Intelligent medical diagnosis system and method based on artificial intelligence and big data analysis

Abstract

The intelligent medical diagnosis method based on artificial intelligence and big data analysis disclosed in the application comprises the following steps: pre-processing data of a real-time acquired medical data set to obtain a medical data set in a unified format, and then using a data set fusion algorithm to obtain a comprehensive medical data set; based on features extracted from the comprehensive medical data set, using a feature scoring algorithm to calculate feature scores, setting a score threshold, and selecting features with scores higher than the score threshold to form an optimal feature vector; based on the optimal feature vector and a rule base, using a rule matching algorithm to calculate a rule matching degree, and then using an intelligent medical diagnosis matching algorithm to evaluate a diagnosis matching degree of a disease, and selecting a disease with the highest diagnosis matching degree among all diseases as a final diagnosis result. The application has the technical effects of reliable data basis, high diagnosis accuracy, high diagnosis accuracy and matching degree, etc. The application also discloses an intelligent medical diagnosis system based on artificial intelligence and big data analysis.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and big data analysis, and in particular to intelligent medical diagnostic systems and methods based on artificial intelligence and big data analysis. Background Technology

[0002] With the continuous advancement of technology, the application of artificial intelligence and big data analytics in the medical field is becoming increasingly widespread, bringing revolutionary changes to medical diagnosis. Traditional medical diagnosis methods mainly rely on doctors' professional knowledge and clinical experience, but this approach is easily limited by the individual abilities and experience of doctors, and the efficiency and accuracy of diagnosis are difficult to guarantee. In contrast, intelligent medical diagnostic systems based on artificial intelligence and big data analytics can automatically analyze and interpret medical data, providing doctors with accurate diagnostic support and possessing broad application prospects. With the continuous advancement of artificial intelligence and big data analytics technologies and the expansion of application scenarios, intelligent medical diagnostic systems based on artificial intelligence and big data analytics will play a vital role in disease prevention, diagnosis, and treatment, contributing to human health.

[0003] Chinese patent application number CN202410365358.8, published on May 3, 2024, discloses a medical information processing method and system based on big data. It utilizes big data and artificial intelligence technologies to process and analyze medical diagnostic images, extracting semantic features and identifying and segmenting lesion areas within the images. This assists doctors in identifying lesion areas in medical diagnostic images, thereby helping them make more accurate diagnostic and treatment decisions.

[0004] However, the above-mentioned technologies have at least the following technical problems:

[0005] 1. Medical data is heterogeneous in terms of source, format, structure, and storage method, which poses a great challenge when conducting data analysis and integration. Traditional data integration methods are difficult to accurately integrate medical data, thus limiting the depth and breadth of medical data analysis and failing to fully reflect the patient's health status.

[0006] 2. Traditional fusion algorithms struggle to reflect the weight changes of different medical data over different time periods. The weighting of the importance of medical data is not flexible enough and cannot be dynamically adjusted according to specific medical application scenarios, resulting in insufficient representativeness and practicality of the fusion results.

[0007] 3. Existing feature scoring algorithms lack comprehensiveness and flexibility, and are prone to ignoring important features, affecting the final data analysis and diagnostic results.

[0008] 4. Existing technologies lack a mechanism for nonlinear adjustment of complex relationships between different features, resulting in insufficient accuracy and flexibility in matching degree calculation. Summary of the Invention

[0009] This invention provides an intelligent medical diagnostic system and method based on artificial intelligence and big data analysis to address the following problems in the current application of artificial intelligence and big data technologies in the medical field: the inability to accurately integrate medical data, thus limiting the depth and breadth of medical data analysis and failing to comprehensively reflect the patient's health status; the lack of flexibility in setting the importance weights of medical data, which cannot be dynamically adjusted according to specific medical application scenarios, resulting in insufficient representativeness and practicality of the fusion results; and the insufficient accuracy of the final data analysis and diagnostic results and the lack of precision and flexibility in the matching degree calculation.

[0010] An embodiment of the present invention discloses an intelligent medical diagnosis method based on artificial intelligence and big data analysis, comprising the following steps:

[0011] S1: Real-time acquisition of medical datasets, preprocessing of data in the medical datasets to obtain a unified format medical dataset, and using a dataset fusion algorithm based on the unified format medical dataset to obtain a comprehensive medical dataset;

[0012] S2: Based on a comprehensive medical dataset, principal component analysis is used to extract features. Based on the extracted features, a feature scoring algorithm is used to calculate feature scores. Based on the feature scores, a scoring threshold is set, and features with scores higher than the scoring threshold are selected to form the preferred feature vector.

[0013] S3: Based on the optimized feature vector and rule base, the rule matching degree is calculated using a rule matching algorithm;

[0014] S4: Based on the rule matching degree, use an intelligent medical diagnosis matching algorithm to evaluate the diagnostic matching degree of the disease. Based on the diagnostic matching degree of the disease, select the disease with the highest diagnostic matching degree among all diseases as the final diagnosis result.

[0015] As one specific implementation method, in step S1, the medical dataset includes electronic medical records, medical images, and test data.

[0016] As a specific implementation method, in step S1, the integrated medical dataset assigns different weights to different medical datasets in a unified format through a dataset fusion algorithm, and calculates the weights based on time adjustment parameters and time weights.

[0017] As a specific implementation, in step S2, the feature score is calculated by the feature scoring algorithm based on the extracted features, combined with the feature importance weight, relevance score, frequency adjustment factor and nonlinear adjustment factor.

[0018] As a specific implementation method, step S3, the construction of the rule base includes:

[0019] Diagnostic criteria and symptoms of diseases are extracted from medical literature and expert knowledge to form diagnostic rules;

[0020] The diagnostic rules are encoded to build a rule base.

[0021] In one specific implementation, in step S3, the rule matching degree is calculated by the rule matching algorithm by weighting and normalizing the features in the preferred feature vector.

[0022] As a specific implementation, in step S4, the intelligent medical diagnosis matching algorithm performs weighted processing on the matching degree of all rules, nonlinear processing on the features using the tangent function and standard deviation, and smoothing on the rule matching degree using the exponential decay function to obtain the diagnostic matching degree of the disease.

[0023] Another embodiment of the present invention discloses an intelligent medical diagnostic system based on artificial intelligence and big data analysis. Applying the above-described intelligent medical diagnostic method based on artificial intelligence and big data analysis, the intelligent medical diagnostic system based on artificial intelligence and big data analysis includes:

[0024] The medical dataset acquisition module is used to acquire medical datasets in real time.

[0025] The data preprocessing module is used to receive the medical dataset from the medical dataset acquisition module and preprocess the data in the medical dataset to obtain a medical dataset in a unified format.

[0026] The dataset fusion module receives a unified format medical dataset from the data preprocessing module and processes the unified format medical dataset using a dataset fusion algorithm to obtain a comprehensive medical dataset.

[0027] The feature extraction module, based on the comprehensive medical dataset from the dataset fusion module, uses principal component analysis to extract features. Based on the extracted features, a feature scoring algorithm is used to calculate feature scores. Based on the feature scores, a scoring threshold is set, and features with scores higher than the scoring threshold are combined into a preferred feature vector.

[0028] The rule base construction module is used to extract diagnostic criteria and symptoms of diseases from medical literature and expert knowledge, form diagnostic rules, and encode the diagnostic rules to build a rule base;

[0029] The rule matching module, based on the preferred feature vectors from the feature extraction module and the rule base of the rule base construction module, uses a rule matching algorithm to calculate the rule matching degree;

[0030] The intelligent medical diagnosis module uses the rule matching degree calculated by the rule matching module to evaluate the diagnostic matching degree of the disease using the intelligent medical diagnosis matching algorithm. Based on the diagnostic matching degree of the disease, the disease with the highest diagnostic matching degree among all diseases is selected as the final diagnosis result.

[0031] The technical solutions of the embodiments of the present invention have at least the following beneficial effects:

[0032] 1. The dataset fusion algorithm highlights important medical data by assigning different weights to different datasets. By introducing a time weight factor, it ensures the timeliness and consistency of dataset fusion, guarantees the comprehensiveness and accuracy of the integrated medical dataset, improves the representativeness and practical value of the data, and provides a reliable data foundation for subsequent feature extraction.

[0033] 2. The feature scoring algorithm further scores the extracted features, comprehensively considering the importance, relevance, and frequency of occurrence of the features, calculates the feature score, sets a scoring threshold, and selects the preferred feature vectors. This can extract features with representativeness and practical value, effectively improving the accuracy of diagnosis.

[0034] 3. Based on the optimized feature vector, the system uses a rule matching algorithm to calculate the matching degree of the rules. By standardizing and nonlinearly processing the features, the comparability between features and the accuracy of the rule matching degree evaluation are ensured, enhancing the robustness and adaptability of the rule matching algorithm and providing a scientific basis for intelligent disease diagnosis.

[0035] 4. The intelligent diagnostic algorithm performs weighted and non-linear processing on the matching degree of all rules, and uses the exponential decay function and tangent function to smooth and adjust the matching degree, comprehensively evaluates the matching degree of the disease, ensures the rationality and reliability of the diagnostic matching degree, and makes the diagnostic results accurate and scientific. Attached Figure Description

[0036] Figure 1 This is a structural diagram of an intelligent medical diagnostic system based on artificial intelligence and big data analysis according to an embodiment of the present invention;

[0037] Figure 2 This is a flowchart of another embodiment of the present invention: an intelligent medical diagnosis method based on artificial intelligence and big data analysis. Detailed Implementation

[0038] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0040] The following description, in conjunction with the accompanying drawings, details the specific solutions of the intelligent medical diagnostic system and method based on artificial intelligence and big data analysis provided by this invention.

[0041] See attached document Figure 1 An embodiment of the present invention provides an intelligent medical diagnosis system based on artificial intelligence and big data analysis, including a medical dataset acquisition module, a data preprocessing module, a dataset fusion module, a feature extraction module, a rule base construction module, a rule matching module, and an intelligent medical diagnosis module.

[0042] The medical dataset acquisition module is used to acquire medical datasets in real time and output them to the data preprocessing module. For example, the medical dataset includes electronic medical records, medical images, and test data.

[0043] The data preprocessing module receives the medical dataset from the medical dataset acquisition module, preprocesses the data in the medical dataset to obtain a medical dataset in a unified format, and then outputs the unified format medical dataset to the dataset fusion module.

[0044] The dataset fusion module receives a medical dataset in a unified format from the data preprocessing module, uses a dataset fusion algorithm to obtain a comprehensive medical dataset, and outputs the comprehensive medical dataset to the feature extraction module.

[0045] The feature extraction module is used to extract features from the comprehensive medical dataset based on the dataset fusion module. It uses principal component analysis to extract features, calculates feature scores based on the extracted features using a feature scoring algorithm, sets a scoring threshold based on the feature scores, selects features with scores higher than the scoring threshold to form a preferred feature vector, and outputs the preferred feature vector to the rule matching module.

[0046] The rule base construction module is used to extract diagnostic criteria and symptoms of diseases from medical literature and expert knowledge, form diagnostic rules, encode the diagnostic rules, build a rule base, and output the rule base to the rule matching module.

[0047] The rule matching module is used to build the rule base of the rule base module based on the preferred feature vectors of the feature extraction module and the rule base. It uses the rule matching algorithm to calculate the rule matching degree and outputs the rule matching degree to the intelligent medical diagnosis module.

[0048] The intelligent medical diagnosis module is used to evaluate the diagnostic matching degree of diseases based on the rule matching degree output by the rule matching module, and selects the disease with the highest diagnostic matching degree among all diseases as the final diagnosis result.

[0049] See attached document Figure 2 Another embodiment of the present invention provides an intelligent medical diagnosis method based on artificial intelligence and big data analysis, comprising the following steps:

[0050] S1. Acquire medical datasets in real time, preprocess the data in the medical datasets to obtain a medical dataset in a unified format, and use a dataset fusion algorithm based on the unified format medical dataset to obtain a comprehensive medical dataset.

[0051] For example, the acquired medical dataset includes electronic medical records, medical images, and test data. Electronic medical records include diagnostic records and medication records; medical images include radiographs (plain films), CT scans (computed tomography), and MRI (magnetic resonance imaging); test data includes blood test data, urine test data, etc.

[0052] The data in the medical dataset is preprocessed to obtain a medical dataset in a unified format for dataset fusion. The data preprocessing can be performed using natural language processing and / or image processing techniques, which are well-known to those skilled in the art and will not be elaborated here.

[0053] Based on a unified format of medical datasets, a dataset fusion algorithm is used to obtain a comprehensive medical dataset, which improves the comprehensiveness and accuracy of the comprehensive medical dataset and ensures that the comprehensive medical dataset has representativeness and practical value.

[0054] Dataset fusion algorithms assign different weights W to different medical datasets. i This can highlight important medical datasets; by adjusting the time parameter γ and the time weight t i It can adjust the impact of the time dimension in the fusion of medical datasets, ensuring the timeliness and consistency of medical datasets.

[0055] The specific calculation formula for the comprehensive medical dataset is as follows:

[0056]

[0057] in, This represents a comprehensive medical dataset; The W symbol represents the summation symbol used to sum all medical datasets. i This represents the weight of the i-th medical dataset, reflecting its importance in the fusion process; This represents the i-th medical dataset; This represents the time weighting factor, comprehensively considering the impact of time to ensure the rationality and consistency of time factors in dataset fusion; t i γ represents the timestamp of the i-th medical dataset, reflecting the time dimension of the medical dataset; γ represents the time adjustment parameter, which controls the degree of influence of the time weight. To represent an exponential function and ensure timeliness; log(1+t) i () represents a logarithmic function, which smooths out time weights and prevents the time weight factor from having an excessive influence; The function represents a trigonometric function, with periodic time weighting adjustments introduced; T represents the period of dataset fusion; and π represents the constant of the periodic adjustment.

[0058] A comprehensive medical dataset was obtained by using a dataset fusion algorithm, which provided a reliable data foundation for subsequent feature extraction.

[0059] S2. Based on the comprehensive medical dataset, principal component analysis is used to extract features. Based on the extracted features, a feature scoring algorithm is used to calculate the feature scores. Based on the feature scores, a scoring threshold is set, and features with scores higher than the scoring threshold are selected to form the preferred feature vector.

[0060] Principal component analysis is a well-known technique in the field and will not be elaborated here. In order to identify key features that have an important impact on medical diagnosis, feature scores are calculated using feature scoring algorithms based on the extracted features.

[0061] The feature scoring algorithm ensures the comprehensiveness, rationality, and flexibility of feature scores by comprehensively considering the importance weight of features, relevance scores, frequency adjustment factors, and nonlinear adjustment factors, thereby achieving the effect of extracting representative and practically valuable features from complex and diverse medical datasets.

[0062] The specific formula for calculating feature scores is as follows:

[0063]

[0064] Among them, S j w represents the score of the j-th feature, used to evaluate the importance and priority of the feature; j The weight of the j-th feature is used to adjust the importance of different features; r jThe relevance score of the j-th feature is calculated using statistical methods, a technique well-known to those skilled in the art, and will not be elaborated upon here; f i This represents the frequency of the j-th feature, used to reflect the prevalence of the feature's occurrence. This represents the frequency adjustment factor, which adjusts the characteristic frequency using the reciprocal of the square root, balancing universal and rare features; ln(1+a·f i ) represents the logarithmic adjustment factor of frequency, which further adjusts the influence of feature frequency on feature score; a represents the frequency adjustment parameter, which controls the degree of influence of the logarithmic function of frequency; An exponential adjustment factor representing correlation is used, and an exponential function is used to process the correlation score to ensure that the feature scores are reasonable.

[0065] Based on feature scores, a scoring threshold is set, which can be customized according to the specific implementation scenario; no specific limit is imposed here. Features with scores higher than the scoring threshold are selected to form the preferred feature vector. The specific formula is as follows:

[0066]

[0067] in, This represents the preferred feature vector, which contains all features above the scoring threshold. m represents the number of features whose feature scores are higher than the scoring threshold, and F j S represents the j-th feature, j∈[1,m]; j S represents the score of the j-th feature; S′ represents the scoring threshold.

[0068] S3. Based on the optimized feature vector and rule base, the rule matching degree is calculated using a rule matching algorithm.

[0069] Diagnostic criteria and symptoms of diseases are extracted from medical literature and expert knowledge to form diagnostic rules. These diagnostic rules are then encoded to construct a rule base. The methods for constructing the rule base are well-known to those skilled in the art and will not be elaborated upon here.

[0070] The rule matching algorithm improves the comparability between different features by weighting and normalizing the features in the preferred feature vector, thus ensuring the accuracy of rule matching. It reduces computational complexity by using logarithmic normalization and weighted exponents, and can dynamically adapt to different application scenarios and needs by non-linearly adjusting the rule priority.

[0071] The specific formula for calculating rule matching degree is as follows:

[0072]

[0073] Among them, M l This indicates the matching degree of the l-th rule; This represents the Sigmoid function, used for non-linear adjustment to ensure smooth changes in priority, improving the flexibility and accuracy of rule matching; P l This indicates the priority of the l-th rule, determining its importance in the matching degree calculation; The sum of features is represented by α; α represents the rule matching weight of the j-th feature, reflecting the importance of the j-th feature in rule matching; log(μ) j +∈) represents a logarithmic transformation, used to normalize eigenvalues, improve the comparability between different features, and avoid zero-value problems in logarithmic calculations by using the offset ∈; μ j represents the average value of the j-th feature, used to normalize feature values ​​and ensure their stability in matching calculations; ∈ represents the offset, preventing the feature average value μ from being misaligned. j The problem of calculating the logarithm when β is zero; j Let u represent the matching factor for the j-th feature, ensuring the reasonableness of the feature in the rule matching process; j This represents the weighting exponent of the j-th feature, which enhances the influence of the feature weights through a power function.

[0074] The use of rule matching algorithms has improved the accuracy and efficiency of rule matching, enhanced the dynamic adaptability of intelligent medical diagnostic systems, and provided reliable data support and decision-making basis for disease diagnosis.

[0075] S4. Based on the rule matching degree, use an intelligent medical diagnosis matching algorithm to evaluate the diagnostic matching degree of the disease. Based on the diagnostic matching degree of the disease, select the disease with the highest diagnostic matching degree among all diseases as the final diagnosis result.

[0076] Based on rule matching degree, an intelligent medical diagnosis matching algorithm is used to evaluate the diagnostic matching degree of diseases, thereby achieving intelligent medical diagnosis. The intelligent medical diagnosis matching algorithm comprehensively evaluates the matching degree of diseases by weighting and non-linearly processing the matching degrees of all rules; it uses an exponential decay function. The influence of rule matching degree is smoothed out; tangent function and standard deviation adjustment are introduced to ensure the rationality and reliability of disease diagnosis matching degree.

[0077] The specific formula for calculating the diagnostic matching degree of the disease is as follows:

[0078]

[0079] Among them, D k R represents the diagnostic match for the k-th disease; k M represents the set of rules associated with the k-th disease; l This indicates the matching degree of the l-th rule; The exponential decay function representing the matching degree of a rule is used to smooth out the impact of the matching degree of the rule. δ represents the non-linear adjustment term, using the tangent function and standard deviation to non-linearly adjust the features, ensuring the rationality and flexibility of the diagnostic match; tan represents the tangent function, used to introduce non-linear adjustment to handle complex relationships between features; l This represents the adjustment factor for the l-th rule, used to linearly adjust the eigenvalues; σ represents the average value of the features in rule l. l This represents the standard deviation of the l-th rule, used to reduce dimensional differences between different characteristics.

[0080] Based on the diagnostic matching degree, the disease with the highest diagnostic matching degree among all diseases is selected as the final diagnosis result, ensuring the scientific nature and accuracy of the intelligent medical diagnostic system. The specific formula for calculating the diagnostic result is as follows:

[0081]

[0082] Where D′ represents the diagnostic result, i.e. the disease with the highest diagnostic match; This represents the maximum value operation, used to select the disease with the highest diagnostic match; D k This represents the diagnostic match degree for the k-th disease.

[0083] The order of the embodiments is for illustrative purposes only and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0084] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0085] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. An intelligent medical diagnostic method based on artificial intelligence and big data analysis, characterized in that: Includes the following steps: S1: Real-time acquisition of medical datasets; preprocessing of data within the medical datasets to obtain a unified format medical dataset; based on this unified format medical dataset, a dataset fusion algorithm is used to obtain a comprehensive medical dataset. The specific calculation formula is as follows: in, This represents a comprehensive medical dataset; W represents the summation symbol. i This represents the weight of the i-th medical dataset; This represents the i-th medical dataset; Indicates the time weighting factor; t i The timestamp of the i-th medical dataset is represented by γ; the time adjustment parameter is represented by T; the period of dataset fusion is represented by π; and the constant of periodic adjustment is represented by π. S2: Based on a comprehensive medical dataset, principal component analysis is used to extract features. Based on the extracted features, a feature scoring algorithm is used to calculate the feature score. The specific calculation formula is as follows: Among them, S j w represents the score of the j-th feature; j The weight of the j-th feature is represented by r. j f represents the relevance score of the j-th feature; j This represents the frequency of the j-th feature; Represents the frequency adjustment factor; ln(1+a·f) j ) represents the logarithmic adjustment factor of the frequency; a represents the frequency adjustment parameter; An index moderating factor indicating correlation; Based on feature scores, a scoring threshold is set, and features with scores higher than the scoring threshold are selected to form the preferred feature vector. S3: Based on the optimized feature vector and rule base, the rule matching degree is calculated using a rule matching algorithm. The specific calculation formula is as follows: Among them, M l P represents the matching degree of the l-th rule; l Indicates the priority of the l-th rule; α j μ represents the rule matching weight for the j-th feature. j The β represents the average value of the j-th feature; ∈ represents the offset; β j Represents the matching factor for the j-th feature; u j This represents the weighting index of the j-th feature; S4: Based on rule matching degree, an intelligent medical diagnostic matching algorithm is used to evaluate the diagnostic matching degree of the disease. The specific calculation formula is as follows: Among them, D k R represents the diagnostic match for the k-th disease; k M represents the set of rules associated with the k-th disease; l This indicates the matching degree of the l-th rule; Represents the nonlinear adjustment term; δ l This represents the adjustment factor for rule l; σ represents the average value of the features in rule l. l This represents the standard deviation of the l-th rule; Based on the diagnostic matching degree of the disease, the disease with the highest diagnostic matching degree among all diseases is selected as the final diagnosis result.

2. The intelligent medical diagnosis method based on artificial intelligence and big data analysis as described in claim 1, characterized in that, In step S1, the medical dataset includes electronic medical records, medical images, and test data.

3. The intelligent medical diagnosis method based on artificial intelligence and big data analysis as described in claim 1, characterized in that, In step S1, the integrated medical dataset assigns different weights to different medical datasets in a unified format through a dataset fusion algorithm, and calculates the weights based on time adjustment parameters and time weights.

4. The intelligent medical diagnosis method based on artificial intelligence and big data analysis as described in claim 1, characterized in that, In step S2, the feature score is calculated by the feature scoring algorithm based on the extracted features, combined with the feature importance weight, relevance score, frequency adjustment factor and nonlinear adjustment factor.

5. The intelligent medical diagnostic method based on artificial intelligence and big data analysis as described in claim 1, characterized in that, In step S3, the construction of the rule base includes: Diagnostic criteria and symptoms of diseases are extracted from medical literature and expert knowledge to form diagnostic rules; these diagnostic rules are then encoded to build a rule base.

6. The intelligent medical diagnosis method based on artificial intelligence and big data analysis as described in claim 1, characterized in that, In step S3, the rule matching degree is calculated by the rule matching algorithm by weighting and normalizing the features in the preferred feature vector.

7. The intelligent medical diagnosis method based on artificial intelligence and big data analysis as described in claim 1, characterized in that, In step S4, the intelligent medical diagnosis matching algorithm performs weighted processing on the matching degree of all rules, non-linear processing on the features using the tangent function and standard deviation, and smoothing on the rule matching degree using the exponential decay function to obtain the diagnostic matching degree of the disease.

8. An intelligent medical diagnostic system based on artificial intelligence and big data analysis, characterized in that: The intelligent medical diagnostic method based on artificial intelligence and big data analysis as described in any one of claims 1 to 7 is used, wherein the intelligent medical diagnostic system based on artificial intelligence and big data analysis comprises: The medical dataset acquisition module is used to acquire medical datasets in real time. The data preprocessing module is used to receive the medical dataset from the medical dataset acquisition module and preprocess the data in the medical dataset to obtain a medical dataset in a unified format. The dataset fusion module is used to receive the unified format medical dataset from the data preprocessing module, and process the unified format medical dataset using a dataset fusion algorithm to obtain a comprehensive medical dataset. The feature extraction module extracts features using principal component analysis based on the comprehensive medical dataset from the dataset fusion module. Based on the extracted features, a feature scoring algorithm is used to calculate feature scores. Based on the feature scores, a scoring threshold is set, and features with scores higher than the scoring threshold are grouped into a preferred feature vector. The rule base construction module is used to extract diagnostic criteria and symptoms of diseases from medical literature and expert knowledge, form diagnostic rules, and encode the diagnostic rules to build a rule base; The rule matching module calculates the rule matching degree using a rule matching algorithm based on the preferred feature vector from the feature extraction module and the rule base from the rule base construction module. The intelligent medical diagnosis module uses an intelligent medical diagnosis matching algorithm to evaluate the diagnostic matching degree of a disease based on the rule matching degree calculated by the rule matching module. Based on the diagnostic matching degree of the disease, the disease with the highest diagnostic matching degree among all diseases is selected as the final diagnosis result.

Images