Health state monitoring management system for traditional Chinese medicine AI digital health steward

Abstract

The invention discloses a health state monitoring management system for a traditional Chinese medicine AI digital health manager, and belongs to the technical field of health management. Comprising an information receiving module; a health index calculation module; a personal case library construction module; a primary disease screening module; a secondary disease screening module; and a disease diagnosis module. According to the invention, by constructing a personal case library, adopting primary and secondary grading screening mechanisms and combining with an analytic hierarchy process to dynamically set feature weights and standardize data, accurate personalized health state monitoring, efficient disease screening and diagnosis and scientific quantitative evaluation effects conforming to traditional Chinese medicine syndrome differentiation logic are achieved; the problems of insufficient utilization of personalized health data, low disease screening efficiency and unscientific health index quantitative evaluation in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the field of health management technology, and in particular to a health status monitoring and management system for a traditional Chinese medicine AI digital health manager. Background Art

[0002] With the advancement of technology and rising health awareness, people's demand for health management continues to grow. The application of Traditional Chinese Medicine (TCM) AI technology in health management has become a research hotspot. Existing TCM health management systems largely rely on manual experience, resulting in low efficiency and a lack of data support. While some systems have incorporated intelligent technology, they still have many shortcomings.

[0003] However, in the process of implementing the technical solutions of the embodiments of the present application, the present application discovered that the above technology has at least the following technical problems:

[0004] In the existing technology, the traditional Chinese medicine health management system has problems such as insufficient utilization of users' historical case data, lack of a grading mechanism for disease screening resulting in low efficiency, unscientific quantitative assessment of health indicators, and insufficient accuracy of multi-dimensional feature matching, making it difficult to achieve accurate personalized health management and disease diagnosis. Summary of the Invention

[0005] The embodiments of the present application provide a health status monitoring and management system for a Traditional Chinese Medicine AI digital health butler, thereby solving the problems of insufficient utilization of personalized data in Traditional Chinese Medicine health management, low disease screening efficiency, and unscientific quantitative assessment of health indicators in the prior art, and achieving the technical effects of accurate personalized health monitoring, efficient graded diagnosis, and precise matching of multi-dimensional features.

[0006] The embodiment of the present application provides a health status monitoring and management system for a traditional Chinese medicine AI digital health manager, comprising: an information receiving module: for receiving personal physical condition information uploaded by a user;

[0007] Health index calculation module: used to obtain the user's health index based on the received personal physical condition information;

[0008] Personal case database construction module: used to build a personal case database based on the user's historical case data;

[0009] Primary disease screening module: When the health index is not greater than the preset health threshold, the user's physical condition information is compared with the personal case database for characteristics. If the comparison result meets a certain disease standard, the possibility of the disease is output;

[0010] Secondary disease screening module: used to compare the user's physical condition information with all disease information in the knowledge base when the primary disease screening module does not output the disease possibility;

[0011] Disease diagnosis module: used to determine whether the user is sick based on the disease possibility output by the primary disease screening module or the comparison result output by the secondary disease screening module.

[0012] Furthermore, the step of obtaining the user's health index based on the received personal physical condition information includes:

[0013] Extract the characteristics of the personal physical condition information to obtain multiple characteristic indicators. Let the characteristic indicators be x1, x2, ..., x n , each of the characteristic indicators corresponds to a characteristic dimension;

[0014] Set a weight coefficient for each feature dimension to form a weight coefficient sequence w1, w2, ..., w n ;

[0015] The characteristic index is standardized to obtain a standardized characteristic index sequence x1′, x2′, ..., x n ';

[0016] The user health index is calculated using the health index formula.

[0017] Furthermore, the steps for obtaining the health index formula are:

[0018] The health index formula is obtained by performing weighted summation on the standardized characteristic index sequence and the weight coefficient sequence:

[0019]

[0020] Where x i is the original value of the i-th characteristic index, is the weight coefficient of the i-th characteristic dimension, calculated using the hierarchical analysis method, is the standardized characteristic index, and is obtained through the standardization function Calculated, where max(x i ) represents the maximum value among all characteristic indicators, min(x i ) represents the minimum value of all characteristic indicators, and n is the total number of characteristic indicators.

[0021] Furthermore, the steps of building a personal case database based on the user's historical case data include:

[0022] Performing data cleaning on the user's historical case data to obtain cleaned case data;

[0023] Perform feature extraction on the cleaned case data to obtain multiple feature vectors, set as y1,y2,...,y m , each of the feature vectors corresponds to a case feature;

[0024] Normalize the feature vector to obtain a normalized feature vector sequence y1′, y2′, ..., y′ m ;

[0025] Construct a feature matrix, use all normalized feature vectors as row vectors to form a feature matrix, and obtain a personal case database.

[0026] Furthermore, the step of comparing the user's physical condition information with the personal medical database includes:

[0027] Extract the features of the user's physical condition information and obtain the current feature vector, which is set as z1, z2, ..., z k ;

[0028] Normalizing the current feature vector to obtain a normalized current feature vector;

[0029] Calculate the Euclidean distance between the normalized current feature vector and each row vector in the feature matrix to obtain a distance sequence d1, d2, ..., d m ;

[0030] By obtaining the minimum value in the distance sequence and comparing it with a preset distance threshold, if the minimum value is not greater than the preset distance threshold, the disease type of the case corresponding to the minimum value is output.

[0031] Furthermore, the step of calculating the Euclidean distance between the normalized current eigenvector and each row vector in the eigenmatrix is:

[0032] Each row vector of the feature matrix is ​​represented as y′ j =[y′ j1 ,y′ j2 ,...,y′ jk ], where j = 1, 2, ..., m;

[0033] For each row vector y′ j , calculate the square of the difference between it and the corresponding component of z′;

[0034] Obtaining the squared Euclidean distance between the row vector and the current eigenvector;

[0035] Take the square root of the squared Euclidean distance to get the final Euclidean distance d j :

[0036]

[0037] Where z′ i is the i-th component of the normalized current eigenvector, y′ ji is the i-th component of the j-th row vector of the characteristic matrix, d jis the Euclidean distance between the current eigenvector and the j-th row vector of the eigenmatrix.

[0038] Furthermore, the step of comparing the user's physical condition information with all disease information in the knowledge base includes:

[0039] Extract the characteristics of the user's physical condition information to obtain the symptom feature vector, which is set as a1, a2, ..., a p ;

[0040] Extract features of each disease information in the knowledge base to obtain multiple disease feature vectors, forming a disease feature set {B1, B2, ..., B q}, each disease feature vector is represented by b1,b2,...,b p ;

[0041] Calculate the dot product of the symptom feature vector and each disease feature vector to obtain the similarity sequence s1, s2, ..., s q ;

[0042] The similarity calculation formula is:

[0043]

[0044] Where b ji is the jth component of the i-th disease feature vector.

[0045] Furthermore, the step of calculating the dot product of the symptom feature vector and each disease feature vector is:

[0046] The symptom feature vector is represented as a=[a1,a2,...,a p ], and the disease feature vector is represented as b i =[b i1 ,b i2 ,...,b ip ], where i = 1, 2, ..., q;

[0047] For each disease feature vector b i , calculate the dot product between it and the corresponding component of the symptom feature vector a;

[0048] The dot product calculation formula is:

[0049]

[0050] Normalize the dot product to get the similarity S i , the calculation formula is:

[0051]

[0052] Where a j is the jth component of the symptom feature vector, b ij is the jth component of the i-th disease feature vector, S i is the similarity between the symptom feature vector and the i-th disease feature vector.

[0053] Furthermore, the step of comparing the user's physical condition information with all disease information in the knowledge base includes:

[0054] Extracting features from the user's physical condition information to obtain a symptom feature vector;

[0055] Screening out disease categories related to the symptom feature vector from the knowledge base to obtain a preliminary disease list;

[0056] For each disease in the preliminary disease list, the preliminary disease list is sorted according to the similarity, and the top N diseases with the highest similarity are selected as the final comparison results.

[0057] Furthermore, the step of determining whether the user is sick based on the disease possibility output by the primary disease screening module or the comparison result output by the secondary disease screening module includes:

[0058] From the similarity sequence S1, S2, ..., S q Determine the maximum similarity S max corresponding diseases;

[0059] Determine the maximum similarity S max Is it greater than or equal to the preset similarity threshold θ? If S max ≥θ, the user is judged to have the corresponding disease, otherwise it is judged that the user does not have the disease in the knowledge base.

[0060] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0061] 1. By building a personal case database and adopting a hierarchical mechanism of primary screening and secondary screening, we can quickly locate high-probability diseases based on the user's historical disease characteristics and reduce invalid calculations, thereby achieving accurate screening and efficient diagnosis of personalized diseases, effectively solving the problems of insufficient utilization of personalized health data and low disease screening efficiency in existing technologies.

[0062] 2. Dynamically set the characteristic dimension weight coefficient through the hierarchical analysis method and standardize the multi-source health indicators, so as to scientifically quantify the user's health index and eliminate the impact of data dimension differences, thereby realizing the quantitative assessment of health status in accordance with the logic of traditional Chinese medicine dialectics, and effectively solving the problems of subjective setting of health indicator weights and insufficient accuracy of evaluation results in existing technologies.

[0063] 3. Through the hierarchical collaboration mechanism of the primary disease screening module and the secondary disease screening module, a layered diagnostic process of "personal historical case priority matching + global disease feature supplementary comparison" is formed, thereby realizing personalized identification of the user's health status and full-scene coverage, effectively solving the problem in existing technologies that a single screening mode is difficult to take into account both individual specificity and disease diversity. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a structural diagram of a health status monitoring and management system for a Traditional Chinese Medicine AI digital health manager provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] The embodiments of the present application provide a health status monitoring and management system for a Traditional Chinese Medicine AI digital health butler, which solves the problems of insufficient utilization of personalized health data, low disease screening efficiency, and unscientific quantitative evaluation of health indicators in the prior art. By constructing a personal case database, adopting a hierarchical screening mechanism, and combining the hierarchical analysis method to dynamically set feature weights and data standardization processing, accurate personalized health monitoring, efficient disease diagnosis, and scientific quantitative evaluation in accordance with the logic of Traditional Chinese Medicine syndrome differentiation are achieved.

[0066] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0067] like Figure 1 The figure shows a structure diagram of a health status monitoring and management system for a TCM AI digital health manager provided by an embodiment of the present application, including: an information receiving module: used to receive personal physical condition information uploaded by users, including but not limited to symptom descriptions, tongue and facial image data, historical diagnosis and treatment records, etc., and can receive physiological health data collected by IoT devices;

[0068] Health index calculation module: used to obtain the user's health index based on the received personal physical condition information;

[0069] Personal case database construction module: used to organize, classify and extract features based on the user's historical case data to build the user's personal case database;

[0070] Primary disease screening module: When the health index is lower than the preset threshold, the user's current physical condition information is compared with the personal case database. If the comparison result meets the diagnostic criteria of a certain disease, the possibility of the disease is output;

[0071] Secondary disease screening module: used to compare the user's physical condition information with all disease information in the knowledge base when the primary disease screening module does not output the disease possibility;

[0072] Disease diagnosis module: used to determine whether the user is sick based on the disease possibility output by the primary disease screening module or the comparison result output by the secondary disease screening module.

[0073] Furthermore, the step of obtaining the user's health index based on the received personal physical condition information includes:

[0074] Extract the characteristics of the personal physical condition information to obtain multiple characteristic indicators. Let the characteristic indicators be x1, x2, ..., x n , each of the characteristic indicators corresponds to a characteristic dimension;

[0075] Set a weight coefficient for each feature dimension to form a weight coefficient sequence w1, w2, ..., w n , the method for determining the weight coefficient adopts the hierarchical analysis method;

[0076] According to the index standardization function, the characteristic index is standardized to obtain the standardized characteristic index sequence x1′, x2′, ..., x n ';

[0077] The user health index is calculated using the health index formula.

[0078] Furthermore, the steps for obtaining the health index formula are:

[0079] The health index formula is obtained by performing weighted summation on the standardized characteristic index sequence and the weight coefficient sequence:

[0080]

[0081] Where x i is the original value of the i-th characteristic index, is the weight coefficient of the i-th characteristic dimension, calculated using the hierarchical analysis method, is the standardized characteristic index, and is obtained through the standardization function Calculated, where max(x i ) represents the maximum value among all characteristic indicators, min(x i ) represents the minimum value of all characteristic indicators, and n is the total number of characteristic indicators.

[0082] Furthermore, the steps of building a personal case database based on the user's historical case data include:

[0083] Performing data cleaning on the user's historical case data to obtain cleaned case data, including removing duplicate data, filling missing values, and correcting erroneous data;

[0084] Perform feature extraction on the cleaned case data to obtain multiple feature vectors, set as y1,y2,...,ym , each of the feature vectors corresponds to a case feature;

[0085] Normalize the feature vector to obtain a normalized feature vector sequence y1′, y2′, ..., y′ m , the normalization function is Where max(y j ) is the maximum value among all eigenvectors, min(y j ) is the minimum value among all eigenvectors;

[0086] Construct a feature matrix, use all normalized feature vectors as row vectors to form a feature matrix, and obtain a personal case database.

[0087] Furthermore, the step of comparing the user's physical condition information with the personal medical database includes:

[0088] Extract the features of the user's physical condition information and obtain the current feature vector, which is set as z1, z2, ..., z k ;

[0089] The current feature vector is normalized to obtain a normalized current feature vector. The processing method is: Where max(z) is the maximum value in the current eigenvector, and min(z) is the minimum value;

[0090] Calculate the Euclidean distance between the normalized current feature vector and each row vector in the feature matrix to obtain a distance sequence d1, d2, ..., d m ;

[0091] By obtaining the minimum value in the distance sequence and comparing it with a preset distance threshold, if the minimum value is not greater than the preset distance threshold, the disease type of the case corresponding to the minimum value is output.

[0092] Furthermore, the step of calculating the Euclidean distance between the normalized current eigenvector and each row vector in the eigenmatrix is:

[0093] Each row vector of the feature matrix is ​​represented as y′ j =[y′ j1 ,y′ j2 ,...,y′ jk ], where j = 1, 2, ..., m;

[0094] For each row vector y′ j , calculate the square of the difference between it and the corresponding component of z′;

[0095] Obtaining the squared Euclidean distance between the row vector and the current eigenvector;

[0096] Take the square root of the squared Euclidean distance to get the final Euclidean distance d j :

[0097]

[0098] Where z′ i is the i-th component of the normalized current eigenvector, y′ ji is the i-th component of the j-th row vector of the characteristic matrix, d j is the Euclidean distance between the current eigenvector and the j-th row vector of the eigenmatrix.

[0099] Furthermore, the step of comparing the user's physical condition information with all disease information in the knowledge base includes:

[0100] Extract the characteristics of the user's physical condition information to obtain the symptom feature vector, which is set as a1, a2, ..., a p ;

[0101] Extract features of each disease information in the knowledge base to obtain multiple disease feature vectors, forming a disease feature set {B1, B2, ..., B q}, each disease feature vector is represented by b1,b2,...,b p ;

[0102] Calculate the dot product of the symptom feature vector and each disease feature vector to obtain the similarity sequence s1, s2, ..., s q ;

[0103] The similarity calculation formula is:

[0104]

[0105] Where b ji is the jth component of the i-th disease feature vector.

[0106] Furthermore, the step of calculating the dot product of the symptom feature vector and each disease feature vector is:

[0107] The symptom feature vector is represented as a=[a1,a2,...,a p ], and the disease feature vector is represented as b i =[b i1 ,b i2 ,...,b ip ], where i = 1, 2, ..., q;

[0108] For each disease feature vector b i , calculate the dot product between it and the corresponding component of the symptom feature vector a;

[0109] The dot product calculation formula is:

[0110]

[0111] Normalize the dot product to get the similarity S i , the calculation formula is:

[0112]

[0113] Where a j is the jth component of the symptom feature vector, b ij is the jth component of the i-th disease feature vector, S i is the similarity between the symptom feature vector and the i-th disease feature vector.

[0114] Furthermore, the step of comparing the user's physical condition information with all disease information in the knowledge base includes:

[0115] Extracting features from the user's physical condition information to obtain a symptom feature vector;

[0116] Screening out disease categories related to the symptom feature vector from the knowledge base to obtain a preliminary disease list;

[0117] For each disease in the preliminary disease list, the preliminary disease list is sorted according to the similarity, and the top N diseases with the highest similarity are selected as the final comparison results.

[0118] Furthermore, the step of determining whether the user is sick based on the disease possibility output by the primary disease screening module or the comparison result output by the secondary disease screening module includes:

[0119] From the similarity sequence S1, S2, ..., S q Determine the maximum similarity S max corresponding diseases;

[0120] Determine the maximum similarity S max Is it greater than or equal to the preset similarity threshold θ? If S max ≥θ, the user is judged to have the corresponding disease, otherwise it is judged that the user does not have the disease in the knowledge base.

[0121] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0122] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0125] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0126] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A health status monitoring and management system for a traditional Chinese medicine AI digital health butler, characterized in that: include: Information receiving module: used to receive personal physical condition information uploaded by users; Health index calculation module: used to obtain the user's health index based on the received personal physical condition information; Personal case database construction module: used to build a personal case database based on the user's historical case data; Primary disease screening module: When the health index is not greater than the preset health threshold, the user's physical condition information is compared with the personal case database for characteristics. If the comparison result meets a certain disease standard, the possibility of the disease is output; Secondary disease screening module: used to compare the user's physical condition information with all disease information in the knowledge base when the primary disease screening module does not output the disease possibility; Disease diagnosis module: used to determine whether the user is sick based on the disease possibility output by the primary disease screening module or the comparison result output by the secondary disease screening module.

2. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 1, characterized in that: The steps of obtaining the user health index based on the received personal physical condition information include: Extract the characteristics of the personal physical condition information to obtain multiple characteristic indicators. Let the characteristic indicators be x1, x2, ..., x n , each of the characteristic indicators corresponds to a characteristic dimension; Set a weight coefficient for each feature dimension to form a weight coefficient sequence w1, w2, ..., w n ; The characteristic index is standardized to obtain a standardized characteristic index sequence x1′, x2′, ..., x n '; The user health index is calculated using the health index formula.

3. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 1, characterized in that: The steps to obtain the health index formula are: The health index formula is obtained by performing weighted summation on the standardized characteristic index sequence and the weight coefficient sequence: Where x i is the original value of the i-th characteristic index, is the weight coefficient of the i-th characteristic dimension, calculated using the hierarchical analysis method, is the standardized characteristic index, and is obtained through the standardization function Calculated, where max(x i ) represents the maximum value among all characteristic indicators, min(x i ) represents the minimum value of all characteristic indicators, and n is the total number of characteristic indicators.

4. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 1, characterized in that: The steps to build a personal case database based on the user's historical case data include: Performing data cleaning on the user's historical case data to obtain cleaned case data; Perform feature extraction on the cleaned case data to obtain multiple feature vectors, set as y1,y2,...,y m , each of the feature vectors corresponds to a case feature; Normalize the feature vector to obtain a normalized feature vector sequence y1′, y2′, ..., y′ m ; Construct a feature matrix, use all normalized feature vectors as row vectors to form a feature matrix, and obtain a personal case database.

5. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 1, characterized in that: The steps of comparing the user's physical condition information with the personal medical database include: Extract the features of the user's physical condition information and obtain the current feature vector, which is set as z1, z2, ..., z k ; Normalizing the current feature vector to obtain a normalized current feature vector; Calculate the Euclidean distance between the normalized current feature vector and each row vector in the feature matrix to obtain a distance sequence d1, d2, ..., d m ; By obtaining the minimum value in the distance sequence and comparing it with a preset distance threshold, if the minimum value is not greater than the preset distance threshold, the disease type of the case corresponding to the minimum value is output.

6. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 5, characterized in that: The steps of calculating the Euclidean distance between the normalized current eigenvector and each row vector in the eigenmatrix are: Each row vector of the feature matrix is ​​represented as y′ j =[y′ j1 ,y′ j2 ,...,y′ jk ], where j = 1, 2, …, m; For each row vector y′ j , calculate the square of the difference between it and the corresponding component of z′; Obtaining the squared Euclidean distance between the row vector and the current eigenvector; Take the square root of the squared Euclidean distance to get the final Euclidean distance d j : Where z′ i is the i-th component of the normalized current eigenvector, y′ ji is the i-th component of the j-th row vector of the characteristic matrix, d j is the Euclidean distance between the current eigenvector and the j-th row vector of the eigenmatrix.

7. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 6, characterized in that: The steps of comparing the user's physical condition information with all the disease information in the knowledge base include: Extract the characteristics of the user's physical condition information to obtain the symptom feature vector, which is set as a1, a2, ..., a p ; Extract features of each disease information in the knowledge base to obtain multiple disease feature vectors, forming a disease feature set {B1, B2, ..., B q }, each disease feature vector is represented by b1,b2,...,b p ; Calculate the dot product of the symptom feature vector and each disease feature vector to obtain the similarity sequence s1, s2, ..., s q ; The similarity calculation formula is: Where b ji is the jth component of the i-th disease feature vector.

8. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 7, characterized in that: The steps for calculating the dot product of the symptom feature vector and each disease feature vector are: The symptom feature vector is represented as a=[a1,a2,...,a p ], and the disease feature vector is represented as b i =[b i1 ,b i2 ,...,b ip ], where i = 1, 2, ..., q; For each disease feature vector b i , calculate the dot product between it and the corresponding component of the symptom feature vector a; The dot product calculation formula is: Normalize the dot product to get the similarity S i , the calculation formula is: Where a j is the jth component of the symptom feature vector, b ij is the jth component of the i-th disease feature vector, S i is the similarity between the symptom feature vector and the i-th disease feature vector.

9. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 1, characterized in that: The steps of comparing the user's physical condition information with all the disease information in the knowledge base include: Extracting features from the user's physical condition information to obtain a symptom feature vector; Screening out disease categories related to the symptom feature vector from the knowledge base to obtain a preliminary disease list; For each disease in the preliminary disease list, the preliminary disease list is sorted according to the similarity, and the top N diseases with the highest similarity are selected as the final comparison results.

10. A health status monitoring and management system for a TCM AI digital health manager as claimed in claim 1, characterized in that: Based on the disease probability output by the primary disease screening module or the comparison result output by the secondary disease screening module, the steps of determining whether the user is sick include: From the similarity sequence S1, S2, ..., S q Determine the maximum similarity S max corresponding diseases; Determine the maximum similarity S max Is it greater than or equal to the preset similarity threshold θ? If S max ≥θ, the user is judged to have the corresponding disease, otherwise it is judged that the user does not have the disease in the knowledge base.

Images