AI auxiliary diagnosis and treatment system for intelligent identification and formula optimization of traditional Chinese medicinal materials

Abstract

The invention relates to the technical field of traditional Chinese medicinal material identification and formula optimization AI diagnosis and treatment, and particularly discloses a traditional Chinese medicinal material intelligent identification and formula optimization AI auxiliary diagnosis and treatment system which comprises a symptom similarity acquisition module, a basic dose confirmation module, a traditional Chinese medicinal material quality identification module, a traditional Chinese medicinal material formula optimization module, a formula dynamic adjustment module and a database. Quantitative matching of symptom vectors is achieved through one-hot coding and cosine similarity, the types are determined based on historical case high-frequency medicinal material statistics, the medicinal material quality qualification degree is evaluated through a multi-modal data fusion algorithm, and the dosage is dynamically adjusted according to quality deviation and physiological parameters. The subjectivity and experience limitation of traditional Chinese medicine diagnosis and treatment are broken through, objective symptom differentiation, intelligent medicinal material identification and dynamic dose optimization are achieved, a whole-process closed loop of data acquisition-analysis-prescription adjustment is constructed, the accuracy and curative effect of traditional Chinese medicine diagnosis and treatment are remarkably improved, and the method is suitable for intelligent diagnosis and treatment scenes of traditional Chinese medicine pavilions.

Description

Technical Field

[0001] The present invention relates to the technical field of AI diagnosis and treatment for the identification and formula optimization of traditional Chinese medicinal materials. Specifically, it relates to an AI-assisted diagnosis and treatment system for the intelligent identification and formula optimization of traditional Chinese medicinal materials. Background Art

[0002] Although the traditional Chinese medicine diagnosis and treatment system has unique advantages of holistic view and syndrome differentiation and treatment, it faces significant challenges in modern applications. Therefore, in order to break through the subjectivity and empirical limitations of traditional Chinese medicine diagnosis and treatment and improve the standardization level of the quality control of traditional Chinese medicinal materials and the individual precision of prescription compatibility, it is urgent to construct an intelligent and data-based AI-assisted diagnosis and treatment system.

[0003] There are also the following problems in the prior art: 1. Only relying on the experience of physicians or fixed-dose templates to determine the dosage of traditional Chinese medicinal materials required by patients, without dynamically adjusting according to the quality of the medicinal materials, lacking an automated response mechanism to the quality differences of the medicinal materials, which is likely to lead to unstable curative effects.

[0004] 2. Mostly relying on a single detection method to evaluate the quality of traditional Chinese medicinal materials (such as only appearance inspection or chemical composition analysis), without proposing multi-modal data fusion (dual analysis of color and smell) analysis, unable to comprehensively evaluate the quality of traditional Chinese medicinal materials, which may lead to missed detection of inferior medicinal materials.

[0005] 3. Mostly static prescription recommendations, unable to optimize the dosage for the next course of treatment according to the real-time physiological parameters of patients after taking the medicine and the quality changes of the medicinal materials, thus unable to achieve the closed-loop process of "treatment - feedback - optimization". Summary of the Invention

[0006] In view of this, in order to solve the problems raised in the above background art, an AI-assisted diagnosis and treatment system for the intelligent identification and formula optimization of traditional Chinese medicinal materials is now proposed.

[0007] The object of the present invention can be achieved by the following technical solutions: The present invention provides an AI-assisted diagnosis and treatment system for the intelligent identification and formula optimization of traditional Chinese medicinal materials, including: a symptom similarity acquisition module, which extracts the types of diseases and various symptoms suffered by the current patient input to the AI diagnosis and treatment platform of the target traditional Chinese medicine pharmacy, and extracts the various symptoms corresponding to each historical patient with the same type of disease in the historical database of the AI diagnosis and treatment platform, and accordingly obtains the symptom vector similarity between the current patient and each historical patient.

[0008] A basic dose confirmation module, which extracts the information on the taking of traditional Chinese medicinal materials by each historical patient, and based on the symptom vector similarity, confirms the types of traditional Chinese medicinal materials required by the current patient and the basic doses of various traditional Chinese medicinal materials.

[0009] A traditional Chinese medicinal material quality identification module, which starts the automatic grabbing machine of the medicinal materials in the target traditional Chinese medicine pharmacy and collects the quality information of various traditional Chinese medicinal materials through it, and uses a multi-modal data fusion algorithm to obtain the quality qualification degree of various traditional Chinese medicinal materials.

[0010] The traditional Chinese medicine formula optimization module adjusts the initial doses of various traditional Chinese medicines required for the current patient based on the basic doses and quality qualification degrees of various traditional Chinese medicines.

[0011] The formula dynamic adjustment module collects the real-time physiological parameters of the current patient at the end of the current medication course, and collects the quality information of various traditional Chinese medicines in the target traditional Chinese medicine pharmacy after the end of the current medication course, and accordingly optimizes the doses of various traditional Chinese medicines required for the current patient in the next medication course.

[0012] Specifically, the specific process of obtaining the symptom vector similarity between the current patient and each historical patient is as follows: Summarize all the symptoms that appear corresponding to all historical patients and the current patient in the same type of disease in the historical database of the AI diagnosis and treatment platform to form a symptom set.

[0013] Based on the symptom set, use one-hot encoding to generate the symptom vector corresponding to the disease suffered by the current patient and the symptom vectors corresponding to each historical patient.

[0014] Based on the symptom vector corresponding to the disease suffered by the current patient and the symptom vectors corresponding to each historical patient, calculate the cosine similarity to obtain the symptom vector similarity between the current patient and each historical patient.

[0015] Specifically, the specific process of confirming the types of traditional Chinese medicines required for the current patient is as follows: Compare the symptom vector similarity between the current patient and each historical patient with the set reference symptom vector similarity. If the symptom vector similarity between the current patient and a certain historical patient is greater than or equal to the set reference symptom vector similarity, then record this historical patient as a highly similar patient, and thus screen out each highly similar patient corresponding to the current patient.

[0016] Extract the types of traditional Chinese medicines taken by each highly similar patient and the initial doses of various traditional Chinese medicines from the traditional Chinese medicine taking information of each historical patient.

[0017] Count the number of occurrences of various traditional Chinese medicines, and use the ratio between the number of occurrences of various traditional Chinese medicines and the number of highly similar patients as the frequency of occurrence of various traditional Chinese medicines.

[0018] Compare the frequency of occurrence of various traditional Chinese medicines with the set reference frequency of occurrence of traditional Chinese medicines. If the frequency of occurrence of a certain type of traditional Chinese medicine is greater than or equal to the set reference frequency of occurrence of traditional Chinese medicines, then record this type of traditional Chinese medicine as the target traditional Chinese medicine, and thus obtain the types of target traditional Chinese medicines, and use them as the types of traditional Chinese medicines required for the current patient.

[0019] Specifically, the specific method for confirming the basic dosages of various traditional Chinese medicines required for the current patient is as follows: Extract the initial dosages of various traditional Chinese medicines required for the current patient that appear each time from the initial dosages of various traditional Chinese medicines taken by each highly similar patient, and perform an average calculation on them. Take the calculation result as the basic dosage of various traditional Chinese medicines required for the current patient.

[0020] Specifically, the specific process for obtaining the quality qualification degrees of various traditional Chinese medicines by using the multi-modal data fusion algorithm is as follows: Based on the grayscale images in the quality information of various traditional Chinese medicines, perform color processing to obtain the color qualification degrees of various traditional Chinese medicines.

[0021] Based on the coupling analysis of each eigenvalue in the odor component spectrum in the quality information of various traditional Chinese medicines and each characteristic standard value in the standard component spectrum of various traditional Chinese medicines stored in the database, obtain the odor qualification degrees of various traditional Chinese medicines.

[0022] Perform weighted calculation and summation on the color qualification degrees and odor qualification degrees of various traditional Chinese medicines with the corresponding weights to obtain the quality qualification degrees of various traditional Chinese medicines.

[0023] Specifically, the specific method for obtaining the color qualification degrees of various traditional Chinese medicines is as follows: Extract the grayscale values corresponding to each grayscale region from the grayscale images of various traditional Chinese medicines, and compare them with the grayscale value intervals corresponding to various traditional Chinese medicines under standard conditions stored in the database.

[0024] If the grayscale value corresponding to a certain grayscale region of a certain traditional Chinese medicine is not within the grayscale value interval corresponding to it under standard conditions, then mark this grayscale region of this traditional Chinese medicine as an abnormal region, and count the number of abnormal regions of various traditional Chinese medicines.

[0025] Count the number of grayscale regions corresponding to various traditional Chinese medicines from the grayscale images of various traditional Chinese medicines, and record the ratio between the number of abnormal regions and the number of grayscale regions of various traditional Chinese medicines as the abnormal region ratio of various traditional Chinese medicines.

[0026] Take the ratio of the difference between the set reference abnormal region ratio and the abnormal region ratio of various traditional Chinese medicines to the set reference abnormal region ratio, and take the ratio result as the color qualification degree of various traditional Chinese medicines.

[0027] Specifically, the specific process for obtaining the odor qualification degrees of various traditional Chinese medicines is as follows: Combine each eigenvalue in the odor component spectrum of various traditional Chinese medicines into a multi-dimensional vector as the multi-dimensional feature vector of various traditional Chinese medicines.

[0028] Combine each characteristic standard value in the standard component spectrum of various traditional Chinese medicines stored in the database into a multi-dimensional vector as the standard feature vector of various traditional Chinese medicines.

[0029] Obtain the Euclidean distances between the multi-dimensional feature vectors and the standard feature vectors of various Chinese medicinal materials.

[0030] Based on the Euclidean distances between the multi-dimensional feature vectors and the standard feature vectors of various Chinese medicinal materials, calculate to obtain the odor qualification degrees of various Chinese medicinal materials.

[0031] Specifically, the specific process of adjusting the initial doses of various Chinese medicinal materials required for the current patient is as follows: Compare the quality qualification degrees of various Chinese medicinal materials with the set reference quality qualification degree. If the quality qualification degree of a certain type of Chinese medicinal material is greater than the set reference quality qualification degree, then mark this type of Chinese medicinal material as a high-quality medicinal material; if the quality qualification degree of a certain type of Chinese medicinal material is less than the set reference quality qualification degree, then mark this type of Chinese medicinal material as a low-quality medicinal material; if the quality qualification degree of a certain type of Chinese medicinal material is equal to the set reference quality qualification degree, then mark this type of Chinese medicinal material as a standard-quality medicinal material.

[0032] If a certain type of Chinese medicinal material required for the current patient is a standard-quality medicinal material, then keep the basic dose of this type of Chinese medicinal material unchanged.

[0033] If a certain type of Chinese medicinal material required for the current patient is a high-quality medicinal material, then obtain the difference between the quality qualification degree of this type of Chinese medicinal material and the set reference quality qualification degree, and take the product of the difference and the dose to be adjusted corresponding to the unit quality qualification degree deviation of this type of Chinese medicinal material stored in the database as the dose to be reduced for this type of Chinese medicinal material, and take the difference between the basic dose and the dose to be reduced as the initial dose of this type of Chinese medicinal material.

[0034] If a certain type of Chinese medicinal material required for the current patient is a low-quality medicinal material, then obtain the difference between the set reference quality qualification degree and the quality qualification degree of this type of Chinese medicinal material, and take the product of the difference and the dose to be adjusted corresponding to the unit quality qualification degree deviation of this type of Chinese medicinal material stored in the database as the dose to be increased for this type of Chinese medicinal material, and take the sum of the basic dose and the dose to be increased as the initial dose of this type of Chinese medicinal material.

[0035] In summary, obtain the initial doses of various Chinese medicinal materials required for the current patient.

[0036] Specifically, the specific process of optimizing the doses of various Chinese medicinal materials required for the current patient in the next medication course is as follows: Based on the pulse rate and tongue coating images in the real-time physiological parameters corresponding to the end of the current medication course of the current patient, perform fusion processing to obtain the physiological health index corresponding to the end of the current medication course of the current patient.

[0037] Based on the quality information of various Chinese medicinal materials in the target Chinese medicine pharmacy after the end of the current medication course, analyze the quality qualification degrees of various Chinese medicinal materials after the end of the current medication course in the same way as the analysis method of the quality qualification degrees of various Chinese medicinal materials.

[0038] Based on the physiological health index corresponding to the end of the current medication course of the current patient and the quality qualification degree of various Chinese medicinal materials after the end of the current medication course, an optimization analysis is carried out to obtain the dosages of various Chinese medicinal materials that the current patient needs to take in the next medication course.

[0039] Specifically, the specific process of obtaining the physiological health index corresponding to the end of the current medication course of the current patient is as follows: Based on the pulse rate corresponding to the end of the current medication course of the current patient, an abnormal pulse condition analysis is carried out to obtain the abnormal pulse condition degree corresponding to the end of the current medication course of the current patient.

[0040] Based on the tongue coating image corresponding to the end of the current medication course of the current patient, an abnormal tongue coating color analysis is carried out to obtain the abnormal tongue coating color degree corresponding to the end of the current medication course of the current patient.

[0041] A comprehensive analysis is carried out on the abnormal pulse condition degree and the abnormal tongue coating color degree corresponding to the end of the current medication course of the current patient to obtain the physiological health index corresponding to the end of the current medication course of the current patient.

[0042] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention generates symptom vectors through one-hot encoding, combines the cosine similarity to calculate the symptom matching degree between the current patient and historical cases, and transforms the "syndrome differentiation" of traditional Chinese medicine into a quantifiable numerical analysis, reducing subjective errors.

[0043] (2) The present invention adopts a multi-modal data fusion algorithm, analyzes the color and luster qualification degree through grayscale image analysis, and calculates the odor qualification degree based on the Euclidean distance of the odor component spectrum, realizing the digital evaluation of the color and luster and odor of Chinese medicinal materials, improving the accuracy of the quality determination of Chinese medicinal materials, ensuring the quality of the medicinal materials used, and at the same time ensuring the stability of the curative effect.

[0044] (3) The present invention adjusts the initial dose based on the quality qualification degree, reduces the dose of high-quality medicinal materials according to the deviation ratio, and increases the dose of low-quality medicinal materials according to the ratio, avoiding insufficient curative effect or toxicity risk caused by fluctuations in the components of the medicinal materials.

[0045] (4) The present invention dynamically adjusts the prescription by combining physiological parameters, comprehensively calculates the physiological health index through the abnormal pulse rate degree and the abnormal tongue coating color degree, optimizes the dose in the next course while considering the real-time quality of the medicinal materials and the curative effect feedback of the patient, forming a "monitoring-adjusting" closed loop, improving the effective rate of the course, and realizing the dynamic adjustment of the Chinese medicinal material formula. Description of the Drawings

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0047] Figure 1 It is a schematic diagram of the connection of the system module structure of the present invention.

[0048] Figure 2 It is a schematic diagram of the analysis process of the quality qualification of traditional Chinese medicinal materials of the present invention.

[0049] Figure 3 It is a pulse rate fluctuation graph of normal people under normal conditions of the present invention. Detailed implementation manners

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0051] Please refer to Figure 1 As shown, the present invention provides an AI-assisted diagnosis and treatment system for intelligent identification and formula optimization of traditional Chinese medicinal materials, including: a symptom similarity acquisition module, a basic dose confirmation module, a traditional Chinese medicinal material quality identification module, a traditional Chinese medicinal material formula optimization module, and a formula dynamic adjustment module.

[0052] It should be noted that the present invention also includes a database for storing the grayscale value intervals corresponding to various traditional Chinese medicinal materials under standard conditions, the characteristic standard values in the standard component spectra of various traditional Chinese medicinal materials, the required adjusted doses corresponding to the unit quality qualification deviation of various traditional Chinese medicinal materials, the pulse rate intervals of normal people under normal conditions, and the RGB values in the tongue coating pictures.

[0053] The symptom similarity acquisition module is connected to the basic dose confirmation module, both the basic dose confirmation module and the traditional Chinese medicinal material quality identification module are connected to the traditional Chinese medicinal material formula optimization module, both the traditional Chinese medicinal material quality identification module and the traditional Chinese medicinal material formula optimization module are connected to the formula dynamic adjustment module, and the traditional Chinese medicinal material quality identification module, the traditional Chinese medicinal material formula optimization module, and the formula dynamic adjustment module are all connected to the database.

[0054] The symptom similarity acquisition module extracts the types of diseases suffered by the current patient input to the AI diagnosis and treatment platform of the target traditional Chinese medicine pharmacy and various symptoms, and extracts various symptoms corresponding to each historical patient with the same type of disease in the historical database of the AI diagnosis and treatment platform, and thereby obtains the symptom vector similarity between the current patient and each historical patient.

[0055] In a specific embodiment of the present invention, the types of diseases suffered include but are not limited to colds, stomachaches, and high blood pressure. The symptoms corresponding to a cold include but are not limited to fever, runny nose, sneezing, headache, and pale red tongue. The symptoms corresponding to a stomachache include but are not limited to weakness of the limbs, unsmooth bowel movements, white tongue coating, and taut pulse. The symptoms corresponding to high blood pressure include but are not limited to dizziness, tinnitus, bitter taste in the mouth, and yellow tongue coating.

[0056] In a specific embodiment of the present invention, the specific process of obtaining the symptom vector similarity between the current patient and each historical patient is as follows: Summarize all the symptoms that appear corresponding to all historical patients with the same type of disease in the historical database of the AI diagnosis and treatment platform and the current patient to form a symptom set.

[0057] Based on the symptom set, use one-hot encoding to generate the symptom vector corresponding to the disease suffered by the current patient and the symptom vectors corresponding to each historical patient.

[0058] It should be noted that the specific method of using one-hot encoding to generate the symptom vector corresponding to the disease suffered by the current patient and the symptom vectors corresponding to each historical patient based on the symptom set is as follows: Compare each type of symptom corresponding to the disease suffered by the current patient with each type of symptom in the symptom set. If the current patient has a certain type of symptom, the corresponding dimension value is 1. If the current patient does not have a certain type of symptom, the corresponding dimension value is 0, and thus the symptom vector corresponding to the disease suffered by the current patient is obtained.

[0059] Compare each type of symptom corresponding to each historical patient with each type of symptom in the symptom set. If a historical patient has a certain type of symptom, the corresponding dimension value is 1. If a historical patient does not have a certain type of symptom, the corresponding dimension value is 0, and thus the symptom vectors corresponding to each historical patient are obtained.

[0060] In a specific embodiment of the present invention, if the type of disease suffered is a cold, then the symptom set is defined as {fever, runny nose, sneezing, headache, pale red tongue}. If a historical patient A has the symptoms of "fever, runny nose", then his vector A = (1, 1, 0, 0, 0). If the current patient B has the symptoms of "fever, sneezing, headache", then his vector B = (1, 0, 1, 1, 0).

[0061] Perform cosine similarity calculation based on the symptom vector corresponding to the disease suffered by the current patient and the symptom vectors corresponding to each historical patient to obtain the symptom vector similarity between the current patient and each historical patient.

[0062] It should be noted that the specific method for obtaining the symptom vector similarity between the current patient and each historical patient is as follows: Multiply the dimension values in the symptom vector corresponding to the disease suffered by the current patient and the symptom vectors corresponding to each historical patient respectively, and then sum them up. The sum result is used as the dot product between the symptom vectors of the current patient and each historical patient.

[0063] Take the square root of the sum of the squares of each dimension value in the symptom vector corresponding to the disease suffered by the current patient as the norm of the symptom vector of the current patient.

[0064] Take the square root of the sum of the squares of each dimension value in the symptom vectors of each historical patient as the norm of the symptom vectors of each historical patient.

[0065] Divide the dot product between the symptom vectors of the current patient and each historical patient by the product of the norm of the symptom vector of the current patient and the norm of the symptom vectors of each historical patient. The division result is used as the symptom vector similarity between the current patient and each historical patient.

[0066] In the embodiment of the present invention, one-hot encoding is used to generate symptom vectors, and the cosine similarity is combined to calculate the symptom matching degree between the current patient and historical cases, converting the "syndrome differentiation" in traditional Chinese medicine into quantifiable numerical analysis, reducing subjective errors.

[0067] The basic dose confirmation module extracts the traditional Chinese medicine taking information of each historical patient, and based on the symptom vector similarity, confirms the types of traditional Chinese medicines required for the current patient and the basic doses of various traditional Chinese medicines.

[0068] It should be noted that the traditional Chinese medicine taking information of each historical patient is directly extracted from the AI diagnosis and treatment platform of the target traditional Chinese medicine pharmacy.

[0069] In a specific embodiment of the present invention, the specific process for confirming the types of traditional Chinese medicines required for the current patient is as follows: Compare the symptom vector similarity between the current patient and each historical patient with the symptom vector similarity of the set reference. If the symptom vector similarity between the current patient and a certain historical patient is greater than or equal to the symptom vector similarity of the set reference, then mark this historical patient as a highly similar patient, and thus screen out each highly similar patient corresponding to the current patient.

[0070] Extract the types of traditional Chinese medicines taken by each highly similar patient and the initial doses of various traditional Chinese medicines from the traditional Chinese medicine taking information of each historical patient.

[0071] Count the number of occurrences of various traditional Chinese medicines, and take the ratio between the number of occurrences of various traditional Chinese medicines and the number of highly similar patients as the frequency of occurrence of various traditional Chinese medicines.

[0072] Compare the frequencies of various types of traditional Chinese medicines with the frequencies of the reference traditional Chinese medicines. If the frequency of a certain type of traditional Chinese medicine is greater than or equal to the frequency of the reference traditional Chinese medicine, then record this type of traditional Chinese medicine as the target traditional Chinese medicine, thereby obtaining the types of target traditional Chinese medicines, and use them as the types of traditional Chinese medicines that the current patient needs to take.

[0073] In a specific embodiment of the present invention, the specific method for confirming the basic doses of various types of traditional Chinese medicines that the current patient needs to take is as follows: Extract the initial doses of each occurrence of various types of traditional Chinese medicines that the current patient needs to take from the initial doses of various types of traditional Chinese medicines taken by each highly similar patient, and perform an average calculation on them, and use the calculation result as the basic doses of various types of traditional Chinese medicines that the current patient needs to take.

[0074] The traditional Chinese medicine quality identification module starts the automatic medicine grabbing machine in the target Chinese medicine hall and collects the quality information of various types of traditional Chinese medicines through it, and uses a multi-modal data fusion algorithm to obtain the quality qualification degrees of various types of traditional Chinese medicines.

[0075] Please refer to Figure 2 As shown, in a specific embodiment of the present invention, the specific process of using a multi-modal data fusion algorithm to obtain the quality qualification degrees of various types of traditional Chinese medicines is as follows: Perform color processing on the grayscale images in the quality information of various types of traditional Chinese medicines to obtain the color qualification degrees of various types of traditional Chinese medicines.

[0076] It should be noted that the grayscale images of various types of traditional Chinese medicines are obtained by collecting images through a high-definition camera installed on the automatic medicine grabbing machine, and the collected images are imported into professional image processing software for grayscale processing to obtain the grayscale images of various types of traditional Chinese medicines.

[0077] In a specific embodiment of the present invention, the specific method for obtaining the color qualification degrees of various types of traditional Chinese medicines is as follows: Extract the grayscale values corresponding to each grayscale region from the grayscale images of various types of traditional Chinese medicines, and compare them with the grayscale value intervals corresponding to various types of traditional Chinese medicines under standard conditions stored in the database.

[0078] If the grayscale value corresponding to a certain grayscale region of a certain type of traditional Chinese medicine is not within the grayscale value interval corresponding to it under standard conditions, then record this grayscale region of this type of traditional Chinese medicine as an abnormal region, and count the number of abnormal regions of various types of traditional Chinese medicines.

[0079] Count the number of grayscale regions corresponding to various types of traditional Chinese medicines from the grayscale images of various types of traditional Chinese medicines, and record the ratio between the number of abnormal regions and the number of grayscale regions of various types of traditional Chinese medicines as the abnormal region ratio of various types of traditional Chinese medicines.

[0080] Take the ratio of the difference between the set reference abnormal region ratio and the abnormal region ratio of various types of traditional Chinese medicines to the set reference abnormal region ratio, and use the ratio result as the color qualification degree of various types of traditional Chinese medicines.

[0081] Based on the coupling analysis of each eigenvalue in the odor component spectrum of the quality information of various Chinese medicinal materials and each characteristic standard value in the standard component spectrum of various Chinese medicinal materials stored in the database, the odor qualification of various Chinese medicinal materials is obtained.

[0082] It should be noted that the acquisition method of the odor component spectrum of various Chinese medicinal materials is as follows: 1) Data acquisition: An electronic nose sensor usually consists of a sensor array with different sensitivities to different odor components. When the odor molecules of Chinese medicinal materials come into contact with the sensor array of the electronic nose installed on the automatic grasping machine, each sensor will generate corresponding electrical signal changes. 2) Signal preprocessing: Use a digital filter (such as a low-pass filter) to remove high-frequency noise to make the signal smoother. Then, unify the signal values of each sensor to a specific range (such as between 0 and 1) to eliminate the influence of sensitivity differences between different sensors. Finally, automatically extract the parameters that can represent the odor characteristics from the preprocessed signal (common eigenvalues include the peak value, mean value, and standard deviation of the signal). 3) Pattern generation: Combine the extracted eigenvalues into a multi-dimensional vector, and this vector is the odor component spectrum.

[0083] In a specific embodiment of the present invention, the specific process of obtaining the odor qualification of various Chinese medicinal materials is as follows: Combine each eigenvalue in the odor component spectrum of various Chinese medicinal materials into a multi-dimensional vector as the multi-dimensional characteristic vector of various Chinese medicinal materials.

[0084] Combine each characteristic standard value in the standard component spectrum of various Chinese medicinal materials stored in the database into a multi-dimensional vector as the standard characteristic vector of various Chinese medicinal materials.

[0085] Obtain the Euclidean distance between the multi-dimensional characteristic vector and the standard characteristic vector of various Chinese medicinal materials.

[0086] It should be noted that the specific method for obtaining the Euclidean distance between the multi-dimensional characteristic vector and the standard characteristic vector of various Chinese medicinal materials is: Take the square root of the sum of the squares of the differences between the corresponding eigenvalues of the multi-dimensional characteristic vector and the standard characteristic vector of various Chinese medicinal materials as the Euclidean distance between the multi-dimensional characteristic vector and the standard characteristic vector of various Chinese medicinal materials.

[0087] Based on the calculation of the Euclidean distance between the multi-dimensional characteristic vector and the standard characteristic vector of various Chinese medicinal materials, obtain the odor qualification of various Chinese medicinal materials.

[0088] It should be noted that the specific method for obtaining the odor qualification of various Chinese medicinal materials is: Calculate the odor qualification of various Chinese medicinal materials by dividing 1 by 1 plus the Euclidean distance.

[0089] It should be further noted that the smaller the Euclidean distance, the closer the two vectors are, the higher the matching degree, which also means the higher the odor qualification degree. Therefore, the Euclidean distance is inversely proportional to the odor qualification degree. So, by dividing 1 by 1 plus the Euclidean distance, the inverse proportional relationship between the Euclidean distance and the odor qualification degree can be obtained. Additionally, adding 1 to the Euclidean distance is to avoid a denominator of 0 and make the fraction meaningful.

[0090] The color qualification degree and odor qualification degree of various traditional Chinese medicines are weighted and calculated with the corresponding weights and summed to obtain the quality qualification degree of various traditional Chinese medicines.

[0091] In a specific embodiment of the present invention, when calculating the quality qualification degree of various traditional Chinese medicines, the corresponding proportions of the color qualification degree and odor qualification degree are equally important. Therefore, the corresponding proportion weights of the color qualification degree and odor qualification degree are 0.5 and 0.5 respectively.

[0092] The embodiment of the present invention adopts a multi-modal data fusion algorithm, analyzes the color qualification degree through grayscale images, and calculates the odor qualification degree based on the Euclidean distance of the odor component spectrum, realizing the digital evaluation of the color and odor of traditional Chinese medicines, improving the accuracy of the quality determination of traditional Chinese medicines, ensuring the quality of the medicine for use, and at the same time ensuring the stability of the curative effect.

[0093] The traditional Chinese medicine formula optimization module adjusts the initial doses of various traditional Chinese medicines required for the current patient based on the basic doses and quality qualification degrees of various traditional Chinese medicines.

[0094] In a specific embodiment of the present invention, the specific process of adjusting the initial doses of various traditional Chinese medicines required for the current patient is as follows: Compare the quality qualification degree of each type of traditional Chinese medicine with the set reference quality qualification degree. If the quality qualification degree of a certain type of traditional Chinese medicine is greater than the set reference quality qualification degree, then mark this type of traditional Chinese medicine as a high-quality medicine; if the quality qualification degree of a certain type of traditional Chinese medicine is less than the set reference quality qualification degree, then mark this type of traditional Chinese medicine as a low-quality medicine; if the quality qualification degree of a certain type of traditional Chinese medicine is equal to the set reference quality qualification degree, then mark this type of traditional Chinese medicine as a standard-quality medicine.

[0095] If a certain type of traditional Chinese medicine required for the current patient is a standard-quality medicine, then keep the basic dose of this type of traditional Chinese medicine unchanged.

[0096] If a certain type of traditional Chinese medicine required for the current patient is a high-quality medicine, then obtain the difference between the quality qualification degree of this type of traditional Chinese medicine and the set reference quality qualification degree, and take the product of the difference and the dose adjustment corresponding to the unit quality qualification degree deviation of this type of traditional Chinese medicine stored in the database as the required reduction dose of this type of traditional Chinese medicine, and take the difference between the basic dose and the required reduction dose as the initial dose of this type of traditional Chinese medicine.

[0097] It should be noted that the specific method for obtaining the deviation of the unit quality qualification corresponding to the required adjustment dose is as follows: 1) Data collection: Record the actual dose adjustment amount due to quality deviation during the clinical use of traditional Chinese medicinal materials to form a historical data set of "quality deviation - dose adjustment"; 2) Establish a mathematical model: Use linear regression statistical methods to analyze the relationship between quality deviation and dose adjustment amount. For example, let the quality deviation be the independent variable x and the dose adjustment amount be the dependent variable y. Through the least squares method, fit y = kx + b (k is the dose adjustment coefficient of the unit quality deviation, b is the intercept. If the dose adjustment is 0 when there is no quality deviation, b can be ignored), and determine the value of k through regression analysis, that is, determine the required adjustment dose corresponding to the deviation of the unit quality qualification.

[0098] If a certain type of traditional Chinese medicinal material required to be taken by the current patient is of low quality, then obtain the difference between the set reference quality qualification and the quality qualification of this type of traditional Chinese medicinal material, and take the product of the difference and the required adjustment dose corresponding to the deviation of the unit quality qualification of this type of traditional Chinese medicinal material stored in the database as the required increased dose of this type of traditional Chinese medicinal material, and take the sum of the basic dose and the required increased dose as the initial dose of this type of traditional Chinese medicinal material.

[0099] In summary, the initial doses of various types of traditional Chinese medicinal materials required to be taken by the current patient are obtained.

[0100] In the embodiment of the present invention, by adjusting the initial dose based on the quality qualification, the high-quality medicinal materials reduce the dose according to the deviation ratio, and the low-quality medicinal materials increase the dose according to the ratio, avoiding insufficient curative effect or toxicity risk caused by the fluctuation of the medicinal material components.

[0101] The formula dynamic adjustment module collects the real-time physiological parameters corresponding to the end of the current medication course of the current patient, and collects the quality information of various types of traditional Chinese medicinal materials in the target Chinese medicine pharmacy after the end of the current medication course, and accordingly optimizes the doses of various types of traditional Chinese medicinal materials required for the current patient in the next medication course.

[0102] In a specific embodiment of the present invention, the specific process of optimizing the doses of various types of traditional Chinese medicinal materials required for the current patient in the next medication course is as follows: Based on the pulse rate and tongue coating image in the real-time physiological parameters corresponding to the end of the current medication course of the current patient, perform fusion processing to obtain the physiological health index corresponding to the end of the current medication course of the current patient.

[0103] It should be noted that the pulse rate corresponding to the end of the current medication course of the current patient is collected by a pulse diagnosis instrument worn at the end of the current medication course, and the tongue coating image is collected by a high-definition camera installed.

[0104] In a specific embodiment of the present invention, the specific process of obtaining the physiological health index corresponding to the end of the current medication course for the current patient is as follows: Based on the pulse rate corresponding to the end of the current medication course of the current patient, abnormal pulse condition analysis is performed to obtain the abnormal pulse condition degree corresponding to the end of the current medication course of the current patient.

[0105] Please refer to Figure 3 As shown, it should be noted that the specific process of obtaining the abnormal pulse condition degree corresponding to the end of the current medication course for the current patient is as follows: The pulse rate corresponding to the end of the current medication course of the current patient is compared with the pulse rate range of normal people under normal conditions stored in the database. If the pulse rate corresponding to the end of the current medication course of the current patient is within the pulse rate range of normal people under normal conditions, the abnormal pulse condition degree corresponding to the end of the current medication course of the current patient is recorded as 0. If the pulse rate corresponding to the end of the current medication course of the current patient is not within the pulse rate range of normal people under normal conditions, the abnormal pulse condition degree corresponding to the end of the current medication course of the current patient is recorded as 1. Thus, the abnormal pulse condition degree corresponding to the end of the current medication course of the current patient is obtained, and the value is 0 or 1.

[0106] In a specific embodiment of the present invention, the pulse rate range of normal people under normal conditions is 60 - 100 beats per minute.

[0107] Based on the tongue coating picture corresponding to the end of the current medication course of the current patient, abnormal tongue coating color analysis is performed to obtain the abnormal tongue coating color degree corresponding to the end of the current medication course of the current patient.

[0108] It should be noted that the specific method of obtaining the abnormal tongue coating color degree corresponding to the end of the current medication course for the current patient is as follows: Extract the RGB values from the tongue coating picture corresponding to the end of the current medication course of the current patient, and mark them respectively as 、 and .

[0109] Extract the RGB values from the tongue coating pictures of normal people under normal conditions from the database, and mark them respectively as 、 and .

[0110] Calculate the abnormal tongue coating color degree corresponding to the end of the current medication course for the current patient , .

[0111] It should be further noted that the design idea of the above abnormal tongue coating color degree calculation formula is as follows: Using the RGB color model to convert the tongue coating color into a computable value ( 、 and ), by comparing with the RGB standard values of the tongue coating of normal people ( , and ), the degree of color abnormality of the current tongue coating is quantified. The difference of each color channel is divided by 256 to normalize the difference range to (0 - 1), eliminate the dimensional difference of the RGB channels, and calculate the distance between the current tongue coating and the normal tongue coating in the three-dimensional color space. The greater the distance, the higher the degree of color abnormality.

[0112] Comprehensively analyze the pulse abnormality degree and the tongue coating color abnormality degree corresponding to the end of the current medication course of the current patient to obtain the physiological health index corresponding to the end of the current medication course of the current patient.

[0113] It should be noted that the specific method for obtaining the physiological health index corresponding to the end of the current medication course of the current patient is as follows: The pulse abnormality degree and the tongue coating color abnormality degree corresponding to the end of the current medication course of the current patient are weighted and calculated respectively with the corresponding proportion weights and then summed up to obtain the physiological abnormality degree corresponding to the end of the current medication course of the current patient. The physiological abnormality degree is used as the power and substituted into the exponential function with as the base to obtain the physiological health index corresponding to the end of the current medication course of the current patient.

[0114] It should be further noted that the meaning of substituting the physiological abnormality degree as the power into the exponential function with as the base is to ensure that the physiological abnormality degree is negatively correlated with the physiological health index and at the same time ensure that the value of the physiological health index is always greater than 0.

[0115] In a specific embodiment of the present invention, when calculating the physiological abnormality degree corresponding to the end of the current medication course of the current patient, the corresponding proportions of the pulse abnormality degree and the tongue coating color abnormality degree are equally important. Therefore, the corresponding proportion weights of the pulse abnormality degree and the tongue coating color abnormality degree are 0.5 and 0.5 respectively.

[0116] Based on the quality information of various Chinese medicinal materials in the target traditional Chinese medicine pharmacy after the end of the current medication course, analyze the quality qualification degrees of various Chinese medicinal materials after the end of the current medication course in the same way as the analysis method of the quality qualification degree of various Chinese medicinal materials.

[0117] It should be noted that the acquisition method of the quality information of various Chinese medicinal materials after the end of the current medication course is the same as the quality information acquisition method mentioned above, and will not be elaborated here.

[0118] Based on the physiological health index corresponding to the end of the current medication course of the current patient and the quality qualification degrees of various Chinese medicinal materials after the end of the current medication course, conduct an optimization analysis to obtain the dosages of various Chinese medicinal materials that the current patient needs to take in the next medication course.

[0119] It should be noted that the specific formula for obtaining the dosages of various traditional Chinese medicinal materials required for the current patient in the next medication course is as follows: , where represents the dosage of the -th type of traditional Chinese medicinal material required for the current patient in the next medication course, represents the initial dosages of various traditional Chinese medicinal materials required for the current patient, and respectively represent the physiological health index corresponding to the end of the current medication course of the current patient and the set reference physiological health index, and respectively represent the quality qualification degree of various traditional Chinese medicinal materials after the end of the current medication course and the set reference quality qualification degree, represents the dosage to be adjusted corresponding to the deviation of the unit quality qualification degree of various traditional Chinese medicinal materials stored in the database, represents the number of various traditional Chinese medicinal materials, .

[0120] In the embodiment of the present invention, the prescription is dynamically adjusted by combining physiological parameters. The physiological health index is comprehensively calculated through the abnormal pulse rate and the abnormal tongue coating color. The dosage optimization in the next course takes into account the real-time quality of the medicinal materials and the feedback of the patient's curative effect at the same time, forming a "monitoring - adjustment" closed loop, improving the effective rate of the course, and realizing the dynamic adjustment of the traditional Chinese medicinal material formula.

[0121] It should be noted that: for the formulas mentioned above, through the principle of dimensional consistency and mathematical standardization means (such as normalization processing, dimensionless parameter conversion or unit system unification), physical quantities with different attributes can be translated into dimensionless standard values or superimposable parameters with the same dimension, so as to eliminate the interference of different dimensions on the operation logic, and make the formula have mathematical operation rationality and objective law adaptability while retaining the original data distribution characteristics. The above is only an exemplary embodiment of the present invention and cannot be used to limit the scope of the present invention.

[0122] The above content is only an example and explanation of the concept of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. An AI-assisted diagnosis and treatment system for intelligent identification and formula optimization of traditional Chinese medicinal materials, characterized in that, Including: A symptom similarity acquisition module, which extracts the types of diseases and various symptoms suffered by the current patient input into the AI diagnosis and treatment platform of the target traditional Chinese medicine pharmacy, and extracts the various symptoms corresponding to each historical patient with the same type of disease in the historical database of the AI diagnosis and treatment platform, and thereby obtains the symptom vector similarity between the current patient and each historical patient; A basic dosage confirmation module, which extracts the traditional Chinese medicine taking information of each historical patient, and based on the symptom vector similarity, confirms the types of traditional Chinese medicines required for the current patient and the basic dosages of various traditional Chinese medicines; A traditional Chinese medicine quality identification module, which starts the automatic medicine grabbing machine of the target traditional Chinese medicine pharmacy and collects the quality information of various traditional Chinese medicines through it, and uses a multi-modal data fusion algorithm to obtain the quality qualification degree of various traditional Chinese medicines; A traditional Chinese medicine formula optimization module, which adjusts the initial dosages of various traditional Chinese medicines required for the current patient based on the basic dosages and quality qualification degrees of various traditional Chinese medicines; A formula dynamic adjustment module, which collects the real-time physiological parameters corresponding to the end of the current medication course of the current patient, and collects the quality information of various traditional Chinese medicines in the target traditional Chinese medicine pharmacy after the end of the current medication course, and thereby optimizes the dosages of various traditional Chinese medicines required for the current patient in the next medication course.

2. The intelligent identification and formula optimization AI-assisted diagnosis and treatment system for traditional Chinese medicines according to claim 1, wherein: The specific process of obtaining the symptom vector similarity between the current patient and each historical patient is as follows: Summarize all the symptoms that appear corresponding to all historical patients and the current patient with the same type of disease in the historical database of the AI diagnosis and treatment platform to form a symptom set; Based on the symptom set, use one-hot encoding to generate the symptom vector corresponding to the disease suffered by the current patient and the symptom vectors corresponding to each historical patient; Based on the symptom vector corresponding to the disease suffered by the current patient and the symptom vectors corresponding to each historical patient, perform cosine similarity calculation to obtain the symptom vector similarity between the current patient and each historical patient.

3. The AI-assisted diagnosis and treatment system for intelligent identification and formula optimization of traditional Chinese medicine according to claim 1, characterized in that: The specific process of confirming the types of traditional Chinese medicines required for the current patient is as follows: Compare the symptom vector similarity between the current patient and each historical patient with the set reference symptom vector similarity. If the symptom vector similarity between the current patient and a certain historical patient is greater than or equal to the set reference symptom vector similarity, then record this historical patient as a highly similar patient, and thus screen out each highly similar patient corresponding to the current patient; Extract the types of traditional Chinese medicines and the initial dosages of various traditional Chinese medicines taken by each highly similar patient from the traditional Chinese medicine taking information of each historical patient; Count the number of occurrences of various traditional Chinese medicines, and take the ratio between the number of occurrences of various traditional Chinese medicines and the number of highly similar patients as the frequency of occurrence of various traditional Chinese medicines; Compare the frequency of occurrence of various traditional Chinese medicines with the set reference frequency of occurrence of traditional Chinese medicines. If the frequency of occurrence of a certain type of traditional Chinese medicine is greater than or equal to the set reference frequency of occurrence of traditional Chinese medicines, then record this type of traditional Chinese medicine as the target traditional Chinese medicine, and thus obtain the types of target traditional Chinese medicines, and use them as the types of traditional Chinese medicines required for the current patient.

4. The intelligent identification and formula optimization AI-assisted diagnosis and treatment system for traditional Chinese medicine according to claim 3, characterized in that: The specific method for confirming the basic dosages of various traditional Chinese medicines required for the current patient is as follows: Extract the initial dosages of various traditional Chinese medicines required for the current patient that appear each time from the initial dosages of various traditional Chinese medicines taken by each highly similar patient, and calculate their average value. Take the calculation result as the basic dosage of various traditional Chinese medicines required for the current patient.

5. The AI-assisted diagnosis and treatment system for intelligent identification and formula optimization of traditional Chinese medicine according to claim 1, wherein: The specific process for obtaining the quality qualification degrees of various traditional Chinese medicines by using the multi-modal data fusion algorithm is as follows: Perform color processing on the grayscale images in the quality information of various traditional Chinese medicines to obtain the color qualification degrees of various traditional Chinese medicines; Perform coupling analysis based on each eigenvalue in the odor component spectrum of various traditional Chinese medicines and each characteristic standard value in the standard component spectra of various traditional Chinese medicines stored in the database to obtain the odor qualification degrees of various traditional Chinese medicines; Perform weighted calculation and summation on the color qualification degrees and odor qualification degrees of various traditional Chinese medicines with corresponding weights to obtain the quality qualification degrees of various traditional Chinese medicines.

6. The AI-assisted diagnosis and treatment system for intelligent identification and formula optimization of traditional Chinese medicine according to claim 5, wherein: The specific method for obtaining the color qualification degrees of various traditional Chinese medicines is as follows: Extract the grayscale values corresponding to each grayscale region from the grayscale images of various traditional Chinese medicines, and compare them with the grayscale value intervals corresponding to various traditional Chinese medicines under standard conditions stored in the database; If the grayscale value corresponding to a certain grayscale region of a certain traditional Chinese medicine is not within the grayscale value interval corresponding to it under standard conditions, then mark this grayscale region of this traditional Chinese medicine as an abnormal region, and count the number of abnormal regions of various traditional Chinese medicines; Count the number of grayscale regions corresponding to various traditional Chinese medicines from the grayscale images of various traditional Chinese medicines, and record the ratio between the number of abnormal regions and the number of grayscale regions of various traditional Chinese medicines as the abnormal region ratio of various traditional Chinese medicines; Take the ratio of the difference between the set reference abnormal region ratio and the abnormal region ratio of various traditional Chinese medicines to the set reference abnormal region ratio, and take the ratio result as the color qualification degree of various traditional Chinese medicines.

7. The intelligent identification and formula optimization AI-assisted diagnosis and treatment system for traditional Chinese medicine according to claim 5, characterized in that: The specific process for obtaining the odor qualification degrees of various traditional Chinese medicines is as follows: Combine each eigenvalue in the odor component spectrum of various traditional Chinese medicines into a multi-dimensional vector as the multi-dimensional characteristic vector of various traditional Chinese medicines; Combine each characteristic standard value in the standard component spectra of various traditional Chinese medicines stored in the database into a multi-dimensional vector as the standard characteristic vector of various traditional Chinese medicines; Obtain the Euclidean distance between the multi-dimensional characteristic vector and the standard characteristic vector of various traditional Chinese medicines; Perform calculations based on the Euclidean distance between the multi-dimensional characteristic vector and the standard characteristic vector of various traditional Chinese medicines to obtain the odor qualification degrees of various traditional Chinese medicines.

8. The AI-assisted diagnosis and treatment system for intelligent identification and formula optimization of traditional Chinese medicine according to claim 1, wherein: The specific process for adjusting the initial dosages of various traditional Chinese medicines required for the current patient is as follows: Compare the quality qualification degrees of various traditional Chinese medicines with the set reference quality qualification degree. If the quality qualification degree of a certain traditional Chinese medicine is greater than the set reference quality qualification degree, then mark this traditional Chinese medicine as a high-quality medicine. If the quality qualification degree of a certain traditional Chinese medicine is less than the set reference quality qualification degree, then mark this traditional Chinese medicine as a low-quality medicine. If the quality qualification degree of a certain traditional Chinese medicine is equal to the set reference quality qualification degree, then mark this traditional Chinese medicine as a standard-quality medicine; If a certain type of traditional Chinese medicine required by the current patient is a standard-quality medicine, the basic dose of this type of traditional Chinese medicine remains unchanged; If a certain type of traditional Chinese medicine required by the current patient is a high-quality medicine, obtain the difference between the quality compliance of this type of traditional Chinese medicine and the set reference quality compliance, and take the product of the difference and the adjustment dose corresponding to the unit quality compliance deviation of this type of traditional Chinese medicine stored in the database as the required reduction dose of this type of traditional Chinese medicine. Take the difference between the basic dose and the required reduction dose as the initial dose of this type of traditional Chinese medicine; If a certain type of traditional Chinese medicine required by the current patient is a low-quality medicine, obtain the difference between the set reference quality compliance and the quality compliance of this type of traditional Chinese medicine, and take the product of the difference and the adjustment dose corresponding to the unit quality compliance deviation of this type of traditional Chinese medicine stored in the database as the required increase dose of this type of traditional Chinese medicine. Take the sum of the basic dose and the required increase dose as the initial dose of this type of traditional Chinese medicine; In summary, obtain the initial doses of various types of traditional Chinese medicine required by the current patient.

9. The intelligent identification and formula optimization AI-assisted diagnosis and treatment system for traditional Chinese medicine according to claim 5, characterized in that: The specific process of optimizing the doses of various types of traditional Chinese medicine required by the current patient in the next medication course is as follows: Based on the pulse rate and tongue coating image in the real-time physiological parameters corresponding to the end of the current medication course of the current patient, perform fusion processing to obtain the physiological health index corresponding to the end of the current medication course of the current patient; Based on the quality information of various types of traditional Chinese medicine in the target Chinese medicine pharmacy after the end of the current medication course, analyze the quality compliance of various types of traditional Chinese medicine after the end of the current medication course in the same way as the analysis method of the quality compliance of various types of traditional Chinese medicine; Based on the physiological health index corresponding to the end of the current medication course of the current patient and the quality compliance of various types of traditional Chinese medicine after the end of the current medication course, perform optimization analysis to obtain the doses of various types of traditional Chinese medicine required by the current patient in the next medication course.

10. The intelligent identification and formula optimization AI-assisted diagnosis and treatment system for traditional Chinese medicine according to claim 9, characterized in that: The specific process of obtaining the physiological health index corresponding to the end of the current medication course of the current patient is as follows: Based on the pulse rate corresponding to the end of the current medication course of the current patient, perform abnormal pulse analysis to obtain the abnormal pulse degree corresponding to the end of the current medication course of the current patient; Based on the tongue coating image corresponding to the end of the current medication course of the current patient, perform abnormal tongue coating color analysis to obtain the abnormal tongue coating color degree corresponding to the end of the current medication course of the current patient; Perform comprehensive analysis on the abnormal pulse degree and abnormal tongue coating color degree corresponding to the end of the current medication course of the current patient to obtain the physiological health index corresponding to the end of the current medication course of the current patient.

Images