Traditional Chinese medicine acupuncture point curative effect database construction method

Abstract

The invention relates to the technical field of medical data processing, in particular to a traditional Chinese medicine acupuncture point curative effect database construction method. The method comprises the following steps: determining a comprehensive correlation coefficient based on correlation strength and acupoint information similarity between occurrence conditions of two acupoints in an acupuncture diagnosis and treatment record of disease types; determining the compatibility behavior disorder degree based on the disorder degree of the comprehensive correlation coefficient of each acupuncture point and other acupuncture points under the continuous disease types in the disease evolution sequence; on the basis of a curative effect evaluation index containing the acupuncture diagnosis and treatment record of each acupuncture point, the compatibility behavior disorder degree and the comprehensive correlation coefficient of each acupuncture point and other acupuncture points under the disease type, determining the functional concentration degree of the acupuncture points; and determining the function label value of the acupoint based on the function concentration degree, and optimizing the traditional Chinese medicine acupuncture curative effect database. According to the method, the complex incidence relation is converted into the compatibility behavior disorder degree, the function label value is determined from the collaboration capability, compatibility behavior and curative effect dimensions, and the database query efficiency is improved.

Description

A Method for Constructing a Database of Therapeutic Effects of Acupuncture Points in Traditional Chinese Medicine Technical Field

[0001] This invention relates to the field of medical data processing technology, specifically to a method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine. Background Technology

[0002] Currently, traditional Chinese medicine acupuncture has established a unique diagnostic and treatment system centered on acupoints and using meridians as the transmission pathway. It is an important means of treating pain, functional disorders, chronic diseases, and some intractable diseases. However, in the process of modernization, the "fragmentation" and "non-standardization" of clinical evidence on the efficacy of acupuncture are becoming increasingly prominent, urgently requiring systematic integration through database technology.

[0003] Currently, mainstream TCM acupuncture databases employ a structured relational model-based construction approach. This model decomposes and stores acupuncture prescriptions, acupoints, and therapeutic information through predefined data table structures and field relationships. However, acupuncture treatment plans often involve complex and highly coupled semantic relationships such as multiple acupoint combinations and syndrome differentiation. When processing this highly correlated data, the model requires performing numerous deep multi-table join queries, leading to performance bottlenecks in reconstructing the complete acupuncture diagnosis and treatment knowledge context, thus limiting the system's query efficiency in supporting clinical decision-making. Summary of the Invention

[0004] To address the technical problem of low database query efficiency caused by the highly correlated and complex semantic data resulting from the combination of multiple acupoints and syndrome differentiation in acupuncture treatment plans, this invention aims to provide a method for constructing a database of therapeutic effects of acupuncture points in Traditional Chinese Medicine (TCM). The specific technical solution adopted is as follows: One embodiment of this invention provides a method for constructing a database of therapeutic effects of acupuncture points in Traditional Chinese Medicine (TCM). This method includes: acquiring acupuncture treatment records for different disease types, wherein the acupuncture treatment records include acupoints and therapeutic effect evaluation indicators; constructing a complete acupoint set from the acupuncture treatment records for all disease types; and determining the occurrence of any two acupoints within the complete acupoint set in the acupuncture treatment records for each disease type. The correlation strength between two acupoints and the similarity of their acupoint characteristics are used to determine the comprehensive correlation coefficient of the two acupoints under each disease type. Based on the similarity of disease information in different disease types, the disease evolution sequence is determined. Based on the disorder of the comprehensive correlation coefficient between each acupoint and the other acupoints in the disease evolution sequence under consecutive disease types, the compatibility behavior disorder of each acupoint is determined. Based on the efficacy evaluation index of acupuncture treatment records containing each acupoint, the compatibility behavior disorder, and the comprehensive correlation coefficient between each acupoint and the other acupoints under all disease types, the functional label value of each acupoint is determined, and the TCM acupuncture efficacy database is optimized.

[0005] Further, determining the comprehensive correlation coefficient of two corresponding acupoints under each disease type includes: determining the acupoint synergy coefficient of two corresponding acupoints under each disease type based on the correlation strength between the occurrence of any two acupoints in the acupuncture treatment records of each disease type within the overall acupoint set; obtaining the acupoint characteristic information text of each acupoint, performing text vectorization on the acupoint characteristic information text to obtain the acupoint characteristic vector of each acupoint; obtaining the cosine similarity between the acupoint characteristic vectors of any two acupoints within the overall acupoint set, denoted as the pathological theoretical fit of the two corresponding acupoints; and obtaining the comprehensive correlation coefficient of any two acupoints under each disease type based on the acupoint synergy coefficient and the pathological theoretical fit.

[0006] Further, determining the acupoint synergy coefficient for each of the two corresponding acupoints under each disease type includes: taking the proportion of acupuncture treatment records for each disease type that include every acupoint in the overall acupoint set as the probability of occurrence of the corresponding acupoint under each disease type; taking the proportion of acupuncture treatment records for each disease type that simultaneously include any two acupoints in the overall acupoint set as the co-occurrence probability of the two corresponding acupoints under each disease type; randomly selecting a disease type as an example type, and using the co-occurrence probability of any two acupoints in the overall acupoint set under the example type as the numerator and the product of the occurrence probabilities of the two corresponding acupoints under the example type as the denominator to obtain the ratio as the acupoint synergy coefficient for the two corresponding acupoints under the example type.

[0007] Further, determining the disease evolution sequence includes: acquiring disease information text for each disease type; performing text vectorization on the disease information text to obtain disease vectors for each disease type; performing hierarchical clustering on all disease types based on the cosine similarity between the disease vectors of different disease types to obtain a disease tree diagram; the leaf nodes in the disease tree diagram represent disease types; performing an inorder traversal on the disease tree diagram, arranging all leaf nodes corresponding to disease types in traversal order to obtain the disease evolution sequence.

[0008] Further, determining the disorder of the compatibility behavior of each acupoint includes: averaging the comprehensive correlation coefficients between each acupoint in the overall acupoint set and the other acupoints under each disease type to obtain the compatibility state value of each acupoint under each disease type; arranging the compatibility state values ​​of each acupoint in the overall acupoint set under all disease types according to the order of disease types in the disease evolution sequence to obtain the compatibility sequence of the corresponding acupoint; traversing the compatibility sequence using a sliding window of a preset length, with each element in the sliding window after each slide forming an N-tuple, where N is the preset length; and obtaining the information entropy of the N-tuple corresponding to the compatibility sequence of each acupoint as the disorder of the compatibility behavior of the corresponding acupoint.

[0009] Further, determining the functional label value of each acupoint includes: selecting any acupoint as an example acupoint; taking the average of the efficacy evaluation indicators of acupuncture treatment records containing the example acupoint as the overall efficacy value of the example acupoint; taking the average of the compatibility status values ​​of the example acupoint under all disease types as the overall compatibility strength of the example acupoint; obtaining the functional focus of the example acupoint based on the overall compatibility strength, the disorder of the compatibility behavior, and the overall efficacy value; and determining the functional label value of each acupoint based on the functional focus.

[0010] Furthermore, the method for obtaining the functional label value includes: clustering all acupoints in the overall acupoint set based on the absolute value of the difference in functional focus of different acupoints to obtain several clusters; taking the mean of the functional focus of all acupoints in the same cluster as the overall focus of each cluster; the larger the overall focus, the smaller the functional label value of the acupoints in the cluster.

[0011] Furthermore, the overall compatibility strength and the overall therapeutic effect value are both positively correlated with the functional focus, while the degree of compatibility disorder is negatively correlated with the functional focus.

[0012] Furthermore, the method for hierarchical clustering of all disease types is the unweighted group average method.

[0013] Furthermore, N is 2.

[0014] This invention offers the following advantages: In its embodiments, the comprehensive correlation coefficient, combined with the close relationship between two acupoints in pathological theory and clinical practice, makes the association between the two acupoints in disease types more convincing and practical. The disease evolution sequence presents the evolutionary order of the disease from its initial state to its evolved state. The comprehensive correlation coefficient can represent the compatibility degree between each acupoint and commonly used acupoints in the disease type. Based on the degree of disorder of the comprehensive correlation coefficient between each acupoint and other acupoints in the disease evolution sequence under continuous disease types, the complexity of the combination behavior transfer model of each acupoint is analyzed, resulting in the disorder of the combination behavior. This solution transforms complex relationships into directly searchable data attributes, avoiding time-consuming multi-table join operations and solving the problem that traditional relational databases require a large number of deep multi-table join queries to obtain acupoint combination relationships. Then, from three dimensions—collaboration ability, combination behavior pattern, and final efficacy—the functional label values ​​of acupoints are determined, simplifying the data access path from complex network associations to linear attribute filtering, greatly reducing the complexity of data access and effectively improving the query efficiency of the TCM acupuncture efficacy database. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 is a flowchart of the steps of a method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to an embodiment of the present invention; Figure 2 is a flowchart of a method for obtaining comprehensive correlation coefficients according to an embodiment of the present invention; Figure 3 is a system structure diagram of a system for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to an embodiment of the present invention; Figure 4 is a schematic diagram of a computer device for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to an embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a method for constructing a database of therapeutic effects of acupuncture points according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, 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 pertains.

[0019] The following describes in detail, with reference to the accompanying drawings, a specific scheme for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine provided by the present invention.

[0020] Example 1: This invention proposes a method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine. Please refer to Figure 1, which shows a flowchart of the steps of a method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine provided in an embodiment of this invention. The method includes: Step S1: Obtaining acupuncture diagnosis and treatment records for different disease types. The acupuncture diagnosis and treatment records include acupuncture points and therapeutic effect evaluation indicators; the acupuncture points contained in the acupuncture diagnosis and treatment records for all disease types constitute a complete set of acupuncture points.

[0021] Structured acupuncture treatment records, including acupoint prescriptions and efficacy evaluation indicators, are retrieved from the electronic pathology system and clinical research database of collaborative medical institutions using standardized data interfaces. The acupoint prescriptions include acupoint combinations and the classification of primary and secondary acupoints. Each acupuncture treatment record corresponds to one acupoint prescription and efficacy evaluation indicator, and each record also has a specific disease type. Natural language processing technology is used to perform preliminary structure extraction on the retrieved structured acupuncture treatment records, automatically identifying core information such as acupoint names, disease descriptions, and efficacy conclusions in the record text, and incorporating this information into the text database to be processed.

[0022] The efficacy evaluation index is the result of judging the efficacy level after acupuncture treatment. In this embodiment of the invention, the visual analog scale for pain can be used to determine the efficacy evaluation index, or a clinically routine efficacy standard can be selected. Typically, the physician directly records the efficacy evaluation index based on professional judgment, and this is not limited here. It is important to ensure that the higher the treatment effect, the larger the efficacy evaluation index.

[0023] Common preprocessing techniques such as noise reduction, deduplication, and format standardization are applied to the collected text library. Semantic standardization is performed on entity keywords, specifically including: acupoint terminology: unifying alternative names to standardized names, for example, unifying "Hegu" to "Hegu" and "Taichong" to "Taichong"; disease terminology: unifying synonymous expressions to standardized classifications, such as unifying "liver qi stagnation syndrome" to "liver qi stagnation syndrome"; therapeutic efficacy terminology: unifying therapeutic efficacy descriptions to a three-level standardized expression of "cured = 2, significantly effective = 1, effective = 0", clarifying the judgment criteria corresponding to each level of expression, such as "significantly effective" corresponding to "symptoms significantly improved, signs basically recovered".

[0024] Using pre-trained TCM domain word vector models, such as the BERT model fine-tuned based on TCM diagnosis and treatment corpus, normalized entity keywords such as "acupoints," "symptoms," and "therapeutic effects" are mapped to corresponding vectors for data storage. The data is organized according to a preset "symptom-acupoint-therapeutic effect" data model to generate an intermediate data table containing key entities and their relationships. The intermediate data table that conforms to the preset data pattern is output as input for the next stage of knowledge fusion and database construction.

[0025] Step S2: Based on the correlation strength between the occurrence of any two acupoints in the acupuncture treatment records of each disease type within the overall acupoint set, and the similarity of the acupoint characteristics of the two acupoints, determine the comprehensive correlation coefficient of the two acupoints under each disease type.

[0026] The similarity of the acupoint properties of two acupoints reflects the similarity of their pathological theories. However, it cannot guarantee whether doctors will use both acupoints together when treating a specific pathological condition. The correlation strength between the occurrence of two acupoints in the acupuncture treatment records for each disease type is based on the experience doctors have gained in practice as presented in the acupuncture treatment records. Combining both can help analyze the closeness of the relationship between the theory and clinical practice of two acupoints, making the comprehensive correlation coefficient more convincing and practical.

[0027] Step S3: Determine the disease evolution sequence based on the similarity of disease information for different disease types; determine the disorder of the matching behavior of each acupoint based on the degree of disorder of the comprehensive correlation coefficient between each acupoint and other acupoints in the disease evolution sequence under consecutive disease types.

[0028] Traditional Chinese medicine emphasizes a holistic view and syndrome differentiation and treatment. Diseases do not exist in isolation, but are internally connected and have transitional relationships. The degree of similarity of disease information in different disease types reflects the correlation of pathological mechanisms. Based on the correlation of pathological mechanisms, disease types are arranged in an evolutionary sequence from the initial state to the evolved state.

[0029] The core characteristic of the transmission of disease mechanisms in traditional Chinese medicine is its gradual nature. Changes between adjacent disease mechanisms are continuous and gentle, rather than abrupt leaps. For example, the transmission from kidney yin deficiency syndrome to kidney yin-yang deficiency syndrome is a gradual process of yin deficiency accumulating into yang deficiency over time. The comprehensive correlation coefficient reflects the close connection between each acupoint and most commonly used acupoints in acupoint prescriptions for disease types in traditional Chinese medicine theory and clinical practice. It can represent the compatibility of each acupoint with commonly used acupoints for disease types. The degree of disorder in the comprehensive correlation coefficient between each acupoint and other acupoints under continuous disease types in the disease evolution sequence measures the complexity of the combination behavior transfer model for each acupoint, yielding the disorder of the combination behavior.

[0030] Step S4: Based on the efficacy evaluation indicators of acupuncture treatment records containing each acupoint, the disorder of combination behavior, and the comprehensive correlation coefficient between each acupoint and other acupoints under all disease types, determine the functional label value of each acupoint and optimize the TCM acupuncture efficacy database.

[0031] The chaotic compatibility behavior quantifies the complexity of the compatibility behavior transfer pattern of each acupoint. The comprehensive correlation coefficient of each acupoint with other acupoints across all disease types reflects the degree of compatibility of each acupoint with commonly used acupoints across all disease types, but it cannot reflect whether the collaboration can be translated into actual therapeutic effect. For example, there may be some acupoints that are frequently combined but have mediocre effects. Introducing efficacy evaluation indicators can test whether the collaboration is effectively translated into clinical value. This step determines the functional label value of acupoints from three dimensions: collaborative ability, behavioral pattern, and final efficacy. It simplifies the data access path from a complex network association to linear attribute filtering, greatly reducing the complexity of data access and effectively improving the query efficiency of the TCM acupuncture efficacy database.

[0032] Preferably, in some possible implementations of the present invention, the method for obtaining the comprehensive correlation coefficient is shown in Figure 2, which illustrates a flowchart of a method for obtaining the comprehensive correlation coefficient provided by an embodiment of the present invention. The method includes: step S210: determining the acupoint synergy coefficient of the corresponding two acupoints under each disease type based on the correlation strength between the occurrence of any two acupoints in the acupuncture diagnosis and treatment records of each disease type within the overall acupoint set.

[0033] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the acupoint synergy coefficient includes: taking the proportion of acupuncture treatment records for each disease type that include every acupoint in the overall acupoint set as the probability of occurrence of the corresponding acupoint in each disease type; taking the proportion of acupuncture treatment records for each disease type that simultaneously include any two acupoints in the overall acupoint set as the co-occurrence probability of the corresponding two acupoints in each disease type; randomly selecting a disease type as an example type, taking the co-occurrence probability of any two acupoints in the overall acupoint set in the example type as the numerator, and the product of the occurrence probabilities of the corresponding two acupoints in the example type as the denominator, and using the ratio obtained as the acupoint synergy coefficient of the corresponding two acupoints in the example type.

[0034] It should be noted that when the acupoint synergy coefficient is equal to 1, the two acupoints appear independently in the acupuncture treatment record of the example type, meaning that the combination of the two acupoints in the example type has no special clinical significance; when the acupoint synergy coefficient is greater than 1, the two acupoints are positively correlated, meaning that the synergistic relationship between the two acupoints in the acupuncture treatment record of the example type is stronger; when the acupoint synergy coefficient is less than 1, the two acupoints are negatively correlated in the example type, meaning that the two acupoints may conflict or inhibit each other in the acupuncture treatment record of the example type, that is, the synergistic relationship between the two acupoints in the example type is weaker.

[0035] It should be noted that the method for obtaining the synergistic effect coefficient of acupoints for the two acupoints is the same for both the example type and all disease types.

[0036] Step S220: Obtain the acupoint information text of each acupoint, perform text vectorization on the acupoint information text to obtain the acupoint vector of each acupoint; obtain the cosine similarity between the acupoint vectors of any two acupoints in the overall acupoint set, and record it as the pathological theory fit degree of the corresponding two acupoints.

[0037] It should be noted that the greater the cosine similarity between the acupoint characteristic vectors of two acupoints, the more compatible the functions, meridians, and indications of the two acupoints are, and the stronger the theoretical fit for the same pathology; conversely, the greater the difference in the TCM attributes of the two acupoints, the weaker the theoretical fit for the same pathology.

[0038] In this embodiment of the invention, the acupoint information includes functional description, meridian affiliation and indications, etc. The text vectorization can be performed using models such as Word2Vec and BERT, which are not limited here.

[0039] Step S230: Based on the synergistic effect coefficient of acupoints and the fit of pathological theory, obtain the comprehensive correlation coefficient of any two acupoints in the overall acupoint set under each disease type.

[0040] It should be noted that the larger the synergistic effect coefficient of acupoints and the greater the fit between them and the pathological theory, the closer the correlation between the two acupoints in theory and clinical practice, and the larger the overall correlation coefficient. Therefore, the synergistic effect coefficient of acupoints, the fit between them and the pathological theory, and the overall correlation coefficient are all positively correlated. In this embodiment of the invention, the fit between the pathological theory of the two acupoints is normalized, and the product of the normalized result and the synergistic effect coefficient of the two acupoints under the example type is used as the overall correlation coefficient of the two acupoints under the example type.

[0041] In this embodiment of the invention, since the range of cosine similarity is from -1 to 1, the pathological theory fit can be normalized by using the maximum value of 1 and the minimum value of -1 in the range of cosine similarity. Normalization methods such as the Sigmoid function can also be used, which are not limited here.

[0042] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the disease evolution sequence includes: obtaining disease information text for each disease type; performing text vectorization on the disease information text to obtain disease vectors for each disease type; performing hierarchical clustering on all disease types based on the cosine similarity between disease vectors of different disease types to obtain a disease tree diagram; the leaf nodes in the disease tree diagram are disease types; performing an inorder traversal on the disease tree diagram, arranging all leaf nodes corresponding to disease types according to the traversal order to obtain the disease evolution sequence.

[0043] It should be noted that, in this embodiment of the invention, the disease information includes: the etiology, pathogenesis, and symptoms of the disease type. The cosine similarity between disease vectors of different disease types reflects the correlation of pathological mechanisms. For example, the text similarity between Liver Qi Stagnation Syndrome and Liver Yang Rising Syndrome is high, indicating a close relationship between the two in Traditional Chinese Medicine theory. They may transform into or influence each other, reflecting the pathological transmission relationship between them. Hierarchical clustering based on the cosine similarity between pathological vectors of different disease types yields a disease tree diagram, presenting the classification and evolutionary path of diseases. Inorder traversal of the disease tree diagram generates a disease evolution sequence from the simplest or basic disease to the most complex or evolved disease, conforming to the laws of pathological transmission.

[0044] In one implementation of this invention, the hierarchical algorithm uses the unweighted group average method, and the text vectorization can use models such as Word2Vec and BERT, which are not limited here.

[0045] It is important to note that when clustering disease types, the cosine similarity between the disease vectors of any two disease types needs to be negatively correlated and normalized. The result is then used as the distance metric between the two disease types during the clustering process. Specifically, the data to be processed is used as the exponent of an exponential function with the natural constant as its base, thus achieving negative correlation and normalization of the data.

[0046] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the disorder of compatibility behavior includes: averaging the comprehensive correlation coefficients between each acupoint in the overall acupoint set and the other acupoints under each disease type to obtain the compatibility state value of each acupoint under each disease type; arranging the compatibility state values ​​of each acupoint in the overall acupoint set under all disease types according to the order of disease types in the disease evolution sequence to obtain the compatibility sequence of the corresponding acupoints; traversing the compatibility sequence using a sliding window of a preset length, with each element in the sliding window after each slide forming an N-tuple, where N is the preset length; obtaining the information entropy of the N-tuple corresponding to the compatibility sequence of each acupoint as the disorder of the compatibility behavior of the corresponding acupoint.

[0047] It should be noted that the higher the average comprehensive correlation coefficient between each acupoint and other acupoints under each disease type, the closer the connection between each acupoint and most commonly used acupoints in the acupoint prescription for that disease type in terms of TCM theory and clinical practice, and the more prominent the core position of each acupoint in the acupoint prescription for that pathological type, the stronger the compatibility between each acupoint and the commonly used acupoints for that disease type, resulting in a higher compatibility value. The compatibility sequence shows the changes in acupoint compatibility behavior as the disease evolves. The N-tuple represents the changes in the compatibility behavior of acupoints in adjacent disease types, and the disorder of compatibility behavior measures the stability of the compatibility behavior transition of each acupoint. If the disorder of compatibility behavior is smaller, it indicates that the compatibility state transition pattern of each acupoint is highly concentrated, the behavior model is stable and predictable, and the acupoint is suitable as a core acupoint; conversely, it indicates that the compatibility state transition pattern of each acupoint is more complex, the behavior is random and unpredictable, and it can adapt to a variety of different pathologies. The stronger the clinical adaptability of the acupoint, the more often it is used for emergency treatment or plays a synergistic role in broad-spectrum treatment plans.

[0048] In one implementation of this invention, the preset length N of the sliding window is set to 2 and the step size is set to 1, where N is less than the number of elements in the matching sequence. The implementer can set these values ​​according to the specific circumstances.

[0049] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining functional focus includes: selecting an acupoint as an example acupoint, taking the average value of the efficacy evaluation indicators of acupuncture treatment records containing the example acupoint as the overall efficacy value of the example acupoint; taking the average value of the compatibility status values ​​of the example acupoint under all disease types as the overall compatibility strength of the example acupoint; obtaining the functional focus of the example acupoint based on the overall compatibility strength, the disorder of compatibility behavior, and the overall efficacy value; and determining the functional label value of each acupoint based on the functional focus.

[0050] It should be noted that the overall compatibility strength reflects the overall level of compatibility between each acupoint and commonly used acupoints across all disease types. A higher overall compatibility strength indicates a stronger collaborative ability of the acupoint, meaning that theoretically, the acupoint is compatible with the pathogenesis of many diseases, and clinically, it can form a synergistic effect with many other acupoints. The disorder of compatibility behavior measures the stability of the transfer of compatibility behavior for each acupoint. A lower disorder indicates that the compatibility behavior of each acupoint is highly stable and predictable, and it can stably play a core role in specific disease environments, consistent with the stable attribute of "acupoints having primary diseases" in Traditional Chinese Medicine. The overall therapeutic effect value measures the overall therapeutic effect brought about by each acupoint in clinical practice; the higher the overall therapeutic effect value, the more significant the actual therapeutic value of the acupoint. With a higher overall compatibility strength and lower disorder in compatibility behavior, each acupoint possesses both high collaborative ability and a stable behavioral pattern. The collaborative ability of this acupoint is highly focused, and when the overall therapeutic effect value is higher, each acupoint exhibits focused behavior and higher actual therapeutic effect in specific diseases, thus increasing functional focus. Therefore, the overall compatibility strength and overall therapeutic value are both positively correlated with functional focus, while the degree of compatibility disorder is negatively correlated with functional focus.

[0051] In this embodiment of the invention, the overall compatibility strength of the example acupoint is used as the numerator, and the sum of the disorder of compatibility behavior and a preset positive number is used as the denominator to obtain a ratio. The product of the ratio and the overall therapeutic effect value is normalized to obtain the functional focus of the example acupoint. The preset positive number is used to prevent the denominator from being zero, and an empirical value of 0.01 is taken. The implementer can set it according to the specific situation.

[0052] In this embodiment of the invention, max-min normalization is used for normalization. Alternatively, normalization methods such as the Sigmoid function can be selected, and no limitation is made here.

[0053] It should be noted that the method for obtaining the focus level of the example acupoint is the same as that for all acupoints.

[0054] In this embodiment of the invention, the method for obtaining the functional label value includes: clustering all acupoints in the overall acupoint set based on the absolute value of the difference in functional focus of different acupoints to obtain several clusters; taking the mean of the functional focus of all acupoints in the same cluster as the overall focus of each cluster; the larger the overall focus, the smaller the functional label value of the acupoints in the cluster.

[0055] It should be noted that acupoints within clusters with higher overall focus tend to exhibit more focused behavior and higher actual therapeutic effects in specific ailments. These acupoints are more likely to be highly effective and specialized core acupoints, possessing high reliability in Traditional Chinese Medicine theory and practice, and are therefore preferred in database construction and prescription recommendation. Acupoints with smaller functional tag values ​​are more central in status, meaning they have higher priority.

[0056] In one implementation of this invention, the K-means clustering algorithm is used to cluster acupoints, with K set to 3. The absolute value of the difference in functional focus among different acupoints is used as the distance index in the clustering process. Acupoints within the cluster with the highest overall focus are designated as core acupoints. These acupoints have powerful effects, definite curative effects, and stable behavior in specific pathogenesis, such as "Taixi" in kidney deficiency. Acupoints within the cluster with the second highest overall focus are designated as synergistic acupoints. These acupoints are highly auxiliary and versatile, often combined with core acupoints, such as "Zusanli" in spleen and stomach disorders. Acupoints within the cluster with the lowest overall focus are designated as broad-spectrum acupoints. These acupoints have broad basic effects and strong adaptability, but their combination patterns are not significant, such as "Hegu" used for various emergency treatments. Implementers can set the number of clusters and the types of acupoints according to specific circumstances.

[0057] In this embodiment of the invention, an "Acupoint Function Table" is constructed based on the association between the functional label values ​​of each acupoint and the intermediate data table of "Disease-Acupoint-Efficacy". This table includes fields such as acupoint ID, functional label value, and feature vector. To improve query efficiency, the following operations are implemented: Index optimization: A composite index is created for "functional label value" and "disease type" to support fast retrieval of acupoints by disease and functional label value; Materialized view: The result set of common query scenarios is calculated, such as all core acupoints under a certain disease (i.e., the acupoint with the smallest functional label value), and stored as a materialized view to reduce the overhead of multi-table join queries; Semantic caching: For high-frequency query patterns, such as "high synergistic effect acupoint pairs in liver qi stagnation syndrome", their comprehensive correlation coefficient and matching results are cached to reduce real-time computing load.

[0058] The optimized database supports rapid diagnosis and acupoint selection. For example, in clinical decision-making, physicians can prioritize searching for combinations of "core acupoints" and "synergistic acupoints" to improve diagnostic efficiency and accuracy, which is in line with the TCM principle of "treating the symptoms in urgent cases and addressing the root cause in chronic cases".

[0059] This invention is now complete.

[0060] Example 2: This invention proposes a system for constructing a database of therapeutic effects of acupuncture points in Traditional Chinese Medicine (TCM). Please refer to Figure 3, which shows a system structure diagram of such a system according to an embodiment of the invention. The system includes: a data acquisition module 510, used to acquire acupuncture treatment records for different disease types, including acupuncture points and therapeutic effect evaluation indicators; a set of acupuncture points comprised of all acupuncture treatment records for all disease types; and an acupuncture point association analysis module 520, used to analyze the correlation strength between any two acupuncture points appearing in the acupuncture treatment records for each disease type, and the acupuncture point characteristic information of the corresponding two acupuncture points. The similarity degree is used to determine the comprehensive correlation coefficient between two corresponding acupoints under each disease type; the compatibility behavior analysis module 530 is used to determine the disease evolution sequence based on the similarity of disease information of different disease types; the degree of disorder of the compatibility behavior of each acupoint is determined based on the degree of disorder of the comprehensive correlation coefficient between each acupoint and other acupoints in the disease evolution sequence under consecutive disease types; the database construction module 540 is used to determine the functional label value of each acupoint based on the efficacy evaluation index of acupuncture diagnosis and treatment records containing each acupoint, the degree of disorder of compatibility behavior, and the comprehensive correlation coefficient between each acupoint and other acupoints under all disease types, and to optimize the TCM acupuncture efficacy database.

[0061] It should be noted that the devices provided in the above embodiments are only illustrative examples of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the TCM acupuncture point efficacy database construction system and the TCM acupuncture point efficacy database construction method embodiment provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiment, and will not be repeated here.

[0062] Example 3: Figure 4 is a schematic diagram of a computer device for constructing a database of therapeutic effects of acupuncture points according to an embodiment of the present invention. Exemplarily, as shown in Figure 4, the computer device includes: a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602. When the processor 602 executes the computer program 603, the computer device can execute any of the aforementioned methods for constructing a database of therapeutic effects of acupuncture points.

[0063] Furthermore, this application also protects an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a method for constructing a database of therapeutic effects of acupuncture points provided in this application.

[0064] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0065] It should be understood that the device provided in this embodiment is used to execute the above-described method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine, and therefore can achieve the same effect as the above-described implementation method.

[0066] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of program code by the workpiece.

[0067] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits contained in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0068] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for constructing a database of therapeutic effects of acupuncture points in Traditional Chinese Medicine, characterized in that, The method includes: acquiring acupuncture treatment records for different disease types, wherein the acupuncture treatment records include acupoints and efficacy evaluation indicators; constructing an overall acupoint set from the acupuncture treatment records for all disease types; determining the comprehensive correlation coefficient of two acupoints under each disease type based on the correlation strength between the occurrence of any two acupoints in the acupuncture treatment records for each disease type, and the similarity of the acupoint characteristics of the two acupoints; determining the disease evolution sequence based on the similarity of disease information for different disease types; determining the disorder of the compatibility behavior of each acupoint based on the disorder of the comprehensive correlation coefficient between each acupoint and other acupoints under consecutive disease types in the disease evolution sequence; determining the functional label value of each acupoint based on the efficacy evaluation indicators of the acupuncture treatment records containing each acupoint, the disorder of the compatibility behavior, and the comprehensive correlation coefficient between each acupoint and other acupoints under all disease types, and optimizing the TCM acupuncture efficacy database.

2. The method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 1, characterized in that, The determination of the comprehensive correlation coefficient of two acupoints under each disease type includes: determining the acupoint synergy coefficient of two acupoints under each disease type based on the correlation strength between the occurrence of any two acupoints in the acupuncture treatment records of each disease type within the overall acupoint set; obtaining the acupoint characteristic information text of each acupoint, performing text vectorization on the acupoint characteristic information text to obtain the acupoint characteristic vector of each acupoint; obtaining the cosine similarity between the acupoint characteristic vectors of any two acupoints within the overall acupoint set, denoted as the pathological theoretical fit of the two acupoints; and obtaining the comprehensive correlation coefficient of any two acupoints under each disease type based on the acupoint synergy coefficient and the pathological theoretical fit.

3. The method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 2, characterized in that, The determination of the acupoint synergy coefficient for two corresponding acupoints under each disease type includes: taking the proportion of acupuncture treatment records for each disease type that include every acupoint in the overall acupoint set as the probability of occurrence of the corresponding acupoint under each disease type; taking the proportion of acupuncture treatment records for each disease type that simultaneously include any two acupoints in the overall acupoint set as the co-occurrence probability of the two corresponding acupoints under each disease type; randomly selecting a disease type as an example type, and taking the ratio obtained by multiplying the co-occurrence probability of any two acupoints in the overall acupoint set under the example type as the numerator and the occurrence probability of the two corresponding acupoints under the example type as the denominator as the acupoint synergy coefficient for the two corresponding acupoints under the example type.

4. The method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 1, characterized in that, The process of determining the disease evolution sequence includes: acquiring disease information text for each disease type; performing text vectorization on the disease information text to obtain disease vectors for each disease type; performing hierarchical clustering on all disease types based on the cosine similarity between the disease vectors of different disease types to obtain a disease tree diagram; the leaf nodes in the disease tree diagram represent disease types; and performing an inorder traversal on the disease tree diagram to arrange all leaf nodes corresponding to disease types in traversal order to obtain the disease evolution sequence.

5. The method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 1, characterized in that, The determination of the disorder of the compatibility behavior of each acupoint includes: averaging the comprehensive correlation coefficients between each acupoint and the other acupoints in the overall acupoint set under each disease type to obtain the compatibility status value of each acupoint under each disease type; arranging the compatibility status values ​​of each acupoint in the overall acupoint set under all disease types according to the order of disease types in the disease evolution sequence to obtain the compatibility sequence of the corresponding acupoints; traversing the compatibility sequence using a sliding window of a preset length, with each sliding window containing elements forming an N-tuple, where N is the preset length; and obtaining the information entropy of the N-tuple corresponding to the compatibility sequence of each acupoint as the disorder of the compatibility behavior of the corresponding acupoint.

6. The method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 5, characterized in that, The process of determining the functional label value for each acupoint includes: selecting any acupoint as an example acupoint; using the average of the efficacy evaluation indicators of acupuncture treatment records containing the example acupoint as the overall efficacy value of the example acupoint; using the average of the compatibility status values ​​of the example acupoint under all disease types as the overall compatibility strength of the example acupoint; obtaining the functional focus of the example acupoint based on the overall compatibility strength, the disorder of the compatibility behavior, and the overall efficacy value; and determining the functional label value for each acupoint based on the functional focus.

7. The method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 6, characterized in that, The method for obtaining the functional label value includes: clustering all acupoints in the overall acupoint set based on the absolute value of the difference in functional focus of different acupoints to obtain several clusters; taking the mean of the functional focus of all acupoints in the same cluster as the overall focus of each cluster; the larger the overall focus, the smaller the functional label value of the acupoints in the cluster.

8. The method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 6, characterized in that, The overall compatibility strength and the overall therapeutic effect value are both positively correlated with the functional focus, while the degree of disorder in compatibility behavior is negatively correlated with the functional focus.

9. The method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 4, characterized in that, The method for hierarchical clustering of all disease types is the unweighted group average method.

10. A method for constructing a database of therapeutic effects of acupuncture points in traditional Chinese medicine according to claim 5, characterized in that, The value of N is 2.

Images