A method for recommending daily diet for patients with rheumatism in traditional Chinese medicine

Abstract

The present invention relates to the technical field of medical care, and specifically to a method for recommending a daily diet for patients with rheumatism in traditional Chinese medicine. The present invention reduces the dimension of rheumatism data to obtain all principal components; obtains the importance index of each preset dimension according to the data change of each preset dimension in each principal component and the data change of the dietary recommendation plan; obtains the overall correlation degree according to the data difference and correlation degree between any two preset dimensions in the principal component; obtains the correlation index of the principal component in combination with the factor loading difference between any two dimensions; obtains the comprehensive contribution factor according to the correlation index, the importance index and the factor loading; obtains the final rheumatism principal component according to the comprehensive contribution factor; and recommends a daily diet for patients with rheumatism in traditional Chinese medicine according to the final rheumatism principal component. The present invention provides a relatively clear explanation and basis, so that relevant medical personnel can make accurate recommendations on daily diet.

Description

Technical Field

[0001] The invention relates to the technical field of medical care, and in particular to a method for recommending daily diet for patients with rheumatism in traditional Chinese medicine. Background Art

[0002] Rheumatism in traditional Chinese medicine refers to various types of arthralgia, which are mainly manifested as muscle and joint pain and swelling caused by the invasion of wind, cold and dampness into the human body. In addition to drug treatment, traditional Chinese medicine attaches great importance to the dietary conditioning of patients with rheumatism, believing that a reasonable diet can help relieve symptoms and improve physical fitness. Due to the differences in specific symptoms, physical fitness, dietary preferences, etc. of different patients, it is necessary to customize the diet according to the needs of each patient to improve the scientificity and effectiveness of dietary recommendations.

[0003] In the prior art, daily diet recommendations for patients with rheumatic diseases are usually implemented through user-based collaborative filtering algorithms. This method uses the information of each patient to calculate the similarity between them to mine similar patients, and then formulates a suitable diet plan based on the performance of similar patients on various types of diets. It is known that when calculating similarity, there are too many data attributes of patients with rheumatic diseases, which may include data from multiple directions such as symptoms, constitution, medical history, treatment records and dietary preferences. At this time, a dimensionality reduction algorithm is usually used to reduce the dimensionality of patient data. However, in actual applications, the principal components obtained by the dimensionality reduction algorithm are only linear combinations of the original features, and it may be difficult to explain the actual meaning behind these combinations. In addition, the rehabilitation process of traditional Chinese medicine rheumatism often requires clearer explanations and bases, which ultimately leads to the inability of relevant personnel to make accurate recommendations on the daily diet of patients with traditional Chinese medicine rheumatic diseases. Summary of the invention

[0004] In order to solve the technical problem that when using a dimensionality reduction algorithm to reduce the dimensionality of rheumatic disease patient data, the principal components in the dimensionality reduction algorithm are difficult to explain their actual meaning, and the rehabilitation process of TCM rheumatism often requires clearer explanations and basis, which ultimately leads to the inability of relevant personnel to make accurate recommendations on daily diets, the purpose of the present invention is to provide a method for recommending a daily diet for TCM rheumatic disease patients, and the technical scheme adopted is as follows: a method for recommending a daily diet for TCM rheumatic disease patients, the method comprising: obtaining rheumatic disease data of all preset dimensions for each TCM rheumatic disease patient; performing data dimensionality reduction on all rheumatic disease data to obtain all rheumatic disease principal components and all preset dimensions in all rheumatic disease principal components; selecting any rheumatic disease principal component as a reference principal component, and selecting any preset dimension in the reference principal component as a target dimension; and selecting the target dimension of each TCM rheumatic disease patient according to the target dimension. The importance index of the target dimension is obtained based on the changing characteristics of rheumatism data and the changing characteristics of the corresponding dietary plan data of the rheumatism data of each target dimension; the overall correlation between the target dimension and each other preset dimension is obtained based on the difference in rheumatism data between the target dimension and each other preset dimension in the reference principal component, as well as the correlation between the target dimension and each other preset dimension; the correlation index of the reference principal component is obtained based on the difference in factor loadings and the overall correlation between any two preset dimensions in the reference principal component; the correlation index of the reference principal component is weighted based on the importance index and factor loading of each preset dimension in the reference principal component to obtain the comprehensive contribution factor of the reference principal component; all final rheumatism principal components are obtained based on the comprehensive contribution factors; daily diet recommendations are made for TCM rheumatism patients based on the final rheumatism principal components.

[0005] Furthermore, the method for obtaining the importance index of the target dimension includes: constructing a Cartesian coordinate system with all rheumatic disease data in the target dimension as the horizontal coordinate and corresponding dietary recommendation data as the vertical coordinate; obtaining the importance index according to the importance index calculation formula, and the importance index calculation formula is as follows: In the formula, An indicator of the importance of the target dimension; Represents the maximum value of rheumatology data in the target dimension; Represents the first-order difference between each two adjacent dietary recommendation data; represents the number of extreme points of the rheumatology data in the target dimension; Represents the first-order difference between every two adjacent extreme points of rheumatism data.

[0006] Furthermore, the method for obtaining the overall correlation degree includes: obtaining the overall correlation degree according to an overall correlation degree calculation formula, and the overall correlation degree calculation formula is as follows: In the formula, Indicates the ordinal number of the target dimension in the reference principal component; Indicates the target dimension and The overall correlation between the other pre-set dimensions; Indicates the target dimension and The degree of correlation between other pre-set dimensions; Indicates the number of extreme points of rheumatism data within the target dimension; Indicates The number of extreme value points of rheumatism data in other preset dimensions; Indicates the target dimension and The number of extreme points of the preset dimension with fewer extreme points of rheumatism data among other preset dimensions; Indicates the target dimension and of the other preset dimensions The distance between the extreme points of rheumatism data.

[0007] Furthermore, the method for obtaining the correlation index includes: obtaining the correlation index according to a correlation index calculation formula, and the correlation index calculation formula is as follows: In the formula, Indicates the serial number of the reference principal component; represents the correlation index of the reference principal component; Indicates the preset number of dimensions of the reference principal component; Indicates the target dimension and The overall correlation between the other pre-set dimensions; represents the factor loading of the target dimension of the reference principal component; Indicates The factor loadings of other preset dimensions.

[0008] Furthermore, the method for obtaining the comprehensive contribution factor includes: calculating the average value of the product between the importance index of each preset dimension in the reference principal component and the factor loading as the correlation weight of the reference principal component; and taking the product between the correlation weight of the reference principal component and the correlation index as the comprehensive contribution factor of the reference principal component.

[0009] Furthermore, the method for obtaining the final rheumatic disease principal component includes: obtaining the principal component contribution rates of all principal components according to the dimensionality reduction algorithm, and summing up the products of the principal component contribution rate of each principal component and the comprehensive contribution factor as the principal component cumulative contribution rate; when the principal component cumulative contribution rate is not less than the preset first threshold, each corresponding principal component is used as the final rheumatic disease principal component.

[0010] Furthermore, the target dimension is combined with The Pearson correlation coefficient between the target dimension and the other preset dimensions is used as the The correlation between the other preset dimensions.

[0011] A daily diet recommendation system for patients with rheumatism in traditional Chinese medicine. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for recommending a daily diet for patients with rheumatism in traditional Chinese medicine are implemented.

[0012] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for recommending a daily diet for patients with rheumatism in traditional Chinese medicine.

[0013] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for recommending a daily diet for patients with rheumatism by traditional Chinese medicine are implemented.

[0014] The present invention has the following beneficial effects: the present invention obtains rheumatism data of all preset dimensions for each TCM rheumatism patient; since the rheumatism data of TCM rheumatism patients have too many dimensions, it is necessary to reduce the dimension of the multi-dimensional rheumatism data of TCM rheumatism patients through a dimensionality reduction algorithm; since in actual situations, relevant medical personnel need to consider the importance of rheumatism data of each dimension when recommending dietary plans for TCM rheumatism patients, so the influence of rheumatism data of each dimension of different TCM rheumatism patients on the dietary plan recommendation of medical personnel is studied, and the importance index of the target dimension is obtained according to the change characteristics of the rheumatism data of the target dimension of each TCM rheumatism patient and the change characteristics of the dietary plan data corresponding to the rheumatism data of each target dimension; since in actual situations, rheumatism data of different dimensions are correlated to a certain extent, according to the target dimension in the reference principal component The difference of rheumatism data between the target dimension and each other preset dimensions, as well as the correlation degree between the target dimension and each other preset dimensions, obtain the overall correlation degree between the target dimension and each other preset dimensions, and combine the difference in factor loading to obtain the correlation index of the reference principal component; the importance index of each preset dimension in the reference principal component can characterize the reference value of rheumatism data of each preset dimension of TCM rheumatism patients in dietary recommendation, and the correlation index can characterize the effectiveness and interpretability of the reference principal component in obtaining the dietary plan. Therefore, according to the importance index and factor loading of each preset dimension in the reference principal component, the embodiment of the present invention weights the correlation index of the reference principal component, obtains the comprehensive contribution factor of the reference principal component, and then obtains all the final rheumatism principal components; according to the final rheumatism principal component, the daily diet of TCM rheumatism patients is recommended. The present invention provides a clearer explanation and basis for the dietary recommendation of TCM rheumatism, so that relevant medical personnel can make accurate recommendations on daily diet. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a method for recommending a daily diet for patients with rheumatism in Traditional Chinese Medicine provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is combined with the accompanying drawings and preferred embodiments to propose a daily diet recommendation method for patients with rheumatism in traditional Chinese medicine according to the present invention, and its specific implementation methods, structures, features and effects are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the daily diet recommendation method for patients with rheumatism in Traditional Chinese Medicine provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a method for recommending daily diet for patients with rheumatism in Traditional Chinese Medicine provided by an embodiment of the present invention, the method comprising: Step S1: obtaining rheumatism data of all preset dimensions for each patient with rheumatism in Traditional Chinese Medicine.

[0021] The embodiment of the present invention is mainly applied to the dietary recommendation scenario for patients with TCM rheumatism. In reality, relevant medical personnel usually recommend a dietary plan for each patient with rheumatism based on the similarity of rheumatism data of other patients with TCM rheumatism in multiple dimensions such as symptoms, constitution, medical history, treatment records and dietary preferences. Therefore, the present invention obtains rheumatism data of all preset dimensions for each patient with TCM rheumatism. In one embodiment of the present invention, the preset dimensions are set to the symptoms, constitution, medical history, treatment records and dietary preferences of patients with TCM rheumatism, wherein the rheumatism data of each dimension of patients with TCM rheumatism can be directly obtained through the database of the relevant institution.

[0022] Step S2: Perform data dimensionality reduction on all rheumatism data to obtain all rheumatism principal components and all preset dimensions in all rheumatism principal components; select any rheumatism principal component as the reference principal component, and select any preset dimension in the reference principal component as the target dimension; obtain the importance index of the target dimension based on the change characteristics of the rheumatism data of the target dimension of each TCM rheumatism patient, and the change characteristics of the corresponding dietary plan data of the rheumatism data of each target dimension; obtain the overall correlation between the target dimension and each other preset dimension based on the difference in rheumatism data between the target dimension and each other preset dimension in the reference principal component, and the correlation between the target dimension and each other preset dimension; obtain the correlation index of the reference principal component based on the difference in factor loading and the overall correlation between any two preset dimensions in the reference principal component.

[0023] Since the rheumatism data of TCM rheumatism patients have too many dimensions, it is necessary to reduce the dimensions of the multi-dimensional rheumatism data of TCM rheumatism patients through a dimensionality reduction algorithm. In one embodiment of the present invention, the PCA algorithm is used for dimensionality reduction in the following operations. It should be noted that in other embodiments of the present invention, other dimensionality reduction algorithms can also be used, and the PCA algorithm is a technical means well known to those skilled in the art, and is not limited or elaborated herein.

[0024] Because in actual situations, when relevant medical personnel recommend diet plans for patients with TCM rheumatism, they need to consider the importance of rheumatism data in each dimension, so the influence of rheumatism data in each dimension of different TCM rheumatism patients on the diet plan recommendation of medical personnel is studied, so in an embodiment of the present invention, a corresponding relationship between rheumatism data in each dimension and diet plan data of each TCM rheumatism patient is established. Among them, the diet plan data can be represented by a multidimensional vector. For example, the diet plan of a certain TCM rheumatism patient is three types of carbohydrates, proteins and fats. The content of the three types of diets can be set by the implementer. The content of each type of diet is combined into a multidimensional vector, and the multidimensional vector is replaced by the L2 norm. The specific process is a technical means well known to those skilled in the art, and it is not limited or elaborated here. Finally, according to the change characteristics of the rheumatism data of the target dimension of each TCM rheumatism patient, and the corresponding diet plan data change characteristics of the rheumatism data of each target dimension, the importance index of the target dimension is obtained.

[0025] Preferably, in one embodiment of the present invention, a method for obtaining an importance index of a target dimension includes: constructing a Cartesian coordinate system using all rheumatism data in the target dimension as the horizontal coordinate and corresponding dietary recommendation plan data as the vertical coordinate, wherein when the rheumatism data in the target dimension increases, the dietary plan changes significantly, indicating that the target dimension has a stronger influence on the dietary recommendation plan, and that the more extreme points there are and the more concentrated they are during the growth of the target dimension, indicating that changes in the target dimension can easily cause fluctuations in the dietary plan, and that relevant medical personnel need to focus on analyzing the rheumatism data in the target dimension when performing analysis.

[0026] The importance index is obtained according to the importance index calculation formula. The importance index calculation formula is as follows: In the formula, An indicator of the importance of the target dimension; Represents the maximum value of rheumatology data in the target dimension; Represents the first-order difference between each two adjacent dietary recommendation data; represents the number of extreme points of the rheumatology data in the target dimension; It represents the first-order difference between every two adjacent extreme points of rheumatism data; represents the absolute value function. Unless otherwise specified below, They all represent absolute value functions.

[0027] In the importance index calculation formula, the smaller the difference between two adjacent extreme value points of rheumatism data in the Cartesian coordinate system, the closer the extreme value points are. The smaller it is, the more extreme points there are, and the more drastic the changes in the rheumatism data in the target dimension cause the changes in the dietary recommendation data to be, that is, The larger it is, the greater the importance index of the target dimension is.

[0028] Any rheumatism principal component is used as the reference principal component. In the PCA algorithm, the reference principal component is obtained by combining rheumatism data of multiple dimensions in a certain specific way, and the proportion of the original rheumatism data of each dimension preserved in the reference principal component is called the factor loading. In reality, rheumatism data of different dimensions have a certain correlation. Therefore, in an embodiment of the present invention, the overall correlation between the target dimension and each other preset dimension is obtained according to the difference in rheumatism data between the target dimension and each other preset dimension in the reference principal component, as well as the correlation between the target dimension and each other preset dimension, and the correlation index of the reference principal component is obtained in combination with the difference in factor loading.

[0029] Preferably, in one embodiment of the present invention, the method for obtaining the overall correlation degree includes: obtaining the overall correlation degree according to an overall correlation degree calculation formula, and the overall correlation degree calculation formula is as follows: In the formula, Indicates the ordinal number of the target dimension in the reference principal component; Indicates the target dimension and The overall correlation between the other pre-set dimensions; Indicates the target dimension and The degree of correlation between other pre-set dimensions; Indicates the number of extreme points of rheumatism data within the target dimension; Indicates The number of extreme value points of rheumatism data in other preset dimensions; Indicates the target dimension and The number of extreme points of the preset dimension with fewer extreme points of rheumatism data among other preset dimensions; Indicates the target dimension and of the other preset dimensions The distance between the extreme points of rheumatism data.

[0030] In the overall correlation calculation formula, the target dimension is matched one-to-one with the extreme points of each other preset dimension in the Cartesian coordinate system, and the mean distance between the corresponding extreme points is calculated. , the smaller the distance mean is, and the smaller the difference in the number of extreme points between the target dimension and each other preset dimension is, the smaller the difference is, indicating that the curve changes of the two dimensions are similar, and the overall correlation between the two dimensions is higher; the target dimension is The higher the Pearson correlation coefficient between the other preset dimensions, the higher the correlation between the target dimension and the The higher the overall correlation between the other preset dimensions.

[0031] Preferably, in one embodiment of the present invention, the method for obtaining the correlation index includes: obtaining the correlation index according to a correlation index calculation formula, and the correlation index calculation formula is as follows: In the formula, Indicates the serial number of the reference principal component; represents the correlation index of the reference principal component; Indicates the preset number of dimensions of the reference principal component; Indicates the target dimension and The overall correlation between the other pre-set dimensions; represents the factor loading of the target dimension of the reference principal component; Indicates The factor loadings of other preset dimensions.

[0032] In the correlation index calculation formula, in the reference principal component, the target dimension is The factor loading differences of other pre-set dimensions The smaller the overall correlation The larger the value, the stronger the correlation between the two dimensions. If the factor loading of the target dimension is larger, it means that the The stronger the consistency of the performance of other preset dimensions, the more correlation between each preset dimension and other preset dimensions. Find the average. The larger the value, the greater the correlation index of the reference principal component.

[0033] Step S3: According to the importance index of each preset dimension in the reference principal component and the factor loading, the correlation index of the reference principal component is weighted to obtain the comprehensive contribution factor of the reference principal component; all final rheumatic disease principal components are obtained according to the comprehensive contribution factor; and daily diet recommendations are made for TCM rheumatic disease patients based on the final rheumatic disease principal components.

[0034] The importance index of each preset dimension in the reference principal component can characterize the reference value of rheumatism data of each preset dimension of TCM rheumatism patients in dietary recommendations, and the correlation index can characterize the effectiveness and interpretability of the reference principal component in obtaining dietary plans. Therefore, the embodiment of the present invention weights the correlation index of the reference principal component according to the importance index of each preset dimension in the reference principal component and the factor loading amount to obtain the comprehensive contribution factor of the reference principal component.

[0035] Preferably, in one embodiment of the present invention, the method for obtaining the comprehensive contribution factor includes: calculating the average value of the product between the importance index of each preset dimension in the reference principal component and the factor loading as the correlation weight of the reference principal component; and taking the product between the correlation weight of the reference principal component and the correlation index as the comprehensive contribution factor of the reference principal component. In one embodiment of the present invention, the calculation formula of the comprehensive contribution factor is as follows: In the formula, represents the comprehensive contribution factor of the reference principal component; represents the correlation index of the reference principal component; Indicates the preset number of dimensions of the reference principal component; Represents the importance index of the target dimension of the reference principal component; Represents the factor loading of the target dimension of the reference principal component.

[0036] In the calculation formula of the comprehensive contribution factor, the larger the importance index and factor loading of each preset dimension in the reference principal component, the more valuable the rheumatism data of the reference principal component for dietary recommendations; the larger the correlation index of the reference principal component, the stronger the correlation between all dimensions in the reference principal component, the more effective the rheumatism data of each preset dimension in the reference principal component, and the stronger the interpretability of the rheumatism data of each preset dimension in the reference principal component.

[0037] All final rheumatic disease principal components are obtained using the comprehensive contribution factor of each rheumatic disease principal component. Preferably, in one embodiment of the present invention, the method for obtaining the final rheumatic disease principal component includes: obtaining the principal component contribution rate of all principal components according to the dimensionality reduction algorithm, wherein this operation is a technical means well known to those skilled in the art and will not be described in detail here. The product between the principal component contribution rate of each principal component and the comprehensive contribution factor is added and summed as the principal component cumulative contribution rate; when the principal component cumulative contribution rate is not less than the preset first threshold, each corresponding principal component is used as the final rheumatic disease principal component.

[0038] In one embodiment of the present invention, the preset first threshold is set to 0.8. It should be noted that the preset first threshold can be set voluntarily and is not limited here.

[0039] The selected final rheumatism principal components are combined into a new data set, and a collaborative filtering algorithm is applied to the new data set to obtain dietary recommendations for different patients. It should be noted that the collaborative filtering algorithm is a technical means well known to those skilled in the art and will not be described in detail here.

[0040] This completes the daily dietary recommendations for patients with rheumatism in Traditional Chinese Medicine.

[0041] In summary, the rheumatism data of all preset dimensions of each TCM rheumatism patient are obtained; data dimensionality reduction is performed on all rheumatism data to obtain all rheumatism principal components and all preset dimensions in all rheumatism principal components; one rheumatism principal component is selected as the reference principal component, and one preset dimension in the reference principal component is selected as the target dimension; the importance index of the target dimension is obtained according to the change characteristics of the rheumatism data of the target dimension of each TCM rheumatism patient, and the corresponding dietary plan data change characteristics of the rheumatism data of each target dimension; the overall correlation between the target dimension and each other preset dimension is obtained according to the difference in rheumatism data between the target dimension and each other preset dimension in the reference principal component, and the correlation between the target dimension and each other preset dimension; the correlation index of the reference principal component is obtained according to the difference in factor loading and the overall correlation between any two preset dimensions in the reference principal component; the correlation index of the reference principal component is weighted according to the importance index and factor loading of each preset dimension in the reference principal component to obtain the comprehensive contribution factor of the reference principal component; all final rheumatism principal components are obtained according to the comprehensive contribution factor; daily diet recommendations are made for TCM rheumatism patients according to the final rheumatism principal components.

[0042] The second purpose of an embodiment of the present invention is to provide a daily diet recommendation system for patients with rheumatism in traditional Chinese medicine, the system comprising a memory, a processor and a computer program, wherein the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, it can implement the method described in steps S1-S3.

[0043] The third objective of an embodiment of the present invention is to provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the method described in steps S1-S3 when executing the computer program.

[0044] A fourth objective of an embodiment of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in steps S1-S3 can be implemented.

[0045] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0046] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for recommending daily diet for patients with rheumatism in traditional Chinese medicine, characterized in that: The method includes: obtaining rheumatism data of all preset dimensions for each TCM rheumatism patient; performing data dimensionality reduction on all rheumatism data to obtain all rheumatism principal components and all preset dimensions in all rheumatism principal components; selecting any rheumatism principal component as a reference principal component, and selecting any preset dimension in the reference principal component as a target dimension; obtaining an importance index of the target dimension based on the change characteristics of the rheumatism data of the target dimension for each TCM rheumatism patient, and the change characteristics of the diet plan data corresponding to the rheumatism data of each target dimension; obtaining the overall correlation degree between the target dimension and each other preset dimension based on the difference in rheumatism data between the target dimension and each other preset dimension in the reference principal component, and the correlation degree between the target dimension and each other preset dimension. degree; according to the difference in factor loadings between any two preset dimensions in the reference principal component and the overall correlation degree, obtain the correlation index of the reference principal component; according to the importance index and factor loading of each preset dimension in the reference principal component, weight the correlation index of the reference principal component to obtain the comprehensive contribution factor of the reference principal component; according to the comprehensive contribution factor, obtain all final rheumatic disease principal components; according to the final rheumatic disease principal components, make daily diet recommendations for TCM rheumatic disease patients; the method for obtaining the importance index of the target dimension includes: taking all rheumatic disease data in the target dimension as the horizontal coordinate and the corresponding dietary recommendation plan data as the vertical coordinate to construct a Cartesian coordinate system; obtaining the importance index according to the importance index calculation formula, and the importance index calculation formula is as follows: In the formula, An indicator of the importance of the target dimension; Represents the maximum value of rheumatology data in the target dimension; Represents the first-order difference between each two adjacent dietary recommendation data; represents the number of extreme points of the rheumatology data in the target dimension; represents the first-order difference between each two adjacent extreme value points of rheumatism data; the method for obtaining the overall correlation degree includes: obtaining the overall correlation degree according to the overall correlation degree calculation formula, and the overall correlation degree calculation formula is as follows: In the formula, Indicates the ordinal number of the target dimension in the reference principal component; Indicates the target dimension and The overall correlation between the other pre-set dimensions; Indicates the target dimension and The degree of correlation between other pre-set dimensions; Indicates the number of extreme points of rheumatism data within the target dimension; Indicates The number of extreme value points of rheumatism data in other preset dimensions; Indicates the target dimension and The number of extreme points of the preset dimension with fewer extreme points of rheumatism data among other preset dimensions; Indicates the target dimension and of the other preset dimensions The distance between the extreme value points of rheumatism data; the method for obtaining the correlation index includes: obtaining the correlation index according to the correlation index calculation formula, and the correlation index calculation formula is as follows: In the formula, Indicates the serial number of the reference principal component; represents the correlation index of the reference principal component; Indicates the preset number of dimensions of the reference principal component; Indicates the target dimension and The overall correlation between the other pre-set dimensions; represents the factor loading of the target dimension of the reference principal component; Indicates The factor loadings of other preset dimensions.

2. A method for recommending a daily diet for patients with rheumatism according to claim 1, characterized in that: The method for obtaining the comprehensive contribution factor includes: calculating the average value of the product between the importance index of each preset dimension in the reference principal component and the factor loading as the correlation weight of the reference principal component; and taking the product between the correlation weight of the reference principal component and the correlation index as the comprehensive contribution factor of the reference principal component.

3. A method for recommending a daily diet for patients with rheumatism according to claim 1, characterized in that: The method for obtaining the final rheumatic disease principal component includes: obtaining the principal component contribution rates of all principal components according to a dimensionality reduction algorithm, and summing up the products of the principal component contribution rate of each principal component and the comprehensive contribution factor as the principal component cumulative contribution rate; when the principal component cumulative contribution rate is not less than a preset first threshold, taking each corresponding principal component as the final rheumatic disease principal component.

4. A method for recommending a daily diet for patients with rheumatism according to claim 1, characterized in that: Combine the target dimension with the The Pearson correlation coefficient between the target dimension and the other preset dimensions is used as the The correlation between the other preset dimensions.

5. A daily diet recommendation system for patients with rheumatism in traditional Chinese medicine, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a method for recommending a daily diet for patients with rheumatism in Traditional Chinese Medicine as described in any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a method for recommending a daily diet for patients with rheumatism according to any one of claims 1 to 4 are implemented.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for recommending a daily diet for patients with rheumatism in Traditional Chinese Medicine as described in any one of claims 1 to 4 are implemented.

Images