Intelligent recommendation method and system for Chinese medicine compatibility

Abstract

The present invention relates to the field of intelligent drug compatibility technology, specifically to an intelligent recommendation method and system for Chinese medicine compatibility, which includes the following steps: collating various basic attributes of Chinese medicine properties, meridians, and historical use cases into a database, simulating the interaction of multiple drug combinations, and recording the changes caused by drug interactions, and constructing a drug information record table. The present invention, by introducing a constraint-based reasoning algorithm, can define clear drug compatibility rules and conditional constraints, thereby identifying the best recommendations among many possible drug combinations. The algorithm effectively screens out drug combinations that meet clinical guidelines and pharmacological principles by simulating the thinking process of medical experts, while automatically excluding those combinations that may cause adverse interactions or violate treatment principles. Not only does it improve the accuracy and safety of drug selection, but it also enhances treatment efficiency and reliability.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent drug compatibility, and in particular to an intelligent recommendation method and system for traditional Chinese medicine compatibility. Background Art

[0002] Intelligent drug compatibility technology uses artificial intelligence, machine learning, big data analysis and other technologies to analyze and recommend the best drug compatibility scheme. It combines the drug compatibility principles of traditional Chinese medicine with modern computing technology to improve the efficiency and accuracy of drug compatibility. Through intelligent algorithms, historical treatment data, drug properties and patient characteristics are analyzed to optimize drug combinations to enhance efficacy and reduce side effects.

[0003] The intelligent recommendation method for TCM drug compatibility is a method of recommending TCM drug compatibility in an intelligent way through artificial intelligence and data analysis. By analyzing a large amount of TCM drug compatibility data, pharmacodynamic principles and the specific conditions of the patient, the drug compatibility scheme that best suits the patient's current condition is automatically recommended. This reduces the cost of trial and error, speeds up the realization of treatment effects, and also provides technical support for precision medicine in TCM.

[0004] Although existing technologies have achieved remarkable results in the field of drug compatibility and improved the efficiency and accuracy of drug compatibility, there are still some limitations. For example, in dealing with the prediction and analysis of complex drug interactions, there is a lack of sufficient flexibility and adaptability. In the face of variable biological mechanisms and individual differences among patients, it is difficult to fully capture and accurately predict the dynamic changes of interactions. In addition, although existing technologies can analyze the immediate effects of drug compatibility, they are not mature enough in predicting the effects of drug compatibility over time, which limits their application in long-term treatment planning and adjustment. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method and system for intelligently recommending Chinese medicine compatibility.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a method for intelligent recommendation of Chinese medicine compatibility comprises the following steps;

[0007] S1: Organize the basic properties of Chinese medicine, such as nature and flavor, meridians, and historical use cases, into the database, simulate the interaction of multiple drug combinations, record the changes caused by drug interactions, and construct a drug information record table;

[0008] S2: Based on the drug information record table, screening drug combinations with synergistic effects and excluding drug combinations with antagonistic effects, to generate a synergistic drug combination catalog;

[0009] S3: Analyze the combinations in the synergistic drug combination catalog, refer to the effects of dosage and frequency of use on the compatibility effect, record the compatibility under various dosages and frequencies, and establish a dosage and frequency recommendation matrix;

[0010] S4: Based on the dose and frequency recommendation matrix, analyze the impact of environmental conditions on drug compatibility, record drug interactions under environmental changes, and formulate environmental condition adjustment recommendations;

[0011] S5: Combine the environmental condition adjustment suggestions with clinical case data to analyze the compatibility effects under various environmental conditions and dosage frequencies, extract key data, and construct a drug compatibility effect analysis model;

[0012] S6: Use the drug compatibility effect analysis model to analyze the law of drug compatibility effect changes with treatment time, record the influence of seasonal changes and various time factors of treatment cycle, and establish a drug compatibility and time effect analysis model.

[0013] The present invention has the following improvements: the drug information record table includes the nature, flavor, meridians, mutual promotion and restraint information of the drug and compatibility examples based on historical documents; the synergistic drug combination catalog includes adjusted drug ratios, synergistic drug pairs and excluded antagonistic drug pairs; the dosage and frequency recommendation matrix includes dosage ranges of multiple drug combinations, recommended usage frequencies and analysis of the effects of dosage and frequency on compatibility effects; the environmental condition adjustment suggestions include the adjustment range of ambient temperature, optimization measures for humidity levels and drug compatibility suggestions under specified storage conditions; the drug compatibility effect analysis model includes predictions of compatibility effects under multiple environmental conditions, compatibility suggestions after dosage and frequency optimization and clinical case analysis results; the drug compatibility and time effect analysis model includes research on the effects of treatment cycles on compatibility effects, correlation analysis between seasonal changes and drug compatibility and examples of compatibility optimization after time adjustment.

[0014] The present invention has improved the following steps: arranging the basic properties of Chinese medicine, such as nature and taste, meridians, and historical use cases, simulating the interaction of multiple drug combinations, and recording the changes caused by drug interactions. The specific steps of constructing the drug information record table are as follows;

[0015] S101: Organize the basic properties of Chinese medicine, such as nature and flavor, meridians, and historical use cases, into a database, record the changes caused by drug interactions, and obtain a drug property database through data entry and classification management;

[0016] S102: Based on the drug attribute database, referring to the nature, taste, meridians and interaction records of the drugs in historical use cases, simulating the interaction of multiple drug combinations, identifying and recording the synergistic or antagonistic effects between drugs, and generating a drug interaction simulation record;

[0017] S103: Based on the drug interaction simulation record, iteratively optimize the data analysis process, generate a drug information record table through detailed analysis of the drug interaction, combined with the basic properties of the drugs and the simulated interaction effects.

[0018] The present invention is improved in that, based on the drug information record table, drug combinations with synergistic effects are screened and drug combinations with antagonistic effects are excluded. The specific steps of generating a synergistic drug combination catalog are as follows:

[0019] S201: Based on the drug information record table, a constraint satisfaction problem algorithm is used to comprehensively analyze the synergistic and antagonistic effects between drug combinations, exclude drug combinations with antagonistic effects, and mark combinations with synergistic effects to generate initial drug combination screening results;

[0020] The constraint satisfaction problem algorithm is based on Formula I:

[0021] C i =(X A ·X B ·W AB )∨(X C ·W C )∨(X D ·W D )

[0022] Calculate the synergistic and antagonistic effects between drug combinations and generate initial drug combination screening results;

[0023] Among them, C i is a Boolean value representing whether drug combination i has synergistic or antagonistic effects, X A represents the comprehensive properties of drug A, X B represents the comprehensive properties of drug B, X C represents the comprehensive properties of drug C, X D represents the comprehensive properties of drug D, W AB is the weight coefficient representing the interaction between drugs A and B, which is determined through the study and evaluation of the interaction between drugs A and B. C is the weight coefficient representing drug C, which is determined by analyzing the clinical effect data and pharmacological properties of drug C. D is the weight coefficient representing drug D, which is determined by comprehensively referring to the safety, side effect level and historical use cases of drug D;

[0024] S202: Based on the initial drug combination screening results, the efficacy and safety of the screened drug combination are evaluated by adjusting the ratio, dosage, and frequency of use of the drug combination to generate drug combination efficacy and risk evaluation results;

[0025] S203: Based on the efficacy and risk assessment results of the drug combination, combined with current clinical needs and environmental factors, refine the selection and adjustment of the drug combination and generate a synergistic drug combination catalog.

[0026] The present invention is improved in that the combinations in the synergistic drug combination catalog are analyzed, the effects of the dosage and the frequency of use on the compatibility effect are referred to, the compatibility conditions under various dosages and frequencies are recorded, and the specific steps of establishing a dosage and frequency recommendation matrix are as follows;

[0027] S301: Analyze each drug combination in the synergistic drug combination catalog, and record the compatibility effects under various dosages and usage frequencies, including collecting the effect data of each drug combination under various dosage levels and the influence of various usage frequencies on the treatment effect, and generate a drug compatibility and dosage frequency relationship data set;

[0028] S302: Based on the drug compatibility and dosage frequency relationship data set, analyze the drug compatibility effects under various dosages and usage frequencies, identify the influence of dosage and frequency on the compatibility effect, and generate dosage and frequency optimization suggestions;

[0029] S303: Comprehensively analyze and adjust the dosage and frequency optimization suggestions, and generate a dosage and frequency recommendation matrix with reference to individual differences of patients and drug combination requirements.

[0030] The present invention has the following improvements: based on the dosage and frequency recommendation matrix, the influence of environmental conditions on drug compatibility is analyzed, drug interactions under environmental changes are recorded, and specific steps for formulating environmental condition adjustment suggestions are as follows;

[0031] S401: Based on the dosage and frequency recommendation matrix, collect and analyze the variation data of drug compatibility effects under various environmental conditions, including the effects of ambient temperature, humidity and storage conditions on drug interactions, and generate an environmental factor impact analysis data set;

[0032] S402: Analyze the environmental factor impact analysis data set, identify environmental variables that affect the drug compatibility effect, including a selected temperature or humidity range, determine the priority and direction of environmental adjustment, and generate an environmental adjustment priority analysis result;

[0033] S403: Based on the environmental adjustment priority analysis result, the environmental condition parameters that need to be adjusted are listed, and an adjustment plan is formulated, including setting temperature and humidity ranges, improving storage conditions, and related environmental adjustments, and generating environmental condition adjustment suggestions.

[0034] The present invention is improved in that the specific steps of combining the environmental condition adjustment suggestions with clinical case data, analyzing the compatibility effects under various environmental conditions and dosage frequencies, extracting key data, and constructing a drug compatibility effect analysis model are as follows;

[0035] S501: Collect the data in the environmental condition adjustment suggestions and the effect data of drug compatibility under various environmental conditions and dosage frequencies in clinical cases, including temperature, humidity, dosage, and frequency of use, to generate a drug compatibility clinical and environmental data set;

[0036] S502: Analyze the clinical and environmental data sets of drug compatibility, extract key variables that affect the effect of drug compatibility, including the dose-response relationship under specified environmental conditions, the effect of frequency of use on the effect, identify ways to optimize the effect of drug compatibility, and generate drug compatibility key variable analysis results;

[0037] S503: sorting out the key variables identified in the drug compatibility key variable analysis results, including environmental condition variables and dosage frequency variables, and constructing a drug compatibility effect analysis model based on the interaction of the variables and their impact on the compatibility effect.

[0038] The present invention is improved in that the drug compatibility effect analysis model is used to analyze the law of drug compatibility effect changes with treatment time, record the influence of seasonal changes and various time factors of treatment cycle, and the specific steps of establishing the drug compatibility and time effect analysis model are as follows;

[0039] S601: using the drug compatibility effect analysis model, inputting time variables in the treatment process, including treatment cycle, seasonal change data, applying hidden Markov model, simulating and analyzing the law of drug compatibility effect changes over time, including the changes in drug compatibility effect in multiple seasons, and the influence of treatment cycle on the effect, and generating time variable simulation analysis results;

[0040] The hidden Markov model, according to formula II:

[0041]

[0042] Calculate the time-varying patterns of drug combination effects and generate time-variable simulation analysis results;

[0043] Among them, P(S t |O 1：t , E) is in state S at time t under the observation sequence and environmental factor E t The probability of β is the normalization factor adjusted according to environmental factors and determined by environmental sensitivity analysis. t |S t , E) is the given state S under environmental factor Et Observed O t The probability, P(S t |S t-1 , E) is under environmental factor E, from state S t-1 Transfer to state S t The probability, P(S t-1 |O 1：t-1 , E) is in state S under environmental factors E and previous observations t-1 probability;

[0044] S602: Analyze the time variable simulation analysis results to identify the influence of time factors on the drug combination effect, including the enhancement or weakening of the drug combination effect by a specified season, the effect of the treatment cycle on the sustainability of the effect, and extract key data on the influence of time factors;

[0045] S603: Based on the key data affected by the time factor, by analyzing the patterns and trends in the data, setting analysis parameters, including the classification of time periods and seasonal effects, a drug compatibility and time effect analysis model is constructed.

[0046] An intelligent recommendation system for Chinese medicine compatibility, the system comprising:

[0047] The drug property analysis module analyzes the nature, flavor, meridians, and historical use cases of traditional Chinese medicine, extracts the key properties and potential therapeutic effects of the drugs, and organizes them into structured information to obtain a drug property information set;

[0048] The interaction prediction module performs interaction analysis between multiple drugs based on the drug property information set, including prediction of synergistic and antagonistic effects, and obtains interaction analysis results;

[0049] The synergistic recognition module screens drug combinations with synergistic potential based on the interaction analysis results, excludes potential antagonistic combinations, and generates a synergistic combination list;

[0050] The dosage frequency adjustment module performs dosage and usage frequency adjustment analysis based on the synergistic combination list, optimizes the dosage frequency combination according to the balance between therapeutic effect and safety, and establishes dosage frequency adjustment suggestions;

[0051] The environmental adaptability analysis module analyzes the influence of various environmental factors on the drug compatibility effect based on the dosage frequency adjustment suggestion, formulates matching environmental condition adjustment measures, and obtains environmental adjustment suggestions;

[0052] The compatibility effect analysis module combines the environmental adjustment suggestions with the current clinical case data to analyze the compatibility effects under various environmental conditions and dosage frequencies, optimizes the compatibility strategy, and obtains the compatibility effect optimization strategy;

[0053] The treatment cycle and seasonal adjustment module uses the above-mentioned compatibility effect optimization strategy to study the effect of treatment time including seasonal changes and treatment cycle on the compatibility effect, and puts forward suggestions for time adjustment of drug compatibility.

[0054] Compared with the prior art, the advantages and positive effects of the present invention are:

[0055] In the present invention, by introducing a constraint-based reasoning algorithm, clear drug compatibility rules and conditional constraints can be defined, thereby identifying the best recommendations among many possible drug combinations. The algorithm effectively screens drug combinations that comply with clinical guidelines and pharmacological principles by simulating the thinking process of medical experts, while automatically excluding those combinations that may cause adverse interactions or violate treatment principles. It not only improves the accuracy and safety of drug selection, but also enhances treatment efficiency and reliability. The effects of drug compatibility at different treatment stages and their dynamic changes over time are analyzed by hidden Markov models, providing doctors with in-depth data support. Effectively predict the changing trend of drug compatibility effects during treatment. Enable doctors to adjust drug compatibility recommendations based on the model's predictions to better adapt to patients' condition changes and treatment responses, especially in long-term or complex treatment plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flow chart of the intelligent recommendation method for TCM drug compatibility proposed by the present invention;

[0057] Figure 2 The present invention provides a detailed flow chart of step S1 in the intelligent recommendation method for TCM drug compatibility;

[0058] Figure 3 The present invention provides a detailed flow chart of step S2 in the intelligent recommendation method for TCM drug compatibility;

[0059] Figure 4 The present invention provides a detailed flow chart of step S3 in the intelligent recommendation method for TCM drug compatibility;

[0060] Figure 5 The present invention provides a detailed flow chart of step S4 in the intelligent recommendation method for TCM drug compatibility;

[0061] Figure 6 The present invention provides a detailed flow chart of step S5 in the intelligent recommendation method for TCM drug compatibility;

[0062] Figure 7 The present invention provides a detailed flow chart of step S6 in the intelligent recommendation method for TCM drug compatibility;

[0063] Figure 8A module diagram of an intelligent recommendation system for Chinese medicine compatibility is proposed for the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0065] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0066] Example

[0067] See also Figure 1 ,The present invention provides a technical solution: a method for intelligently recommending Chinese medicine compatibility, comprising the following steps;

[0068] S1: Organize the basic properties of Chinese medicine, such as nature and flavor, meridians, and historical use cases, into the database, simulate the interaction of multiple drug combinations, record the changes caused by drug interactions, and construct a drug information record table;

[0069] S2: Based on the drug information record table, screen drug combinations with synergistic effects, exclude drug combinations with antagonistic effects, and generate a synergistic drug combination catalog;

[0070] S3: Analyze the combinations in the synergistic drug combination catalog, refer to the effects of dosage and frequency of use on the compatibility effect, record the compatibility under various dosages and frequencies, and establish a dosage and frequency recommendation matrix;

[0071] S4: Based on the dose and frequency recommendation matrix, analyze the impact of environmental conditions on drug compatibility, record drug interactions under environmental changes, and formulate environmental condition adjustment recommendations;

[0072] S5: Combine the environmental condition adjustment suggestions with clinical case data to analyze the compatibility effects under various environmental conditions and dosage frequencies, extract key data, and construct a drug compatibility effect analysis model;

[0073] S6: Use the drug compatibility effect analysis model to analyze the changes in drug compatibility effects over treatment time, record the impact of seasonal changes and multiple time factors of the treatment cycle, and establish a drug compatibility and time effect analysis model.

[0074] The drug information record sheet includes the drug's nature, flavor, meridians, mutual promotion and restraint information, and compatibility examples based on historical documents. The synergistic drug combination catalog includes adjusted drug ratios, synergistic drug pairs, and excluded antagonistic drug pairs. The dosage and frequency recommendation matrix includes the dosage range of multiple drug compatibility, recommended frequency of use, and analysis of the impact of dosage and frequency on the compatibility effect. Environmental condition adjustment suggestions include the adjustment range of ambient temperature, optimization measures for humidity levels, and drug compatibility suggestions under specified storage conditions. The drug compatibility effect analysis model includes the prediction of compatibility effects under various environmental conditions, compatibility suggestions after dosage and frequency optimization, and clinical case analysis results. The drug compatibility and time effect analysis model includes research on the impact of treatment cycle on compatibility effect, correlation analysis between seasonal changes and drug compatibility, and examples of compatibility optimization after time adjustment.

[0075] See also Figure 2 , sort out the basic properties of Chinese medicine, such as nature and taste, meridians, and historical use cases, simulate the interaction of multiple drug combinations, and record the changes caused by drug interactions. The specific steps for constructing a drug information record table are as follows;

[0076] S101: Organize the basic properties of Chinese medicine, such as nature and taste, meridians, and historical use cases, into a database, record the changes caused by drug interactions, and obtain a drug property database through data entry and classification management.

[0077] Sub-step S101 is based on the information of the nature and flavor of traditional Chinese medicine, meridians, and historical use cases, and uses a relational database management system such as MySQL or Oracle to execute SQL commands to establish database tables, such as CREATE TABLE and INSERT, to determine the field type corresponding to each drug attribute, such as VARCHAR for text and INT for numeric values, to create a drug attribute database, and at the same time apply JOIN statements to realize the associated query of drug interaction data, and use UPDATE statements to update the interaction change records between drugs to generate a drug attribute database.

[0078] S102: Based on the drug attribute database, referring to the nature, taste, meridians and interaction records of the drugs in historical use cases, simulate the interaction of multiple drug combinations, identify and record the synergistic or antagonistic effects between drugs, and generate the specific process of drug interaction simulation records as follows;

[0079] Sub-step S102 is based on the drug attribute database and adopts rule-based reasoning algorithms such as the Rete algorithm to define a rule set for drug interactions, including the judgment logic for synergistic and antagonistic effects. For example, the rule for synergistic effect may be "if drug A and drug B both have certain properties and flavors, they are judged to be synergistic". A rule engine such as Drools or Jess is used to simulate and analyze drug combinations, perform operations matching the rule set, and record the matching results. At the same time, an analysis method based on historical data such as time series analysis is used to identify the usage patterns of drug combinations in historical cases and generate drug interaction simulation records.

[0080] S103: Based on the simulated records of drug interactions, the data analysis process is iteratively optimized. Through detailed analysis of drug interactions, combined with the basic properties of the drugs and the simulated interaction effects, the specific process of generating a drug information record table is as follows;

[0081] Sub-step S103 uses data mining techniques such as decision tree algorithm based on drug interaction simulation records, uses SciKit-Learn library to implement DecisionTreeClassifier class, defines parameters such as depth and branch conditions of decision tree, such as max_depth is set to 10, which means that the maximum depth of decision tree is 10 layers, executes training process through fit method, inputs drug attribute data and simulated interaction effect data, performs model training, uses predict method to execute the prediction function of the model, generates drug information record table through detailed analysis of drug interaction and combining basic properties of drugs.

[0082] See also Figure 3 ,Based on the drug information record table, screen the drug combinations with synergistic effects, and exclude the drug combinations with antagonistic effects.,The specific steps for generating the synergistic drug combination catalog are as follows;

[0083] S201: Based on the drug information record table, the constraint satisfaction problem algorithm is used to comprehensively analyze the synergistic and antagonistic effects between drug combinations, exclude drug combinations with antagonistic effects, and mark combinations with synergistic effects. The specific process for generating the initial drug combination screening results is as follows;

[0084] The S201 sub-step is based on the drug information record table and uses a constraint satisfaction problem algorithm, specifically a SAT (Boolean Satisfaction Problem) algorithm. This algorithm expresses the synergistic and antagonistic effects between drug combinations as Boolean expressions at the logical level, such as "a synergistic effect is produced when drug A and drug B exist at the same time" is expressed as A∧B. The Boolean expression is parsed through a logic solver such as MiniSat or Z3 to identify drug combinations that meet the conditions, such as the combination of drugs A and B, and exclude those drug combinations that do not meet the conditions, such as the combination of drugs C and D with antagonistic effects. The drug combinations that meet the conditions are marked to generate initial drug combination screening results.

[0085] The constraint satisfaction problem algorithm is as follows:

[0086] C i =(X A ·X B ·W AB )∨(X C ·W C )∨(X D ·W D )

[0087] Calculate the synergistic and antagonistic effects between drug combinations and generate initial drug combination screening results;

[0088] Among them, C i is a Boolean value representing whether drug combination i has synergistic or antagonistic effects. A represents the comprehensive attributes of drug A, such as nature, taste, meridian, efficacy category and side effect level. B represents the comprehensive properties of drug B. C represents the comprehensive properties of drug C. D represents the comprehensive properties of drug D. AB represents the weight coefficient of the interaction between drugs A and B, which is determined through the study and evaluation of the interaction between drugs A and B. C represents the weight coefficient of drug C, which is determined by analyzing the clinical effect data and pharmacological properties of drug C, reflecting its relative importance in the drug combination. D is the weight coefficient representing drug D, which is determined by comprehensively referring to the safety, side effect level and historical use cases of drug D, reflecting its relative importance in the drug combination;

[0089] The execution process is as follows:

[0090] Collect comprehensive attribute data of the drugs A, B, C, and D involved, including nature and taste, meridians, efficacy category, and side effect level.

[0091] For each drug combination i, calculate its Boolean value C based on the collected data and the determined weight coefficient i , including the comprehensive attribute value X of each drug A , X B , X C , X D , and its corresponding weight coefficient W AB , W C , W D The results are then multiplied and subjected to a logical operation to determine whether the drug combination produces a synergistic or antagonistic effect.

[0092] The calculated Boolean value C for each drug combination i , generate initial drug combination screening results. The results will indicate which drug combinations have potential synergistic effects and which may produce antagonistic effects, thus providing an important basis for subsequent drug compatibility.

[0093] S202: Based on the initial drug combination screening results, the efficacy and safety of the screened drug combination are evaluated by adjusting the ratio, dosage, and frequency of use of the drug combination. The specific process for generating the drug combination efficacy and risk evaluation results is as follows;

[0094] The S202 sub-step performs a multi-parameter optimization process based on the initial drug combination screening results, specifically using a genetic algorithm that simulates the selection, crossover, and mutation mechanisms in the biological evolution process, defines the proportion, dosage, and frequency of use of the drug combination as the genes of the chromosome, and sets a fitness function to evaluate the efficacy and safety of the drug combination. For example, a drug combination with high efficacy and low side effects has a higher fitness. A genetic algorithm framework such as DEAP is used to iteratively generate a new generation of drug combinations, evaluate the efficacy and safety of the combination, and generate drug combination efficacy and risk assessment results.

[0095] S203: Based on the results of drug combination efficacy and risk assessment, combined with current clinical needs and environmental factors, the specific process of refining the selection and adjustment of drug combinations and generating a synergistic drug combination catalog is as follows;

[0096] Based on the results of drug combination efficacy and risk assessment, sub-step S203 adopts a multi-criteria decision analysis method, specifically the analytic hierarchy process. By constructing a hierarchical model, clinical needs and environmental factors are used as evaluation criteria, the relative importance of the evaluation criteria is defined, and the importance of the criteria is quantified through a pairwise comparison matrix. Hierarchical analysis tools such as Expert Choice are used to evaluate different drug combinations, compare the degree to which they meet clinical needs and adapt to environmental factors, refine the selection of the most suitable drug combination, and make necessary adjustments to generate a catalog of synergistic drug combinations.

[0097] See also Figure 4 , analyze the combinations in the synergistic drug combination catalog, refer to the dosage, and the effect of the frequency of use on the compatibility effect, record the compatibility under various dosages and frequencies, and establish the dosage and frequency recommendation matrix. The specific steps are as follows;

[0098] S301: Analyze each drug combination in the synergistic drug combination catalog, and record the compatibility effects under various dosages and usage frequencies, including collecting the effect data of each drug combination under various dosage levels and the influence of various usage frequencies on the treatment effect. The specific process of generating a drug compatibility and dosage frequency relationship data set is as follows;

[0099] Sub-step S301 uses statistical analysis methods, specifically analysis of variance, based on the catalog of synergistic drug combinations. By comparing the therapeutic effects of drug combinations at different doses and frequencies of use, the statistical differences are identified. Statistical software such as SPSS or R is used to execute analysis of variance functions. For example, the aov() function is used in R to input data on multiple dose levels and frequencies of use, such as low, medium, and high doses, and low, medium, and high frequencies of use. The F statistic and the corresponding p-value are calculated to determine whether the effects of dose and frequency on the effect of the combination are significant. The effect data of each drug combination under the conditions are collected to generate a data set on the relationship between drug combination and dose frequency.

[0100] S302: Based on the drug compatibility and dosage frequency relationship data set, analyze the drug compatibility effects under various dosages and usage frequencies, identify the influence of dosage and frequency on the compatibility effect, and generate dosage and frequency optimization suggestions. The specific process is as follows;

[0101] Sub-step S302 uses a linear regression analysis method based on the drug compatibility and dosage frequency relationship data set to predict the compatibility effect under different doses and frequencies by constructing a relationship model between dose and frequency of use and the drug compatibility effect. Data analysis tools such as Python's SciPy or Pandas library are used to execute linear regression analysis functions. For example, the stats.linregress() function is used in Python to input the dose and frequency data and the corresponding drug compatibility effect data. By calculating the regression coefficient and correlation, the influence of dose and frequency on the compatibility effect is identified, and dose and frequency optimization suggestions are generated.

[0102] S303: The specific process of comprehensively analyzing and adjusting the dosage and frequency optimization suggestions, referring to the individual differences of patients and the drug combination requirements, and generating the dosage and frequency recommendation matrix is ​​as follows;

[0103] The S303 sub-step optimizes the dosage and frequency recommendations, conducts comprehensive analysis and adjustments, and uses a decision support system. This tool combines multiple decision analysis models and user interfaces to support the resolution of complex decision problems, defines the possible range of dosage and frequency, such as dosage from minimum to maximum, and frequency from once a day to multiple times a day, inputs data on individual patient differences, such as age, weight, medical history, and specific requirements for drug combinations, such as treatment goals and expected effects, and uses the decision model of the DSS tool to comprehensively analyze the data, adjust the dosage and frequency selection, and generate a dosage and frequency recommendation matrix.

[0104] See also Figure 5 , based on the dose and frequency recommendation matrix, analyze the impact of environmental conditions on drug compatibility, record drug interactions under environmental changes, and formulate specific steps for environmental condition adjustment recommendations as follows;

[0105] S401: Based on the dose and frequency recommendation matrix, collect and analyze the changing data of drug compatibility effects under various environmental conditions, including the effects of ambient temperature, humidity and storage conditions on drug interactions. The specific process of generating the environmental factor impact analysis data set is as follows;

[0106] Sub-step S401 collects data on changes in drug compatibility effects under environmental conditions based on the dose and frequency recommendation matrix. It uses data acquisition software such as LabVIEW or Matlab to collect data on environmental temperature, humidity, and storage conditions. For example, it uses temperature and humidity sensors to obtain environmental data in real time. It uses the recording function of data acquisition software, such as Matlab's DataAcquisition Toolbox, to record real-time data and associate the data with drug compatibility information. For example, it creates an association table between environmental conditions and drug compatibility in a database, combines environmental condition data with drug compatibility data through SQL JOIN queries, analyzes the effects of environmental temperature, humidity, and storage conditions on drug interactions, and generates an environmental factor impact analysis data set.

[0107] S402: Analyze the environmental factor impact analysis data set, identify environmental variables that affect the drug compatibility effect, including the selected temperature or humidity range, determine the priority and direction of environmental adjustment, and generate the specific process of the environmental adjustment priority analysis result as follows;

[0108] Sub-step S402 uses a cluster analysis method based on the environmental factors to analyze the data set, specifically K-means clustering. Through data analysis tools such as Python's SciKit-Learn library, the K-means algorithm is executed to define the number of clusters. For example, setting the K value to 3 means dividing the data into three categories. The environmental condition data is input and the data is divided into different groups through cluster analysis. It is identified which environmental conditions have the greatest impact on the drug compatibility effect. For example, the drug compatibility effect of the group with higher temperature is significantly different. The priority and adjustment direction of the environmental variables are determined. For example, temperature adjustment takes precedence over humidity adjustment. The environmental adjustment priority analysis results are generated.

[0109] S403: Based on the results of the environmental adjustment priority analysis, the environmental condition parameters that need to be adjusted are listed, and an adjustment plan is formulated, including setting temperature and humidity ranges, improving storage conditions, and related environmental adjustments. The specific process of generating environmental condition adjustment suggestions is as follows;

[0110] Based on the results of the environmental adjustment priority analysis, sub-step S403 develops an environmental condition adjustment plan, uses project management tools such as Microsoft Project, lists the environmental condition parameters that need to be adjusted, such as the setting range of temperature and humidity, and specific measures to improve storage conditions, and arranges adjustment steps and schedules through the Project's planning function, including setting specific values ​​for the temperature and humidity range, such as controlling the temperature at 20°C to 25°C and the humidity at 40% to 60%, and makes suggestions for improving storage conditions, such as using a constant temperature and humidity storage cabinet, plans related environmental adjustment activities, and generates environmental condition adjustment suggestions.

[0111] See also Figure 6 ,Combining environmental condition adjustment suggestions with clinical case data, analyzing the compatibility effects under various environmental conditions and dosage frequencies, extracting key data, and constructing a drug compatibility effect analysis model are as follows;

[0112] S501: Collect data from environmental condition adjustment suggestions and data from clinical cases on the effects of drug combinations under various environmental conditions and dosage frequencies, including temperature, humidity, dosage, and frequency of use. The specific process for generating drug combination clinical and environmental data sets is as follows;

[0113] Sub-step S501 performs clinical case data collection based on environmental condition adjustment recommendations, and uses a database management system such as MySQL or Oracle to extract temperature, humidity, dosage, and frequency of use information related to drug compatibility from different data tables through SQL query statements such as SELECT and JOIN, including but not limited to specific numerical ranges, such as temperature from 15°C to 30°C, humidity from 30% to 70%, dosage from low to high levels, and frequency of use from once a day to multiple times a day. By integrating data, including the relationship between temperature, humidity and drug compatibility effects, as well as the effects of dosage and frequency on therapeutic effects, a drug compatibility clinical and environmental data set is generated.

[0114] S502: Analyze the clinical and environmental data sets of drug compatibility, extract key variables that affect the effect of drug compatibility, including the dose-response relationship under specified environmental conditions, the effect of frequency of use on the effect, identify ways to optimize the effect of drug compatibility, and generate the specific process of drug compatibility key variable analysis results as follows;

[0115] Sub-step S502 performs key variable extraction based on the drug compatibility clinical and environmental data sets, uses data mining tools such as Python's Pandas library, and analyzes the dose-response relationship and the impact of frequency of use on the effect through data analysis functions such as DataFrame's describe() and corr(), including calculating the correlation between variables, such as the correlation coefficient between dose and therapeutic effect, and the correlation coefficient between frequency and therapeutic effect, identifying key variables that affect the effect of drug compatibility, such as a specific dose range or a specific frequency of use, and generating drug compatibility key variable analysis results.

[0116] S503: Sorting out the key variables identified in the results of the drug compatibility key variable analysis, including environmental condition variables and dosage frequency variables, and constructing a drug compatibility effect analysis model based on the interaction of the variables and their impact on the compatibility effect. The specific process is as follows;

[0117] The S503 sub-step sorts out the analysis results of the key variables of drug compatibility, executes the construction of the drug compatibility effect analysis model, uses a machine learning framework such as SciKit-Learn, through regression analysis or decision tree models, such as using the LinearRegression or DecisionTreeRegressor class, defines the parameters of the model, such as setting the max_depth parameter in the decision tree model to control the model complexity, inputs the key variable data of drug compatibility, such as environmental condition variables and dosage frequency variables, and trains the model based on the interaction of variables and their impact on the compatibility effect, such as using the fit() method for model training, and using the predict() method for effect prediction, to build a drug compatibility effect analysis model.

[0118] See also Figure 7 ,Use the drug compatibility effect analysis model, analyze the law of drug compatibility effect changing with treatment time, record the influence of seasonal changes and treatment cycle and other time factors, and the specific steps of establishing the drug compatibility and time effect analysis model are as follows;

[0119] S601: Use the drug compatibility effect analysis model to input the time variables in the treatment process, including the treatment cycle and seasonal changes, and apply the hidden Markov model to simulate and analyze the law of drug compatibility effect changes over time, including the changes in drug compatibility effects in multiple seasons and the impact of the treatment cycle on the effect. The specific process of generating the time variable simulation analysis results is as follows;

[0120] Sub-step S601 uses the drug compatibility effect analysis model, inputs time variable data such as treatment cycle and seasonal changes, and performs hidden Markov model analysis. It is specifically implemented using Python's hmmlearn library, defines the number of states of the hidden Markov model, such as setting the number of states to different levels of drug compatibility effects, initializes model parameters, including state transition probability matrix and observation probability matrix, trains the model through the fit() method, inputs time variable data such as seasons of spring, summer, autumn, and winter and short-term, medium-term, and long-term treatment cycles, simulates changes in drug compatibility effects under different time conditions, such as the probability distribution of drug compatibility effects in spring, and changes in effects under long-term treatment cycles, predicts effects through the predict() method, and generates time variable simulation analysis results.

[0121] Hidden Markov model, according to Formula II:

[0122]

[0123] Calculate the time-varying patterns of drug combination effects and generate time-variable simulation analysis results;

[0124] Among them, P(S t |O 1：t，E ) is the state S at time t under the observation sequence and environmental factor E t The probability of the model being affected by environmental factors is β, which is a normalization factor adjusted according to environmental factors. It is determined by environmental sensitivity analysis, which can be performed by comparing the drug compatibility effect data under different environmental conditions. The degree of influence of environmental variables on the model is analyzed by linear regression, so as to estimate and adjust the weight coefficient, P(O t |S t , E) is the given state S under environmental factor E t The probability of observing Ot under t |S t-1 , E) is under environmental factor E, from state S t-1Transfer to state S t The probability, P(S t-1 |O 1：t-1 , E) is in state S under environmental factors E and previous observations t-1 probability;

[0125] The execution process is as follows:

[0126] Collect data on temporal variables (such as treatment cycles and seasonal changes) and environmental factors (such as temperature and humidity) related to the effects of drug combinations.

[0127] In the hidden Markov model, different states are defined to represent different levels of drug combination effects (eg, low effect, medium effect, and high effect).

[0128] Referring to the influence of environmental factor E, the state transition probability matrix and observation probability matrix of the model are initialized.

[0129] The Hidden Markov Model is trained using the collected data on time variables and environmental factors. This is achieved by adjusting the model parameters to best reflect the observed data sequence.

[0130] Using the trained model, combined with specific time variables and environmental conditions, the changes in the drug combination effect are predicted through Formula II. When executing the predict() method, Formula II is used to calculate the most likely state of the drug combination at each time point based on current and previous observations and environmental factors.

[0131] S602: Analyze the results of the time variable simulation analysis to identify the influence of the time factor on the drug combination effect, including the enhancement or weakening of the drug combination effect by a specified season, and the effect of the length of the treatment cycle on the sustainability of the effect. The specific process for extracting key data on the influence of the time factor is as follows;

[0132] The S602 sub-step identifies the influence of time factors based on the results of the time variable simulation analysis, uses data analysis methods such as time series analysis, and specifically uses Python's statsmodels library to execute time series analysis functions such as the ARIMA model. The data of the time variable simulation analysis results are input, and model parameters are set, such as the p, d, and q values ​​of the ARIMA model. The model is fitted, and the impact of seasonal changes on the effect of drug combinations is analyzed through the model prediction function, such as the improvement or reduction of the effect of drug combinations in summer, and the impact of the length of the treatment cycle on the sustainability of the effect, and key data on the impact of time factors are extracted.

[0133] S603: Based on the key data affected by time factors, by analyzing the patterns and trends in the data, setting analysis parameters, including the classification of time periods and seasonal effects, the specific process of constructing a drug compatibility and time effect analysis model is as follows;

[0134] In sub-step S603, a drug compatibility and time effect analysis model is constructed based on the key data affected by the time factor. Machine learning methods such as random forest are used. Specifically, the RandomForestRegressor class in Python's SciKit-Learn library is used to define the model parameters, such as the number and depth of trees. The key data affected by the time factor is input, and the model is trained through the fit() method. The classification and seasonal effects of different time periods are considered, and the performance of the drug compatibility effect in future time periods is predicted through the predict() method to construct a drug compatibility and time effect analysis model.

[0135] See also Figure 8 , Intelligent recommendation system for Chinese medicine compatibility, the system includes:

[0136] The drug property analysis module analyzes the nature, flavor, meridians, and historical use cases of traditional Chinese medicine, extracts the key properties and potential therapeutic effects of the drugs, and organizes them into structured information to obtain a drug property information set;

[0137] The interaction prediction module conducts interaction analysis between multiple drugs based on the drug property information set, including the prediction of synergistic and antagonistic effects, and obtains the interaction analysis results;

[0138] The synergistic identification module screens drug combinations with synergistic potential based on the interaction analysis results, excludes potential antagonistic combinations, and generates a list of synergistic combinations;

[0139] The dose frequency adjustment module conducts dose and frequency adjustment analysis based on the synergistic combination list, optimizes the dose frequency combination based on the balance between therapeutic effect and safety, and establishes dose frequency adjustment recommendations;

[0140] The environmental adaptability analysis module analyzes the impact of various environmental factors on the drug compatibility effect based on the dosage frequency adjustment suggestions, formulates matching environmental condition adjustment measures, and obtains environmental adjustment suggestions;

[0141] The compatibility effect analysis module combines environmental adjustment suggestions with current clinical case data to analyze the compatibility effects under various environmental conditions and dosage frequencies, optimizes the compatibility strategy, and obtains the compatibility effect optimization strategy;

[0142] The treatment cycle and seasonal adjustment module uses the compatibility effect optimization strategy to study the impact of treatment time, including seasonal changes and treatment cycles, on the compatibility effect, and puts forward suggestions for time adjustment of drug compatibility.

[0143] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent recommendation method for Chinese medicine compatibility, characterized in that: The steps include: Organize the basic properties of Chinese medicine, such as its nature and flavor, meridians, and historical use cases, into the database, simulate the interactions of multiple drug combinations, record the changes caused by drug interactions, and construct a drug information record table; Based on the drug information record table, screening drug combinations with synergistic effects and excluding drug combinations with antagonistic effects, the specific steps of generating a synergistic drug combination catalog are as follows; Based on the drug information record table, the synergistic and antagonistic effects between drug combinations are comprehensively analyzed through a constraint satisfaction problem algorithm, drug combinations with antagonistic effects are excluded, and combinations with synergistic effects are marked to generate initial drug combination screening results; The constraint satisfaction problem algorithm is based on Formula I: Calculate the synergistic and antagonistic effects between drug combinations and generate initial drug combination screening results; in, Representative drug combinations A Boolean value indicating whether the effect is synergistic or antagonistic. represents the comprehensive properties of drug A, represents the comprehensive properties of drug B, represents the comprehensive properties of drug C, represents the comprehensive properties of drug D, represents the weight coefficient of the interaction between drugs A and B, which is determined through the study and evaluation of the interaction between drugs A and B. is the weight coefficient representing drug C, which is determined by analyzing the clinical effect data and pharmacological properties of drug C. is the weight coefficient representing drug D, which is determined by comprehensively referring to the safety, side effect level and historical use cases of drug D; Based on the initial drug combination screening results, the efficacy and safety of the screened drug combination are evaluated by adjusting the ratio, dosage, and frequency of use of the drug combination to generate drug combination efficacy and risk evaluation results; Based on the efficacy and risk assessment results of the drug combination, combined with current clinical needs and environmental factors, refine the selection and adjustment of the drug combination and generate a synergistic drug combination catalog; Analyze the combinations in the synergistic drug combination catalog, refer to the effects of dosage and frequency of use on the compatibility effect, record the compatibility under various dosages and frequencies, and establish a dosage and frequency recommendation matrix; Based on the dose and frequency recommendation matrix, analyze the impact of environmental conditions on drug compatibility, record drug interactions under environmental changes, and formulate environmental condition adjustment recommendations; Combine the environmental condition adjustment suggestions with clinical case data to analyze the compatibility effects under various environmental conditions and dosage frequencies, extract key data, and build a drug compatibility effect analysis model; Using the drug compatibility effect analysis model, analyze the law of drug compatibility effect changes with treatment time, record the influence of seasonal changes and various time factors of treatment cycle, and establish a drug compatibility and time effect analysis model; The drug information record table includes the nature, flavor, meridians, mutual promotion and restraint information of the drugs, and compatibility examples based on historical documents. The synergistic drug combination catalog includes adjusted drug ratios, synergistic drug pairs, and excluded antagonistic drug pairs. The dosage and frequency recommendation matrix includes the dosage ranges of multiple drug compatibilities, recommended usage frequencies, and analysis of the impact of dosage and frequency on the compatibility effect. The environmental condition adjustment suggestions include the adjustment range of ambient temperature, optimization measures for humidity levels, and drug compatibility suggestions under specified storage conditions. The drug compatibility effect analysis model includes predictions of compatibility effects under multiple environmental conditions, compatibility suggestions after dosage and frequency optimization, and clinical case analysis results. The drug compatibility and time effect analysis model includes research on the impact of treatment cycles on compatibility effects, correlation analysis between seasonal changes and drug compatibility, and examples of compatibility optimization after time adjustment.

2. The intelligent recommendation method for Chinese medicine compatibility according to claim 1, characterized in that: Organize the basic properties of Chinese medicine, such as its nature and flavor, meridians, and historical use cases, simulate the interactions of multiple drug combinations, and record the changes caused by drug interactions. The specific steps for constructing a drug information record table are as follows; Organize the basic properties of Chinese medicine, such as its nature and flavor, meridians, and historical use cases, into a database, record the changes caused by drug interactions, and obtain a drug property database through data entry and classification management; Based on the drug property database, referring to the nature, taste, meridians and interaction records of the drugs in historical use cases, simulating the interaction of multiple drug combinations, identifying and recording the synergistic or antagonistic effects between drugs, and generating drug interaction simulation records; Based on the drug interaction simulation record, the data analysis process is iteratively optimized, and a drug information record table is generated through a detailed analysis of the drug interaction, combined with the basic properties of the drugs and the simulated interaction effects.

3. The intelligent recommendation method for Chinese medicine compatibility according to claim 1 is characterized by: The specific steps of analyzing the combinations in the synergistic drug combination catalog, referring to the effects of dosage and frequency of use on the compatibility effect, recording the compatibility under various dosages and frequencies, and establishing a dosage and frequency recommendation matrix are as follows; Analyze each drug combination in the synergistic drug combination catalog, record the compatibility effects at various dosages and usage frequencies, including collecting the effect data of each drug combination at various dosage levels and the influence of various usage frequencies on the therapeutic effect, and generate a data set of the relationship between drug compatibility and dosage frequency; Based on the drug compatibility and dosage frequency relationship data set, analyze the drug compatibility effects under various dosages and usage frequencies, identify the influence of dosage and frequency on the compatibility effect, and generate dosage and frequency optimization suggestions; The dosage and frequency optimization suggestions are comprehensively analyzed and adjusted, and a dosage and frequency recommendation matrix is ​​generated with reference to individual differences of patients and drug combination requirements.

4. The intelligent recommendation method for Chinese medicine compatibility according to claim 1, characterized in that: Based on the dosage and frequency recommendation matrix, analyze the impact of environmental conditions on drug compatibility, record drug interactions under environmental changes, and formulate specific steps for environmental condition adjustment recommendations as follows; Based on the dosage and frequency recommendation matrix, collect and analyze the changing data of drug compatibility effects under various environmental conditions, including the effects of ambient temperature, humidity and storage conditions on drug interactions, and generate an environmental factor impact analysis data set; Analyze the environmental factor impact analysis data set, identify environmental variables that affect the drug compatibility effect, including a selected temperature or humidity range, determine the priority and direction of environmental adjustment, and generate environmental adjustment priority analysis results; Based on the environmental adjustment priority analysis results, the environmental condition parameters that need to be adjusted are listed, and an adjustment plan is formulated, including setting temperature and humidity ranges, improving storage conditions, and associated environmental adjustments, to generate environmental condition adjustment recommendations.

5. The intelligent recommendation method for Chinese medicine compatibility according to claim 1 is characterized in that: The specific steps of combining the environmental condition adjustment suggestions with clinical case data, analyzing the compatibility effects under various environmental conditions and dosage frequencies, extracting key data, and constructing a drug compatibility effect analysis model are as follows; Collect the data in the environmental condition adjustment recommendations and the effect data of drug compatibility under various environmental conditions and dosage frequencies in clinical cases, including temperature, humidity, dosage, and frequency of use, to generate a clinical and environmental data set for drug compatibility; Analyze the clinical and environmental data sets of the drug compatibility, extract key variables that affect the effect of drug compatibility, including the dose-response relationship under specified environmental conditions, the effect of frequency of use on the effect, identify ways to optimize the effect of drug compatibility, and generate key variable analysis results of drug compatibility; The key variables identified in the key variable analysis results of the drug compatibility are sorted out, including environmental condition variables and dosage frequency variables, and a drug compatibility effect analysis model is constructed based on the interaction of variables and their impact on the compatibility effect.

6. The intelligent recommendation method for Chinese medicine compatibility according to claim 1, characterized in that: The drug compatibility effect analysis model is used to analyze the law of drug compatibility effect changes with treatment time, record the influence of seasonal changes and various time factors of treatment cycle, and the specific steps of establishing the drug compatibility and time effect analysis model are as follows; Using the drug compatibility effect analysis model, inputting time variables in the treatment process, including treatment cycle, seasonal change data, applying hidden Markov model, simulating and analyzing the law of drug compatibility effect change over time, including the change of drug compatibility effect in multiple seasons, and the influence of treatment cycle on effect, and generating time variable simulation analysis results; The hidden Markov model, according to formula II: Calculate the time-varying patterns of drug combination effects and generate time-variable simulation analysis results; in, is given from time 1 to The observation sequence and environmental factors Time In the state of drug compatibility effect The probability of is a normalization factor adjusted according to environmental factors and determined through environmental sensitivity analysis. It is the environmental factors Next, given the state Lower Observation Value The probability of occurrence, It is the environmental factors Next, from the state Transfer to state The probability of Given time 1 to The observation sequence and environmental factors , the drug combination effect is in a state probability; Analyze the time variable simulation analysis results to identify the influence of time factors on the drug combination effect, including the enhancement or weakening of the drug combination effect by a specified season, the effect of the length of the treatment cycle on the sustainability of the effect, and extract key data on the influence of time factors; Based on the key data affected by the time factor, by analyzing the patterns and trends in the data, setting the analysis parameters, including the classification of time periods and seasonal effects, a drug compatibility and time effect analysis model is constructed.

7. Intelligent recommendation system for Chinese medicine compatibility, characterized by: According to any one of claims 1 to 6, the intelligent recommendation method for TCM drug compatibility is implemented, and the system comprises: The drug property analysis module analyzes the nature, flavor, meridians, and historical use cases of traditional Chinese medicine, extracts the key properties and potential therapeutic effects of the drugs, and organizes them into structured information to obtain a drug property information set; The interaction prediction module performs interaction analysis between multiple drugs based on the drug property information set, including prediction of synergistic and antagonistic effects, and obtains interaction analysis results; The synergistic recognition module screens drug combinations with synergistic potential based on the interaction analysis results, excludes potential antagonistic combinations, and generates a synergistic combination list; The dosage frequency adjustment module performs dosage and usage frequency adjustment analysis based on the synergistic combination list, optimizes the dosage frequency combination according to the balance between therapeutic effect and safety, and establishes dosage frequency adjustment suggestions; The environmental adaptability analysis module analyzes the influence of various environmental factors on the drug compatibility effect based on the dosage frequency adjustment suggestion, formulates matching environmental condition adjustment measures, and obtains environmental adjustment suggestions; The compatibility effect analysis module combines the environmental adjustment suggestions with the current clinical case data to analyze the compatibility effects under various environmental conditions and dosage frequencies, optimizes the compatibility strategy, and obtains the compatibility effect optimization strategy; The treatment cycle and seasonal adjustment module uses the above-mentioned compatibility effect optimization strategy to study the effect of treatment time including seasonal changes and treatment cycle on the compatibility effect, and puts forward suggestions for time adjustment of drug compatibility.

Images