Healthcare management system and method based on multi-source data collection and analysis

Abstract

A health management system and method based on multi-source data collection and analysis is provided. [Solution] The health management system includes a data collection and processing module, a user classification and user profile construction module, a knowledge graph construction module, a health management solution matching module, and a personalized health management module. The data collection and processing module obtains users' multi-source historical data and constructs a user feature dataset. The user classification and user profile construction module categorizes users and creates corresponding user profiles. The knowledge graph construction module constructs a knowledge graph and a key feature set based on the feature dataset and the user profile. The health management solution matching module matches with a health management solution list. The personalized health management module generates a personalized health management solution.

Description

[Technical Field]

[0001] The present invention relates to the technical field of data analysis, and in particular to a health management system and method based on multi-source data collection and analysis. [Background technology]

[0002] With the rapid development of information technology, health management has become a hot topic in modern society. Traditional health management methods often rely on single medical testing methods such as health checkup reports and medical interview records, and these data sources are monolithic and difficult to fully reflect an individual's health status and its dynamic changes. With the rise of technologies such as the Internet of Things, big data, and cloud computing, multi-source data collection and analysis has shown great potential in the field of health management, enabling more accurate and comprehensive assessment of an individual's health status and providing personalized health management solutions.

[0003] However, most traditional health management systems use simple statistical analysis methods for data analysis, making it difficult to deeply mine the relationships and trends behind the data. Furthermore, due to differences in data format and quality from different sources, traditional health management systems have difficulty dealing with the complexity and diversity of multi-source data, resulting in insufficient accuracy of analysis results. Furthermore, the health advice provided by traditional health management systems is often general and lacks specificity and personalization. It is often based on a single or limited health test indicator, ignoring individual differences and diverse needs, resulting in insufficient health management effectiveness. Summary of the Invention [Problem to be solved by the invention]

[0004] SUMMARY OF THE INVENTION In order to solve the problems in the background art described above, the present invention aims to provide a health management system and method based on multi-source data collection and analysis.

[0005] In order to solve the above technical problems, the present invention provides the following technical means. [Means for solving the problem]

[0006] The health management method based on multi-source data collection and analysis includes the following steps S100 to S400: In step S100, obtain multi-source history data of all predetermined users from the database, perform corresponding selection and integration for each predetermined user's multi-source history data to construct a predetermined user feature data set, classify the predetermined users according to the predetermined user feature data set, and create corresponding predetermined user profiles for each category of predetermined users; In step S200, for a predetermined user in each category, a knowledge graph of the predetermined user is constructed based on the predetermined user feature dataset and the predetermined user profile, and the knowledge graph of the predetermined user and the predetermined user feature dataset are combined and analyzed. Based on the analysis result, key features of the predetermined user in the corresponding category are identified; In step S300, obtain predetermined health management solutions provided for predetermined users of different categories in the database, and compare and analyze the predetermined health management solutions of each category with the key features of the corresponding predetermined users to obtain a correspondence relationship between the predetermined health management solutions and the key features of the corresponding predetermined users; In step S400, a real-time user inputs initial data, a real-time user image is constructed based on the initial data, the real-time user image is matched with a predetermined user image, and a corresponding predetermined health management solution list is output based on the matching result, multi-source real-time data of the real-time user is obtained, the multi-source real-time data is extracted to identify real-time feature data of the real-time user, and the real-time feature data is compared with and analyzed with the key features of the predetermined user, thereby generating a personalized health management solution.

[0007] Furthermore, step S100 includes the following steps S101 to S103: In step S101, the multi-source history data of all predetermined users is obtained from the database, the predetermined users refer to a user group stored in the database, and the multi-source history data refer to user health-related information collected from multiple different data sources. The multi-source history data of the predetermined users is uniformly converted into a uniform format, and the multi-source history data is grouped according to a predetermined user ID. Corresponding feature data is extracted from the multi-source history data of each predetermined user, and the extracted feature data is standardized. The specific formula for the standardization process is as follows: JPEG0007724032000002.jpg10166where F i,j is the j-th standardized feature data of a given user i X i,j is the jth original feature data of a given user i μ j and σ j are the mean and standard deviation of the j-th feature data, respectively. In step S102, a correlation analysis is performed on the standardized feature data of each user to obtain a linear relationship between the standardized feature data, and the value evaluating the linear relationship is defined as a correlation coefficient R. Typically, Pearson's correlation coefficient is used to evaluate the linear relationship between two features. For feature data whose absolute value of the correlation coefficient R is equal to a threshold value R0, a linear regression model is used to establish the corresponding linear relationship. The linear regression model is expressed as follows: JPEG0007724032000003.jpg11166Here, β0 is the intercept β1 is the feature F i,j Coefficient of ε is the error term Calculate the regression coefficients β0 and β1 using the least squares method, and use a linear regression model to estimate the feature F using the following formula: i,k Update JPEG0007724032000004.jpg10167. Construct a feature dataset for a given user by traversing all the standardized processed feature data for the given user, where one element in the feature dataset for a given user corresponds to one given user, and the number of elements in the feature dataset for a given user is equal to the number of given users in the database; In step S103, based on the feature data set of the predetermined user, a clustering analysis is performed on the predetermined user, and the predetermined user is divided into K categories. For the predetermined user in each category, a corresponding predetermined user profile is created. The process of creating the predetermined user profile is as follows: For a predetermined user in each category, a corresponding feature vector V is extracted from the feature dataset of the predetermined user, and the mean value and standard deviation of each feature in the category are calculated based on the feature vector V, and the feature weight W is obtained by normalizing based on the standard deviation. A predetermined user image U for each category is constructed based on the mean value and weight of the clustering category, and the predetermined user image U is denoted as a weighted feature vector.

[0008] Furthermore, a clustering analysis is performed on the predetermined user based on the characteristic dataset of the predetermined user. The specific clustering analysis process is as follows: According to the feature dataset of a predetermined user, obtain the feature data of the predetermined user, and use Euclidean distance as the initial distance metric to perform two-to-two distance metric calculation for all the predetermined users, and the distance metric is as follows: JPEG0007724032000005.jpg10167where, F a,k and F b,k are the standardized values of given users a and b for the kth feature, respectively. n is the total number of features Hierarchical clustering is applied as the initial clustering, and each given user is regarded as a single cluster. Clusters whose distance metric d(a, b) is greater than or equal to the threshold d are gradually merged. Based on the results of hierarchical clustering, the number of clusters K0 for an initial clustering is selected. K0 clusters are selected from the final clusters of the hierarchical clustering as the initial center points of K-means. The K-means clustering algorithm is then run. After each iteration, the quality of the clusters is evaluated and the K value is dynamically adjusted as follows: The specific analysis process is as follows: Calculate the within-cluster sum of squares (WCSS). The specific calculation formula for WCSS is as follows: JPEG0007724032000006.jpg14166 where M is the number of clusters Cm is the mth cluster f(p,k) is the value of the pth sample in the kth feature μm,k is the mean value of the mth cluster for the kth feature If the decrease in WCSS is less than a threshold t in c consecutive iterations, stop the iteration; otherwise, continue the iteration to adjust the value of K, and based on the finally determined K, re-run the K-means clustering algorithm to divide a given user into K categories.

[0009] Furthermore, step S200 includes the following steps S201 to S202: In step S201, for a predetermined user in each category, based on the predetermined user feature dataset and the predetermined user image, extract the feature data of the predetermined user as an entity, combine the predetermined user image to extract the relationship between the feature data of the predetermined user, set the entities as nodes of the knowledge graph, set the relationships between the entities as edges of the knowledge graph, and combine the average values and weights of the clustering categories in step S103 to construct a knowledge graph of the predetermined user for each category; In step S202, obtain the knowledge graph of a given user for each category, define any node as the initial node, start from the initial node, traverse the knowledge graph of the given user, collect all reachable nodes J and paths P, and obtain a corresponding path set Pa, calculate the corresponding path weight w(path) for each path in the path set, and the value of w(path) is equal to the product of the weights of each feature in the path, and define the importance index G(J_h) according to the path weight w(path) by the following formula: JPEG0007724032000007.jpg11165Here, |P| is the path length I is the indicator function If node J_h is on path P, I(J_h∈P)=1; otherwise, I(J_h∈P)=0, where h indicates the node number. The importance index G(J_h) is compared with the corresponding threshold G0 to determine whether it is greater or smaller. If G(J_h)>G0, the corresponding node J_h is defined as a key node, and the feature corresponding to node J_h is defined as a key feature.

[0010] Furthermore, step S300 The method includes the steps of: extracting health care solutions corresponding to predetermined users of different categories from the database, and associating the corresponding health care solutions with the predetermined users of each category; constructing a key feature set Tu for each predetermined user based on key features corresponding to the predetermined users, where u indicates the predetermined user number; and sequentially calculating symmetric differences for the key feature set Tu of the predetermined users, comparing the health care solutions of the corresponding predetermined users with the health care solutions of the corresponding predetermined users, and correlating the symmetric difference results with the comparison results to obtain the correspondence between the predetermined health care solutions and the key features of the corresponding predetermined users.

[0011] Furthermore, step S400 includes the following steps S401 to S402: In step S401, a real-time user inputs initial data, and performs the same analysis process on the initial data as on the multi-source historical data to construct a real-time user profile U1 based on the initial data, calculate the similarity between the real-time user profile U1 and a predetermined user profile U, and match it with a corresponding predetermined user category based on the similarity calculation result, and the one with the largest similarity is taken as the matching result, and output a predetermined health management solution list corresponding to the predetermined user category based on the matching result; In step S402, based on the predetermined health management solution list, the real-time user selects one predetermined health management solution, implements the predetermined health management solution, obtains multi-source real-time data of the real-time user for each selected period, extracts corresponding real-time feature data based on the multi-source real-time data, compares the real-time feature data with key features corresponding to the predetermined health management solution list, and if the real-time feature data is the same as the key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently implemented by the real-time user, appropriately adjusts the currently implemented predetermined health management solution according to the other predetermined health management solutions based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, thereby generating a personalized health management solution.

[0012] A health management system based on multi-source data collection and analysis, the system including: a data collection and processing module; a user classification and user profile construction module; a knowledge graph construction module; a health management solution matching module; and a personalized health management module; The data collection and processing module obtains multi-source historical data of a specific user from multiple databases, uniformly converts the multi-source historical data of different formats and structures, extracts and standardizes the characteristic data of the specific user, and thereby constructs a characteristic data set of the specific user; The user classification and user profile construction module performs correlation analysis on the feature data in the specified user feature dataset, calculates the linear relationship between features, establishes the relationship between features using a linear regression model, divides users into different categories using clustering analysis, and creates a corresponding specified user profile for each category; The knowledge graph construction module defines nodes and edges and establishes relationships between entities based on the feature dataset of the given user and the given user profile, constructs a knowledge graph for the given user, and builds a key feature set for each given user by traversing the knowledge graph and identifying key nodes and key features; The health management solution matching module uses the initial data input by the real-time user to construct a real-time user profile and matches it with a predetermined user profile to obtain a category corresponding to the real-time user, and outputs a list of predetermined health management solutions corresponding to the predetermined user category based on the matching result; The personalized health management module obtains multi-source real-time data of the real-time user based on the predetermined health management solution selected by the real-time user, extracts corresponding real-time feature data based on the multi-source real-time data, compares the real-time feature data with key features corresponding to the predetermined health management solution list, and if the real-time feature data is the same as the key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently being implemented by the real-time user, appropriately adjusts the currently implemented predetermined health management solution according to the other predetermined health management solutions based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, thereby generating a personalized health management solution.

[0013] Furthermore, the data collection and processing module includes a data collection unit and a data processing unit; The data collection unit collects multi-source history data of the specified user from the database; the data processing unit unifies the multi-source history data of different formats and structures, extracts and standardizes feature data of the specified user, and thereby constructs a feature data set of the specified user; The user classification and user profile building module includes a user classification unit and a user profile building unit; The user classification unit performs clustering analysis on the predetermined user features in the predetermined user feature dataset to divide the predetermined users into multiple categories, and the user image creation unit creates a predetermined user image for the predetermined users in each category by creating a weighted feature vector based on the predetermined user feature dataset.

[0014] Furthermore, the knowledge graph construction module includes: a knowledge graph construction unit; and a key feature identification unit; The knowledge graph construction unit constructs a knowledge graph for a predetermined user in each category based on the feature dataset of the predetermined user and the predetermined user profile, and the key feature identification unit performs association analysis in the knowledge graph to identify key features of the predetermined user in each category, and constructs a key feature set for each predetermined user.

[0015] The personalized health management module includes a real-time data collection unit, a similarity calculation unit, and a solution adjustment unit; The real-time data collection unit obtains data entered by the user in real time and performs corresponding analysis to construct a real-time user image; the similarity calculation unit calculates the similarity between the real-time user image and the predetermined user image and determines a predetermined user category corresponding to the real-time user; the solution adjustment unit compares the real-time feature data with key features corresponding to the predetermined health management solution list; if the real-time feature data is the same as the key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently being implemented by the real-time user, then based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, appropriately adjusts the currently implemented predetermined health management solution according to the other predetermined health management solutions, thereby generating a personalized health management solution. [Effects of the Invention]

[0016] Compared with the prior art, the beneficial effects of the present invention are that the standardization processing and correlation analysis of multi-source historical data can reveal the complex relationships between a given user's health data, improving the accuracy and reliability of the analysis; clustering analysis and feature extraction techniques can be used to build a detailed user profile for each given user, reflecting their unique health conditions and needs; such personalized user profiles contribute to the formulation of more practical health management solutions; building a knowledge graph for a given user can effectively integrate the relationships between the given user's feature data and health management solutions, helping to identify key features and providing a scientific basis for health management; real-time user data input and analysis can enable health management solutions to be timely adjusted according to the user's actual situation, ensuring the effectiveness and adaptability of the solutions; the system can process information from different data sources, solving the problems of differences in data format and quality and improving the system's adaptability to the complexity and variety of multi-source data; and personalized health management solutions can better meet the diverse needs of users and improve the overall effectiveness and satisfaction of health management. [Brief explanation of the drawings]

[0017] The drawings, which are included to provide a further understanding of the invention and constitute a part of this specification, are intended to illustrate the invention in conjunction with the examples of the invention and are not intended to limit the invention.

[0018] [Figure 1] 1 is a block diagram of a health management system based on multi-source data collection and analysis of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0019] In the following, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments.

[0020] Based on the embodiments of the present invention, all other embodiments that can be obtained by those skilled in the art without any creative work fall within the protection scope of the present invention.

[0021] As shown in FIG. 1, the present invention provides the following technical means:

[0022] A health management system based on multi-source data collection and analysis, the system including: a data collection and processing module; a user classification and user profile construction module; a knowledge graph construction module; a health management solution matching module; and a personalized health management module; The data collection and processing module obtains multi-source historical data of a specific user from multiple databases, uniformly converts the multi-source historical data of different formats and structures, extracts and standardizes the characteristic data of the specific user, and thereby constructs a characteristic data set of the specific user; The user classification and user profile construction module performs correlation analysis on the feature data in the specified user feature dataset, calculates the linear relationship between features, establishes the relationship between features using a linear regression model, divides users into different categories using clustering analysis, and creates a corresponding specified user profile for each category; The knowledge graph construction module defines nodes and edges and establishes relationships between entities based on the feature dataset of the given user and the given user profile, constructs a knowledge graph for the given user, and builds a key feature set for each given user by traversing the knowledge graph and identifying key nodes and key features; The health management solution matching module uses the initial data input by the real-time user to construct a real-time user profile and matches it with a predetermined user profile to obtain a category corresponding to the real-time user, and outputs a list of predetermined health management solutions corresponding to the predetermined user category based on the matching result; The personalized health management module obtains multi-source real-time data of the real-time user based on the predetermined health management solution selected by the real-time user, extracts corresponding real-time feature data based on the multi-source real-time data, compares the real-time feature data with key features corresponding to the predetermined health management solution list, and if the real-time feature data is the same as the key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently being implemented by the real-time user, appropriately adjusts the currently implemented predetermined health management solution according to the other predetermined health management solutions based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, thereby generating a personalized health management solution.

[0023] The data collection and processing module includes a data collection unit and a data processing unit; The data collection unit collects multi-source history data of the specified user from the database; the data processing unit unifies the multi-source history data of different formats and structures, extracts and standardizes feature data of the specified user, and thereby constructs a feature data set of the specified user; The user classification and user profile building module includes a user classification unit and a user profile building unit; The user classification unit performs clustering analysis on the predetermined user features in the predetermined user feature dataset to divide the predetermined users into multiple categories, and the user image creation unit creates a predetermined user image for the predetermined users in each category by creating a weighted feature vector based on the predetermined user feature dataset.

[0024] The knowledge graph construction module includes: a knowledge graph construction unit; and a key feature identification unit; The knowledge graph construction unit constructs a knowledge graph for a predetermined user in each category based on the feature dataset of the predetermined user and the predetermined user profile, and the key feature identification unit performs association analysis in the knowledge graph to identify key features of the predetermined user in each category, and constructs a key feature set for each predetermined user.

[0025] The personalized health management module includes a real-time data collection unit, a similarity calculation unit, and a solution adjustment unit; The real-time data collection unit obtains data entered by the user in real time and performs corresponding analysis to construct a real-time user image; the similarity calculation unit calculates the similarity between the real-time user image and the predetermined user image and determines a predetermined user category corresponding to the real-time user; the solution adjustment unit compares the real-time feature data with key features corresponding to the predetermined health management solution list; if the real-time feature data is the same as the key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently being implemented by the real-time user, then based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, appropriately adjusts the currently implemented predetermined health management solution according to the other predetermined health management solutions, thereby generating a personalized health management solution.

[0026] The health management method based on multi-source data collection and analysis includes the following steps S100 to S400: In step S100, obtain multi-source history data of all predetermined users from the database, perform corresponding selection and integration for each predetermined user's multi-source history data to construct a predetermined user feature data set, classify the predetermined users according to the predetermined user feature data set, and create corresponding predetermined user profiles for each category of predetermined users; In step S200, for a predetermined user in each category, a knowledge graph of the predetermined user is constructed based on the predetermined user feature dataset and the predetermined user profile, and the knowledge graph of the predetermined user and the predetermined user feature dataset are combined and analyzed. Based on the analysis result, key features of the predetermined user in the corresponding category are identified; In step S300, obtain predetermined health management solutions provided for predetermined users of different categories in the database, and compare and analyze the predetermined health management solutions of each category with the key features of the corresponding predetermined users to obtain a correspondence relationship between the predetermined health management solutions and the key features of the corresponding predetermined users; In step S400, a real-time user inputs initial data, a real-time user image is constructed based on the initial data, the real-time user image is matched with a predetermined user image, and a corresponding predetermined health management solution list is output based on the matching result, multi-source real-time data of the real-time user is obtained, the multi-source real-time data is extracted to identify real-time feature data of the real-time user, and the real-time feature data is compared with and analyzed with the key features of the predetermined user, thereby generating a personalized health management solution.

[0027] Step S100 includes the following steps S101 to S103: In step S101, the multi-source history data of all predetermined users is obtained from the database, the predetermined users refer to a user group stored in the database, and the multi-source history data refer to user health-related information collected from multiple different data sources. The multi-source history data of the predetermined users is uniformly converted into a uniform format, and the multi-source history data is grouped according to a predetermined user ID. Corresponding feature data is extracted from the multi-source history data of each predetermined user, and the extracted feature data is standardized. The specific formula for the standardization process is as follows: JPEG0007724032000008.jpg10166where, F i,j is the j-th standardized feature data of a given user i X i,j is the jth original feature data of a given user i μ j and σ j are the mean and standard deviation of the j-th feature data, respectively. In this embodiment, in the process of feature extraction and feature dataset construction, corresponding calculations and processing can be performed for different types of features.

[0028] The following are specific calculation methods for physiological characteristics, behavioral characteristics, and health record characteristics.

[0029] Physiological characteristics: Weight is in kilograms (kg) and is calculated by extracting the user's weight record directly from the dataset.

[0030] Height is in cm and is calculated by extracting the user's height record directly from the dataset.

[0031] Body mass index (BMI) is calculated using the extracted weight and height.

[0032] Blood Pressure is in millimeters of mercury (mmHg) and is calculated as: usually recorded as systolic / diastolic, e.g., 120 / 80 mmHg, and extracted from the dataset.

[0033] Behavioral characteristics: Exercise Frequency is calculated by extracting the number of weekly exercises from the user's records.

[0034] Dietary Habits: Explanation: Records the user's dietary preferences (e.g., vegetarian, low sugar, high protein, etc.) and weekly food intake. Calculation: Different dietary habits can be quantified using a coding method, for example: Plain food: 1, Meat eating: 0.

[0035] Health Records: Medical History is a description: records the diseases the user has suffered from (e.g., hypertension, diabetes, etc.) and a calculation: a binary variable that can indicate the presence or absence of a certain disease, e.g., Hypertension: 1 (present), 0 (absent) Diabetes: 1 (present), 0 (absent).

[0036] Allergy History is a binary variable that can indicate whether a user has an allergy to a substance (e.g., pollen, seafood, etc.). Pollen allergy: 1 (yes), 0 (no), Seafood allergy: 1 (yes), 0 (no).

[0037] Feature dataset construction: After the above features are calculated, they can be combined into one feature dataset.

[0038] In step S102, a correlation analysis is performed on the standardized feature data of each predetermined user to obtain the linear relationship between the standardized feature data, and the value evaluating the linear relationship is defined as a correlation coefficient R. Typically, Pearson's correlation coefficient is used to evaluate the linear relationship between two features. For feature data whose absolute value of the correlation coefficient R is equal to a threshold value R0, a linear regression model is used to establish the corresponding linear relationship. The linear regression model is as follows: JPEG0007724032000009.jpg11166Here, β0 is the intercept β1 is the feature F i,j Coefficient of ε is the error term Calculate the regression coefficients β0 and β1 using the least squares method, and use a linear regression model to estimate the feature F using the following formula: i,k Update JPEG0007724032000010.jpg10167. Construct a feature dataset for a given user by traversing all the standardized processed feature data for the given user, where one element in the feature dataset for a given user corresponds to one given user, and the number of elements in the feature dataset for a given user is equal to the number of given users in the database; In step S103, based on the feature data set of the predetermined user, a clustering analysis is performed on the predetermined user, and the predetermined user is divided into K categories. For the predetermined user in each category, a corresponding predetermined user profile is created. The process of creating the predetermined user profile is as follows: For a predetermined user in each category, a corresponding feature vector V is extracted from the feature dataset of the predetermined user, and the mean value and standard deviation of each feature in the category are calculated based on the feature vector V, and the feature weight W is obtained by normalizing based on the standard deviation. A predetermined user image U for each category is constructed based on the mean value and weight of the clustering category, and the predetermined user image U is denoted as a weighted feature vector.

[0039] In this embodiment, the following feature data is assumed.

[0040] Category 1 user characteristics data: User 1: [0.8,3.5,5] [0.8,3.5,5] User 2: [0.9,4,4] [0.9,4,4] User 3: [0.7,3,6] [0.7,3,6] Average value calculation: Feature 1: μ1,1=(0.8+0.9+0.7) / 3=0.8 Feature 2: μ1,2=(3.5+4+3) / 3=3.5 Feature 3: μ1,3=(5+4+6) / 3=5 Standard deviation calculation: Feature 1: σ1,1≒0.13, Feature 2: σ1,2≒0.29, Feature 3: σ1,3≒0.38 Feature weight calculation: W1,j=σ1,j / (σ1,1+σ1,2+σ1,3) User Profile: U1=[W1,1·μ1,1,W1,2·μ1,2,W1,3·μ1,3].

[0041] According to the feature data set of a predetermined user, clustering analysis is performed for the predetermined user. The specific clustering analysis process is as follows: According to the feature dataset of a predetermined user, obtain the feature data of the predetermined user, and use Euclidean distance as the initial distance metric to perform two-to-two distance metric calculation for all the predetermined users, and the distance metric is as follows: JPEG0007724032000011.jpg10167where, F a,k and F b,k are the standardized values of given users a and b for the kth feature, respectively. n is the total number of features Hierarchical clustering is applied as the initial clustering, and each given user is regarded as a single cluster. Clusters whose distance metric d(a, b) is greater than or equal to the threshold d are gradually merged. Based on the results of hierarchical clustering, the number of clusters K0 for an initial clustering is selected. K0 clusters are selected from the final clusters of the hierarchical clustering as the initial center points of K-means. The K-means clustering algorithm is then run. After each iteration, the quality of the clusters is evaluated and the K value is dynamically adjusted as follows: The specific analysis process is as follows: Calculate the within-cluster sum of squares (WCSS). The specific calculation formula for WCSS is as follows: JPEG0007724032000012.jpg14166 where M is the number of clusters Cm is the mth cluster f(p,k) is the value of the pth sample in the kth feature μm,k is the mean value of the mth cluster for the kth feature If the decrease in WCSS is less than a threshold t in c consecutive iterations, stop the iteration; otherwise, continue the iteration to adjust the value of K, and based on the finally determined K, re-run the K-means clustering algorithm to divide a given user into K categories.

[0042] Step S200 includes the following steps S201 to S202: In step S201, for a predetermined user in each category, based on the predetermined user feature dataset and the predetermined user image, extract the feature data of the predetermined user as an entity, combine the predetermined user image to extract the relationship between the feature data of the predetermined user, set the entities as nodes of the knowledge graph, set the relationships between the entities as edges of the knowledge graph, and combine the average values and weights of the clustering categories in step S103 to construct a knowledge graph of the predetermined user for each category; In step S202, obtain the knowledge graph of a given user for each category, define any node as the initial node, start from the initial node, traverse the knowledge graph of the given user, collect all reachable nodes J and paths P, and obtain a corresponding path set Pa, calculate the corresponding path weight w(path) for each path in the path set, and the value of w(path) is equal to the product of the weights of each feature in the path, and define the importance index G(J_h) according to the path weight w(path) by the following formula: JPEG0007724032000013.jpg11165Here, |P| is the path length I is the indicator function If node J_h is on path P, I(J_h∈P)=1; otherwise, I(J_h∈P)=0, where h indicates the node number. The importance index G(J_h) is compared with the corresponding threshold G0 to determine whether it is greater or smaller. If G(J_h)>G0, the corresponding node J_h is defined as a key node, and the feature corresponding to node J_h is defined as a key feature.

[0043] Step S300 is The method includes the steps of: extracting health care solutions corresponding to predetermined users of different categories from the database, and associating the corresponding health care solutions with the predetermined users of each category; constructing a key feature set Tu for each predetermined user based on key features corresponding to the predetermined users, where u indicates the predetermined user number; and sequentially calculating symmetric differences for the key feature set Tu of the predetermined users, comparing the health care solutions of the corresponding predetermined users with the health care solutions of the corresponding predetermined users, and correlating the symmetric difference results with the comparison results to obtain the correspondence between the predetermined health care solutions and the key features of the corresponding predetermined users.

[0044] Step S400 includes the following steps S401 to S402: In step S401, a real-time user inputs initial data, and performs the same analysis process on the initial data as on the multi-source historical data to construct a real-time user profile U1 based on the initial data, calculate the similarity between the real-time user profile U1 and a predetermined user profile U, and match it with a corresponding predetermined user category based on the similarity calculation result, and the one with the largest similarity is taken as the matching result, and output a predetermined health management solution list corresponding to the predetermined user category based on the matching result; In step S402, based on the predetermined health management solution list, the real-time user selects one predetermined health management solution, implements the predetermined health management solution, obtains multi-source real-time data of the real-time user for each selected period, extracts corresponding real-time feature data based on the multi-source real-time data, compares the real-time feature data with key features corresponding to the predetermined health management solution list, and if the real-time feature data is the same as the key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently implemented by the real-time user, appropriately adjusts the currently implemented predetermined health management solution according to the other predetermined health management solutions based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, thereby generating a personalized health management solution.

[0045] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be realized in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, in all respects, all embodiments should be considered as illustrative and not limiting, and the scope of protection of the present invention is limited by the appended claims, and is not limited to the above description, and all changes within the meaning and scope of equivalents falling within the scope of the claims are intended to be included in the present invention. Any reference signs in the claims should not be considered as limiting the relevant claims.

Claims

1. A health management method based on multi-source data collection and analysis, the method including the following steps S100 to S400: In step S100, obtain multi-source history data of all predetermined users from the database, perform corresponding selection and integration on the multi-source history data of each predetermined user to construct a characteristic data set of the predetermined users, classify the predetermined users according to the characteristic data set of the predetermined users, and create corresponding predetermined user profiles for the predetermined users in each category; Step S100 includes the following steps S101 to S103: In step S101, multi-source history data of all predetermined users is obtained from the database, the predetermined users refer to a user group stored in the database, and the multi-source history data refer to user health-related information collected from multiple different data sources. The multi-source history data of the predetermined users is uniformly converted into a uniform format, and the multi-source history data is grouped according to a predetermined user ID. Corresponding feature data is extracted from the multi-source history data of each predetermined user, and the extracted feature data is standardized. The specific calculation formula for the standardization process is as follows: Here, F ｉ，ｊ is the j-th standardized feature data of a given user i X ｉ，ｊ is the j-th original feature data of a given user i μ ｊ and σ ｊ are the mean value and standard deviation of the j-th feature data, respectively. In step S102, a correlation analysis is performed on the standardized feature data of each predetermined user to obtain a linear relationship between the standardized feature data, and a value evaluating the linear relationship is defined as a correlation coefficient R. For feature data whose absolute value of the correlation coefficient R is equal to a threshold value R0, a corresponding linear relationship is established using a linear regression model, where the linear regression model is as follows: where β0 is the intercept β1 is the feature F ｉ，ｊ Coefficient of ε is the error term The regression coefficients β0 and β1 are calculated using the least squares method, and the feature F is calculated using the following equation using a linear regression model: ｉ，ｋ Update Here, F' ｉ，ｋ denotes the k-th standardized feature data of a given user i updated by the linear regression model; construct a feature dataset for the given user by traversing all the standardized processed feature data of the given user, where one element in the feature dataset for the given user corresponds to one given user, and the number of elements in the feature dataset for the given user is equal to the number of given users in the database; In step S103, based on the feature data set of the predetermined user, a clustering analysis is performed on the predetermined user, the predetermined user is divided into K categories, and a corresponding predetermined user profile is created for the predetermined user in each category. The process of creating the predetermined user profile is as follows: For a predetermined user in each category, extract a corresponding feature vector V from the feature dataset of the predetermined user; calculate the mean value and standard deviation of each feature in the category based on the feature vector V; perform normalization based on the standard deviation to obtain the feature weight W; construct a predetermined user image U for each category based on the mean value and weight of the clustering category; and the predetermined user image U is denoted as a weighted feature vector; In step S200, for a predetermined user in each category, a knowledge graph of the predetermined user is constructed based on the predetermined user feature data set and the predetermined user profile, and the knowledge graph of the predetermined user and the predetermined user feature data set are combined and analyzed. Based on the analysis result, key features of the predetermined user in the corresponding category are identified; The step S200 includes the following steps S201 to S202: In step S201, for a predetermined user in each category, feature data of the predetermined user is extracted as an entity based on the feature dataset of the predetermined user and the predetermined user image, and the predetermined user image is combined to extract relationships between the feature data of the predetermined user, the entities are set as nodes of a knowledge graph, and the relationships between the entities are set as edges of the knowledge graph, and the average values and weights of the clustering categories in step S103 are combined to construct a knowledge graph of the predetermined user for each category; In step S202, obtain the knowledge graph of a given user for each category, define any node as an initial node, start from the initial node, traverse the knowledge graph of the given user, collect all reachable nodes J and paths P, and obtain a corresponding path set Pa, calculate the corresponding path weight w(path) for each path in the path set, and the value of w(path) is equal to the product of the weights of each feature in the path, and define the importance index G(J_h) according to the path weight w(path) by the following formula: where |P| is the path length, I is the indicator function If node J_h is on path P, I(J_h∈P)=1; otherwise, I(J_h∈P)=0, where h indicates the node number. Determine the magnitude relationship between the importance index G(J_h) and the corresponding threshold G0. If G(J_h)>G0, define the corresponding node J_h as a key node, and define the feature corresponding to node J_h as a key feature. In step S300, obtain predetermined health management solutions provided for predetermined users of different categories in the database, and compare and analyze the predetermined health management solutions of each category with the key features of the corresponding predetermined users to obtain a correspondence relationship between the predetermined health management solutions and the key features of the corresponding predetermined users; Step S300 The method includes the steps of: extracting health care solutions corresponding to predetermined users of different categories from the database, and associating the corresponding health care solutions with the predetermined users of each category; constructing a key feature set Tu for each predetermined user based on key features corresponding to the predetermined users, where u indicates a predetermined user number; and sequentially calculating symmetric differences for the key feature sets Tu of the predetermined users, comparing the health care solutions of the corresponding predetermined users with the health care solutions of the corresponding predetermined users, and correlating the symmetric difference results with the comparison results, thereby obtaining correspondence relationships between the predetermined health care solutions and the key features of the corresponding predetermined users; In step S400, a real-time user inputs initial data, a real-time user profile is constructed based on the initial data, the real-time user profile is matched with a predetermined user profile, and a corresponding predetermined health management solution list is output based on the matching result. Multi-source real-time data of the real-time user is obtained, and the multi-source real-time data is extracted to identify real-time feature data of the real-time user, and the real-time feature data is compared with and analyzed with key features of the predetermined user, thereby generating personalized health management solutions.

2. According to the feature data set of a predetermined user, clustering analysis is performed for the predetermined user. The specific clustering analysis process is as follows: According to the feature dataset of a predetermined user, obtain the feature data of the predetermined user, and use Euclidean distance as the initial distance metric to perform two-to-two distance metric calculation for all the predetermined users, and the distance metric is as follows: Here, F ａ，ｋ and F ｂ，ｋ are the standardized values of given users a and b for the k-th feature, respectively. n is the total number of features Hierarchical clustering is applied as the initial clustering, and each predetermined user is regarded as a single cluster. Clusters whose distance metric d(a, b) is greater than or equal to the threshold d are gradually merged. According to the result of hierarchical clustering, the number of clusters K0 of one initial clustering is selected. K0 clusters are selected from the final clusters of the hierarchical clustering as the initial center points of K-means. The K-means clustering algorithm is executed. After each iteration, the quality of the clusters is evaluated as follows to dynamically adjust the K value. The specific analysis process is as follows: The intra-cluster sum of squares (WCSS) is calculated. The specific calculation formula for WCSS is as follows: where M is the number of clusters Cm is the mth cluster f(p, k) is the value of the pth sample in the kth feature μm,k is the mean value of the mth cluster in the kth feature 2. The health management method based on multi-source data collection and analysis according to claim 1, wherein if the decrease in WCSS is less than a threshold t in c consecutive iterations, the iterations are stopped; otherwise, the iterations are continued to adjust the value of K, and based on the finally determined K, the K-means clustering algorithm is re-run to classify the predetermined user into K categories.

3. The step S400 includes steps S401 to S402, In step S401, a real-time user inputs initial data, and performs the same analysis process on the initial data as on the multi-source history data to construct a real-time user profile U1 based on the initial data, calculate the similarity between the real-time user profile U1 and a predetermined user profile U, and match the real-time user profile U1 with a corresponding predetermined user category based on the similarity calculation result, and the one with the largest similarity is taken as the matching result, and output a predetermined health management solution list corresponding to the predetermined user category based on the matching result; 2. The health management method based on multi-source data collection and analysis of claim 1, wherein: in step S402, based on the predetermined health management solution list, the real-time user selects one predetermined health management solution, implements the predetermined health management solution, obtains multi-source real-time data of the real-time user for each selected period, extracts corresponding real-time feature data based on the multi-source real-time data, compares the real-time feature data with key features corresponding to the predetermined health management solution list, and if the real-time feature data is identical to key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently implemented by the real-time user, appropriately adjusts the currently implemented predetermined health management solution according to the other predetermined health management solutions based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, thereby generating a personalized health management solution.

4. A health management system based on multi-source data collection and analysis, which is applied to the health management method based on multi-source data collection and analysis according to any one of claims 1 to 3, wherein the system includes: a data collection and processing module; a user classification and user profile construction module; a knowledge graph construction module; a health management solution matching module; and a personalized health management module; The data collection and processing module acquires multi-source history data of a specific user from multiple databases, uniformly converts the multi-source history data of different formats and structures, and extracts and standardizes feature data of the specific user to build a feature data set of the specific user; The user classification and user profile construction module performs correlation analysis on the feature data in the predetermined user feature dataset, calculates the linear relationship between the features, establishes the relationship between the features using a linear regression model, classifies the users into different categories using clustering analysis, and creates a corresponding predetermined user profile for each category; The knowledge graph construction module defines nodes and edges, establishes relationships between entities, and constructs a knowledge graph for the predetermined user based on the feature dataset of the predetermined user and the predetermined user profile; and constructs a key feature set for each predetermined user by traversing the knowledge graph and identifying key nodes and key features; The health management solution matching module uses initial data input by the real-time user to construct a real-time user profile and matches it with a predetermined user profile to obtain a category corresponding to the real-time user, and outputs a predetermined health management solution list corresponding to the predetermined user category based on the matching result; The personalized health management module obtains multi-source real-time data of the real-time user based on a predetermined health management solution selected by the real-time user, extracts corresponding real-time feature data based on the multi-source real-time data, compares the real-time feature data with key features corresponding to the predetermined health management solution list, and, if the real-time feature data is the same as key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently being implemented by the real-time user, appropriately adjusts the currently implemented predetermined health management solution in accordance with the other predetermined health management solutions based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, thereby generating a personalized health management solution.

5. the data collection and processing module includes a data collection unit and a data processing unit; The data collection unit collects multi-source history data of the predetermined user from a database; the data processing unit unifies the multi-source history data of different formats and structures, extracts and standardizes feature data of the predetermined user, and thereby constructs a feature data set of the predetermined user; The user classification and user profile building module includes: a user classification unit and a user profile building unit; 5. The health management system based on multi-source data collection and analysis of claim 4, wherein the user classification unit performs clustering analysis on the predetermined user features in the predetermined user feature dataset to divide the predetermined users into multiple categories, and the user image creation unit creates a predetermined user image for the predetermined users in each category by creating a weighted feature vector based on the predetermined user feature dataset.

6. The knowledge graph construction module includes: a knowledge graph construction unit; and a key feature identification unit; 5. The health management system based on multi-source data collection and analysis of claim 4, wherein the knowledge graph construction unit constructs a knowledge graph of a predetermined user of each category based on the predetermined user's feature dataset and the predetermined user profile, and the key feature identification unit performs association analysis in the knowledge graph to identify key features of the predetermined user of each category, and constructs a key feature set for each predetermined user.

7. The personalized health management module includes: a real-time data collection unit; a similarity calculation unit; and a solution adjustment unit; 5. The health management system based on multi-source data collection and analysis according to claim 4, wherein the real-time data collection unit obtains data input by the user in real time and performs corresponding analysis to construct a real-time user profile; the similarity calculation unit calculates the similarity between the real-time user profile and a predetermined user profile to determine a predetermined user category corresponding to the real-time user; the solution adjustment unit compares the real-time feature data with key features corresponding to a predetermined health management solution list; and if the real-time feature data is identical to key features of other predetermined health management solutions in the predetermined health management solution list other than the predetermined health management solution currently being implemented by the real-time user, then appropriately adjusts the currently implemented predetermined health management solution according to the other predetermined health management solutions based on the correspondence between the other predetermined health management solutions and the key features of the predetermined user, thereby generating a personalized health management solution.

Images