] ​​It should be noted that the present specification provides method operational steps that can be embodied in many other specific ways unless otherwise specified herein. The order in which the steps are listed is merely one of many sequences of steps that can be implemented. In some embodiments, the steps recited in the examples or flowcharts can be executed in the order presented or in parallel.

[0176] It should be noted that each module / unit contained in the various devices and products described in the above examples can be a software module / unit or a hardware module / unit, or can be partially a software module / unit and partially a hardware module / unit. For example, for each device and product applied to or integrated into a chip, each module / unit contained therein can be implemented in the form of hardware such as a circuit, or at least some of the modules / units can be implemented in the form of a software program running on a processor integrated in the chip, and the remaining (if any) modules / units can be implemented in the form of hardware such as a circuit; for each device and product applied to or integrated into a chip module, each module / unit contained therein can be implemented in the form of hardware such as a circuit, and different modules / units can be located in the same component (e.g., a chip, a circuit module, etc.) or different components of the chip module, or at least some of the modules / units can be implemented in the form of a software program running on a processor integrated in the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as a circuit; for each device and product applied to or integrated into a terminal, each module / unit contained therein can be implemented in the form of hardware such as a circuit, and different modules / units can be located in the same component (e.g., a chip, a circuit module, etc.) or different components of the terminal, or at least some of the modules / units can be implemented in the form of a software program running on a processor integrated in the terminal, and the remaining (if any) modules / units can be implemented in the form of hardware such as a circuit.

[0177] It should be noted that although several modules of the traditional Chinese medicine constitution identification device are mentioned in the above detailed description, such division is merely not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules described above can be implemented in one module. Conversely, the features and functions of one module described above can be further divided into modules.

[0178] It should be noted that the present application can only include Figures 1-9 any one or more features of any one or more embodiments. In other words, not all features shown in the drawings must be implemented in the traditional Chinese medicine constitution identification device and method of the present application.

[0179] Finally, it should be noted that the above only describes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art will appreciate that the technical solutions described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalent ones. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for identifying constitution in traditional Chinese medicine, characterized in that: include: S1: Obtaining optimized medical questionnaires, wherein the optimized medical questionnaires are optimized based on standard medical questionnaires of a standardized TCM constitution scale and a preset number of original medical questionnaire data of the standardized TCM constitution scale; S2: Obtaining a tongue image of the user, and preliminarily determining the TCM constitution type of the user based on the tongue image; S3: Determine personalized medical questions for the user based on the initially determined TCM constitution identification type; and S4: Obtaining the personalized medical consultation data of the user for the personalized medical consultation question, and re-determining the TCM constitution identification type of the user based on the personalized medical consultation data.

2. The method for identifying constitution in Traditional Chinese Medicine according to claim 1, characterized in that: The optimized medical questions are optimized through the following steps: S11: Determine first consultation data for each TCM constitution based on the original consultation data; S12: Preprocessing the first medical inquiry data, converting the first medical inquiry data into a points system, and obtaining second medical inquiry data; and S13: performing cluster analysis on the second medical questionnaire data based on a clustering algorithm, and determining optimized medical questionnaire questions for each TCM constitution based on the cluster analysis results, wherein the number of optimized medical questionnaire questions for each TCM constitution is less than the number of standard medical questionnaire questions; Preferably, the clustering algorithm includes a K-means clustering algorithm, and step S13 includes: S131: Randomly select K sample points as initial cluster centers, where K is equal to the number of optimized medical questions; S132: Based on the second medical inquiry data, calculate the distance between each sample point and the center point of each cluster, and assign it to the cluster with the closest distance; S133: Recalculate the average value of the sample points of each cluster as the new cluster center point; S134: repeating sub-steps S132 to S133 until the cluster center point no longer changes significantly or a preset number of iterations is reached; and S135: The K questions closest to the cluster center are used as the optimized diagnosis questions.

3. The method for identifying constitution in Traditional Chinese Medicine according to claim 1, characterized in that: Step S2 includes: S21: Converting the tongue image from RGB color space to LAB color space; S22: Determine the LAB value range of tongue color based on the LAB color space; and S23: Based on the LAB value range, preliminarily determine the TCM constitution identification type of the user.

4. The method for identifying constitution in Traditional Chinese Medicine according to claim 1, characterized in that: Step S3 includes: Determining personalized medical questions for the user based on the preliminarily determined TCM constitution identification type and its corresponding optimized medical questions; Preferably, step S3 further includes: S31: Determine the user's personal information, including age information, gender information, and answer date information; S32: performing feature coding on the age information, gender information, and answer date information to generate a user feature vector; and S33: Determine the personalized medical question based on the user feature vector; Preferably, sub-step S32 includes: S321: Perform feature encoding on the age information based on a first mapping relationship between age intervals and discrete code values; S322: Based on the mapping relationship between gender and binary code, perform feature encoding on the gender information; and S323: Extract the day information of the answering date information, and encode the answering date information based on the second mapping relationship between the day information and the discrete code value.

5. The method for identifying constitution in Traditional Chinese Medicine according to claim 4, characterized in that: Step S3 further includes: S34: Initializing the weight values ​​of the corresponding optimized medical questions in the age feature dimension, the gender feature dimension, and the answer date feature dimension, respectively, to construct a question weight matrix; Preferably, step S3 further includes: S35: Calculating the personalized scores of the corresponding optimized medical questions based on the question weight matrix and the user feature vector; and S36: Based on the personalized scores, the corresponding optimized medical questions are sorted to generate the personalized medical questions.

6. The method for identifying constitution in Traditional Chinese Medicine according to claim 5, characterized in that: The personalization score is calculated based on the following formula: Among them, Score i is the personalized score of the i-th question, W ij is the weight of the i-th question on the j-th feature dimension, F j is the encoding of the user in the jth feature dimension.

7. The method for identifying constitution in Traditional Chinese Medicine according to claim 5, characterized in that: Step S4 includes: S41: converting the personalized medical consultation data into a points system; and S42: Based on the personalized medical consultation data of the point system, the scores corresponding to the TCM constitution identification types are preliminarily determined, and the TCM constitution identification type with the highest score is used as the TCM constitution identification type of the user.

8. The method for identifying constitution in Traditional Chinese Medicine according to any one of claims 1 to 7, characterized in that: Also includes: S5: Acquire an infrared image of the user's knee joint, and identify the user's muscle and bone condition based on the infrared image of the knee joint; Preferably, the TCM constitution identification method further comprises: S6: Based on the TCM constitution identification type and the muscle and bone state, output conditioning suggestions.

9. A TCM constitution identification device, characterized in that: include: A first image acquisition module is configured to acquire an image of the user's tongue; and a processing module, coupled to the first image acquisition module, configured to execute the TCM constitution identification method according to any one of claims 1 to 8; Preferably, the TCM constitution identification device further includes: a second image acquisition module, coupled to the processing module, and configured to acquire an infrared image of the user's knee joint.

10. A computer-readable storage medium, characterized in that The invention comprises computer executable instructions stored thereon, and when the executable instructions are executed by a processor, the method for identifying constitution of traditional Chinese medicine according to any one of claims 1 to 8 is implemented.

Images