Health guidance report generation method, system and terminal based on traditional Chinese medicine constitution identification

Abstract

The invention discloses a health guidance report generation method and system based on traditional Chinese medicine constitution identification and a terminal, and relates to the technical field of artificial intelligence. According to the method, a guide feature array can be matched for physical characteristics, so that a guide feature matrix for health guidance is obtained, then same guide feature merging processing and exclusive guide feature elimination processing are performed on all updated guide feature matrixes of traditional Chinese medicine physical characteristics, and the remaining guide features are input into a standard time sequence template; a health guidance report with a detailed plan can be obtained; besides, in consideration of missing acquisition of physical characteristics in a traditional Chinese medicine constitution identification process, recessive physical characteristics of corresponding traditional Chinese medicine constitution are mined from the guidance characteristic matrix, and a corresponding recessive guidance characteristic array is matched for the recessive physical characteristics from the database, so that the effectiveness and comprehensiveness of a health guidance report are ensured.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically, to a method, system and terminal for generating a health guidance report based on TCM constitution identification. Background Art

[0002] TCM constitution refers to the unique physiological and pathological characteristics of an individual formed during the growth and development process under the influence of congenital genetics and acquired environmental factors. In general, TCM divides constitution into the following nine basic types: peaceful constitution, qi deficiency constitution, yang deficiency constitution, yin deficiency constitution, phlegm-damp constitution, damp-heat constitution, blood stasis constitution, qi stagnation constitution, and special constitution. TCM constitution identification can help people better understand their physical condition and health trends, so as to take more personalized and effective health management measures.

[0003] The existing health management measures mainly provide an overall description of health management for different TCM constitutions, such as health management measures for qi deficiency: A. Dietary conditioning: Eat more foods that have the effect of replenishing qi, such as yam, jujube, chicken, etc.; eat less or no raw, cold and cold foods. B. Daily life: Avoid overwork, get enough sleep, and avoid staying up late. C. Mental conditioning: Participate in more beneficial social activities, talk and communicate with others more, and cultivate an optimistic personality. D. Exercise: It is suitable to do gentle exercises, such as walking, Tai Chi, etc., and it is not suitable to do heavy load exercises and sweating exercises. Another example is the health management measures for qi deficiency: A. Dietary conditioning: Eat more sweet, cool and moisturizing foods, and eat less spicy and warm foods. B. Daily life: Maintain indoor humidity and avoid dryness; avoid excessive fatigue and staying up late. C. Exercise: Appropriately perform Tai Chi, yoga and other exercises. In the absence of detailed guidance, the target subjects are required to understand the overall health management description and then plan their own health management plan, which is not only difficult for the target subjects, but also difficult to achieve the expected implementation effect. In addition, different target subjects with the same TCM constitution may have different physical characteristics, and the overall health management description cannot achieve personalized and effective health management.

[0004] Therefore, how to research and design a method, system and terminal for generating health guidance reports based on TCM constitution identification that can overcome the above-mentioned defects is a problem that we urgently need to solve. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the purpose of the present invention is to provide a method, system and terminal for generating a health guidance report based on TCM constitution identification. On the basis of correlation analysis of constitution characteristics and guidance characteristics according to historical health guidance data, a guidance feature array can be matched for the constitution characteristics to obtain a guidance feature matrix for health guidance. The updated guidance feature matrices of all TCM constitutions are then processed by merging the same guidance features and eliminating the repulsive guidance features, and the remaining guidance features are input into a standard timing template, so as to obtain a health guidance report with a detailed plan.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions:

[0007] In a first aspect, a method for generating a health guidance report based on TCM constitution identification is provided, comprising the following steps:

[0008] Obtain all the physical characteristics collected by the target object for TCM physical constitution identification to obtain a set of all physical characteristics;

[0009] Extracting the constitution characteristics contained in at least one TCM constitution from the entire constitution characteristic set to obtain a sub-constitution characteristic set of the corresponding TCM constitution;

[0010] Match a guidance feature array for each constitution feature in the sub-constitution feature set from the database to obtain a guidance feature matrix for health guidance for the corresponding TCM constitution;

[0011] Mining the hidden constitution characteristics of the corresponding TCM constitution from the guidance characteristic matrix, and matching the hidden constitution characteristics with the corresponding hidden guidance characteristic array from the database;

[0012] The implicit guidance feature array and the corresponding guidance feature matrix are merged to obtain an updated guidance feature matrix;

[0013] The updated guidance feature matrix of all TCM constitutions is processed by merging the same guidance features and eliminating the repulsive guidance features, and the remaining guidance features are input into the standard time series template to obtain a health guidance report.

[0014] Furthermore, the extraction expression of the sub-constitution feature set of the TCM constitution is:

[0015] η A ={T1,…,T i ,…,T n},T i ∈Z all ,T i ∈Z A ,n≥N;

[0016] Among them, η Arepresents the sub-constitution feature set corresponding to TCM constitution A; T i represents the sub-physique feature set η A The i-th physical characteristic in Z all represents the total qualitative feature set; Z A Represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; n represents the number of constitution features in the sub-constitution feature set corresponding to TCM constitution A; N represents the set threshold.

[0017] Furthermore, the extraction expression of the sub-constitution feature set of the TCM constitution is:

[0018] η A ={T1,…,T i ,…,T n},T i ∈Z all ,T i ∈Z A ,n≥N0×log a (k+a);

[0019] Among them, η A represents the sub-constitution feature set corresponding to TCM constitution A; T i represents the sub-physique feature set η A The i-th physical characteristic in Z all represents the total qualitative feature set; Z A Represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; n represents the number of constitution features in the sub-constitution feature set corresponding to TCM constitution A; N0 represents the basic value; k represents the number of TCM constitutions that meet the extraction conditions; a represents a constant value, which is a positive integer.

[0020] Furthermore, each physical characteristic in the database corresponds to a unique guiding characteristic array;

[0021] Among them, the guidance features in the guidance feature array are divided into diet features, sleep features and exercise features, and each guidance feature is configured with a corresponding time attribute;

[0022] And, the n guiding feature arrays are combined to form a guiding feature matrix of size n×q, q is the maximum number of guiding features in each guiding feature array, and the elements without guiding features in the guiding feature matrix are filled with 0 values.

[0023] Furthermore, the expression for mining the hidden constitution characteristics of the corresponding TCM constitution from the guiding characteristic matrix is ​​specifically:

[0024]

[0025] Among them, G A Represents the guiding feature matrix corresponding to TCM constitution A; Represents a recessive physical trait T y The corresponding implicit guidance feature array; m represents the number of identical guidance features; Represents an array of implicit guidance features The number of guiding features in ; ε represents the ratio of the same guiding features, and its value range is [0.5,1]; T y Indicates the latent constitution characteristics of TCM constitution A; Z A represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; η A Represents the sub-constitution feature set corresponding to TCM constitution A.

[0026] Furthermore, if there are identical guiding features in the updated guiding feature matrices of all TCM constitutions, the identical guiding features are merged into one guiding feature, and the weight coefficient corresponding to the merged guiding feature is the sum of the weight coefficients of the identical guiding features before the merge.

[0027] Furthermore, if there are mutually exclusive guiding features in the updated guiding feature matrix of all TCM constitutions, the mutually exclusive guiding features will be deleted.

[0028] Furthermore, the process of inputting the remaining guidance features into the standard timing template is specifically as follows:

[0029] The remaining guidance features in the updated guidance feature matrix of all TCM constitutions are classified according to guidance items, and the classified guidance features are written into the corresponding guidance items in the standard time series template to obtain a health guidance report;

[0030] Alternatively, the process of inputting the remaining guidance features into the standard timing template is specifically as follows:

[0031] A write threshold H is configured for each guidance item in the standard timing template;

[0032] The remaining guiding features in the updated guiding feature matrix of all TCM constitutions are classified according to the guiding items, and the guiding features divided by each guiding item are arranged in descending order according to the weight value to obtain a guiding feature list for each guiding item;

[0033] Select the top H guidance features from the guidance feature list and write them into the corresponding guidance items in the standard timing template to obtain a health guidance report;

[0034] Among them, the weight coefficient of the implicit guidance feature is smaller than the weight coefficient of the guidance feature.

[0035] In a second aspect, a health guidance report generation system based on TCM constitution identification is provided, the system is used to implement the health guidance report generation method based on TCM constitution identification as described in any one of the first aspects, including:

[0036] A feature acquisition module is used to acquire all the physical characteristics collected by the target object for TCM physical constitution identification to obtain a set of all physical characteristics;

[0037] A feature extraction module is used to extract the constitution features contained in at least one TCM constitution from the entire constitution feature set to obtain a sub-constitution feature set of the corresponding TCM constitution;

[0038] A guidance matching module is used to match a guidance feature array for each constitution feature in the sub-constitution feature set from the database to obtain a guidance feature matrix for health guidance for the corresponding TCM constitution;

[0039] A feature mining module is used to mine the hidden constitution features of the corresponding TCM constitution from the guiding feature matrix, and match the hidden constitution features with the corresponding hidden guiding feature array from the database;

[0040] A guidance fusion module, used for fusing the implicit guidance feature array and the corresponding guidance feature matrix to obtain an updated guidance feature matrix;

[0041] The report generation module is used to merge the same guidance features and eliminate the repulsive guidance features of the updated guidance feature matrix of all TCM constitutions, and input the remaining guidance features into the standard time series template to obtain a health guidance report.

[0042] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for generating a health guidance report based on TCM constitution identification as described in any one of the first aspects is implemented.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. The method for generating a health guidance report based on TCM constitution identification provided by the present invention can match a guidance feature array for the constitution features on the basis of correlation analysis between the constitution features and the guidance features according to historical health guidance data, thereby obtaining a guidance feature matrix for health guidance, and then perform a merging process of identical guidance features and elimination of mutually exclusive guidance features on the updated guidance feature matrices of all TCM constitutions, and input the remaining guidance features into a standard time series template, thereby obtaining a health guidance report with a detailed plan;

[0045] 2. The present invention takes into account the omission of constitution characteristics in the process of TCM constitution identification, digs out the hidden constitution characteristics of the corresponding TCM constitution from the guidance feature matrix, and matches the corresponding hidden guidance feature array for the hidden constitution characteristics from the database, which can enrich the guidance features, thereby ensuring the effectiveness and comprehensiveness of the health guidance report;

[0046] 3. The present invention takes into account the mis-selection of constitution characteristics in the process of TCM constitution identification, extracts at least one constitution characteristic contained in the TCM constitution from the entire constitution characteristic set, and generates a health guidance report based on one or more sub-constitution characteristic sets, which can effectively avoid the interference of mis-selected constitution characteristics on the health guidance report, and effectively ensure the rationality and reliability of the health guidance report;

[0047] 4. The present invention takes into account that some target objects may have multiple TCM constitutions. When extracting sub-constitution feature sets from the entire constitution feature set, the difficulty of the extraction conditions can be flexibly increased as the number of TCM constitutions that meet the extraction conditions increases, thereby avoiding the extreme situations where the TCM constitution cannot be extracted or the number of extracted TCM constitutions is too large. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0049] Figure 1 is a flow chart of Embodiment 1 of the present invention;

[0050] Figure 2 It is a system block diagram in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0052] Example 1: A method for generating a health guidance report based on TCM constitution identification, such as Figure 1 As shown, the following steps are included:

[0053] S1: Obtain all the constitution characteristics collected by the target object for TCM constitution identification to obtain the entire constitution characteristic set;

[0054] S2: extracting the constitution characteristics contained in at least one TCM constitution from the entire constitution characteristic set to obtain a sub-constitution characteristic set of the corresponding TCM constitution;

[0055] S3: Match a guidance feature array for each constitution feature in the sub-constitution feature set from the database to obtain a guidance feature matrix for health guidance for the corresponding TCM constitution;

[0056] S4: mining the hidden constitution characteristics of the corresponding TCM constitution from the guidance feature matrix, and matching the hidden constitution characteristics with the corresponding hidden guidance feature array from the database;

[0057] S5: fusing the implicit guidance feature array and the corresponding guidance feature matrix to obtain an updated guidance feature matrix;

[0058] S6: The updated guidance feature matrix of all TCM constitutions is processed by merging identical guidance features and eliminating mutually exclusive guidance features, and the remaining guidance features are input into the standard time series template to obtain a health guidance report.

[0059] In step S1, the methods of collecting physical characteristics include but are not limited to image recognition, questionnaire survey and data input, and physical characteristics can be generally divided into facial features, tongue characteristics, pulse characteristics, fingerprint characteristics, emotions, living habits, eating habits, voice, body shape and body type characteristics.

[0060] Different types of features can be further subdivided. For example, facial features can be divided into features such as complexion, skin texture, facial luster, eyelid swelling, facial morphology, eyebrow thickness, and lip thickness; tongue features can be divided into features such as tongue color, tongue coating, tongue shape, tongue quality, tooth marks, sublingual veins, and tongue dynamics; fingerprint features can be divided into features such as fingerprint texture, morphology, and distribution.

[0061] All the physical characteristics that can be collected constitute a complete physical characteristic set.

[0062] In step S2, considering the mis-collection of constitution features in the process of TCM constitution identification, for example, the insufficient accuracy of image recognition technology or the influence of factors such as ambient light may lead to incorrect features of complexion recognition, and incorrect constitution features will affect the accuracy of the health guidance report. Therefore, it is necessary to extract a correct sub-constitution feature set belonging to the TCM constitution from the entire constitution feature set.

[0063] As an optional implementation, the constitution feature set can be extracted by setting a fixed threshold. The extraction expression of the sub-constitution feature set of the traditional Chinese medicine constitution is:

[0064] η A ={T1,…,T i ,…,T n},T i ∈Z all ,T i ∈Z A ,n≥N;

[0065] Among them, η A represents the sub-constitution feature set corresponding to TCM constitution A; T i represents the sub-physique feature set η A The i-th physical characteristic in Z all represents the total qualitative feature set; Z A Represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; n represents the number of constitution features in the sub-constitution feature set corresponding to TCM constitution A; N represents the set threshold.

[0066] As an optional implementation, the present invention takes into account that some target subjects may have multiple TCM constitutions. When extracting sub-constitution feature sets from the entire constitution feature set, the difficulty of the extraction conditions is flexibly increased as the number of TCM constitutions that meet the extraction conditions increases, thereby avoiding the extreme situation where no TCM constitution can be extracted or a large number of TCM constitutions are extracted. To this end, the extraction expression of the sub-constitution feature set of the TCM constitution is:

[0067] η A ={T1,…,T i ,…,T n},T i ∈Z all ,T i ∈Z A ,n≥N0×log a (k+a);

[0068] Among them, η A represents the sub-constitution feature set corresponding to TCM constitution A; T i represents the sub-physique feature set η A The i-th physical characteristic in Z all represents the total qualitative feature set; Z A Represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; n represents the number of constitution features in the sub-constitution feature set corresponding to TCM constitution A; N0 represents the basic value; k represents the number of TCM constitutions that meet the extraction conditions; a represents a constant value, which is a positive integer.

[0069] In step S3, each physical characteristic in the database corresponds to a unique guidance feature array; wherein the guidance features in the guidance feature array are divided into diet features, sleep features and exercise features, and each guidance feature is configured with a corresponding time attribute; and n guidance feature arrays are combined to form a guidance feature matrix of size n×q, q is the maximum number of guidance features in each guidance feature array, and elements without guidance features in the guidance feature matrix are filled with 0 values.

[0070] It should be noted that whether the guidance feature is related to the physical feature can be determined by performing a correlation analysis based on historical health guidance data, and all guidance features related to the physical feature can be combined into a corresponding guidance feature array.

[0071] The guidance feature refers to guidance with a specific plan, with clear time and characteristic content. For example, "9.30 am, eat an egg" is a guidance feature. Another example is "12.30-13:30 noon, take a one-hour lunch break" is a guidance feature.

[0072] In step S4, the present invention takes into account the omission of physical characteristics in the process of TCM constitution identification, mines out the latent physical characteristics of the corresponding TCM constitution from the guidance feature matrix, and matches the latent physical characteristics with the corresponding latent guidance feature array from the database, which can enrich the guidance features, thereby ensuring the effectiveness and comprehensiveness of the health guidance report.

[0073] For example, the expression for mining the hidden constitution characteristics of the corresponding TCM constitution from the guiding feature matrix is ​​as follows:

[0074]

[0075] Among them, G A Represents the guiding feature matrix corresponding to TCM constitution A; Represents a recessive physical trait T y The corresponding implicit guidance feature array; m represents the number of identical guidance features; Represents an array of implicit guidance features The number of guiding features in ; ε represents the ratio of the same guiding features, and its value range is [0.5,1]; T y Indicates the latent constitution characteristics of TCM constitution A; Z A represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; η A Represents the sub-constitution feature set corresponding to TCM constitution A.

[0076] In step S5, if the maximum number of guiding features in the n1 implicit guiding feature arrays does not exceed q, then the size of the fused updated guiding feature matrix is ​​(n+n1)×q. If the maximum number of guiding features q1 in the n1 implicit guiding feature arrays exceeds q, then the size of the fused updated guiding feature matrix is ​​(n+n1)×q1.

[0077] In step S6, if there are identical guiding features in the updated guiding feature matrices of all TCM constitutions, the identical guiding features are merged into one guiding feature, and the weight coefficient corresponding to the merged guiding feature is the sum of the weight coefficients of the identical guiding features before the merge.

[0078] If there are mutually exclusive guiding features in the updated guiding feature matrix of all TCM constitutions, the mutually exclusive guiding features will be deleted.

[0079] As an optional implementation, the process of inputting the remaining guidance features into the standard time series template is specifically as follows: the remaining guidance features in the updated guidance feature matrix of all TCM constitutions are classified according to guidance items, and the classified guidance features are written into the corresponding guidance items in the standard time series template to obtain a health guidance report;

[0080] As another optional implementation, the process of inputting the remaining guidance features into the standard timing template is specifically as follows: a write threshold H is configured for each guidance item in the standard timing template; the remaining guidance features in the updated guidance feature matrix of all TCM constitutions are classified according to the guidance items, and the guidance features divided by each guidance item are arranged in descending order according to the weight value to obtain a guidance feature list for each guidance item; the top H guidance features are selected from the guidance feature list and written into the corresponding guidance items in the standard timing template to obtain a health guidance report; wherein the weight coefficient of the implicit guidance feature is less than the weight coefficient of the guidance feature.

[0081] Embodiment 2: A health guidance report generation system based on TCM constitution identification, the system is used to implement the health guidance report generation method based on TCM constitution identification as described in Embodiment 1, such as Figure 2 As shown, it includes a feature acquisition module, a feature extraction module, a guidance matching module, a feature mining module, a guidance fusion module and a report generation module.

[0082] Among them, the feature acquisition module is used to obtain all the physical features collected by the target object for TCM constitution identification, and obtain the whole physical feature set; the feature extraction module is used to extract the physical features contained in at least one TCM constitution from the whole physical feature set, and obtain the sub-physique feature set of the corresponding TCM constitution; the guidance matching module is used to match a guidance feature array for each physical feature in the sub-physique feature set from the database, and obtain the guidance feature matrix for health guidance for the corresponding TCM constitution; the feature mining module is used to mine the implicit physical features of the corresponding TCM constitution from the guidance feature matrix, and match the corresponding implicit guidance feature array for the implicit physical features from the database; the guidance fusion module is used to fuse the implicit guidance feature array and the corresponding guidance feature matrix to obtain an updated guidance feature matrix; the report generation module is used to merge the same guidance features and eliminate the repulsive guidance features on the updated guidance feature matrices of all TCM constitutions, and input the remaining guidance features into the standard timing template to obtain a health guidance report.

[0083] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for generating a health guidance report based on TCM constitution identification as described in Example 1 is implemented.

[0084] Working principle: Based on the correlation analysis of physical characteristics and guidance characteristics according to historical health guidance data, the present invention can match a guidance feature array for physical characteristics, thereby obtaining a guidance feature matrix for health guidance, and then merge the same guidance features and eliminate the repulsive guidance features for the updated guidance feature matrix of all TCM constitutions, and input the remaining guidance features into the standard timing template, so as to obtain a health guidance report with a detailed plan; in addition, considering the omission of physical characteristics in the process of TCM constitution identification, the implicit physical characteristics of the corresponding TCM constitution are mined from the guidance feature matrix, and the corresponding implicit guidance feature array is matched for the implicit physical characteristics from the database, so as to enrich the guidance features, thereby ensuring the effectiveness and comprehensiveness of the health guidance report.

[0085] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0086] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, 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 generate 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 flowchart and / or block diagram. 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.

[0087] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 1A function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0089] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for generating a health guidance report based on TCM constitution identification, characterized in that: The following steps are involved: Obtain all the physical characteristics collected by the target object for TCM physical constitution identification to obtain a set of all physical characteristics; Extracting the constitution characteristics contained in at least one TCM constitution from the entire constitution characteristic set to obtain a sub-constitution characteristic set of the corresponding TCM constitution; Match a guidance feature array for each constitution feature in the sub-constitution feature set from the database to obtain a guidance feature matrix for health guidance for the corresponding TCM constitution; Mining the hidden constitution characteristics of the corresponding TCM constitution from the guidance characteristic matrix, and matching the hidden constitution characteristics with the corresponding hidden guidance characteristic array from the database; The implicit guidance feature array and the corresponding guidance feature matrix are merged to obtain an updated guidance feature matrix; The updated guidance feature matrix of all TCM constitutions is processed by merging the same guidance features and eliminating the repulsive guidance features, and the remaining guidance features are input into the standard time series template to obtain a health guidance report.

2. The method for generating a health guidance report based on TCM constitution identification according to claim 1 is characterized in that: The extraction expression of the sub-constitution feature set of the TCM constitution is: the A ={T1,…,T i ,…,T n },T i ∈Z all ,T i ∈Z A ,n≥N; Among them, η A represents the sub-constitution feature set corresponding to TCM constitution A; T i represents the sub-physique feature set η A The i-th physical characteristic in Z all represents the total qualitative feature set; Z A Represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; n represents the number of constitution features in the sub-constitution feature set corresponding to TCM constitution A; N represents the set threshold.

3. The method for generating a health guidance report based on TCM constitution identification according to claim 1 is characterized in that: The extraction expression of the sub-constitution feature set of the TCM constitution is: the A ={T1,…,T i ,…,T n },T i ∈Z all ,T i ∈Z A ,n≥N0×log a (k+a); Among them, η A represents the sub-constitution feature set corresponding to TCM constitution A; T i represents the sub-physique feature set η A The i-th physical characteristic in Z all represents the total qualitative feature set; Z A Represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; n represents the number of constitution features in the sub-constitution feature set corresponding to TCM constitution A; N0 represents the basic value; k represents the number of TCM constitutions that meet the extraction conditions; a represents a constant value, which is a positive integer.

4. The method for generating a health guidance report based on TCM constitution identification according to claim 1 is characterized in that: Each physical characteristic in the database corresponds to a unique guiding characteristic array; Among them, the guidance features in the guidance feature array are divided into diet features, sleep features and exercise features, and each guidance feature is configured with a corresponding time attribute; And, the n guiding feature arrays are combined to form a guiding feature matrix of size n×q, q is the maximum number of guiding features in each guiding feature array, and the elements without guiding features in the guiding feature matrix are filled with 0 values.

5. The method for generating a health guidance report based on TCM constitution identification according to claim 1 is characterized in that: The expression for mining the hidden constitution characteristics of the corresponding TCM constitution from the guiding characteristic matrix is ​​specifically: Among them, G A Represents the guiding feature matrix corresponding to TCM constitution A; Represents a recessive physical trait T y The corresponding implicit guidance feature array; m represents the number of identical guidance features; Represents an array of implicit guidance features The number of guiding features in ; ε represents the ratio of the same guiding features, and its value range is [0.5,1]; T y Indicates the latent constitution characteristics of TCM constitution A; Z A represents the statistical constitution feature set of TCM constitution A, including all the constitution features exhibited by TCM constitution A; η A Represents the sub-constitution feature set corresponding to TCM constitution A.

6. The method for generating a health guidance report based on TCM constitution identification according to claim 1 is characterized in that: If there are identical guiding features in the updated guiding feature matrices of all TCM constitutions, the identical guiding features will be merged into one guiding feature, and the weight coefficient corresponding to the merged guiding feature is the sum of the weight coefficients of the identical guiding features before the merge.

7. The method for generating a health guidance report based on TCM constitution identification according to claim 1 is characterized in that: If there are mutually exclusive guiding features in the updated guiding feature matrix of all TCM constitutions, the mutually exclusive guiding features will be deleted.

8. The method for generating a health guidance report based on TCM constitution identification according to claim 1 is characterized in that: The process of inputting the remaining guidance features into the standard timing template is specifically as follows: The remaining guidance features in the updated guidance feature matrix of all TCM constitutions are classified according to guidance items, and the classified guidance features are written into the corresponding guidance items in the standard time series template to obtain a health guidance report; Alternatively, the process of inputting the remaining guidance features into the standard timing template is specifically as follows: A write threshold H is configured for each guidance item in the standard timing template; The remaining guiding features in the updated guiding feature matrix of all TCM constitutions are classified according to the guiding items, and the guiding features divided by each guiding item are arranged in descending order according to the weight value to obtain a guiding feature list for each guiding item; Select the top H guidance features from the guidance feature list and write them into the corresponding guidance items in the standard timing template to obtain a health guidance report; Among them, the weight coefficient of the implicit guidance feature is smaller than the weight coefficient of the guidance feature.

9. A health guidance report generation system based on TCM constitution identification, characterized by: The system is used to implement the method for generating a health guidance report based on TCM constitution identification as described in any one of claims 1 to 8, comprising: A feature acquisition module is used to acquire all the physical characteristics collected by the target object for TCM physical constitution identification to obtain a set of all physical characteristics; A feature extraction module is used to extract the constitution features contained in at least one TCM constitution from the entire constitution feature set to obtain a sub-constitution feature set of the corresponding TCM constitution; A guidance matching module is used to match a guidance feature array for each constitution feature in the sub-constitution feature set from the database to obtain a guidance feature matrix for health guidance for the corresponding TCM constitution; A feature mining module is used to mine the hidden constitution features of the corresponding TCM constitution from the guiding feature matrix, and match the hidden constitution features with the corresponding hidden guiding feature array from the database; A guidance fusion module, used for fusing the implicit guidance feature array and the corresponding guidance feature matrix to obtain an updated guidance feature matrix; The report generation module is used to merge the same guidance features and eliminate the repulsive guidance features of the updated guidance feature matrix of all TCM constitutions, and input the remaining guidance features into the standard time series template to obtain a health guidance report.

10. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for generating a health guidance report based on TCM constitution identification as described in any one of claims 1 to 8 is implemented.

Images