AI large model-based tentative and anti-syndrome traditional Chinese medicine thinking diagnosis auxiliary system

Abstract

The invention relates to an AI large model-based tentative and anti-syndrome traditional Chinese medicine thinking medicine auxiliary system of a space agent technology. The system shows the characteristics of diversification and multi-level through the cognition and thinking method of traditional Chinese medicine; comprising eight traditional Chinese medicine thinking modules: observation and speculation (an outside and inside compulsory module and an image thinking module), comparison and analogy (an object-to-thing ratio module and an image-taking ratio module), reflection and pause (a heart law and pause module), empirical and adjustment (a tentative and anti-empirical module), logical reasoning (an induction and deduction module) and an overall and change (a system thinking module). The system deploys a human body area network AI algorithm in a physical medical space, intelligently speculates internal viscera changes of a patient, has an interactive feedback function, and provides dynamic diagnosis suggestions and treatment scheme adjustment; recording a diagnosis process and a treatment result of a traditional Chinese medicine doctor, forming a traditional Chinese medicine thinking and medicine knowledge base, and creating a traditional Chinese medicine thinking and medicine targeted medical new prescription; and traditional Chinese medicine thinking is promoted to construct a new world of international development and artificial intelligence.

Description

Technical Field

[0001] The present invention relates to the field of medical assistance of TCM thinking using spatial intelligent agent technology based on the AI ​​big model for exploration and disproof. More specifically, the present invention relates to an intelligent management system for TCM health diagnosis and treatment management data based on the AI ​​big model of TCM thinking and personalized calculation of TCM thinking. Background Art

[0002] Health data is raw, unprocessed medical and health information, while health management data is data that has been processed, analyzed, and managed to achieve more specific goals; Human Domain Network health management data usually involves the use of technologies such as AI TCM thinking big models to manage data through healthy TCM thinking filling values ​​to provide better individual health diagnosis and treatment management support and decision-making; The existing cognition and thinking methods of traditional Chinese medicine show diversified and multi-level characteristics, including eight traditional Chinese medicine thinking modules: observation and speculation (Siwai Chuan Nei module, Xiang thinking module), comparison and analogy (Yuwu comparison module, Xiang comparison module), reflection and enlightenment (Mind method and enlightenment module), empirical evidence and adjustment (trial and counter-evidence module), logical reasoning (induction and deduction module) and wholeness and change (system thinking module); When the health monitoring TCM thinking and medical auxiliary system module transmits the data of healthy TCM cognition and thinking methods, which show diversified and multi-level characteristics, to the AI ​​TCM thinking big model server in a normal state, the health monitoring device of the data TCM thinking and medical auxiliary system module transmits the health data to the AI ​​TCM thinking big model server to evaluate the available analysis coefficient value of the health data of the AI ​​TCM thinking big model service. At the same time, it verifies the available evaluation coefficient value of the health data of the AI ​​TCM big model service, and evaluates the performance of the AI ​​TCM big model server in processing the data of healthy TCM cognition and thinking methods, which show diversified and multi-level characteristics.

[0003] The prior art has the following deficiencies: There may be failure problems in the data transmission between the health monitoring device and the AI ​​big model's TCM server. At present, the alarm of the failure of the health monitoring device and the AI ​​big model's TCM server is usually after the health monitoring device has failed with the AI ​​big model's TCM server. There is no advance prompt of the status of the data transmission between the health monitoring device and the AI ​​big model's TCM server, which will result in failure to switch to the backup AI big model's TCM server in time. As a result, when the data transmission between the health monitoring device and the AI ​​big model's TCM server fails, the user's health data cannot be processed in time by the AI ​​big model server to generate health management data, resulting in untimely health monitoring of the user, which in turn causes the user to be unable to understand their health status in time and miss early signs of health problems, which may lead to untimely adjustment of life, exercise, and psychology.

[0004] In order to solve the above problems, a technical solution is now provided; Invention content In order to overcome the above defects of the prior art, the embodiments of the present invention provide a cognition and thinking method of traditional Chinese medicine based on the AI ​​traditional Chinese medicine thinking model, showing diversified and multi-level characteristic data to solve the problems raised in the above background technology; To achieve the above purposes, the present invention provides the following. Summary of the invention

[0005] The present invention relates to a medical auxiliary system for TCM thinking based on the spatial intelligent agent technology and the AI ​​large model for probing and disproving; the system is characterized by showing diversified and multi-level characteristics through the cognition and thinking methods of TCM, including eight TCM thinking modules: observation and speculation (external thinking module, image thinking module), comparison and analogy (object comparison module, image comparison module), reflection and epiphany (mind method and epiphany module), empirical evidence and adjustment (probing and disproving module), logical reasoning (inductive deduction module) and wholeness and change (system thinking module); The cognitive and thinking methods of traditional Chinese medicine show diversified and multi-level characteristics. The module technologies are as follows: 1. The following are the functions and module codes related to TCM thinking of "Siwai Chuannei" and "Xiang thinking": We will realize the functions of physiological status monitoring, intrinsic pathology inference, image data analysis and historical case combination; Module Structure We will create a module called TraditionalChineseMedicine that contains the following main functions: Physiological status monitoring Intrinsic pathology speculation Image data analysis Combination of historical cases Code Implementation # traditional_chinese_medicine.py import numpy as np from sklearn.feature_extraction import image class TraditionalChineseMedicine: def __init__(self): # Initialize physiological parameters and historical cases self.vital_signs = {} self.history_cases = [] def monitor_vital_signs(self, sensor_data): """ Monitoring physiological status :param sensor_data: A dictionary containing multiple physiological parameters, for example {'temperature': 36.5, 'pulse': 75} :return: Returns a dictionary of physiological status """ self.vital_signs = sensor_data return self.vital_signs def infer_internal_state(self): """ Inferring internal pathological conditions based on external physiological parameters :return: Internal pathological state """ temperature = self.vital_signs.get('temperature', None) pulse = self.vital_signs.get('pulse', None) if temperature is not None and pulse is not None: return self._g(temperature, pulse) else: return "Missing necessary physiological parameters" def _g(self, temperature, pulse): """ Intrinsic pathology inference function :param temperature: body temperature :param pulse: pulse :return: Internal pathological state """ if temperature > 37.5: return "may have a fever" elif pulse < 60: return "May have bradycardia" else: return "normal" def analyze_image(self, image_data): """ Image data analysis, feature extraction :param image_data: input image data :return: extracted feature data """ # Assume that a simple image processing method is used to extract features features = self._extract_features(image_data) return features def _extract_features(self, image_data): """ Auxiliary functions for extracting image features :param image_data: input image data :return: extracted features """ # More complex image processing algorithms can be used here # For example, using edge detection, color histogram, etc. return np.mean(image_data) # Example: Return the mean of the image as a feature def combine_history_cases(self, features, weights): """ Speculation based on historical cases :param features: Features of the current case :param weights: corresponding weights :return: Presumed intrinsic pathological changes """ if len(features) != len(weights): raise ValueError("features and weights must have the same length") R = sum(w * f for w, f in zip(weights, features)) return R # Example usage if __name__ == "__main__": tcm = TraditionalChineseMedicine() # Simulate sensor data sensor_data = { 'temperature': 38.0, # body temperature 'pulse': 55 # pulse } # Monitoring physiological status vital_signs = tcm.monitor_vital_signs(sensor_data) print("Monitored physiological status:", vital_signs) # Speculate the internal pathological state internal_state = tcm.infer_internal_state() print("Inferred internal pathological state:", internal_state) # Simulate image data image_data = np.random.rand(100, 100) # Generate random image data features = tcm.analyze_image(image_data) print("Extracted image features:", features) # Simulate historical case characteristics and weights historical_features = [0.5, 0.7, 0.9] # Hypothetical historical case features weights = [0.2, 0.3, 0.5] # Corresponding weights # Speculate based on historical cases combined_result = tcm.combine_history_cases(historical_features,weights) print("Internal pathological changes inferred from historical cases:", combined_result) Code Description Module Traditional Chinese Medicine: __init__: Initialize physiological parameters and historical cases; monitor_vital_signs: receives sensor data and stores it in self.vital_signs; infer_internal_state: infers the internal pathological state based on the stored physiological parameters, and calls the _g function for specific inference; _g: internal pathological inference function, returns the corresponding pathological state based on the value of body temperature and pulse; analyze_image: receives image data and extracts features, calling the _extract_features function; _extract_features: Auxiliary function for extracting image features. Here, it simply returns the average value of the image as a feature; combine_history_cases: combines historical case features and weights to make inferences and returns the inferred intrinsic pathological changes; usage In the if __name__ == "__main__": block, we create an instance of the TraditionalChineseMedicine class, simulate sensor data, image data, and historical case characteristics, call related functions, and print out the results; Run the code Save the above code as traditional_chinese_medicine.py and run the file in the command line. You will see the monitored physiological state, the inferred intrinsic pathological state, the extracted image features, and the inferred results combined with historical cases.

[0006] 2. The following are examples of functions and module codes related to "comparison and analogy" in TCM thinking; we will implement the functions of managing similar case databases, similarity measurement, and symptom comparison; Module Structure We will create a module called CaseComparison that contains the following main functions: Adding cases to the database Computing similarity measures Find the case most similar to the current symptoms Code implementation: # case_comparison.py import numpy as np class CaseComparison: def __init__(self): # Initialize the case database self.case_database = [] def add_case(self, symptoms, treatment, effectiveness): """ Adding cases to the database :param symptoms: symptoms :param treatment: treatment plan :param effectiveness: treatment effectiveness """ self.case_database.append((symptoms, treatment,effectiveness)) def euclidean_distance(self, case1, case2): """ Calculate the Euclidean distance between cases :param case1: Symptoms of the first case :param case2: Symptoms of the second case :return: Euclidean distance """ return np.sqrt(np.sum((np.array(case1) - np.array(case2)) **2)) def find_most_similar_case(self, current_symptoms): """ Find the case most similar to the current symptoms :param current_symptoms: current symptoms :return: The index and similarity of the most similar case """ max_similarity = -1 most_similar_case = None most_similar_index = -1 for index, (symptoms, treatment, effectiveness) in enumerate(self.case_database): distance = self.euclidean_distance(current_symptoms,symptoms) similarity = 1 / (1 + distance) # Similarity metric, the smaller the distance, the higher the similarity if similarity > max_similarity: max_similarity = similarity most_similar_case = (symptoms, treatment,effectiveness) most_similar_index = index return most_similar_index, most_similar_case, max_similarity # Example usage if __name__ == "__main__": cc = CaseComparison() # Add cases to the database cc.add_case([1, 2, 3], "Treatment A", "Effective") cc.add_case([2, 3, 4], "Treatment B", "Moderate") cc.add_case([1, 0, 1], "Treatment C", "Not Effective") # Current symptoms current_symptoms = [1, 2, 2] # Find the case most similar to the current symptoms index, similar_case, similarity_score = cc.find_most_similar_case(current_symptoms) print(f"Most similar case index: {index}") print(f"Most similar case: {similar_case}") print(f"Similarity: {similarity_score:.4f}") Code Explanation: Module CaseComparison: __init__: initialize the case database; add_case: add a new case to the database, including symptoms, treatment options and treatment effects; euclidean_distance: calculates the Euclidean distance between two case symptoms; find_most_similar_case: finds the case most similar to the current symptom, and returns the index, case information and similarity of the most similar case; Example usage: In the if __name__ == "__main__": block, we create an instance of the CaseComparison class, add some cases to the database, find the case most similar to the current symptoms, and finally print the results; Run the code: Save the above code as case_comparison.py and run the file in the command line. You will see the output of the index of the most similar case, case information, and similarity.

[0007] 3. Below are some examples of functions and module codes related to “reflection and enlightenment” in TCM diagnosis; we will implement the function of note analysis to extract the key insights of TCM practitioners; Module structure: We will create a module called InsightExtraction with one main function: Extract key insights Code implementation: # insight_extraction.py import re class InsightExtraction: def __init__(self): # Initialize the note list self.notes = [] def add_note(self, note): """ Add a note :param note: Notes from a Chinese medicine practitioner """ self.notes.append(note) def extract_insights(self): """ Extract key insights from your notes :return: List of key insights extracted """ insights = [] for note in self.notes: extracted = self._extract_from_note(note) if extracted: insights.append(extracted) return insights def _extract_from_note(self, note): """ Helper functions for extracting insights from a single note :param note: a single note :return: Extracted insights """ # Assuming key insights start with "Key" match = re.search(r'keyword(.*?)(?=\n|$)', note) if match: return match.group(1).strip() return None # Example usage if __name__ == "__main__": ie = InsightExtraction() # Add a TCM physician's note ie.add_note("The patient has a fever, key: the possibility of infection should be considered, \n") ie.add_note("The pulse is fast, the key: it may be related to emotions,\n") ie.add_note("No obvious symptoms, key: need to observe subsequent changes,\n") # Extract key insights insights = ie.extract_insights() print("Key insights extracted:", insights) Code Explanation: Module InsightExtraction: __init__: initialize the note list; add_note: add a new note to the list; extract_insights: extracts key insights from all notes and returns a list of insights; _extract_from_note: Auxiliary function to extract insights from a single note, assuming the key insights start with "key"; Example usage: In the if __name__ == "__main__": block, we create an instance of the InsightExtraction class, add some notes from the TCM practitioner, extract key insights, and finally print out the results; Run the code: Save the above code as insight_extraction.py and run the file in the command line, you will see the output of the extracted key insights.

[0008] 4. The following are examples of functions and module codes related to “Evidence and Adjustment” in TCM thinking; we will implement the function of feedback loop so that the feedback results can be adjusted according to the treatment effect; Module structure: We will create a module called FeedbackLoop that contains the following main functions: Update feedback results; Code implementation: # feedback_loop.py class FeedbackLoop: def __init__(self, alpha=0.5): """ Initializing the feedback loop :param alpha: smoothing factor, ranging from 0 to 1 """ self.alpha = alpha self.previous_feedback = None # Last feedback result def update_feedback(self, current_effectiveness): """ Update feedback results :param current_effectiveness: Current treatment effectiveness :return: Current feedback result """ if self.previous_feedback is None: # If there is no previous feedback result, initialize to the current treatment effect self.previous_feedback = current_effectiveness return current_effectiveness # Calculate the current feedback result current_feedback = self.alpha * self.previous_feedback + (1 -self.alpha) * current_effectiveness # Update the last feedback result self.previous_feedback = current_feedback return current_feedback # Example usage if __name__ == "__main__": feedback_loop = FeedbackLoop(alpha=0.7) # Simulate treatment effects treatment_effects = [0.8, 0.6, 0.9, 0.7, 0.5] # Hypothetical treatment effects # Update feedback results for effectiveness in treatment_effects: feedback_result = feedback_loop.update_feedback(effectiveness) print(f"Current treatment effect: {effectiveness}, Current feedback result: {feedback_result:.4f}") Code Explanation: Module FeedbackLoop: __init__: Initialize the feedback loop, set the smoothing factor alpha and the last feedback result; update_feedback: Update the feedback result according to the current treatment effect; if there is no previous feedback result, initialize it to the current treatment effect; Example usage: In the if __name__ == "__main__": block, we create an instance of the FeedbackLoop class, simulate a series of treatment effects, update the feedback results, and finally print out the current treatment effect and feedback results; Run the code: Save the above code as feedback_loop.py and run the file in the command line. You will see the output of each treatment effect and the corresponding feedback result.

[0009] 5. The following are examples of functions and module codes related to "logical reasoning" in TCM thinking; we will implement a simple data analysis model and use linear regression for inductive and deductive reasoning; Module structure: We will create a module called LinearRegressionModel with the following main functions: Fitting the model Making predictions Code implementation: # linear_regression_model.py import numpy as np class LinearRegressionModel: def __init__(self): self.beta = None # Model parameters self.intercept = None # intercept def fit(self, X, Y): """ Fitting a linear regression model :param X: input feature matrix (mxn) :param Y: prediction result vector (mx 1) """ # Add an intercept term X_b = np.c_[np.ones((X.shape[0], 1)), X] # Add a column of 1 before X # Calculate model parameters (β) using normal equations self.beta = np.linalg.inv(X_b.T.dot(X_b)).dot(X_b.T).dot(Y) self.intercept = self.beta[0] #Intercept self.beta = self.beta[1:] # Only keep the slope def predict(self, X): """ Making predictions :param X: input feature matrix (mxn) :return: prediction result vector (mx 1) """ X_b = np.c_[np.ones((X.shape[0], 1)), X] # Add intercept term return X_b.dot(np.r_[self.intercept, self.beta]) # Calculate the prediction results # Example usage if __name__ == "__main__": # Simulate data X = np.array([[1], [2], [3], [4], [5]]) # Input features Y = np.array([2, 3, 5, 7, 11]) # Prediction results # Create a linear regression model instance model = LinearRegressionModel() # Fit the model model.fit(X, Y) # Make predictions predictions = model.predict(X) print("Model parameters (slope):", model.beta) print("Model intercept:", model.intercept) print("Prediction results:", predictions) Code Explanation: Module LinearRegressionModel: __init__: Initialize model parameters and intercept; fit: fit the linear regression model and calculate the model parameters (slope and intercept); predict: Make predictions based on input features and return prediction results; Example usage: In the if __name__ == "__main__": block, we create an instance of the LinearRegressionModel class, simulate some input features and prediction results, fit the model and make predictions, and finally print out the model parameters and prediction results; Run the code: Save the above code as linear_regression_model.py and run the file in the command line. You will see the output of the model parameters (slope and intercept) and the prediction results.

[0010] 6. The following are examples of functions and module codes related to the “wholeness and change” in TCM thinking; we will implement the functions of overall health status assessment and change trend analysis; Module structure: We will create a module called HealthAssessment with the following main functions: Overall health assessment Trend Analysis Code implementation: # health_assessment.py import numpy as np class HealthAssessment: def __init__(self): self.data = {} # Store data for each module def add_data(self, module_name, values): """ Add data for each module :param module_name: module name :param values: module data """ self.data[module_name] = values def assess_overall_health(self): """ Assess overall health :return: Overall health status """ # Assume that the overall health is the average of the data of each module overall_health = np.mean([np.mean(values) for values ​​inself.data.values()]) return overall_health def analyze_trend(self, current_param, previous_param): """ Analyze changing trends :param current_param: current physiological parameters :param previous_param: physiological parameters at the previous time point :return: Change trend """ if previous_param == 0: raise ValueError("The physiological parameters at the previous time point cannot be zero to avoid division by zero errors.") trend = (current_param - previous_param) / previous_param return trend # Example usage if __name__ == "__main__": health_assessment = HealthAssessment() # Add data for each module health_assessment.add_data("heart rate", [70, 72, 68, 75]) health_assessment.add_data("blood pressure", [120, 118, 122, 121]) health_assessment.add_data("Body temperature", [36.5, 36.7, 36.6, 36.8]) # Assess overall health overall_health = health_assessment.assess_overall_health() print("Overall health assessment:", overall_health) # Analyze the trend of change current_heart_rate = 75 previous_heart_rate = 70 trend = health_assessment.analyze_trend(current_heart_rate,previous_heart_rate) print("Heart rate trend:", trend) Code Description: Module HealthAssessment: __init__: initialize the data storage dictionary; add_data: add data of each module; assess_overall_health: Assess overall health status, assumed to be the average of the data from each module; analyze_trend: Analyze the trend of changes and calculate the change rate of the current physiological parameters and the physiological parameters at the previous time point; Example usage: In the if __name__ == "__main__": block, we create an instance of the HealthAssessment class, add some module data, assess the overall health status, analyze the trend of heart rate, and finally print out the results; Run the code: Save the above code as health_assessment.py and run the file in the command line. You will see the output of the overall health assessment and heart rate trend.

[0011] The TCM thinking and medical assistance system based on the AI ​​big model is tested and disproved; the TCM thinking and medical assistance system module for health monitoring transmits recent health data to the AI ​​TCM thinking big model server, and evaluates the diversified and multi-level characteristics of the cognition and thinking methods of healthy TCM to determine whether the recent transmission status of the data transmitted to the AI ​​TCM thinking big model server by the TCM thinking and medical assistance system module for health monitoring is normal; When the health monitoring TCM thinking and medical auxiliary system module transmits the data of healthy TCM cognition and thinking methods, showing diversified and multi-level characteristics, to the AI ​​TCM thinking big model server when the status is normal, the health monitoring device of the data TCM thinking and medical auxiliary system module transmits the health data to the AI ​​TCM thinking big model server to evaluate the available analysis coefficient value of the health data of the AI ​​TCM thinking big model service. At the same time, verify the available evaluation coefficient value of the health data of the AI ​​TCM big model service, and evaluate the performance of the AI ​​TCM big model server in processing the data of healthy TCM cognition and thinking methods, showing diversified and multi-level characteristics; record the diagnosis process and treatment results of TCM physicians, form a TCM thinking medical knowledge base, and create new TCM thinking targeted medical prescriptions; promote TCM thinking to build a new world of international development and artificial intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a structural diagram of a TCM thinking and medical auxiliary system module provided in the embodiment of the present application, which provides users with a TCM health diagnosis and treatment management plan with diversified and multi-level characteristics through TCM cognition and thinking methods, including eight TCM thinking modules, to improve the health level of individuals. DETAILED DESCRIPTION

[0013] Through the cognition and thinking methods of traditional Chinese medicine, it shows the characteristics of diversity and multi-level, including eight modules of traditional Chinese medicine thinking: observation and speculation (module of external thinking and internal thinking, module of image thinking), comparison and analogy (module of analogy based on objects, module of analogy based on images), reflection and enlightenment (module of mind method and module of enlightenment), empirical evidence and adjustment (module of trial and counter-evidence), logical reasoning (module of induction and deduction), and wholeness and change (module of system thinking); The health monitoring TCM thinking and medical auxiliary system module transmits recent health data to the AI ​​TCM thinking large model server, and evaluates the diversified and multi-level characteristics of the cognition and thinking methods of healthy TCM to determine whether the recent transmission status of the health monitoring TCM thinking and medical auxiliary system module is normal; At the same time, it integrates the cognitive and thinking methods of traditional Chinese medicine to show diversified and multi-level characteristic data; including a collection of eight traditional Chinese medicine thinking modules to transmit the recent health monitoring data as a whole to the AI ​​traditional Chinese medicine thinking large model server for healthy traditional Chinese medicine cognitive and thinking methods, showing diversified and multi-level characteristic data analysis, evaluating the cognitive and thinking methods of healthy traditional Chinese medicine, showing diversified and multi-level characteristic data available coefficients, and discovering possible health problems; providing dynamic diagnostic suggestions and treatment plan adjustments; recording the diagnosis process and treatment results of traditional Chinese medicine practitioners, forming a traditional Chinese medicine thinking medical knowledge base, and creating new traditional Chinese medicine thinking targeted medical prescriptions; promoting traditional Chinese medicine thinking to build a new world of international development and artificial intelligence.

[0014] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application; therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0015] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The present invention relates to a medical auxiliary system for exploring and disproving traditional Chinese medicine thinking based on a large AI model using spatial intelligent agent technology; it is characterized by: Through the cognition and thinking methods of traditional Chinese medicine, it shows the characteristics of diversity and multi-level, including eight modules of traditional Chinese medicine thinking: observation and speculation (module of external thinking and internal thinking, module of image thinking), comparison and analogy (module of analogy based on objects, module of analogy based on images), reflection and enlightenment (module of mind method and module of enlightenment), empirical evidence and adjustment (module of trial and counter-evidence), logical reasoning (module of induction and deduction), and wholeness and change (module of system thinking); The health monitoring TCM thinking and medical auxiliary system module transmits recent health data to the AI ​​TCM thinking large model server, and evaluates the diversified and multi-level characteristics of the cognition and thinking methods of healthy TCM to determine whether the recent transmission status of the health monitoring TCM thinking and medical auxiliary system module is normal; When the health monitoring TCM thinking and medical auxiliary system module transmits the data of the cognition and thinking methods of healthy TCM, showing diversified and multi-level characteristics, to the AI ​​TCM thinking big model server in a normal state, the health monitoring device of the data TCM thinking and medical auxiliary system module transmits the health data to the AI ​​TCM thinking big model server to evaluate the available analysis coefficient of the health data of the AI ​​TCM thinking big model service, and at the same time, verify the available evaluation coefficient value of the health data of the AI ​​TCM big model service, and evaluate the performance of the AI ​​TCM big model server in processing the cognition and thinking methods of healthy TCM, showing diversified and multi-level characteristics data; Comprehensive TCM cognition and thinking methods, showing diversified and multi-level characteristic data; including a collection of eight TCM thinking modules to transmit the recent health monitoring data as a whole to the AI ​​TCM thinking large model server for health TCM cognition and thinking methods, showing diversified and multi-level characteristic data analysis, evaluate health TCM cognition and thinking methods, showing diversified and multi-level characteristic data available coefficients, and discover possible health problems.

2. The AI ​​big model-based medical auxiliary system for probing and disproving TCM thinking according to claim 1 is characterized by: The data module of the healthy Chinese medicine thinking and medical auxiliary system shows the diversified and multi-level characteristics of the cognition and thinking methods of healthy Chinese medicine; the recent data status of the healthy Chinese medicine cognition and thinking methods of the data transmitted to the AI ​​Chinese medicine thinking big model server is evaluated; a set of Chinese medicine thinking and medical auxiliary system modules is set to transmit the cognition and thinking methods of Chinese medicine, showing the diversified and multi-level characteristics of the data module, the cognition and thinking methods of healthy Chinese medicine, showing the diversified and multi-level characteristics of the data transmission process of the AI ​​Chinese medicine thinking big model server; obtain the number of data packets sent in the process of transmitting the cognition and thinking methods of healthy Chinese medicine of the Chinese medicine thinking and medical auxiliary system module to the AI ​​Chinese medicine thinking big model server, and obtain the data of the process of transmitting the cognition and thinking methods of healthy Chinese medicine of the Chinese medicine thinking and medical auxiliary system module to the AI ​​Chinese medicine thinking big model server; Calculate the coefficient of available health data and the medical cognition and thinking methods in each transmission of healthy Chinese medicine thinking data to the AI ​​Chinese medicine thinking big model server, analyze the data showing diversified and multi-level characteristics, and evaluate the health monitoring and AI Chinese medicine thinking big model server data; set the evaluation coefficient value, and monitor the Chinese medicine thinking medical auxiliary system module to generate normal transmission signals; these characteristics will help the system to evaluate and monitor the cognition and thinking methods of healthy Chinese medicine, showing diversified and multi-level characteristics, and provide Chinese medicine health assessment services.

3. The medical auxiliary system for probing and disproving TCM thinking based on AI big model according to claim 1 and claim 2 is characterized by: Through the cognitive and thinking methods of traditional Chinese medicine, it shows diversified and multi-level characteristics, including eight traditional Chinese medicine thinking modules: observation and speculation (module of external thinking and internal thinking, module of image thinking), comparison and analogy (module of analogy based on objects, module of analogy based on images), reflection and enlightenment (module of mind method and module of enlightenment), empirical evidence and adjustment (module of trial and counter-evidence), logical reasoning (module of induction and deduction), and wholeness and change (module of system thinking); after data processing, it is handed over to the AI ​​traditional Chinese medicine thinking model (the large model after fine-tuning of traditional Chinese medicine thinking) for comprehensive analysis, judgment, and processing of its physiological characteristics; the data determines the cognitive and thinking methods of traditional Chinese medicine, showing diversified The data are diversified and multi-level, and the cognitive and thinking methods of traditional Chinese medicine are integrated to show the diversified and multi-level characteristic data for evaluation; after processing, the data are arrayed for physical, psychological, diet suggestions, skin care and body beauty, and natural therapy suggestions; it emphasizes that most of a healthy life comes from life itself, 60% is related to life, and the existing medical care is only evidence-based medicine indicators, lacking personalized health indicators; it aims to determine the cognitive and thinking methods of traditional Chinese medicine, show the diversified and multi-level characteristic data values, and integrate the cognitive and thinking methods of traditional Chinese medicine, show the diversified and multi-level characteristic data for evaluation, and formulate TCM health indicators.

4. The technical features and applications of the system include integrating the healthy TCM thinking medical auxiliary system data module, combining the AI ​​TCM thinking model to analyze physiological characteristics and provide TCM cognitive and thinking methods, showing diversified and multi-level characteristic data values, and integrating TCM cognitive and thinking methods to evaluate diversified and multi-level characteristic data and formulate TCM personalized health indicators and other aspects of innovation.

5. Model of external and internal management: A cognitive method that uses the external appearance of things to speculate and analyze their internal changes; by observing external physiological and pathological phenomena, inferring and judging the physiological and pathological changes of internal organs, and using this as the basis for diagnosis and treatment; Xiang thinking model: It includes three levels: image thinking, image thinking and image-based thinking; Image thinking: a way of thinking that solves problems through intuitive images and representations; Image thinking: a way of thinking that abstracts from specific things or phenomena based on image thinking; Using the TCM thinking medical auxiliary system data module and TCM cognition and thinking methods, it shows a diversified and multi-level characteristic data value range and judges the health value status method, including the following steps: According to the acquired data, the TCM thinking medical auxiliary system data module processes the data and then hands it over to the AI ​​TCM thinking big model (the big model after TCM thinking fine-tuning) for comprehensive analysis, judgment, and processing of its physiological characteristics; the data determines the TCM cognition and thinking methods of TCM, showing diversified and multi-level characteristics of the data, and integrates the TCM cognition and thinking methods to evaluate the data; after processing, the array is given physical, psychological, diet suggestions, skin care and body beauty, and natural therapy suggestions; dynamic diagnosis suggestions and treatment plan adjustments are provided, the diagnosis process and treatment results of TCM physicians are recorded, and a TCM thinking medical knowledge base is formed.

6. Comparison and Analogy: Aid comparison module: A cognitive method that uses image thinking to infer certain characteristics of the object being studied based on the similarities or similarities between the object being studied and known objects in some aspects; Image comparison module: A method of thinking that uses image thinking to deduce certain characteristics of the object being studied based on the similarities or similarities between the object being studied and known objects in some aspects; Using the TCM thinking medical auxiliary system data module and TCM cognition and thinking methods, it shows a diversified and multi-level characteristic data value range and judges the health value status method, including the following steps: According to the acquired data, the TCM thinking medical auxiliary system data module processes the data and then hands it over to the AI ​​TCM thinking big model (the big model after TCM thinking fine-tuning) for comprehensive analysis, judgment, and processing of its physiological characteristics; the data determines the TCM cognition and thinking methods of TCM, showing diversified and multi-level characteristics of the data, and integrates the TCM cognition and thinking methods to evaluate the data; after processing, the array is given physical, psychological, diet suggestions, skin care and body beauty, and natural therapy suggestions; dynamic diagnosis suggestions and treatment plan adjustments are provided, the diagnosis process and treatment results of TCM physicians are recorded, and a TCM thinking medical knowledge base is formed.

7. Reflection and enlightenment: Mental method and enlightenment module: Mind method: a cognitive method that involves repeatedly pondering certain issues during the research process and ultimately obtaining unique insights; Sudden enlightenment: refers to the sudden realization of a problem after deep contemplation, entering a state of clarity and communication with inspiration; Using the TCM thinking medical auxiliary system data module and TCM cognition and thinking methods, it shows a diversified and multi-level characteristic data value range and judges the health value status method, including the following steps: According to the acquired data, the TCM thinking medical auxiliary system data module processes the data and then hands it over to the AI ​​TCM thinking model for comprehensive analysis, judgment, and processing of its physiological characteristics; the data determines the TCM cognition and thinking methods of TCM, showing diversified and multi-level characteristics of the data, and integrates the TCM cognition and thinking methods to evaluate the data; after processing, the array is given physical, psychological, diet suggestions, skin care and body beauty, and natural therapy suggestions; dynamic diagnosis suggestions and treatment plan adjustments are provided; the diagnosis process and treatment results of TCM physicians are recorded to form a TCM thinking medical knowledge base.

8. Evidence and Adjustment Trial and rebuttal module: Probing: A step-by-step approach to cognition that involves investigating complex objects, proposing preliminary ideas and taking measures, and then adjusting and improving them based on the results of practice. Proof by contradiction: a reverse cognitive method of tracing or inferring the cause from the result and proving it; Using the TCM thinking medical auxiliary system data module and TCM cognition and thinking methods, it shows a diversified and multi-level characteristic data value range and judges the health value status method, including the following steps: According to the acquired data, the TCM thinking medical auxiliary system data module processes the data and then hands it over to the AI ​​TCM thinking model for comprehensive analysis, judgment, and processing of its physiological characteristics; the data determines the TCM cognition and thinking methods of TCM, showing diversified and multi-level characteristics of the data, and integrates the TCM cognition and thinking methods to evaluate the data; after processing, the array is given physical, psychological, diet suggestions, skin care and body beauty, and natural therapy suggestions; dynamic diagnosis suggestions and treatment plan adjustments are provided; the diagnosis process and treatment results of TCM physicians are recorded to form a TCM thinking medical knowledge base.

9. Logical Reasoning Inductive-deductive module: Induction: the thinking process from individual and special knowledge or laws to general and universal conclusions; Deduction: The process of reasoning from the premise of general knowledge to the conclusion of specific or individual knowledge; Using the TCM thinking medical auxiliary system data module and TCM cognition and thinking methods, it shows a diversified and multi-level characteristic data value range and judges the health value status method, including the following steps: According to the acquired data, the TCM thinking medical auxiliary system data module processes the data and then hands it over to the AI ​​TCM thinking model for comprehensive analysis, judgment, and processing of its physiological characteristics; the data determines the TCM cognition and thinking methods of TCM, showing diversified and multi-level characteristics of the data, and integrates the TCM cognition and thinking methods to evaluate the data; after processing, the array is given physical, psychological, diet suggestions, skin care and body beauty, and natural therapy suggestions; dynamic diagnosis suggestions and treatment plan adjustments are provided; the diagnosis process and treatment results of TCM physicians are recorded to form a TCM thinking medical knowledge base.

10. Wholeness and Change System Thinking Module: Emphasis on the overall macro, pursuit of the unity of man and nature, the unity of body and spirit, believing that heaven, earth and man are a unified whole, and that the life activities of the human body are closely related to the laws of nature; Changeable thinking module: Focus on the laws of movement and change of things, use them to study life and health processes and prevent and treat diseases, and believe that all things or phenomena in nature are in constant movement and change; According to the acquired data, the TCM thinking medical auxiliary system data module processes the data and hands it over to the AI ​​TCM thinking model for comprehensive analysis, judgment, and processing of its physiological characteristics; the data determines the TCM cognition and thinking methods of TCM, showing diversified and multi-level characteristic data, and integrates the TCM cognition and thinking methods to evaluate the data; after processing, the array is given physical, psychological, diet suggestions, skin and body beauty, and natural therapy suggestions; dynamic diagnosis suggestions and treatment plan adjustments are provided; the diagnosis process and treatment results of TCM physicians are recorded to form a TCM thinking medical knowledge base; Create new prescriptions for targeted medical treatment based on TCM thinking; promote TCM thinking to build a new world of international development and artificial intelligence.

Images