Traditional Chinese medicine physique intelligent typing method and system for sleep disorder

Abstract

The invention discloses a traditional Chinese medicine physique intelligent typing method and system for sleep disorder, and the method comprises the steps: obtaining the own attribute and symptom data of sleep disorder patients and people with different traditional Chinese medicine physiques, obtaining the attribute feature data corresponding to a sample, and constructing a sample data set; constructing a sleep disorder knowledge base based on the sample data set, wherein the knowledge base comprises different types of sleep disorders and corresponding traditional Chinese medicine constitution attribute data; based on the knowledge base and the sample data set, constructing a decision tree model of the sleep disorder attribute data and the corresponding traditional Chinese medicine constitution category; and inputting sleep disorder data of the detected person into the decision tree model to obtain a traditional Chinese medicine physique intelligent typing and cognition result. Through a sample data set, construction of a knowledge base, construction of a decision tree model and input of data typing, the problems of missed judgment and wrong judgment of manual judgment can be solved, the typing objectivity and accuracy are improved, efficient and intelligent typing is achieved, and a health management scheme is generated to assist diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of TCM constitution identification, and in particular to a TCM constitution intelligent typing method and system for sleep disorders. Background Art

[0002] Sleep disorders are a common health problem, including insomnia, sleep breathing disorders, sleep limb movement disorders, etc., and their clinical manifestations are diverse, such as difficulty falling asleep, night terrors, excessive sleep, sleep apnea, etc. Traditional Chinese medicine classifies sleep disorders into the categories of "insomnia" and "excessive sleep", and believes that they are closely related to factors such as emotional imbalance, improper work and rest, and irregular diet. In addition, different traditional Chinese medicine constitutions (such as the nine constitutions of peaceful constitution, qi deficiency constitution, yang deficiency constitution, etc.) have significant differences in the impact on sleep conditions. For example, phlegm-damp constitution is often associated with snoring and sleep apnea, yin deficiency constitution is prone to insomnia due to internal disturbance of deficiency heat, and blood stasis constitution is often accompanied by symptoms such as dreaming and unresolved sleep.

[0003] In the existing technology, the TCM constitution classification based on sleep disorders mainly relies on manual judgment based on expert experience. However, this method has significant limitations: on the one hand, manual judgment is constrained by individual experience, and when faced with multi-dimensional and complex information such as age, gender, and symptom data, it is easy to miss information or have subjective bias, resulting in missed or wrong judgments; on the other hand, manual analysis is inefficient and difficult to cope with large-scale data processing needs, and cannot meet the actual needs of clinical rapid and accurate classification. In addition, the existing methods lack systematic intelligent modeling means and fail to fully utilize data association features, resulting in the cognition of the correlation between TCM constitution and sleep disorders remaining at the experience level, making it difficult to achieve standardized and intelligent auxiliary diagnosis. Therefore, how to break through the limitations of manual judgment and construct a data-driven intelligent classification method to achieve accurate and efficient TCM constitution classification of patients with sleep disorders has become a technical problem that needs to be solved urgently in the current field of medical auxiliary diagnosis. Summary of the Invention

[0004] In view of this, the present invention proposes a method and system for intelligent TCM constitution classification of sleep disorders, which can effectively solve the inefficiency and subjectivity of manual judgment in the existing technology, and provide an objective and efficient technical solution for the correlation analysis between TCM constitution and sleep disorders. The present invention provides the following technical solutions: A method for intelligent TCM constitution classification of sleep disorders, comprising: Obtain the attribute and symptom data of patients with sleep disorders and people with different TCM constitutions, obtain the attribute feature data corresponding to the samples, and construct a sample data set; Constructing a sleep disorder knowledge base based on the sample data set, wherein the knowledge base includes different categories of sleep disorders and corresponding TCM constitution attribute data; Based on the knowledge base and sample data set, a decision tree model of sleep disorder attribute data and corresponding TCM constitution categories is constructed; the sleep disorder data of the examinee is input into the decision tree model to obtain the results of TCM constitution intelligent classification and cognition.

[0005] Optionally, the self-attribute and symptom data include age, gender, education level, marital status, weight, sleep quality, sleep onset time, sleep time, sleep efficiency and symptom data; The construction of the sample data set includes: dividing the attribute characteristic data by gender and age, and incorporating information on nine major constitution categories in traditional Chinese medicine, namely, balanced 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.

[0006] Optionally, the constructing a sleep disorder knowledge base based on the sample dataset includes: The descriptive texts of the nine constitutions in traditional Chinese medicine in the sample data set are used as training corpus and divided into feature information segmentations; the feature information segmentations are normalized to obtain normalized samples and segmentation sets; The knowledge base stores different TCM constitution categories and corresponding sleep disorder attribute data, including sleep quality, sleep onset time, sleep time, sleep efficiency and symptom characteristics corresponding to different constitutions.

[0007] Optionally, constructing a decision tree model of sleep disorder attribute data and corresponding TCM constitution categories based on the knowledge base and sample data set includes: The information entropy of the sample data set is calculated using the formula: Among them, D is the sample data set, c is the total number of TCM constitution categories, p i is the proportion of samples belonging to constitution category i; When the attribute feature A is selected as the decision tree judgment node for the corresponding sample data set D, the information entropy after the attribute feature is applied is Info A (D), calculated as: Among them, k means that the sample data set D is divided into k parts; Calculate the information gain value Gain(A), the formula is: Gain(A)=Info(D)-Info A (D); The attribute feature with the largest information gain value Gain(A) is used as the root node, and the root node is split into child nodes. The information gain is further calculated and the one with the largest information gain is used as the child node to build a decision tree until all attribute feature values ​​are less than the preset threshold or no attribute feature is selected; The decision tree model is verified using a test set, and the model is optimized based on at least one evaluation metric among classification accuracy, recall rate, false alarm rate, and precision.

[0008] Optionally, the sleep disorder data of the subject includes age, gender, sleep quality, sleep onset time, sleep time, sleep efficiency and symptom data.

[0009] Optionally, the results of obtaining TCM constitution intelligent classification and cognition include: Output the examinee's corresponding TCM constitution type and potential health problems; A personalized health management plan is generated by combining the TCM constitution classification results, the basic information of the examinee and the clinical characteristic information.

[0010] The present invention further discloses a TCM intelligent classification system for sleep disorders, comprising: The data processing module is used to obtain the attribute and symptom data of patients with sleep disorders and people with different TCM constitutions, obtain the attribute feature data corresponding to the samples, and construct a sample data set; A knowledge base construction module, configured to construct a sleep disorder knowledge base based on the sample data set, wherein the knowledge base includes different categories of sleep disorders and corresponding TCM constitution attribute data; A model building module, for building a decision tree model of sleep disorder attribute data and corresponding TCM constitution categories based on the knowledge base and sample data set; The result output module is used to input the sleep disorder data of the subject into the decision tree model to obtain the results of TCM constitution intelligent classification and cognition.

[0011] The present invention further discloses a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0012] The present invention further discloses an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the program.

[0013] The present invention further discloses a computer program product, comprising a computer program, which implements the above method when executed by a processor.

[0014] According to the technical solution of the present invention, by obtaining multi-dimensional self-attribute and symptom data of patients with sleep disorders and people with different TCM constitutions, the nine constitution category information is divided and incorporated into a sample data set, the nine constitution-related description texts in the sample data are divided into feature information segmentation and normalized, and a sleep disorder knowledge base containing symptom characteristics corresponding to different constitutions is constructed. Based on the knowledge base and the sample data set, the information gain algorithm is used to calculate the information entropy of the sample data set, the information entropy after attribute division, and the information gain value. The attribute feature with the maximum gain is used as the root node to recursively split the child nodes to construct a decision tree model, and the model is optimized by combining the test set with indicators such as classification accuracy. Finally, the data of the examinee including age, gender, sleep efficiency, etc. are input into the model, and the corresponding TCM constitution type and potential health problem prompts are output to generate a personalized health management plan. This solution avoids omissions of manual information through standardized collection of multi-dimensional data, breaks through the limitations of traditional empirical judgment through digital storage of knowledge bases, uses decision tree models to automatically learn data association features and optimize and improve classification accuracy, and achieves rapid classification in seconds with the help of model automated calculations, capturing the association between constitution and sleep disorders that are difficult to detect manually. It promotes the standardization of TCM constitution classification with structured results, and supports the expansion of the knowledge base through updating data sets to adapt to dynamic changes in medical data, thereby efficiently and accurately solving the inefficiency and subjectivity of manual classification in existing technologies, reducing missed and wrong judgments, alleviating the shortage of medical resources, and improving clinical diagnosis and treatment efficiency and screening levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] For purposes of illustration and not limitation, the present invention will now be described with reference to embodiments thereof and the accompanying drawings, in which: Figure 1 1 is a flow chart of a method for intelligent TCM constitution classification of sleep disorders according to an embodiment of the present invention; Figure 2 2 is a schematic diagram of the structure of the TCM intelligent constitution classification system for sleep disorders in an embodiment of the present invention; Figure 3 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of this application.

[0017] It should be noted that, in the absence of conflict, the embodiments of the present application and the features thereof can be combined with each other. The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0018] refer to Figure 1 This embodiment discloses a method for intelligent TCM constitution classification of sleep disorders, which includes the following steps: S100: Obtain the attribute and symptom data of patients with sleep disorders and people with different TCM constitutions, obtain the attribute feature data corresponding to the samples, and construct a sample data set.

[0019] First, through clinical investigations and questionnaires, we collected multi-dimensional data covering age, gender, education level, marital status, weight, and other personal attributes, as well as sleep quality, sleep onset time, sleep duration, sleep efficiency, and other sleep status indicators. At the same time, we recorded specific symptom data such as insomnia, snoring, night terrors, and dreaminess. For example, for people with phlegm-dampness constitution, we focused on collecting the presence of snoring, sleep apnea and other symptoms. For people with yin deficiency constitution, we focused on insomnia caused by internal disturbance of deficiency heat and frequent urination at night. For people with blood stasis constitution, we recorded symptoms such as dreaminess, unrefreshing sleep, insomnia, or sleep rhythm disorders.

[0020] After the collection is completed, the original data is cleaned and features are extracted to form structured attribute feature data, where the attribute features include both directly quantifiable numerical data, such as age, weight, and sleep time, as well as categorical data, such as gender, education level, marital status, and TCM constitution categories. Subsequently, the attribute feature data are stratified and divided according to gender (male / female) and age (such as divided into children, youth, middle-aged, and elderly intervals) to ensure a balanced distribution of samples in different genders and age groups. On this basis, the nine major TCM constitution categories, such as 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, are used as labels and associated with the attribute feature data of the corresponding samples, ultimately forming a sample data set containing multidimensional features and constitution labels, providing a standardized data foundation for subsequent knowledge base construction and model training.

[0021] S200: Constructing a sleep disorder knowledge base based on the sample data set, wherein the knowledge base includes different types of sleep disorders and corresponding TCM constitution attribute data.

[0022] When constructing a sleep disorder knowledge base based on the sample data set, first extract the descriptive texts related to the nine traditional Chinese medicine constitutions in the sample data set, such as the sleep quality assessment corresponding to each constitution, the characteristics of sleep onset time, the distribution of sleep time, the sleep efficiency index, and the data of typical symptoms (such as snoring and sleep apnea syndrome descriptions for phlegm-dampness constitution, descriptions of insomnia with internal disturbance of deficiency heat and frequent urination at night for yin deficiency constitution, records of frequent dreams, restless sleep, insomnia or sleep rhythm disorders for blood stasis constitution, etc.), and use them as training corpus.

[0023] ​​​​​​​​​​​​​​​​​Where k represents the sample data set D is divided into k parts; the information gain value Gain(A) is calculated as follows: Gain(A)=Info(D)-Info A (D); The attribute feature with the largest information gain value Gain(A) is used as the root node, and the root node is split into child nodes. The information gain is further calculated and the one with the largest information gain is used as the child node to build a decision tree until all attribute feature values ​​are less than the preset threshold or no attribute feature is selected; The decision tree model is verified through the test set, and the model is optimized based on at least one evaluation indicator among classification accuracy, recall rate, false alarm rate and precision. Specifically, the constructed decision tree model is verified through an independent test set. The test set contains sample data that did not participate in the training, and the training set and test set are divided into 7:3 ratios. The performance of the model is evaluated by using indicators such as classification accuracy, that is, the number of correctly predicted samples / total number of samples, recall rate, that is, the number of correctly predicted samples of a certain category / the actual number of samples of that category, false alarm rate, that is, the number of incorrectly predicted samples of a certain category / the actual number of samples not of that category, and precision, that is, the number of correctly predicted samples of a certain category / the number of samples predicted to be of that category. If the indicators do not meet expectations, the model is optimized by adjusting the preset threshold, pruning or supplementing sample data until the accuracy requirements of clinical auxiliary diagnosis are met.

[0027] Through the above process, the decision tree model can automatically learn the nonlinear association between sleep disorder attribute data and TCM constitution categories. For example, it can capture the strong directionality of the combined features of "body mass index > 28 + snoring + age > 50 years old" for phlegm-damp constitution, or the predictive weight of "difficulty falling asleep + night sweats + age < 40 years old" for yin deficiency constitution, thereby realizing intelligent mapping from multidimensional data to constitution types and providing reliable algorithm support for subsequent classification applications.

[0028] S400: Inputting the sleep disorder data of the subject into the decision tree model to obtain the results of TCM constitution intelligent classification and cognition.

[0029] When the sleep disorder data of the subject is input into the decision tree model to obtain the TCM constitution intelligent classification and cognitive results, the sleep disorder data of the subject is first obtained, specifically including structured information such as age, gender, sleep quality, time to fall asleep, sleep time, sleep efficiency and symptom data, and the data is normalized and preprocessed.

[0030] The preprocessed feature vector is fed into a trained decision tree model, which traverses the tree layer by layer, starting from the root node. For example, if the root node is "Does the subject have snoring symptoms?" and the subject's data is labeled "yes," the tree branches to the next node; if the subject's data is labeled "no," the tree branches to the next node. By recursively determining the values ​​of each attribute feature, the tree eventually reaches a leaf node and outputs the corresponding TCM constitution category and the probability confidence level for that constitution.

[0031] Based on the output constitution category, the typical sleep disorder characteristics and health problems corresponding to the constitution in the knowledge base are matched to generate a structured report: for example, if the output is "phlegm-damp constitution", it will simultaneously prompt "Potential health problems: higher risk of sleep apnea syndrome", and combined with the basic information such as age and gender of the subject, the preset plan is retrieved from the health management unit to generate personalized suggestions.

[0032] In summary, this embodiment obtains multi-dimensional self-attribute and symptom data such as age, gender, sleep quality, symptoms, etc. of patients with sleep disorders and people with different TCM constitutions, and divides them into the nine TCM constitution categories according to gender and age to construct a sample data set. The descriptive texts related to the nine constitutions in the sample data are divided into feature information segmentation and normalized to construct a structured sleep disorder knowledge base containing symptom characteristics such as sleep quality, sleep time, snoring due to phlegm-dampness constitution, and insomnia due to deficiency of yin constitution and heat, etc. corresponding to different constitutions. Based on the knowledge base and the sample data set, the information gain algorithm is used to calculate the information entropy and information gain value. The attribute feature with the maximum gain is used as the root node to recursively split the child nodes to construct a decision tree model, and the model is optimized by combining the test set with indicators such as classification accuracy. Finally, the data of the examinee including age, gender, sleep efficiency, etc. are input into the model to output the corresponding TCM constitution type, potential health problem prompts, and generate a personalized health management plan. This solution avoids omissions of manual information through standardized multi-dimensional data collection, breaks through the limitations of traditional empirical judgment through digital storage of knowledge bases, uses decision tree models to automatically learn data association features and optimize and improve classification accuracy, and achieves rapid classification in seconds with the help of model automated calculations. It captures the association between constitution and sleep disorders that is difficult to detect manually and promotes the standardization of TCM constitution classification with structured results. It supports expanding the knowledge base through updating data sets to adapt to dynamic changes in medical data, and implements the TCM concept of preventing illness by combining clinical characteristics, thereby efficiently and accurately solving the inefficiency and subjectivity of manual classification in existing technologies, reducing missed and wrong judgments, alleviating the shortage of medical resources, improving clinical diagnosis and treatment efficiency, screening level and auxiliary diagnosis objectivity, and providing a standardized intelligent modeling solution for the analysis of the correlation between TCM constitution and sleep disorders.

[0033] refer to Figure 2This embodiment further discloses a TCM constitution intelligent classification system for sleep disorders, including: a data processing module 21, used to obtain the self-attribute and symptom data of patients with sleep disorders and people with different TCM constitutions, obtain attribute characteristic data corresponding to the samples, and construct a sample data set, including: dividing the attribute characteristic data according to gender and age, and incorporating information on the nine major TCM constitution categories of balanced 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.

[0034] The knowledge base construction module 22 is used to construct a sleep disorder knowledge base based on the sample data set, wherein the knowledge base includes different categories of sleep disorders and corresponding TCM constitution attribute data; the construction of the sleep disorder knowledge base based on the sample data set includes: using the relevant descriptive text of the nine major TCM constitutions in the sample data set as training corpus, dividing it into feature information segmentation; normalizing the feature information segmentation to obtain normalized samples and segmentation sets; the knowledge base stores different TCM constitution categories and corresponding sleep disorder attribute data, including sleep quality, sleep onset time, sleep time, sleep efficiency and symptom characteristics corresponding to different constitutions.

[0035] The model building module 23 is used to build a decision tree model of sleep disorder attribute data and corresponding TCM constitution categories based on the knowledge base and sample data set; including: calculating the information entropy of the sample data set, the formula is: Among them, D is the sample data set, c is the total number of TCM constitution categories, p i is the proportion of samples belonging to physical category i; when the corresponding sample data set D selects attribute feature A as the decision tree judgment node, the information entropy after the attribute feature acts is Info A (D), calculated as: Where k represents the sample data set D is divided into k parts; the information gain value Gain(A) is calculated as follows: Gain(A)=Info(D)-Info A (D); take the attribute feature with the largest information gain value Gain(A) as the root node, split the child node from the root node, further calculate the information gain and take the one with the largest information gain as the child node, and build a decision tree until all attribute feature values ​​are less than the preset threshold or no attribute feature is selected; verify the decision tree model through the test set, and optimize the model based on at least one evaluation indicator among classification accuracy, recall rate, false alarm rate and precision.

[0036] The result output module 24 is used to input the sleep disorder data of the subject into the decision tree model to obtain the results of the TCM constitution intelligent classification and cognition, including: outputting the TCM constitution type corresponding to the subject and potential health problem prompts; combining the TCM constitution classification results, the subject's basic information and clinical characteristic information to generate a personalized health management plan.

[0037] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 3 As shown, the electronic device 50 includes: a processor 501 (processor), a memory 502 (memory) and a bus 503; The processor 501 and the memory 502 communicate with each other via the bus 503 ; the processor 501 is used to call program instructions in the memory 502 to execute the methods provided by the above-mentioned method implementation methods.

[0038] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above-mentioned method embodiments.

[0039] Those skilled in the art will understand that all or part of the steps for implementing the above-mentioned method implementation method can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method implementation method; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc. Various storage media that can store program codes.

[0040] The device embodiments described above are merely illustrative. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of these modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0041] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or certain parts of the embodiment.

[0042] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A TCM intelligent classification method for sleep disorders, characterized by: The method comprises: Obtain attribute and symptom data samples of patients with sleep disorders and people with different TCM constitutions, and obtain the attribute feature data corresponding to the samples to construct a sample data set; Constructing a sleep disorder knowledge base based on the sample data set, wherein the knowledge base includes different categories of sleep disorders and corresponding TCM constitution attribute data; Based on the knowledge base and sample data set, a decision tree model of sleep disorder attribute data and corresponding TCM constitution categories is constructed; the sleep disorder data of the examinee is input into the decision tree model to obtain the results of TCM constitution intelligent classification and cognition.

2. The TCM intelligent classification method for sleep disorders according to claim 1, characterized in that: The personal attributes and symptom data include age, gender, education level, marital status, weight, sleep quality, time to sleep, sleep time, sleep efficiency and symptom data; The construction of the sample data set includes: dividing the attribute characteristic data by gender and age, and incorporating information on nine major constitution categories in traditional Chinese medicine, namely, balanced 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.

3. The TCM intelligent classification method for sleep disorders according to claim 2, characterized in that: The constructing of a sleep disorder knowledge base based on the sample data set includes: The descriptive texts of the nine constitutions in traditional Chinese medicine in the sample data set are used as training corpus and divided into feature information segmentations; the feature information segmentations are normalized to obtain normalized samples and segmentation sets; The knowledge base stores different TCM constitution categories and corresponding sleep disorder attribute data, including sleep quality, sleep onset time, sleep time, sleep efficiency and symptom characteristics corresponding to different constitutions.

4. The TCM intelligent classification method for sleep disorders according to claim 1, characterized in that: The step of constructing a decision tree model based on the knowledge base and the sample data set and the sleep disorder attribute data and the corresponding TCM constitution categories includes: The information entropy of the sample data set is calculated using the formula: Where D is the sample data set, c is the total number of TCM constitution categories, and pi is the proportion of samples belonging to constitution category i; When the attribute feature A is selected as the decision node of the decision tree for the corresponding sample data set D, the information entropy after the attribute feature is applied is InfoA(D), and the calculation formula is: Among them, k means that the sample data set D is divided into k parts; Calculate the information gain value Gain(A), the formula is: Gain(A)=Info(D)-Info A (D); The attribute feature with the largest information gain value Gain(A) is used as the root node, and the root node is split into child nodes. The information gain is further calculated and the one with the largest information gain is used as the child node to build a decision tree until all attribute feature values ​​are less than the preset threshold or no attribute feature is selected; The decision tree model is verified using a test set, and the model is optimized based on at least one evaluation metric among classification accuracy, recall rate, false alarm rate, and precision.

5. The TCM intelligent classification method for sleep disorders according to claim 1, characterized in that: The sleep disorder data of the subject include age, gender, sleep quality, sleep onset time, sleep time, sleep efficiency and symptom data.

6. The TCM intelligent classification method for sleep disorders according to claim 1, characterized in that: The results of TCM constitution intelligent classification and cognition include: Output the examinee's corresponding TCM constitution type and potential health problems; A personalized health management plan is generated by combining the TCM constitution classification results, the basic information of the examinee and the clinical characteristic information.

7. A TCM intelligent classification system for sleep disorders, characterized by: include: The data processing module is used to obtain the attribute and symptom data of patients with sleep disorders and people with different TCM constitutions, obtain the attribute feature data corresponding to the samples, and construct a sample data set; A knowledge base construction module, configured to construct a sleep disorder knowledge base based on the sample data set, wherein the knowledge base includes different categories of sleep disorders and corresponding TCM constitution attribute data; A model building module, for building a decision tree model of sleep disorder attribute data and corresponding TCM constitution categories based on the knowledge base and sample data set; The result output module is used to input the sleep disorder data of the subject into the decision tree model to obtain the results of TCM constitution intelligent classification and cognition.

8. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device 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 according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images