Intestinal micro-ecological health assessment method and system based on big data

Abstract

The present application relates to the field of health care technology, in particular to a method and system for evaluating intestinal micro-ecological health based on big data, comprising: S1, obtaining multi-dimensional health data of a target object at multiple consecutive time points; S2, constructing an individualized intestinal ecological topology graph changing with time based on the multi-dimensional health data; S3, performing evolution analysis on the intestinal ecological topology graph to determine the health status evaluation result of the intestinal micro-ecology. The present application constructs an intestinal ecological topology graph evolving with time by obtaining and aligning multi-modal data at consecutive time points, so that the evaluation is no longer limited to the composition of the bacterial community at a certain moment, but can reproduce the dynamic evolution process of the intestinal micro-ecosystem before and after intervention, and truly reflects the time series behavior and response trajectory.

Description

[0001] Big Data-Based Methods and Systems for Assessing Gut Microbiota Health Technical Field

[0002] This invention relates to the field of healthcare technology, specifically to a method and system for assessing gut microbiota health based on big data. Background Technology

[0003] The human gut microbiota is a complex and dynamic system composed of hundreds of microorganisms, host cells, and the metabolic environment. Its balance is closely related to the overall health of the host. With the popularization of high-throughput sequencing technology, detecting the gut microbiota and assessing its health status has become an important part of health management.

[0004] Currently, mainstream methods for assessing gut health have the following limitations: First, existing methods rely on microbial sequencing of fecal samples at a single time point to generate a static report reflecting the relative abundance of species. This method can only reveal the community composition at the sampling time and cannot capture the dynamic evolution of the microbiome with diet, lifestyle, and especially external interventions (such as taking probiotic preparations). Furthermore, it separates microbial data from the user's physiological state and behavioral data, failing to provide a comprehensive analysis. Second, existing big data-based analysis methods often input multidimensional health data into pre-set machine learning or deep learning models to obtain a classifier (e.g., healthy / sub-healthy / disease). The conclusions of this assessment method are usually simple labels or probabilities, unable to explain how the microbiome interacts specifically with the host, nor can they clearly elucidate which key microorganisms an intervention affects and what ecological effects it triggers. Summary of the Invention

[0005] This invention addresses the technical problems existing in the prior art by providing a method and system for assessing gut microbiota health based on big data.

[0006] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A gut microbiota health assessment method based on big data, comprising the following steps: S1. Obtain multi-dimensional health data of the target object at multiple consecutive time points; S2. Based on multi-dimensional health data, construct a personalized gut ecosystem topology map that changes over time; S3. Perform evolution analysis on the gut microbiota topology to determine the health status assessment results of the gut microbiota.

[0007] In a preferred embodiment, in S1, the target object acquires a first type of data, a second type of data, and a third type of data at multiple consecutive collection time points. The first type of data is microbial species composition data generated based on microbial community detection, the second type of data is user physiological data generated based on health monitoring equipment, and the third type of data is recorded intervention event data including the time and dosage of probiotic preparation intake. Using the occurrence time of the intervention event data as the baseline time point, the data from the microbial species data and user physiological data that are closest to the baseline time point are aligned to the baseline time point to form a unified time series.

[0008] In a preferred embodiment, in S2, based on a unified time series, a microbial species is defined as a microbial node, and each piece of user physiological data and each intervention event are defined as a user node and an intervention node, respectively. For any two different nodes in the same event sequence, extract the change sequence of the corresponding data of the two different nodes at all collection time points, calculate the directional consistency ratio and amplitude coordination coefficient between the two change sequences, and define the product of the directional consistency ratio and amplitude coordination coefficient as the edge interaction strength between the two different nodes. Using all nodes as vertices and the edge interaction strength as the weight of the edge connecting the corresponding vertex, a gut ecosystem topology graph is generated. Extracting the change sequences of data corresponding to two different nodes at all data collection time points includes the following steps: From the unified time series, the data values ​​corresponding to two different nodes at all collection time points are extracted to form the original data sequence of node A and the original data sequence of node B. The two sequences correspond one-to-one according to the order of collection time points. For the original data sequence of node A, starting from the second collection time point, the data value of the current time point is subtracted from the data value of the previous time point in turn to obtain the change value of node A at each time point. These change values ​​are used to form the change value sequence of node A. For the original data sequence of node B, starting from the second collection time point, the data value of the current time point is subtracted from the data value of the previous time point in turn to obtain the change value of node B at each time point. These change values ​​constitute the change value sequence of node B. The change value sequence of node A and the change value sequence of node B are paired and aligned according to their corresponding collection time points to form a pair of change sequences; The specific steps for calculating the directional consistency ratio are as follows: For each change value in the change sequence, if the change value is greater than zero, the direction of change is defined as positive; if the change value is less than zero, it is defined as negative; and if the change value is equal to zero, it is defined as no change. The two change sequences are matched one-to-one according to the time point order, and the change direction attribute of the two change values ​​at each time point is compared. The number of time points in all comparison time points where the change direction of the two change sequences is simultaneously positive or simultaneously negative is recorded as the number of points with consistent direction. The quotient obtained by dividing the number of points with consistent direction by the total number of time points involved in the comparison is the proportion of consistent direction. The specific steps for calculating amplitude coherence are as follows: For each time point, take the absolute values ​​of the two change values ​​to obtain the change amplitude A and change amplitude B. Take the smaller value of change amplitude A and change amplitude B and divide it by the larger value to obtain the single-point amplitude ratio of the time point. If one of the change amplitudes is zero, then the single-point amplitude ratio of that time point is defined as zero. The sum of the single-point amplitude ratios calculated for all time points is obtained as the cumulative amplitude ratio sum. The cumulative amplitude ratio sum is then divided by the total number of time points involved in the calculation, and the resulting quotient is the amplitude coordination coefficient.

[0009] In a preferred embodiment, in step S3, in the intestinal ecological topology map, all microbial nodes that are directly connected to the intervention node and whose edge interaction strength exceeds a first preset threshold are identified as first-level response nodes, and all other microbial nodes or user nodes that are directly connected to any first-level response node and whose edge interaction strength exceeds a second preset threshold are identified as second-level response nodes. The intervention node, the first-level response node, the second-level response node, and the connecting edges between them that meet the threshold conditions together constitute the intervention response path; Within a continuous analysis event window that includes the time points of intervention events, calculate the standard deviation of the edge interaction strength of all edges in the gut ecosystem topology graph and the mean rate of change of the edge interaction strength of all edges on the intervention response path. The standard deviation is calculated by extracting the edge interaction strength values ​​of all connected edges in the individualized ecological interaction network to form a first set of values. The arithmetic mean of all values ​​in the first set of values ​​is calculated. The difference between each value in the first set of values ​​and the arithmetic mean is calculated. Each difference is squared. All squared values ​​are summed and divided by the total number of values ​​in the first set of values ​​to obtain the variance. The positive square root of the variance is taken as the standard deviation of all edge interaction strengths. The mean change rate is calculated by defining the time period before the intervention event within a continuous analysis time window as the baseline period and the time period from the intervention event until the end of the analysis window as the response period. On the intervention-response path, the edge interaction strength values ​​of all connected edges at each time point within the baseline period are extracted, and the arithmetic mean is calculated as the baseline period strength mean. The edge interaction strength values ​​of the same connected edges at each time point within the response period are extracted, and their arithmetic mean is calculated as the response period strength mean. The difference between the response period strength mean and the baseline period strength mean is calculated, and the difference is divided by the baseline period strength mean. The resulting ratio is the mean change rate. Based on the topological complexity, standard deviation, and mean change rate of the intervention response pathway, an assessment conclusion on gut ecological health status that includes intervention responsiveness and stability is generated. Analyze the topology of the intervention response path, and comprehensively judge the complexity of the topology based on the total number of nodes, the number of connecting edges, and the degree of branching in the intervention response path. This includes the following steps: From the intervention response path, count the total number of all nodes it contains as the total number of nodes, count the total number of all connecting edges it contains as the number of connecting edges, identify all nodes in the intervention response path that are connected by at least two connecting edges (excluding the intervention node), and mark them as branch nodes. For each branch node, calculate the number of other nodes directly connected to it in the path, and subtract one from this number to get the number of direct branches of the branch node. Calculate the sum of the number of direct branches of all branch nodes as the total number of direct branches. The average number of connections obtained by dividing the total number of nodes and the number of connected edges by the total number of nodes, and the sum of the number of direct branches are compared with preset quantity thresholds, connection density thresholds, and branch thresholds, respectively. When the total number of nodes is greater than the quantity threshold, the average number of connections is greater than the connection density threshold, and the sum of the number of direct branches is greater than the branch threshold, the topology complexity is determined to be high; otherwise, it is determined to be low. The mean rate of change is compared with a preset positive response threshold. If the mean rate of change is greater than the preset positive response threshold and the topological complexity is high, a strong positive response is generated. If the mean rate of change is greater than the preset positive response threshold but the topological complexity is low, a local positive response is generated. If the mean rate of change is not greater than the preset positive response threshold, a response that is not significant or a negative response is generated. The standard deviation is compared with a preset stability threshold: if the standard deviation is less than the preset stability threshold, a conclusion of high global stability is generated; if the standard deviation is not less than the preset stability threshold, a conclusion of low global stability is generated.

[0010] This invention also provides a gut microbiota health assessment system based on big data, including: Data acquisition module: Acquires multi-dimensional health data of the target object at multiple consecutive time points; Topology map generation module: Based on multi-dimensional health data, constructs a personalized gut ecosystem topology map that changes over time; Status assessment module: Performs evolution analysis on the gut microbiota topology to determine the health status assessment results of the gut microbiota.

[0011] The beneficial effects of this invention are as follows: By acquiring and aligning multimodal data from consecutive time points, this invention constructs a time-evolving gut ecological topology map, enabling assessments to move beyond the microbiota composition at a single moment and reproduce the dynamic evolution of the gut microbiota ecosystem before and after intervention. This accurately reflects temporal behavior and response trajectories. By outputting a multidimensional comprehensive conclusion that includes intervention responsiveness and stability, this invention can not only determine whether an individual's gut ecology is healthy but also accurately describe its response type to specific interventions and its robustness, providing a direct decision-making basis for developing or adjusting personalized health management plans. Attached Figure Description

[0012] Figure 1 This is a flowchart of the present invention; Figure 2 This is a system block diagram of the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0015] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0016] like Figure 1 This embodiment provides a method for assessing gut microbiota health based on big data, including the following steps: S1. Obtain multi-dimensional health data of the target object at multiple consecutive time points; Furthermore, in S1, the target object acquires a first type of data, a second type of data, and a third type of data at multiple consecutive collection time points. The first type of data is microbial species composition data generated based on microbial community detection, the second type of data is user physiological data generated based on health monitoring equipment, and the third type of data is recorded intervention event data including the time and dosage of probiotic preparation intake. Using the occurrence time of the intervention event data as the baseline time point, the data from the microbial species data and user physiological data that are closest to the baseline time point are aligned to the baseline time point to form a unified time series.

[0017] It should be noted that the first type of data directly reflects the species composition and structure of the gut microbiota. The second type of data uses wearable devices, home medical devices, or clinical testing methods to continuously or intermittently monitor and record user physiological parameters closely related to the gut microbiota status. These parameters may include, but are not limited to, body temperature, heart rate variability, continuous blood glucose levels, body composition data, and self-reported symptom scores. There is a bidirectional regulatory relationship between the user's physiological state and the function of the gut microbiota. Changes in physiological indicators are an important manifestation of the influence of microbiota activity on the host and the feedback of the host's state on the microbiota. The principle of obtaining the third type of data relies on the target subjects actively recording their diet, daily routine information, and precise intervention records, including the brand, dosage, and intake time of probiotic preparations, through applications, electronic logs, or structured questionnaires.

[0018] S2. Based on multi-dimensional health data, construct a personalized gut ecosystem topology map that changes over time; Furthermore, in S2, based on a unified time series, a microbial species is defined as a microbial node, and each piece of user physiological data and each intervention event are defined as a user node and an intervention node, respectively. For any two different nodes in the same event sequence, extract the change sequence of the corresponding data of the two different nodes at all collection time points, calculate the directional consistency ratio and amplitude coordination coefficient between the two change sequences, and define the product of the directional consistency ratio and amplitude coordination coefficient as the edge interaction strength between the two different nodes. Using all nodes as vertices and the edge interaction strength as the weight of the edge connecting the corresponding vertex, a gut ecosystem topology graph is generated. Extracting the change sequences of data corresponding to two different nodes at all data collection time points includes the following steps: From the unified time series, the data values ​​corresponding to two different nodes at all collection time points are extracted to form the original data sequence of node A and the original data sequence of node B. The two sequences correspond one-to-one according to the order of collection time points. For the original data sequence of node A, starting from the second collection time point, the data value of the current time point is subtracted from the data value of the previous time point in turn to obtain the change value of node A at each time point. These change values ​​are used to form the change value sequence of node A. For the original data sequence of node B, starting from the second collection time point, the data value of the current time point is subtracted from the data value of the previous time point in turn to obtain the change value of node B at each time point. These change values ​​constitute the change value sequence of node B. The change value sequence of node A and the change value sequence of node B are paired and aligned according to their corresponding collection time points to form a pair of change sequences; The specific steps for calculating the directional consistency ratio are as follows: For each change value in the change sequence, if the change value is greater than zero, the direction of change is defined as positive; if the change value is less than zero, it is defined as negative; and if the change value is equal to zero, it is defined as no change. The two change sequences are matched one-to-one according to the time point order, and the change direction attribute of the two change values ​​at each time point is compared. The number of time points in all comparison time points where the change direction of the two change sequences is simultaneously positive or simultaneously negative is recorded as the number of points with consistent direction. The quotient obtained by dividing the number of points with consistent direction by the total number of time points involved in the comparison is the proportion of consistent direction. The specific steps for calculating amplitude coherence are as follows: For each time point, take the absolute values ​​of the two change values ​​to obtain the change amplitude A and change amplitude B. Take the smaller value of change amplitude A and change amplitude B and divide it by the larger value to obtain the single-point amplitude ratio of the time point. If one of the change amplitudes is zero, then the single-point amplitude ratio of that time point is defined as zero. The sum of the single-point amplitude ratios calculated for all time points is obtained as the cumulative amplitude ratio sum. The cumulative amplitude ratio sum is then divided by the total number of time points involved in the calculation, and the resulting quotient is the amplitude coordination coefficient.

[0019] It should be noted that, based on the aligned first type of data (microbial composition data), each detected and identified microbial species is defined as a basic node. Each microbial species is an independent functional or structural unit in the gut ecosystem, and its changes represent the activity and influence of the unit in the ecosystem. Mapping species to nodes is the structural basis for constructing a topological network with the interactions between microorganisms and between microorganisms and the environment as the core. Based on the second and third types of data, user physiological indicators that have known or potential associations with the gut ecosystem and explicit external interventions (such as probiotic intake events) are defined as external nodes. The user's physiological state is the internal environment for the survival of the microbiota, while diet and probiotic intervention are exogenous disturbances that directly affect the system. Both are key factors driving changes in the microecology. When there is functional coupling, causal influence, or shared regulation by the same factor between two nodes, the numerical change pattern between the two nodes over a continuous period of time should show a certain degree of synergy, consistency, or regularity in following the relationship. The calculation of the correlation strength is a quantitative measure of the dynamic synergy or following pattern across time. Using the association strength as the weight of the connecting edge means that there is a connecting edge between any two nodes. The weight value of this edge is the association strength value between the two nodes calculated in the previous step. The resulting graph is a dynamically weighted complete graph. The "dynamic" here means that when the input data is time series data from different time windows, a topological network graph reflecting the interaction patterns of different periods can be calculated and generated.

[0020] S3. Perform evolutionary analysis on the gut microbiota topology to determine the health status assessment results of the gut microbiota; Furthermore, in S3, in the intestinal ecological topology map, all microbial nodes that are directly connected to the intervention node and whose edge interaction strength exceeds the first preset threshold are identified as first-level response nodes, and all other microbial nodes or user nodes that are directly connected to any first-level response node and whose edge interaction strength exceeds the second preset threshold are identified as second-level response nodes. The intervention node, the first-level response node, the second-level response node, and the connecting edges between them that meet the threshold conditions together constitute the intervention response path; Within a continuous analysis event window that includes the time points of intervention events, calculate the standard deviation of the edge interaction strength of all edges in the gut ecosystem topology graph and the mean rate of change of the edge interaction strength of all edges on the intervention response path. The standard deviation is calculated by extracting the edge interaction strength values ​​of all connected edges in the individualized ecological interaction network to form a first set of values. The arithmetic mean of all values ​​in the first set of values ​​is calculated. The difference between each value in the first set of values ​​and the arithmetic mean is calculated. Each difference is squared. All squared values ​​are summed and divided by the total number of values ​​in the first set of values ​​to obtain the variance. The positive square root of the variance is taken as the standard deviation of all edge interaction strengths. The mean change rate is calculated by defining the time period before the intervention event within a continuous analysis time window as the baseline period and the time period from the intervention event until the end of the analysis window as the response period. On the intervention-response path, the edge interaction strength values ​​of all connected edges at each time point within the baseline period are extracted, and the arithmetic mean is calculated as the baseline period strength mean. The edge interaction strength values ​​of the same connected edges at each time point within the response period are extracted, and their arithmetic mean is calculated as the response period strength mean. The difference between the response period strength mean and the baseline period strength mean is calculated, and the difference is divided by the baseline period strength mean. The resulting ratio is the mean change rate. Based on the topological complexity, standard deviation, and mean change rate of the intervention response pathway, an assessment conclusion on gut ecological health status that includes intervention responsiveness and stability is generated. Analyze the topology of the intervention response path, and comprehensively judge the complexity of the topology based on the total number of nodes, the number of connecting edges, and the degree of branching in the intervention response path. This includes the following steps: From the intervention response path, count the total number of all nodes it contains as the total number of nodes, count the total number of all connecting edges it contains as the number of connecting edges, identify all nodes in the intervention response path that are connected by at least two connecting edges (excluding the intervention node), and mark them as branch nodes. For each branch node, calculate the number of other nodes directly connected to it in the path, and subtract one from this number to get the number of direct branches of the branch node. Calculate the sum of the number of direct branches of all branch nodes as the total number of direct branches. The average number of connections obtained by dividing the total number of nodes and the number of connected edges by the total number of nodes, and the sum of the number of direct branches are compared with preset quantity thresholds, connection density thresholds, and branch thresholds, respectively. When the total number of nodes is greater than the quantity threshold, the average number of connections is greater than the connection density threshold, and the sum of the number of direct branches is greater than the branch threshold, the topology complexity is determined to be high; otherwise, it is determined to be low. The mean rate of change is compared with a preset positive response threshold. If the mean rate of change is greater than the preset positive response threshold and the topological complexity is high, a strong positive response is generated. If the mean rate of change is greater than the preset positive response threshold but the topological complexity is low, a local positive response is generated. If the mean rate of change is not greater than the preset positive response threshold, a response that is not significant or a negative response is generated. The standard deviation is compared with a preset stability threshold: if the standard deviation is less than the preset stability threshold, a conclusion of high global stability is generated; if the standard deviation is not less than the preset stability threshold, a conclusion of low global stability is generated.

[0021] It should be noted that the first preset threshold serves as a threshold for screening core microorganisms directly associated with the intervention node. Only when the edge interaction strength between a microbial node and the probiotic intervention event exceeds the first preset threshold is it considered to have received a significant intervention impact and thus included in the first-level response node. The second preset threshold serves as a strength threshold for screening microorganisms or user physiological indicators indirectly affected by the intervention. Only when the association strength between a node and the first-level response node exceeds the second preset threshold is it considered to have experienced a significant secondary effect and thus included in the second-level response node. The preset quantity threshold, connection density threshold, and branch threshold together serve as three dimensions for determining the complexity of the intervention response path topology. The preset quantity threshold is used to measure... The path size limit is set at a minimum, requiring the path to contain a sufficient number of nodes. The connection density threshold is used to measure the minimum degree of internal connection within the path. The branch threshold is used to measure the minimum degree of nonlinearity and divergence of the path. The preset positive response threshold is used to determine whether the mean change rate constitutes a positive response. Only when the average increase in the correlation strength of the response path after intervention exceeds the preset positive response threshold is it considered to have generated a meaningful positive response, rather than a minor fluctuation. The preset stability threshold is used to determine whether the standard deviation of the entire topology network signifies stable volatility. Only when the volatility of all interactions in the dynamic topology network is lower than the preset stability threshold is the entire topology network considered to be in a highly stable state. It should be noted that the preset threshold in this invention is obtained by those skilled in the art by collecting multiple sets of sample data and setting a corresponding preset ratio coefficient for each set of sample data; substituting the set preset ratio coefficient and the collected sample data into the formula, any two formulas constitute a system of two first equations, and the calculated coefficients are filtered and averaged to obtain the value. The size of the coefficient is a specific value obtained by quantifying each parameter to facilitate subsequent comparison. The size of the coefficient depends on the amount of sample data and the preset proportional coefficient initially set by those skilled in the art for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantified value.

[0022] It should be noted that a local positive response indicates that the intervention has produced some positive effects, but these effects are limited and not widely spread. Specifically, it means that the ingested probiotics have successfully affected a few gut bacteria that are directly related to them (i.e., primary response nodes), which may have promoted the colonization or metabolic activities of these bacteria. However, this effect has failed to further trigger or significantly change the broader gut microbiota network (i.e., there is a lack of rich secondary response nodes and complex branches). This suggests that the intervention is effective, but may have a narrow scope of action, or that the current state of the individual's gut ecosystem can only support this local adjustment. A non-significant or negative response indicates that the intervention failed to effectively stimulate the expected ecological changes and may have produced a slight disturbance or inhibitory effect. Specifically, it means that the introduction of probiotics failed to induce a identifiable and sufficiently strong positive synergistic change. This may be due to a mismatch between the probiotic strain and the individual's current gut microbiota composition, resulting in ineffective colonization or function, or insufficient intervention dosage or duration, leaving the individual's gut ecology in an inert or resistant state. A negative response suggests that the intervention may have slightly disturbed the original, relatively stable intermicrobial balance, but did not induce systemic disorder. High system global stability indicates that the intensity of various interactions within the gut microbiota network fluctuates very little throughout the entire observation period (including before and after intervention), and the overall structure exhibits strong anti-interference ability and resilience. Specifically, the individual gut ecology has good resilience. Even with the introduction of external interventions such as probiotics, the basic interaction pattern of the entire gut (network edge interaction intensity) remains stable without significant fluctuations. This is a positive health signal, meaning that the gut ecological foundation is good and can cope with external changes. The impact of intervention measures may be absorbed and integrated more smoothly. Low global stability indicates that the intensity of various interactions within the gut microbiota network fluctuates significantly throughout the observation period, and the overall structure is relatively fragile and easily disturbed. Specifically, it indicates that the individual's gut ecology is in an unstable or sensitive state, and the strength of network connections fluctuates within a large range. This may reflect the instability of the competitive relationship between the microbiota. Introducing interventions (such as probiotics) in this state may result in unpredictable responses or require more careful monitoring.

[0023] like Figure 2 The present invention also provides a gut microbiota health assessment system based on big data, comprising: Data acquisition module: Acquires multi-dimensional health data of the target object at multiple consecutive time points; Topology map generation module: Based on multi-dimensional health data, constructs a personalized gut ecosystem topology map that changes over time; Status assessment module: Performs evolution analysis on the gut microbiota topology to determine the health status assessment results of the gut microbiota; It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0024] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0025] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0026] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0027] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0028] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0029] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for assessing gut microbiota health based on big data, characterized in that, Includes the following steps: S1. Obtain multi-dimensional health data of the target object at multiple consecutive time points; S2. Based on multi-dimensional health data, construct a personalized gut ecosystem topology map that changes over time; S3. Perform evolution analysis on the gut microbiota topology to determine the health status assessment results of the gut microbiota.

2. The method for assessing gut microbiota health based on big data according to claim 1, characterized in that, In S1, the target object acquires first type of data, second type of data, and third type of data at multiple consecutive collection time points. The first type of data is microbial species composition data generated based on microbial community detection, the second type of data is user physiological data generated based on health monitoring equipment, and the third type of data is recorded intervention event data including the time and dosage of probiotic preparation intake. Using the occurrence time of the intervention event data as the baseline time point, the data from the microbial species data and user physiological data that are closest to the baseline time point are aligned to the baseline time point to form a unified time series.

3. The method for assessing gut microbiota health based on big data according to claim 1, characterized in that, In S2, based on a unified time series, a microbial species is defined as a microbial node, and each piece of user physiological data and each intervention event are defined as a user node and an intervention node, respectively. For any two different nodes in the same event sequence, extract the change sequence of the corresponding data of the two different nodes at all collection time points, calculate the directional consistency ratio and amplitude coordination coefficient between the two change sequences, and define the product of the directional consistency ratio and amplitude coordination coefficient as the edge interaction strength between the two different nodes. Using all nodes as vertices and the edge interaction strength as the weight of the edge connecting the corresponding vertex, a gut ecosystem topology graph is generated.

4. The method for assessing gut microbiota health based on big data according to claim 3, characterized in that, Extracting the change sequences of data corresponding to two different nodes at all collection time points includes the following steps: From the unified time series, the data values ​​corresponding to two different nodes at all collection time points are extracted to form the original data sequence of node A and the original data sequence of node B. The two sequences correspond one-to-one according to the order of collection time points. For the original data sequence of node A, starting from the second collection time point, the data value of the current time point is subtracted from the data value of the previous time point in turn to obtain the change value of node A at each time point. These change values ​​constitute the change value sequence of node A. For the original data sequence of node B, starting from the second collection time point, the data value of the current time point is subtracted from the data value of the previous time point in turn to obtain the change value of node B at each time point. These change values ​​constitute the change value sequence of node B. The change value sequence of node A and the change value sequence of node B are paired and aligned according to their corresponding collection time points to form a pair of change sequences.

5. The method for assessing gut microbiota health based on big data according to claim 3, characterized in that, The specific steps for calculating the directional consistency ratio are as follows: For each change value in the change sequence, if the change value is greater than zero, the direction of change is defined as positive; if the change value is less than zero, it is defined as negative; and if the change value is equal to zero, it is defined as no change. The two change sequences are matched one-to-one according to the time point order, and the change direction attribute of the two change values ​​at each time point is compared. The number of time points in all comparison time points where the change direction of the two change sequences is simultaneously positive or simultaneously negative is recorded as the number of points with consistent direction. The quotient obtained by dividing the number of points with consistent direction by the total number of time points involved in the comparison is the proportion of consistent direction.

6. The method for assessing gut microbiota health based on big data according to claim 3, characterized in that, The specific steps for calculating amplitude coherence are as follows: For each time point, take the absolute values ​​of the two change values ​​to obtain the change amplitude A and change amplitude B. Take the smaller value of change amplitude A and change amplitude B and divide it by the larger value to obtain the single-point amplitude ratio of the time point. If one of the change amplitudes is zero, then the single-point amplitude ratio of that time point is defined as zero. The sum of the single-point amplitude ratios calculated for all time points is obtained as the cumulative amplitude ratio sum. The cumulative amplitude ratio sum is then divided by the total number of time points involved in the calculation, and the resulting quotient is the amplitude coordination coefficient.

7. The method for assessing gut microbiota health based on big data according to claim 1, characterized in that, In S3, in the intestinal ecological topology map, all microbial nodes that are directly connected to the intervention node and whose edge interaction strength exceeds the first preset threshold are identified as first-level response nodes, and all other microbial nodes or user nodes that are directly connected to any first-level response node and whose edge interaction strength exceeds the second preset threshold are identified as second-level response nodes. The intervention node, the first-level response node, the second-level response node, and the connecting edges between them that meet the threshold conditions together constitute the intervention response path; Within a continuous analysis event window that includes the time points of intervention events, the standard deviation of the intensity of all edge interactions in the gut ecosystem topology graph and the mean rate of change of the intensity of all edge interactions on the intervention response path are calculated.

8. The method for assessing gut microbiota health based on big data according to claim 7, characterized in that, The standard deviation is calculated by extracting the edge interaction strength values ​​of all connected edges in the individualized ecological interaction network to form a first set of values. The arithmetic mean of all values ​​in the first set of values ​​is calculated. The difference between each value in the first set of values ​​and the arithmetic mean is calculated. Each difference is squared. All squared values ​​are summed and divided by the total number of values ​​in the first set of values ​​to obtain the variance. The positive square root of the variance is taken as the standard deviation of all edge interaction strengths. The mean change rate is calculated by defining the period before the intervention event as the baseline period and the period from the intervention event to the end of the analysis window as the response period within the continuous analysis time window. On the intervention-response path, the edge interaction strength values ​​of all connected edges at each time point within the baseline period are extracted, and their arithmetic mean is calculated as the baseline period strength mean. The edge interaction strength values ​​of the same connected edges at each time point within the response period are extracted, and their arithmetic mean is calculated as the response period strength mean. The difference between the response period strength mean and the baseline period strength mean is calculated, and the difference is divided by the baseline period strength mean. The resulting ratio is the mean change rate.

9. The method for assessing gut microbiota health based on big data according to claim 7, characterized in that, Based on the topological complexity, standard deviation, and mean change rate of the intervention response pathway, an assessment conclusion on gut ecological health status that includes intervention responsiveness and stability is generated. Analyze the topology of the intervention response path, and comprehensively judge the complexity of the topology based on the total number of nodes, the number of connecting edges, and the degree of branching in the intervention response path. This includes the following steps: From the intervention response path, count the total number of all nodes it contains as the total number of nodes, count the total number of all connecting edges it contains as the number of connecting edges, identify all nodes in the intervention response path that are connected by at least two connecting edges (excluding the intervention node), and mark them as branch nodes. For each branch node, calculate the number of other nodes directly connected to it in the path, and subtract one from this number to get the number of direct branches of the branch node. Calculate the sum of the number of direct branches of all branch nodes as the total number of direct branches. The average number of connections obtained by dividing the total number of nodes and the number of connected edges by the total number of nodes, and the sum of the number of direct branches are compared with preset quantity thresholds, connection density thresholds, and branch thresholds, respectively. When the total number of nodes is greater than the quantity threshold, the average number of connections is greater than the connection density threshold, and the sum of the number of direct branches is greater than the branch threshold, the topology complexity is determined to be high; otherwise, it is determined to be low. The mean rate of change is compared with a preset positive response threshold. If the mean rate of change is greater than the preset positive response threshold and the topological complexity is high, a strong positive response is generated. If the mean rate of change is greater than the preset positive response threshold but the topological complexity is low, a local positive response is generated. If the mean rate of change is not greater than the preset positive response threshold, a response that is not significant or a negative response is generated. The standard deviation is compared with a preset stability threshold: if the standard deviation is less than the preset stability threshold, a conclusion of high global stability is generated; if the standard deviation is not less than the preset stability threshold, a conclusion of low global stability is generated.

10. A big data-based gut microbiota health assessment system is applied to the big data-based gut microbiota health assessment method as described in any one of claims 1-9, characterized in that, include: This invention also provides a gut microbiota health assessment system based on big data, including: Data acquisition module: Acquires multi-dimensional health data of the target object at multiple consecutive time points; Topology map generation module: Based on multi-dimensional health data, constructs a personalized gut ecosystem topology map that changes over time; Status assessment module: Performs evolution analysis on the gut microbiota topology to determine the health status assessment results of the gut microbiota.

Images