Gastrointestinal health assessment and management method based on big data

Abstract

The invention relates to the technical field of health management, in particular to a gastrointestinal health assessment and management method based on big data, and the method comprises the following steps: S1, health data collection: collecting multi-dimensional health data of a user; s2, data preprocessing: preprocessing the collected multi-dimensional health data; s3, regulating and analyzing intestinal microecology, namely classifying and analyzing intestinal flora based on the intestinal flora gene sequencing data of the user in combination with living habits and diet data, identifying the condition of flora imbalance, and dynamically regulating flora balance through personalized regulation suggestions; s4, gastrointestinal health state evaluation: comprehensively evaluating the gastrointestinal health state of the user; and S5, generating a personalized health management scheme: generating the personalized health management scheme. According to the invention, by monitoring the health feedback of the user in real time, the scheme can be dynamically adjusted, so that the intervention is more flexible and targeted.

Description

Technical Field

[0001] The present invention relates to the field of health management technology, and in particular to a gastrointestinal health assessment and management method based on big data. Background Art

[0002] As people's living standards continue to improve, gastrointestinal health problems have become a common health hazard in modern society. Gastrointestinal dysfunction, intestinal flora imbalance and other problems not only affect digestive function, but are also closely related to the immune system, metabolic diseases, and mental health. Therefore, timely and accurate evaluation and management of gastrointestinal health is of great significance to the overall health of an individual. In recent years, the application of big data and smart health devices has provided new possibilities for real-time monitoring and management of gastrointestinal health, making personalized health management gradually become a trend.

[0003] The current management methods for gastrointestinal health on the market usually rely on a single source of health data, such as gastrointestinal function or intestinal flora testing, and lack the integration of multi-dimensional health data, resulting in one-sidedness and lack of accuracy in the evaluation results. In addition, most existing technologies use static health assessment methods, which are unable to make real-time adjustments and feedback based on changes in the user's health status. Personalized control plans are also relatively simple and difficult to meet the health needs of different users. Therefore, existing technologies have obvious deficiencies in the comprehensiveness, dynamism and personalization of data processing.

[0004] The present invention aims to address the deficiencies in the prior art and proposes a gastrointestinal health assessment and management method based on big data, which can monitor the user's health changes in real time, provide targeted regulation suggestions, and comprehensively cover gastrointestinal function, flora balance, living habits, mental health and other factors, greatly improving the intelligence level and effectiveness of gastrointestinal health management. Summary of the invention

[0005] The present invention provides a gastrointestinal health assessment and management method based on big data.

[0006] The gastrointestinal health assessment and management method based on big data includes the following steps:

[0007] S1, health data collection: collect users' multi-dimensional health data through wearable devices, gastrointestinal monitoring devices, and smart terminals, including gastrointestinal function test data, intestinal flora gene sequencing data, living habits and diet data, and mental health data;

[0008] S2, data preprocessing: preprocessing the collected multidimensional health data, including data denoising, cleaning, formatting, and missing data completion;

[0009] S3, intestinal microecological regulation and analysis: Based on the user's intestinal flora gene sequencing data, combined with living habits and dietary data, the intestinal flora is classified and analyzed, the imbalance of the flora is identified, and the balance of the flora is dynamically regulated through personalized regulation suggestions (such as probiotic supplementation or dietary adjustment), including:

[0010] S31, intestinal flora classification: Based on the collected intestinal flora gene sequencing data, the Gaussian mixture model (GMM) is used to classify the flora, divide the user's intestinal flora into multiple categories, identify the proportion of beneficial bacteria, conditional pathogens and harmful bacteria, and establish the user's individual intestinal flora distribution model based on the classification results;

[0011] S32, intestinal flora imbalance detection: Based on the established intestinal flora distribution model, the system compares the standard model of healthy flora to detect the imbalance of the user's intestinal flora and identify the problems of excessive proliferation of harmful bacteria or lack of beneficial bacteria;

[0012] S33, Personalized microbiome regulation and dynamic adjustment: Based on the detection results of imbalance, a personalized regulation plan is generated for the user, including probiotic supplementation and dietary structure adjustment;

[0013] S4, Gastrointestinal health status assessment: Analyze the pre-processed multi-dimensional health data based on the gastrointestinal health assessment model, and combine the results of intestinal microecological regulation to comprehensively assess the user's gastrointestinal health status;

[0014] S5, generation of personalized health management plan: Based on the assessment results of the user's gastrointestinal health status, a personalized health management plan is generated, including adjustment suggestions on diet, lifestyle, exercise and mental health.

[0015] Optionally, the health data collection in S1 includes:

[0016] S11, Gastrointestinal function test data collection: Gastrointestinal function-related data of the user is collected through gastrointestinal monitoring equipment, including gastric motility frequency and intensity, intestinal motility frequency and rhythm, and gastric acid secretion level;

[0017] S12, intestinal flora gene sequencing data collection: through smart terminals and gene sequencing equipment, obtain the user's intestinal flora gene sequencing data, including flora diversity index, dominant bacterial species ratio, and harmful bacterial species abundance;

[0018] S13, collection of life habits and dietary data: through the intelligent terminal combined with user input and external devices, collect life habits and dietary pattern data, including dietary structure and nutritional intake ratio, meal frequency and time, exercise frequency and intensity;

[0019] S14, mental health data collection: Collect users’ mental health related data through wearable devices, including stress index and sleep duration.

[0020] Optionally, the data preprocessing in S2 includes:

[0021] S21, data denoising: using a low-pass filter to denoise the collected multi-dimensional health data and remove high-frequency interference signals;

[0022] S22, data cleaning: Z-score standardization method was used to clean the collected multidimensional health data to remove outliers and duplicate data;

[0023] S23, data formatting: uniformly format multidimensional data and convert data from different sources and types into a unified structured data format;

[0024] S24, missing data completion: For missing data in the collection process, K nearest neighbor (KNN) interpolation method is used to complete it.

[0025] Optionally, the intestinal flora classification in S31 includes:

[0026] S311, Gaussian mixture model (GMM) classification: Use Gaussian mixture model (GMM) to classify intestinal flora and identify the proportion of beneficial bacteria, conditional pathogens and harmful bacteria;

[0027] S312, establishment of intestinal flora distribution model: Based on the classification results of the Gaussian mixture model, an intestinal flora distribution model of the individual user is established to reflect the abundance of various bacterial species.

[0028] Optionally, the intestinal flora imbalance detection in S32 includes:

[0029] S321, comparison between intestinal flora distribution model and health standard model: according to the intestinal flora distribution model of the user, the relative abundance of each flora category (such as beneficial bacteria, conditional pathogens, and harmful bacteria) is extracted and compared with the corresponding flora proportion in the pre-established health standard model. The health standard model is constructed based on the flora distribution data of healthy individuals and reflects the balance state of intestinal microecology;

[0030] S322, imbalance detection algorithm: uses KL divergence algorithm to quantify the difference between the user's bacterial flora distribution and the healthy standard distribution;

[0031] S323, identification of harmful bacteria proliferation and beneficial bacteria deficiency: Based on the results of imbalance detection, analyze the imbalance of the bacterial flora. When the KL divergence exceeds the set threshold, it is identified as excessive proliferation of harmful bacteria (such as conditional pathogens) or deficiency of beneficial bacteria (such as bifidobacteria and lactic acid bacteria), and potential health risks are marked.

[0032] Optionally, the personalized flora regulation and dynamic adjustment in S33 includes:

[0033] S331, generation of personalized regulation plan: Based on the results of imbalance detection, by analyzing the difference between the user's intestinal flora distribution model and the healthy standard model, a personalized regulation plan is generated, including probiotic supplementation and dietary structure adjustment;

[0034] S332, probiotic supplementation: according to the situation of probiotic deficiency of users, the amount of probiotics required is calculated, and the probiotics are supplemented to reach the abundance level in the health standard model;

[0035] S333, Dietary structure adjustment: Based on the imbalance of the user's intestinal flora, personalized dietary adjustment suggestions are recommended, including increasing dietary fiber or reducing high-fat diet to promote the growth of beneficial bacteria and inhibit the proliferation of harmful bacteria.

[0036] Optionally, the gastrointestinal health status assessment in S4 includes:

[0037] S41, multidimensional health data analysis: Based on the pre-processed multidimensional health data, a comprehensive analysis is performed through the gastrointestinal health assessment model to generate preliminary health analysis results;

[0038] S42, comprehensive assessment of health status: Based on the generated preliminary health analysis results and combined with the results of intestinal microecological regulation, a comprehensive assessment of the user's gastrointestinal health status is conducted.

[0039] Optionally, the gastrointestinal health assessment model in S41 adopts a Bayesian network model, and the Bayesian network model includes:

[0040] S411, feature selection: feature selection of input multi-dimensional health data through mutual information;

[0041] S412, Structural Learning: Structural learning of Bayesian networks determines the dependencies between variables in the network (i.e., directed edges) based on data, and uses the Bayesian Information Criterion (BIC) to evaluate different network structures to select the optimal structure;

[0042] S413, parameter learning: using Bayesian estimation methods to learn the conditional probability table of each node in the network structure;

[0043] S414, Model Evaluation: Evaluate and optimize the model through cross-validation.

[0044] Optionally, the comprehensive health status assessment in S42 includes:

[0045] S421, integration of health analysis results: Based on the preliminary health analysis results, combined with the user's intestinal microecological regulation effect (such as changes in flora after probiotic supplementation, health response after dietary structure adjustment), multi-dimensional health data is comprehensively processed and a weighted algorithm is used to calculate the health status score;

[0046] S422, Comprehensive assessment of health status: Based on the comprehensive scoring results, the user's gastrointestinal health status is assessed using difference analysis by comparing with the health standard model.

[0047] Optionally, the generation of the personalized health management plan in S5 includes:

[0048] S51, generating personalized dietary recommendations: generating personalized dietary adjustment recommendations based on the user's health status assessment results, including increasing dietary fiber intake and reducing fat or sugar intake;

[0049] S52, adjustment of living habits: based on living habits and dietary data, make suggestions for improvement, including adjusting work and rest time, improving sleep quality, and reducing stress index;

[0050] S53, exercise suggestion: Generate a personalized exercise plan based on the user's health status assessment results, including adjusting the exercise frequency, intensity and form;

[0051] S54, Mental Health Support: Based on mental health data, users are advised to adopt meditation and relaxation training methods to maintain their mental state.

[0052] Beneficial effects of the present invention:

[0053] The present invention ensures the comprehensiveness and diversity of data sources through the collection and processing of multidimensional health data, including gastrointestinal function, intestinal flora, living habits, diet and mental health. Through efficient data preprocessing operations (denoising, cleaning, formatting, missing data completion), the accuracy and consistency of the data are guaranteed. The processing of multidimensional health data provides a reliable basis for gastrointestinal health assessment, effectively improves the accuracy of the model, and makes the assessment results more scientific.

[0054] The present invention realizes personalized monitoring and dynamic adjustment of the user's health status through intestinal microecological regulation, health status assessment and generation of personalized management plans. Based on intestinal flora classification and imbalance detection, a personalized regulation plan is generated, including probiotic supplementation, dietary adjustment, lifestyle intervention, etc. By real-time monitoring of the user's health feedback, the plan can be dynamically adjusted, making the intervention more flexible and targeted.

[0055] The present invention, through the application of the Bayesian network model, can dynamically adjust the evaluation according to the health changes of the user, help the user to discover health problems earlier, and achieve long-term and comprehensive health management through precise intervention measures, thereby significantly improving the efficiency and effectiveness of gastrointestinal health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 A schematic diagram of a management method flow chart of an embodiment of the present invention;

[0058] Figure 2 Schematic diagram of intestinal microecological regulation and analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0060] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0061] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0062] like Figure 1-Figure 2 As shown, the gastrointestinal health assessment and management method based on big data includes the following steps:

[0063] S1, health data collection: collect users' multi-dimensional health data through wearable devices, gastrointestinal monitoring devices, and smart terminals, including gastrointestinal function test data, intestinal flora gene sequencing data, living habits and diet data, and mental health data;

[0064] S2, data preprocessing: preprocessing the collected multidimensional health data, including data denoising, cleaning, formatting, and missing data completion;

[0065] S3, intestinal microecological regulation and analysis: Based on the user's intestinal flora gene sequencing data, combined with living habits and dietary data, the intestinal flora is classified and analyzed, the imbalance of the flora is identified, and the balance of the flora is dynamically regulated through personalized regulation suggestions (such as probiotic supplementation or dietary adjustment), including:

[0066] S31, intestinal flora classification: Based on the collected intestinal flora gene sequencing data, the Gaussian mixture model (GMM) is used to classify the flora, divide the user's intestinal flora into multiple categories, identify the proportion of beneficial bacteria, conditional pathogens and harmful bacteria, and establish the user's individual intestinal flora distribution model based on the classification results;

[0067] S32, intestinal flora imbalance detection: Based on the established intestinal flora distribution model, the system compares the standard model of healthy flora to detect the imbalance of the user's intestinal flora and identify the problems of excessive proliferation of harmful bacteria or lack of beneficial bacteria;

[0068] S33, Personalized microbiome regulation and dynamic adjustment: Based on the detection results of imbalance, a personalized regulation plan is generated for the user, including probiotic supplementation and dietary structure adjustment;

[0069] S4, Gastrointestinal health status assessment: Analyze the pre-processed multi-dimensional health data based on the gastrointestinal health assessment model, and combine the results of intestinal microecological regulation to comprehensively assess the user's gastrointestinal health status;

[0070] S5, Personalized health management plan generation: Based on the evaluation results of the user's gastrointestinal health status, a personalized health management plan is generated, including adjustment suggestions on diet, lifestyle, exercise and mental health;

[0071] Through the above steps, gastrointestinal health problems can be accurately identified, and real-time intervention and optimization plans can be provided. This can comprehensively cover multiple factors such as gastrointestinal function, intestinal flora, living habits and mental health, achieve personalized and dynamic health management, and effectively improve the accuracy of gastrointestinal health assessment and regulation effects.

[0072] Health data collection in S1 includes:

[0073] S11, Gastrointestinal function test data collection: Gastrointestinal function-related data of the user is collected through gastrointestinal monitoring equipment, including gastric motility frequency and intensity, intestinal motility frequency and rhythm, and gastric acid secretion level;

[0074] S12, intestinal flora gene sequencing data collection: through smart terminals and gene sequencing equipment, obtain the user's intestinal flora gene sequencing data, including flora diversity index, dominant bacterial species ratio, and harmful bacterial species abundance;

[0075] S13, collection of life habits and dietary data: through the intelligent terminal combined with user input and external devices, collect life habits and dietary pattern data, including dietary structure and nutritional intake ratio, meal frequency and time, exercise frequency and intensity;

[0076] S14, mental health data collection: collect users’ mental health related data through wearable devices, including stress index and sleep duration;

[0077] Through the above content, the user's health status can be monitored in real time, especially personalized analysis of gastrointestinal health, to ensure that the management plan is more targeted and scientific. At the same time, the combination of multi-dimensional data makes the health assessment more comprehensive and accurate, providing reliable support for the user's long-term health management.

[0078] Data preprocessing in S2 includes:

[0079] S21, data denoising: A low-pass filter is used to denoise the collected multi-dimensional health data to remove high-frequency interference signals, which can be expressed as:

[0080]

[0081] Among them, x(τ) is the original input signal, which represents the collected original data, y(t) is the denoised data, T is the filter window, and t is the current time point;

[0082] S22, data cleaning: Z-score standardization method was used to clean the collected multidimensional health data to remove outliers and duplicate data;

[0083] S23, data formatting: uniformly format multidimensional data and convert data from different sources and types into a unified structured data format;

[0084] S24, missing data completion: For missing data in the collection process, the K nearest neighbor (KNN) interpolation method is used to complete it, which is expressed as:

[0085]

[0086] in, is the estimated value of the missing data, x j is the value of the K nearest data points, K is the number of neighboring data;

[0087] Through the above content, the accuracy, completeness and consistency of the collected multidimensional health data are ensured. The denoising and cleaning operations effectively filter out environmental noise and abnormal data, improve the data quality, the formatting processing ensures the compatibility of data from different sources, and the missing data completion enables the data to maintain continuity during the analysis process, providing a reliable and high-quality data foundation for subsequent gastrointestinal health assessment and personalized management plans, greatly improving the accuracy and practicality of the model.

[0088] The intestinal flora classification in S31 includes:

[0089] S311, Gaussian mixture model (GMM) classification: Use Gaussian mixture model (GMM) to classify intestinal flora, identify the proportion of beneficial bacteria, conditional pathogens and harmful bacteria, and use the abundance and gene characteristics of intestinal flora as input to perform cluster analysis of multidimensional features, expressed as:

[0090]

[0091] Where p(x) is the probability density function of data point x, which represents the weighted probability that a data point belongs to different categories under a given mixed model, K is the number of categories in the mixed model, and π k is the mixing coefficient of the kth class, indicating the weight of the kth class in the population, is the probability density function of the normal distribution of the kth class, indicating that the data point x is given by the mean μ k and the covariance matrix ∑ k The probability of belonging to the kth class under the condition of ;

[0092] S312, intestinal flora distribution model establishment: According to the classification results of the Gaussian mixture model, the intestinal flora distribution model of the user is established to reflect the abundance of various bacterial species, which is expressed as:

[0093]

[0094] Among them, Relative Abundance k is the relative abundance of the k-th bacterial group (such as beneficial bacteria, pathogenic bacteria, etc.), indicating the proportion of the k-th bacterial group in all bacterial groups, N k is the number or abundance of the k-th bacterial group, which can be obtained through the classification results in the Gaussian mixture model (GMM), N total It is the total number or abundance of all bacterial flora in the intestine, that is, the sum of the abundance of all bacterial flora categories;

[0095] Through the above content, the ratio of beneficial bacteria, conditional pathogens and harmful bacteria can be effectively identified, and an individualized flora distribution model can be constructed. Key information can be extracted from a large amount of complex flora data, and flora imbalance problems can be identified, thereby providing a scientific basis for personalized regulation plans. At the same time, by calculating the relative abundance of flora, the intestinal health status can be dynamically monitored, providing more accurate health management and intervention measures.

[0096] Intestinal flora imbalance detection in S32 includes:

[0097] S321, Comparison between intestinal flora distribution model and health standard model: According to the intestinal flora distribution model of the user, the relative abundance of each flora category (such as beneficial bacteria, conditional pathogens, and harmful bacteria) is extracted and compared with the corresponding flora proportion in the pre-established health standard model. The health standard model is constructed based on the flora distribution data of healthy individuals and reflects the balance state of intestinal microecology, which is expressed as:

[0098]

[0099] Where Q(i) is the average abundance of the i-th bacterial group in the health standard model (such as beneficial bacteria or harmful bacteria), N ij is the abundance of the i-th bacterial group of the j-th healthy individual, and M is the total number of healthy individuals;

[0100] S322, imbalance detection algorithm: KL divergence algorithm is used to quantify the difference between the user's bacterial population distribution and the healthy standard distribution, expressed as:

[0101]

[0102] Among them, D KL (P||Q) is the KL divergence, which is used to measure the difference between two probability distributions P and Q. P(i) is the probability of the i-th bacterial flora in the user's intestinal flora distribution model, indicating the relative abundance of the i-th bacterial flora in the user's intestinal flora distribution model. Q(i) is the probability of the i-th bacterial flora in the health standard model, indicating the relative abundance of the i-th bacterial flora in healthy individuals. n is the total number of bacterial categories.

[0103] S323, identification of harmful bacteria proliferation and beneficial bacteria deficiency: Analyze the imbalance of the bacterial flora based on the results of imbalance detection. When the KL divergence exceeds the set threshold, it is identified as excessive proliferation of harmful bacteria (such as conditional pathogens) or deficiency of beneficial bacteria (such as bifidobacteria and lactic acid bacteria), and potential health risks are marked;

[0104] The thresholds are set based on historical data of healthy people, including:

[0105] Data collection: Collect intestinal flora distribution data of a large number of healthy people and build a health standard model Q(i) based on these data;

[0106] Divergence calculation: For each individual j in the healthy population, calculate the intestinal flora distribution P j The KL divergence D between (i) and the healthy standard model Q(i) KL (P j ||Q);

[0107] Statistical analysis: Statistical analysis of the KL divergence of all healthy people, and calculate the mean value μ of the KL divergence KL and standard deviation σ KL , expressed as:

[0108]

[0109] Where, M is the sample size of healthy people;

[0110] Threshold setting: Based on the 3σ principle in statistics, the threshold is set to the mean of the KL divergence of healthy people plus several times the standard deviation, expressed as:

[0111] Threshold=μ KL +3·σ KL .

[0112] Through the above content, problems such as the proliferation of harmful bacteria or the lack of beneficial bacteria can be accurately identified, and scientific and reasonable thresholds can be set based on a large amount of historical data to ensure the accuracy and sensitivity of detection, so as to timely detect abnormalities in the intestinal microecology, provide data support for personalized intervention and adjustment, and help users maintain intestinal health.

[0113] The personalized microbiome regulation and dynamic adjustment in S33 include:

[0114] S331, generation of personalized regulation plan: Based on the results of imbalance detection, by analyzing the difference between the user's intestinal flora distribution model and the health standard model, a personalized regulation plan is generated, including probiotic supplementation and dietary structure adjustment, which is expressed as:

[0115] ΔP(i)=Q(i)-P(i);

[0116] Among them, ΔP(i) is the difference between the user's actual bacterial flora abundance and the health standard, Q(i) is the relative abundance of the i-th bacterial flora in the health standard model, and P(i) is the relative abundance of the i-th bacterial flora;

[0117] S332, probiotic supplementation: In case of lack of probiotics in users, calculate the amount of probiotics required to be supplemented, and supplement probiotics to reach the abundance level in the health standard model, expressed as:

[0118] ΔProbiotic=k·ΔP Beneficial ;

[0119] Among them, ΔP Beneficial represents the missing amount of beneficial bacteria, and k is the regulation coefficient;

[0120] S333, dietary structure adjustment: According to the imbalance of the user's intestinal flora, personalized dietary adjustment suggestions are recommended, including increasing dietary fiber or reducing high-fat diet to promote the growth of beneficial bacteria and inhibit the proliferation of harmful bacteria. The optimization of dietary adjustment is optimized through the objective function, which is expressed as:

[0121]

[0122] Where n is the total number of bacterial species, P(i) new is the adjusted relative abundance of the i-th bacterial group, indicating the new distribution of each bacterial group category after the implementation of the personalized regulation scheme;

[0123] Through the above content, refined and dynamic intervention can be carried out according to the individual differences of users to help restore the balance of intestinal flora and improve health status. At the same time, the regulation plan is adjusted in real time according to the user's health feedback to achieve personalized and continuous intestinal health management.

[0124] The gastrointestinal health status assessment in S4 includes:

[0125] S41, multidimensional health data analysis: Based on the pre-processed multidimensional health data, a comprehensive analysis is performed through the gastrointestinal health assessment model to generate preliminary health analysis results;

[0126] S42, comprehensive assessment of health status: Based on the generated preliminary health analysis results and combined with the results of intestinal microecological regulation, a comprehensive assessment of the user's gastrointestinal health status is conducted;

[0127] Through the above content, the accuracy and personalization of the assessment are improved, which can help users detect health problems early and provide targeted regulation plans to achieve more accurate health management.

[0128] The gastrointestinal health assessment model in S41 adopts the Bayesian network model, which includes:

[0129] S411, feature selection: feature selection is performed on the input multi-dimensional health data through mutual information, which is expressed as:

[0130]

[0131] Where I(X;Y) represents the mutual information between random variables X and Y, p(x,y) is the joint probability distribution of X and Y, and p(x) and p(y) represent the marginal probability distributions of X and Y respectively.

[0132] S412, Structural Learning: The structural learning of Bayesian networks determines the dependencies between variables in the network (i.e., directed edges) based on data, and uses the Bayesian Information Criterion (BIC) to evaluate different network structures to select the optimal structure. BIC balances the goodness of fit of the data and the complexity of the model to avoid overfitting, which is expressed as:

[0133]

[0134] Where G is the network structure, D is the data, N is the number of samples, |G| is the number of model parameters, and P(D|G) is the likelihood function of the data D given the network structure G, that is, the probability of the data under this structure;

[0135] S413, parameter learning: Use the Bayesian estimation method to learn the conditional probability table of each node in the network structure, expressed as:

[0136]

[0137] Among them, pa(x i ) is the node x i The parent node of is the observed corresponding parent node and x i , S is the number of states, α is the smoothing parameter (Laplace smoothing), P(x i |pa(x i )) is given by x i The parent node pa(x i ), calculate x i The conditional probability of

[0138] S414, model evaluation: The model is evaluated and optimized through cross-validation to ensure that the model can accurately reflect the gastrointestinal health status and adapt to the health changes of different users, expressed as:

[0139]

[0140] Where k is the number of cross-validation folds, L is the loss function, and They are the test data of the i-th fold and the trained model respectively;

[0141] Through the above content, the model's ability to handle uncertainty and sparse data has been enhanced, making health data analysis more robust and able to dynamically adapt to data changes, providing accurate assessment and decision support for personalized health management, and significantly improving the intelligence level of gastrointestinal health assessment and management.

[0142] The comprehensive assessment of health status in S42 includes:

[0143] S421, health analysis result integration: Based on the preliminary health analysis results, combined with the user's intestinal microecological regulation effect (such as changes in flora after probiotic supplementation, health response after dietary structure adjustment), multi-dimensional health data is comprehensively processed and a weighted algorithm is used to calculate the health status score, which is expressed as:

[0144] H total =w1·H gut +w2·H microbiome +w3·H diet +w4·H lifestyle ;

[0145] Among them, H total is the comprehensive health score, H gut , H microbiome , H diet , H lifestyle are the health scores of gastrointestinal function, flora status, diet and lifestyle habits, respectively. w1, w2, w3 and w4 are weight coefficients, which are used to reflect the relative importance of each health dimension.

[0146]

[0147] Among them, H gut The health score of gastrointestinal function, x i is the gastrointestinal function data of the ith item actually measured by the user, μ i is the health standard mean, the standard mean corresponding to the i-th gastrointestinal function, σ i is the standard deviation, the standard deviation corresponding to the i-th gastrointestinal function reflects the fluctuation of the data, and n is the total number of gastrointestinal function indicators;

[0148]

[0149] Among them, H microbioome is the health score of the microbial community status, π i is the weight of the i-th bacterial group, indicating the proportion of this bacterial group in the whole, μ i is the mean value of the health standard corresponding to the i-th type of bacteria, σ i is the standard deviation corresponding to the i-th bacterial group, and K is the total number of bacterial groups;

[0150]

[0151] Among them, H diet Score the healthiness of your diet, actual i is the user's actual dietary intake value for the i-th item, recommended i is the dietary intake value of the ith item recommended for health, and n is the total number of dietary data items;

[0152]

[0153] Among them, H lifestyle Score the health of your lifestyle habits, x j is the jth item of actual living habit data of the user (such as exercise frequency, sleep quality, etc.), μ j is the mean value of the jth health standard and the corresponding mean value of standard healthy living habits, σ j is the standard deviation of the jth item, and m is the total number of lifestyle indicators;

[0154] The weight coefficients w1, w2, w3, and w4 are set based on the opinions of clinical experts. Experts determine the importance of various dimensions such as gastrointestinal function, flora status, diet and lifestyle habits to overall health based on the user's specific health data and evaluation results. The weights are reasonably distributed according to the impact intensity of different health factors to ensure that the model can accurately reflect the user's health status, w1+w2+w3+w4=1;

[0155] S422, comprehensive evaluation of health status: Based on the comprehensive scoring results, the user's gastrointestinal health status is evaluated by using difference analysis by comparing with the health standard model, expressed as:

[0156]

[0157] Among them, D health Indicates the difference percentage between the user's health status and the health standard, H standard is the score of the health standard model, if D health If the health threshold is exceeded, it indicates that the user has gastrointestinal health problems and needs further regulation;

[0158] Health Threshol health Threshold setting based on historical data of healthy population includes:

[0159] Data collection: Collect gastrointestinal health score data of a large number of healthy individuals and calculate the health score distribution of these healthy individuals;

[0160] Calculate the mean and standard deviation: Calculate the mean (μ health ) and standard deviation (σhealth ), used to construct health reference ranges;

[0161] Threshold setting: The threshold is set using a statistical method based on the 3σ principle, expressed as:

[0162] Threshold health =μ health -k·σ health ;

[0163] Among them, μ health is the mean gastrointestinal health score of healthy individuals, σ health is the standard deviation of the healthy individual score, k is a constant, and according to the set risk level, it takes a value of 3 (i.e., the 3σ principle);

[0164] Through the above content, it is possible to dynamically quantify the impact of different health dimensions on overall health, and by comparing with health standards, identify users' potential health risks. By using weighted algorithms and difference analysis, it is possible to ensure the accuracy of personalized regulation recommendations, which helps users better manage and intervene in their health.

[0165] The generation of personalized health management plans in S5 includes:

[0166] S51, generate personalized diet suggestions: generate personalized diet adjustment suggestions based on the user's health status assessment results, including increasing dietary fiber intake, reducing fat or sugar intake, optimizing diet structure, and ensuring that the user takes in balanced nutrition;

[0167] S52, adjustment of living habits: based on living habits and dietary data, suggestions for improvement are made, including adjusting work and rest time, improving sleep quality, and reducing stress index, to help users improve their overall health;

[0168] S53, exercise suggestions: Generate personalized exercise plans based on the user's health status assessment results, including adjusting exercise frequency, intensity and form to help users maintain good body metabolism and intestinal health;

[0169] S54, Mental Health Support: Based on mental health data, users are advised to adopt meditation and relaxation training methods to maintain their mental state, thereby promoting the improvement of overall health;

[0170] Through the above content, it can ensure that each user receives accurate advice that suits their health status, which helps to improve health problems in a targeted manner. Through comprehensive intervention, users can more effectively regulate gastrointestinal function, optimize bacterial flora status, and improve quality of life, thereby achieving long-term and comprehensive health management.

[0171] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0172] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A gastrointestinal health assessment and management method based on big data, characterized in that: The following steps are involved: S1, health data collection: collect users' multi-dimensional health data through wearable devices, gastrointestinal monitoring devices, and smart terminals, including gastrointestinal function test data, intestinal flora gene sequencing data, living habits and diet data, and mental health data; S2, data preprocessing: preprocessing the collected multidimensional health data, including data denoising, cleaning, formatting, and missing data completion; S3, intestinal microecological regulation and analysis: Based on the user's intestinal flora gene sequencing data, combined with living habits and dietary data, the intestinal flora is classified and analyzed, the imbalance of the flora is identified, and the balance of the flora is dynamically regulated through personalized regulation suggestions, including: S31, intestinal flora classification: Based on the collected intestinal flora gene sequencing data, the Gaussian mixture model is used to classify the flora, divide the user's intestinal flora into multiple categories, identify the proportion of beneficial bacteria, conditional pathogens and harmful bacteria, and establish the user's individual intestinal flora distribution model based on the classification results; S32, intestinal flora imbalance detection: Based on the established intestinal flora distribution model, the system compares the standard model of healthy flora to detect the imbalance of the user's intestinal flora and identify the problems of excessive proliferation of harmful bacteria or lack of beneficial bacteria; S33, Personalized microbiome regulation and dynamic adjustment: Based on the detection results of imbalance, a personalized regulation plan is generated for the user, including probiotic supplementation and dietary structure adjustment; S4, Gastrointestinal health status assessment: Analyze the pre-processed multi-dimensional health data based on the gastrointestinal health assessment model, and combine the results of intestinal microecological regulation to comprehensively assess the user's gastrointestinal health status; S5, generation of personalized health management plan: Based on the assessment results of the user's gastrointestinal health status, a personalized health management plan is generated, including adjustment suggestions on diet, lifestyle, exercise and mental health.

2. The gastrointestinal health assessment and management method based on big data according to claim 1, characterized in that: The health data collection in S1 includes: S11, Gastrointestinal function test data collection: Gastrointestinal function-related data of the user is collected through gastrointestinal monitoring equipment, including gastric motility frequency and intensity, intestinal motility frequency and rhythm, and gastric acid secretion level; S12, intestinal flora gene sequencing data collection: through smart terminals and gene sequencing equipment, obtain the user's intestinal flora gene sequencing data, including flora diversity index, dominant bacterial species ratio, and harmful bacterial species abundance; S13, collection of life habits and dietary data: through the intelligent terminal combined with user input and external devices, collect life habits and dietary pattern data, including dietary structure and nutritional intake ratio, meal frequency and time, exercise frequency and intensity; S14, mental health data collection: Collect users’ mental health related data through wearable devices, including stress index and sleep duration.

3. The gastrointestinal health assessment and management method based on big data according to claim 1, characterized in that: The data preprocessing in S2 includes: S21, data denoising: using a low-pass filter to denoise the collected multi-dimensional health data and remove high-frequency interference signals; S22, data cleaning: Z-score standardization method was used to clean the collected multidimensional health data to remove outliers and duplicate data; S23, data formatting: uniformly format multidimensional data and convert data from different sources and types into a unified structured data format; S24, missing data completion: For missing data in the collection process, K nearest neighbor interpolation method is used to complete it.

4. The gastrointestinal health assessment and management method based on big data according to claim 1, characterized in that: The intestinal flora classification in S31 includes: S311, Gaussian mixture model classification: Use Gaussian mixture model to classify intestinal flora and identify the proportion of beneficial bacteria, conditional pathogens and harmful bacteria; S312, establishment of intestinal flora distribution model: Based on the classification results of the Gaussian mixture model, an intestinal flora distribution model of the individual user is established to reflect the abundance of various bacterial species.

5. The gastrointestinal health assessment and management method based on big data according to claim 4 is characterized in that: The intestinal flora imbalance detection in S32 includes: S321, Comparison between intestinal flora distribution model and health standard model: According to the user's intestinal flora distribution model, the relative abundance of each flora category is extracted and compared with the corresponding flora proportion in the pre-established health standard model. The health standard model is constructed based on the flora distribution data of healthy individuals and reflects the balance state of intestinal microecology; S322, imbalance detection algorithm: uses KL divergence algorithm to quantify the difference between the user's bacterial flora distribution and the healthy standard distribution; S323, identification of harmful bacteria proliferation and beneficial bacteria deficiency: Based on the results of imbalance detection, analyze the imbalance of the bacterial flora. When the KL divergence exceeds the set threshold, it is identified as excessive proliferation of harmful bacteria or deficiency of beneficial bacteria, and potential health risks are marked.

6. The gastrointestinal health assessment and management method based on big data according to claim 5, characterized in that: The personalized flora regulation and dynamic adjustment in S33 includes: S331, generation of personalized regulation plan: Based on the results of imbalance detection, by analyzing the difference between the user's intestinal flora distribution model and the healthy standard model, a personalized regulation plan is generated, including probiotic supplementation and dietary structure adjustment; S332, probiotic supplementation: according to the situation of probiotic deficiency of users, the amount of probiotics required is calculated, and the probiotics are supplemented to reach the abundance level in the health standard model; S333, Dietary structure adjustment: Based on the imbalance of the user's intestinal flora, personalized dietary adjustment suggestions are recommended, including increasing dietary fiber or reducing high-fat diet to promote the growth of beneficial bacteria and inhibit the proliferation of harmful bacteria.

7. The gastrointestinal health assessment and management method based on big data according to claim 1, characterized in that: The gastrointestinal health status assessment in S4 includes: S41, multidimensional health data analysis: Based on the pre-processed multidimensional health data, a comprehensive analysis is performed through the gastrointestinal health assessment model to generate preliminary health analysis results; S42, comprehensive assessment of health status: Based on the generated preliminary health analysis results and combined with the results of intestinal microecological regulation, a comprehensive assessment of the user's gastrointestinal health status is conducted.

8. The gastrointestinal health assessment and management method based on big data according to claim 7, characterized in that: The gastrointestinal health assessment model in S41 adopts a Bayesian network model, and the Bayesian network model includes: S411, feature selection: feature selection of input multi-dimensional health data through mutual information; S412, Structural Learning: Structural learning of Bayesian networks determines the dependencies between variables in the network based on data, and uses the Bayesian Information Criterion to evaluate different network structures to select the optimal structure; S413, parameter learning: using Bayesian estimation methods to learn the conditional probability table of each node in the network structure; S414, Model Evaluation: Evaluate and optimize the model through cross-validation.

9. The gastrointestinal health assessment and management method based on big data according to claim 8, characterized in that: The comprehensive health status assessment in S42 includes: S421, health analysis result integration: Based on the preliminary health analysis results and combined with the user's intestinal microecological regulation effect, the multi-dimensional health data is comprehensively processed and a weighted algorithm is used to calculate the health status score; S422, Comprehensive assessment of health status: Based on the comprehensive scoring results, the user's gastrointestinal health status is assessed using difference analysis by comparing with the health standard model.

10. The gastrointestinal health assessment and management method based on big data according to claim 1, characterized in that: The generation of the personalized health management plan in S5 includes: S51, generating personalized dietary recommendations: generating personalized dietary adjustment recommendations based on the user's health status assessment results, including increasing dietary fiber intake and reducing fat or sugar intake; S52, adjustment of living habits: based on living habits and dietary data, make suggestions for improvement, including adjusting work and rest time, improving sleep quality, and reducing stress index; S53, exercise suggestion: Generate a personalized exercise plan based on the user's health status assessment results, including adjusting the exercise frequency, intensity and form; S54, Mental Health Support: Based on mental health data, users are advised to adopt meditation and relaxation training methods to maintain their mental state.

Images