Health stratification management system based on big data

Abstract

The present invention discloses a health hierarchical management system based on big data, including a physical examination data acquisition and analysis module, a multi-dimensional hierarchical analysis module, and a personalized physical examination recommendation management module, wherein the physical examination data acquisition and analysis module is used to obtain personal information data and physical examination data of physical examination users, the multi-dimensional hierarchical analysis module is used to build a hierarchical model, and the personalized physical examination recommendation management module is used to make personalized physical examination recommendations. The present invention constructs a physical examination data node model for physical examination users, uses a questionnaire to obtain indicator data related to the physical examination users, interprets the indicator data and the analyzed physical examination result data, and then constructs a hierarchical model to analyze from multiple dimensions. Finally, based on the user's physical examination result data and the feature data obtained from the personal health assessment questionnaire, personalized physical examination recommendations are made to the physical examination users according to the sensitive attribute hierarchy, thereby improving the user's physical examination efficiency while also improving the management efficiency of the physical examination terminal.

Description

Technical Field

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

[0002] Current health management systems are designed by hospitals based on different health checkup packages, tailored to specific budgets and requirements. These packages cover various body systems, including recruitment, school enrollment, civil service, and VIP checkups. However, these systems lack tailored health checkup recommendations tailored to the examinee's specific needs and individual circumstances. Furthermore, users often lack a clear understanding of their own health conditions, making it difficult to make informed selections and addressing the most pressing health checkup items. This further hinders the examinee's understanding of the various system functions after the exam, and their uncertainty about how to proceed if an abnormality is detected. Users only receive basic health checkup processing, such as the results and conclusions. This process simply transfers manual health checkup forms to a computer, lacking integration with other health checkup equipment, providing no preventive advice, and failing to prevent and control disease. Therefore, a big data-based tiered health management system is essential to improve health checkup efficiency and optimize the health checkup management process. Summary of the Invention

[0003] The purpose of the present invention is to provide a health stratification management system based on big data to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a health hierarchical management system based on big data, including a physical examination data acquisition and analysis module, a multi-dimensional hierarchical analysis module, and a personalized physical examination recommendation management module, characterized in that: the physical examination data acquisition and analysis module is used to obtain the personal information data and physical examination data of the physical examination user from the physical examination system; the multi-dimensional hierarchical analysis module is used to construct a hierarchical model based on the physical examination results and indicator data values ​​using the hierarchical analysis method, and perform analysis from multiple dimensions; the personalized physical examination recommendation management module is used to make personalized physical examination recommendations for the next cycle of the physical examination user according to the sensitive attribute hierarchy.

[0005] According to the above technical solution, the physical examination data acquisition and analysis module includes: a physical examination data node model module, a physical examination knowledge base module, and a physical examination data link transmission module. The physical examination data node model module is used to form a physical examination data node for each physical examination item category at the physical examination end; the physical examination knowledge base module is used to perform intelligent analysis based on the user's physical examination data using the physical examination knowledge base to obtain physical examination analysis results; the physical examination data link transmission module is used to automatically transmit the physical examination data to the health examination system through the physical examination data node according to the link interface.

[0006] According to the above technical solution, the multi-dimensional hierarchical analysis module includes: an indicator data module, a physical examination result data comparison module, a feedback dimension determination module, a multi-dimensional division determination module, and a sensitive attribute hierarchical output module. The indicator data module is used for the physical examination terminal in the system to push the set questionnaire to the physical examination user to collect physical examination-related indicator data; the physical examination result data comparison module is used to compare and analyze the physical examination result data with the standard data within the set data feature threshold range; the feedback dimension determination module is used to determine the feedback dimension of the physical examination user within the numerical standard range based on the specific physical examination value; the multi-dimensional division determination module is used to determine multiple dimensions of the degree, frequency, and status of the physical examination items accepted by the physical examination user; the sensitive attribute hierarchical output module is used to construct associated sensitivity based on the sensitivity of the identified sensitive attribute itself and the degree of association between the sensitive attributes, and to output the sensitive attributes in a hierarchical manner.

[0007] According to the above technical solution, the personalized physical examination recommendation management module includes: a feature keyword module, a two-dimensional array mapping module, a recommended physical examination item set module, and a physical examination cycle and frequency prediction model module. The feature keyword module is used to collect feature data from the personal health assessment questionnaire of the physical examination user, with the characteristics of each physical examination user as the keyword; the two-dimensional array mapping module is used to arrange the physical examination items corresponding to the sensitive attributes output by all hierarchical levels in order, and map them to the established two-dimensional array; the recommended physical examination item set module is used to retrieve the database key fields according to the recommendation pattern array, output the physical examination items that match the key fields, and generate a recommended physical examination item set; the physical examination cycle and frequency prediction model module is used to establish a physical examination cycle and frequency prediction model at the physical examination end, and provide feedback to the physical examination users who need frequency and cycle prediction.

[0008] According to the above technical solution, the operation method of the health stratification management system includes the following steps:

[0009] Step 1: Build a physical examination data node model for the physical examination user and perform intelligent analysis of the physical examination data;

[0010] Step 2: Synchronously obtain the indicator data related to the physical examination users based on the questionnaire, and interpret the indicator data and the analyzed physical examination result data;

[0011] Step 3: Use the analytic hierarchy process to build a hierarchical model based on the physical examination results and indicator data values, and analyze from multiple dimensions;

[0012] Step 4: Based on the user's physical examination result data and the characteristic data obtained from the personal health assessment questionnaire, personalized physical examination recommendations for the next cycle are made according to the sensitive attribute level.

[0013] According to the above technical solution, the step 1 further includes the following steps:

[0014] Step 11: The physical examination user who enters the system registers and queries the physical examination information through the physical examination user terminal. Each physical examination user has a personal information record of the physical examination and a mark code of the selected physical examination item. The physical examination system records the personal user information and physical examination data by identifying the mark code;

[0015] Step 12: Each medical examination item category on the medical examination side forms a medical examination data node. Based on the medical examination user's selection, the corresponding medical examination item category, medical examination item, department, and keyword are obtained. After the medical examination user completes the examination of each item and generates the results, the system automatically summarizes the medical examination data of each item using the medical examination data node;

[0016] Step 13: Perform intelligent analysis based on the user's physical examination data using the physical examination knowledge base to obtain the physical examination analysis results. Based on the first-level data automatic diagnosis conditions, determine the analysis output or upward transmission of the physical examination data. When the physical examination data node is directly linked to the interface of the health examination system, the physical examination data is automatically transmitted to the health examination system through the physical examination data node according to the link interface.

[0017] According to the above technical solution, the step 2 further includes the following steps:

[0018] Step 21: The physical examination terminal in the system synchronously pushes the options corresponding to the content of the physical examination-related indicator data in the set questionnaire to the physical examination user, selects the required fields from the physical examination data source to be processed according to the interpretation and mining objectives of the physical examination items, performs intervention rule mining on the physical examination data to extract the required data, converts the multi-valued attributes of the physical examination data into classified data, replaces the corresponding data information with coding, and constructs an auxiliary analysis model based on the data features of the pre-processed physical examination data;

[0019] Step 22: Convert the physical examination data of different specifications or distributions to an analytical distribution graph, compare and analyze the physical examination result data with the standard data within the set data feature threshold range, and use the physical examination numerical analysis and expert knowledge base to analyze and judge the single physical examination numerical value in combination with the expert knowledge base to draw conclusions and analytical suggestions;

[0020] Step 23: When the test data is higher or lower than the reference value, a physical examination report is formed based on the diagnostic value and suggestions, and the normal reference value is attached next to the physical examination data result for comparison. When the data in the physical examination user's physical examination report exceeds or is lower than the normal range, and there is a large gap between the value recorded in the physical examination report and the normal value, the physical examination user's feedback dimension is determined according to the specific physical examination value within the numerical standard range. The feedback dimension includes: data value analysis output based on the normal range, data value analysis based on the value outside the normal range, and linking to the medical terminal for further analysis and interpretation based on the abnormal results. The physical examination user can directly recommend the corresponding doctor or MDT team for analysis of the abnormal physical examination data through the doctor's business card function.

[0021] According to the above technical solution, the step three further includes the following steps:

[0022] Step 31: Based on the comparative analysis of each physical examination data of the physical examination user and the standard numerical range, and the values ​​of the index data of the physical examination user in the questionnaire are calculated as evaluation indicators, the index data value table is listed, and the values ​​of the answers to each index are sorted and ranked. Positive indicators are ranked from small to large, and negative indicators are ranked from large to small. Data with the same value are averaged to obtain a rank matrix;

[0023] Step 32: Calculate the rank sum ratio, calculate the weighted rank sum ratio using the analytic hierarchy process combined with the indicator weights, determine the weighted rank sum ratio distribution, compile a rank sum ratio and weighted rank sum ratio frequency distribution table, list the frequency of each group and the cumulative frequency of each group, and calculate the downward cumulative frequency and its corresponding probability unit, construct a linear regression equation with the probability unit as the independent variable and the weighted rank sum ratio as the dependent variable, and rank and sort according to the weighted rank sum ratio predicted value of the regression equation to determine the degree, frequency, and status of the physical examination items accepted by the physical examination users;

[0024] Step 33: Synchronously define high-dimensional data attributes with sensitive attributes, identify high-dimensional data in the three dimensions of the degree, frequency, and status of the physical examination items of the physical examination users based on the attributes, group the high-dimensional data, and use a two-step clustering algorithm to divide the original data into multiple data groups. The sensitive attributes are graded, and the associated sensitivity is constructed based on the sensitivity of the identified sensitive attributes themselves and the degree of association between the sensitive attributes, and the sensitive attributes are output in a hierarchical manner.

[0025] According to the above technical solution, the step 4 further includes the following steps:

[0026] Step 41: Using the characteristic data collected from the personal health assessment questionnaire of the physical examination user, using the characteristics of each physical examination user as keywords, retrieve and extract the physical examination items that have a symptom relationship with the physical examination user from the physical examination data knowledge base, and calculate the physical examination probability associated with the physical examination item, thereby obtaining a recommended ranking list of the physical examination items with a symptom relationship from high to low according to the predicted probability;

[0027] Step 42: Gather the acquired physical examination item contents, merge synonymous physical examination items based on keyword knowledge, define the fusion of identical physical examination items, confirm the final recommended physical examination item set, arrange the physical examination items corresponding to the sensitive attributes output by all hierarchical levels in order, map them to the established two-dimensional array, convert the sequence to be matched into a two-dimensional array, calculate the matching address of each sequence pattern in the sequence to be matched, and return the matching result;

[0028] Step 43: Serialize the physical examination data of the physical examination user and perform sequence pattern matching with the recommended pattern. When the physical examination items of the physical examination user are successfully matched with the recommended items, query the physical examination item database, retrieve the database key fields according to the recommended pattern array, output the physical examination items with matching key fields, and generate a recommended physical examination item set.

[0029] According to the above technical solution, after recommending a set of physical examination items corresponding to the characteristic keywords, medical knowledge related to the physical examination items is formed to recommend physical examination users, including the examination parts of the physical examination items, people who are not suitable for the physical examination items, precautions for the physical examination items, and reference values ​​of relevant physical examination indicators. By establishing a knowledge graph of the relationship between characteristic data and physical examination items, combined with the relationship between the examination items and the examination parts, people who are not suitable for the examination, precautions, and reference values ​​of physical examination indicators in the physical examination data of the physical examination user, a physical examination cycle and frequency prediction model is established on the physical examination end, feedback is provided to the physical examination user who needs to conduct frequency and cycle predictions, and the predicted physical examination recommendations and frequency suggestions for the next cycle are output to the physical examination user terminal.

[0030] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by providing a physical examination data acquisition and analysis module, a multi-dimensional hierarchical analysis module, and a personalized physical examination recommendation management module, constructs a physical examination data node model for physical examination users, uses a questionnaire to obtain indicator data related to physical examination users, interprets the indicator data and the analyzed physical examination result data, and then constructs a hierarchical model to analyze from multiple dimensions. Finally, based on the user's physical examination result data and the feature data obtained from the personal health assessment questionnaire, personalized physical examination recommendations are made for physical examination users according to the sensitive attribute level, personalized physical examination project decisions are made based on the characteristics of the physical examination data, and corresponding explanations are given. After the physical examination, the physical examination report has strong readability and completeness, which can help the physical examination user to clarify his or her own condition and give in-depth physical examination suggestions, thereby improving the user's physical examination efficiency and also improving the management efficiency of the physical examination terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0032] Figure 1 This is a schematic diagram of the module composition of the big data-based health hierarchical management system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] Example 1: This example can be applied to the scenario of user physical examination data analysis and management. The method can be executed by the big data-based health stratification management system provided in this example. The method specifically includes the following steps:

[0035] Step 1: Build a physical examination data node model for the physical examination user and perform intelligent analysis of the physical examination data;

[0036] Step 2: Synchronously obtain the indicator data related to the physical examination users based on the questionnaire, and interpret the indicator data and the analyzed physical examination result data;

[0037] Step 3: Use the analytic hierarchy process to build a hierarchical model based on the physical examination results and indicator data values, and analyze from multiple dimensions;

[0038] Step 4: Based on the user's physical examination result data and the characteristic data obtained from the personal health assessment questionnaire, personalized physical examination recommendations for the next cycle are made according to the sensitive attribute level.

[0039] In an embodiment of the present invention, step one further includes the following steps:

[0040] Step 11: The physical examination user who enters the system registers and queries the physical examination information through the physical examination user terminal. Each physical examination user has a personal information record of the physical examination and a mark code of the selected physical examination item. The physical examination system records the personal user information and physical examination data by identifying the mark code;

[0041] Step 12: Each medical examination item category on the medical examination side forms a medical examination data node. Based on the medical examination user's selection, the corresponding medical examination item category, medical examination item, department, and keyword are obtained. After the medical examination user completes the examination of each item and generates the results, the system automatically summarizes the medical examination data of each item using the medical examination data node;

[0042] Step 13: Perform intelligent analysis based on the user's physical examination data using the physical examination knowledge base to obtain the physical examination analysis results. Based on the first-level data automatic diagnosis conditions, determine the analysis output or upward transmission of the physical examination data. When the physical examination data node is directly linked to the interface of the health examination system, the physical examination data is automatically transmitted to the health examination system through the physical examination data node according to the link interface.

[0043] In an embodiment of the present invention, step 2 further includes the following steps:

[0044] Step 21: The physical examination terminal in the system synchronously pushes the options corresponding to the content of the physical examination-related indicator data in the set questionnaire to the physical examination user, selects the required fields from the physical examination data source to be processed according to the interpretation and mining objectives of the physical examination items, performs intervention rule mining on the physical examination data to extract the required data, converts the multi-valued attributes of the physical examination data into classified data, replaces the corresponding data information with coding, and constructs an auxiliary analysis model based on the data features of the pre-processed physical examination data;

[0045] Step 22: Convert the physical examination data of different specifications or distributions to an analytical distribution graph, compare and analyze the physical examination result data with the standard data within the set data feature threshold range, and use the physical examination numerical analysis and expert knowledge base to analyze and judge the single physical examination numerical value in combination with the expert knowledge base to draw conclusions and analytical suggestions;

[0046] Step 23: When the test data is higher or lower than the reference value, a physical examination report is formed based on the diagnostic value and suggestions, and the normal reference value is attached next to the physical examination data result for comparison. When the data in the physical examination user's physical examination report exceeds or is lower than the normal range, and there is a large gap between the value recorded in the physical examination report and the normal value, the physical examination user's feedback dimension is determined according to the specific physical examination value within the numerical standard range. The feedback dimension includes: data value analysis output based on the normal range, data value analysis based on the value outside the normal range, and linking to the medical terminal for further analysis and interpretation based on the abnormal results. The physical examination user can directly recommend the corresponding doctor or MDT team for analysis of the abnormal physical examination data through the doctor's business card function.

[0047] In an embodiment of the present invention, step three further includes the following steps:

[0048] Step 31: Based on the comparative analysis of each physical examination data of the physical examination user and the standard numerical range, and the values ​​of the index data of the physical examination user in the questionnaire are calculated as evaluation indicators, the index data value table is listed, and the values ​​of the answers to each index are sorted and ranked. Positive indicators are ranked from small to large, and negative indicators are ranked from large to small. Data with the same value are averaged to obtain a rank matrix;

[0049] Step 32: Calculate the rank sum ratio, calculate the weighted rank sum ratio using the analytic hierarchy process combined with the indicator weights, determine the weighted rank sum ratio distribution, compile a rank sum ratio and weighted rank sum ratio frequency distribution table, list the frequency of each group and the cumulative frequency of each group, and calculate the downward cumulative frequency and its corresponding probability unit, construct a linear regression equation with the probability unit as the independent variable and the weighted rank sum ratio as the dependent variable, and rank and sort according to the weighted rank sum ratio predicted value of the regression equation to determine the degree, frequency, and status of the physical examination items accepted by the physical examination users;

[0050] Step 33: Synchronously define high-dimensional data attributes with sensitive attributes, identify high-dimensional data in the three dimensions of the degree, frequency, and status of the physical examination items of the physical examination users based on the attributes, group the high-dimensional data, and use a two-step clustering algorithm to divide the original data into multiple data groups. The sensitive attributes are graded, and the associated sensitivity is constructed based on the sensitivity of the identified sensitive attributes themselves and the degree of association between the sensitive attributes, and the sensitive attributes are output in a hierarchical manner.

[0051] In an embodiment of the present invention, step 4 further includes the following steps:

[0052] Step 41: Using the characteristic data collected from the personal health assessment questionnaire of the physical examination user, using the characteristics of each physical examination user as keywords, retrieve and extract the physical examination items that have a symptom relationship with the physical examination user from the physical examination data knowledge base, and calculate the physical examination probability associated with the physical examination item, thereby obtaining a recommended ranking list of the physical examination items with a symptom relationship from high to low according to the predicted probability;

[0053] Step 42: Gather the acquired physical examination item contents, merge synonymous physical examination items based on keyword knowledge, define the fusion of identical physical examination items, confirm the final recommended physical examination item set, arrange the physical examination items corresponding to the sensitive attributes output by all hierarchical levels in order, map them to the established two-dimensional array, convert the sequence to be matched into a two-dimensional array, calculate the matching address of each sequence pattern in the sequence to be matched, and return the matching result;

[0054] Step 43: Serialize the physical examination data of the physical examination user and perform sequence pattern matching with the recommended pattern. When the physical examination items of the physical examination user are successfully matched with the recommended items, query the physical examination item database, retrieve the database key fields according to the recommended pattern array, output the physical examination items with matching key fields, and generate a recommended physical examination item set.

[0055] In an embodiment of the present invention, step four further includes the following: after recommending a set of physical examination items corresponding to the characteristic keywords, medical knowledge related to the physical examination items is formed to recommend physical examination users, including the examination parts of the physical examination items, people who are not suitable for the physical examination items, precautions for the physical examination items, and reference values ​​of relevant physical examination indicators. By establishing a knowledge graph of the relationship between characteristic data and physical examination items, and combining the relationship between the examination items and the examination parts, people who are not suitable for the examination, precautions, and reference values ​​of physical examination indicators in the physical examination data of the physical examination user, a physical examination cycle and frequency prediction model for the physical examination end is established, feedback is provided to the physical examination user who needs to perform frequency and cycle prediction, and the predicted physical examination recommendations and frequency suggestions for the next cycle are output to the physical examination user terminal.

[0056] Example 2: Example 2 of the present invention provides a health hierarchical management system based on big data. Figure 1 This is a schematic diagram of the module composition of the health hierarchical management system based on big data provided in the second embodiment of the present invention, as shown in FIG. Figure 1 As shown, the system includes:

[0057] The physical examination data acquisition and analysis module is used to obtain the personal information data and physical examination data of the physical examination user from the physical examination system;

[0058] Multi-dimensional hierarchical analysis module, which is used to construct a hierarchical model based on physical examination results and indicator data values ​​using the hierarchical analysis method, and conduct analysis from multiple dimensions;

[0059] The personalized physical examination recommendation management module is used to make personalized physical examination recommendations for the next cycle of physical examination users based on the sensitive attribute level.

[0060] In some embodiments of the present invention, the physical examination data acquisition and analysis module includes:

[0061] The physical examination data node model module is used to form a physical examination data node for each physical examination item category on the physical examination side;

[0062] The physical examination knowledge base module is used to perform intelligent analysis based on the user's physical examination data using the physical examination knowledge base to obtain the physical examination analysis results;

[0063] The physical examination data link transmission module is used to automatically transmit the physical examination data to the health examination system through the physical examination data node according to the link interface.

[0064] In some embodiments of the present invention, the multi-dimensional hierarchical analysis module includes:

[0065] The indicator data module is used by the physical examination terminal in the system to push the set questionnaire to the physical examination user to collect physical examination related indicator data;

[0066] The physical examination result data comparison module is used to compare and analyze the physical examination result data with the standard data within the set data feature threshold range;

[0067] A feedback dimension determination module is used to determine the feedback dimension of the physical examination user within a numerical standard range according to the specific physical examination value;

[0068] A multi-dimensional division determination module is used to determine the multiple dimensions of the degree, frequency, and status of the physical examination items received by the physical examination user;

[0069] The sensitive attribute hierarchical output module is used to construct associated sensitivity based on the sensitivity of the identified sensitive attribute itself and the degree of association between sensitive attributes, and to output the sensitive attributes in a hierarchical manner.

[0070] In some embodiments of the present invention, the personalized physical examination recommendation management module includes:

[0071] The feature keyword module is used to collect feature data from the personal health assessment questionnaire of the physical examination user and use the features of each physical examination user as keywords;

[0072] The two-dimensional array mapping module is used to arrange the physical examination items corresponding to the sensitive attributes output by all hierarchical levels in order and map them into the established two-dimensional array;

[0073] The recommended physical examination item set module is used to retrieve the key fields of the database according to the recommended pattern array, output the physical examination items that match the key fields, and generate a recommended physical examination item set;

[0074] The physical examination cycle and frequency prediction model module is used to establish a physical examination cycle and frequency prediction model for the physical examination end, and provide feedback to physical examination users who need frequency and cycle prediction.

[0075] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0076] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A health hierarchical management system based on big data, including a physical examination data acquisition and analysis module, a multi-dimensional hierarchical analysis module, and a personalized physical examination recommendation management module, is characterized by: The physical examination data acquisition and analysis module is used to obtain the personal information data and physical examination data of the physical examination user from the physical examination system; the multi-dimensional hierarchical analysis module is used to use the hierarchical analysis method to construct a hierarchical model based on the physical examination results and indicator data values, and analyze from multiple dimensions; the personalized physical examination recommendation management module is used to make personalized physical examination recommendations for the next cycle of the physical examination user according to the sensitive attribute level. The operation method of the health stratification management system includes the following steps: Step 1: Build a physical examination data node model for the physical examination user and perform intelligent analysis of the physical examination data; Step 2: Synchronously obtain the indicator data related to the physical examination users based on the questionnaire, and interpret the indicator data and the analyzed physical examination result data; Step 3: Use the analytic hierarchy process to build a hierarchical model based on the physical examination results and indicator data values, and analyze from multiple dimensions; Step 4: Based on the user's physical examination results and the characteristic data obtained from the personal health assessment questionnaire, personalized physical examination recommendations for the next cycle are made according to the sensitive attribute level. The step three further comprises the following steps: Step 31: Based on the comparative analysis of each physical examination data of the physical examination user and the standard numerical range, and the values ​​of the index data of the physical examination user in the questionnaire are calculated as evaluation indicators, the index data value table is listed, and the values ​​of the answers to each index are sorted and ranked. Positive indicators are ranked from small to large, and negative indicators are ranked from large to small. Data with the same value are averaged to obtain a rank matrix; Step 32: Calculate the rank sum ratio, calculate the weighted rank sum ratio using the analytic hierarchy process combined with the indicator weights, determine the weighted rank sum ratio distribution, compile a rank sum ratio and weighted rank sum ratio frequency distribution table, list the frequency of each group and the cumulative frequency of each group, and calculate the downward cumulative frequency and its corresponding probability unit, construct a linear regression equation with the probability unit as the independent variable and the weighted rank sum ratio as the dependent variable, and rank and sort according to the weighted rank sum ratio predicted value of the regression equation to determine the degree, frequency, and status of the physical examination items accepted by the physical examination users; Step 33: Synchronously define high-dimensional data attributes with sensitive attributes, identify high-dimensional data in the three dimensions of the degree, frequency, and status of the physical examination items of the physical examination users based on the attributes, group the high-dimensional data, and use a two-step clustering algorithm to divide the original data into multiple data groups. The sensitive attributes are graded, and the associated sensitivity is constructed based on the sensitivity of the identified sensitive attributes themselves and the degree of association between the sensitive attributes, and the sensitive attributes are output in a hierarchical manner.

2. The big data-based health hierarchical management system according to claim 1, characterized in that: The physical examination data acquisition and analysis module includes: a physical examination data node model module, a physical examination knowledge base module, and a physical examination data link transmission module. The physical examination data node model module is used to form a physical examination data node for each physical examination item category at the physical examination end; the physical examination knowledge base module is used to perform intelligent analysis based on the user's physical examination data using the physical examination knowledge base to obtain physical examination analysis results; the physical examination data link transmission module is used to automatically transmit the physical examination data to the health examination system through the physical examination data node according to the link interface.

3. The big data-based health hierarchical management system according to claim 2, characterized in that: The multi-dimensional hierarchical analysis module includes: an indicator data module, a physical examination result data comparison module, a feedback dimension determination module, a multi-dimensional division determination module, and a sensitive attribute hierarchical output module. The indicator data module is used for the physical examination terminal in the system to push the set questionnaire to the physical examination user to collect physical examination-related indicator data; the physical examination result data comparison module is used to compare and analyze the physical examination result data with the standard data within the set data feature threshold range; the feedback dimension determination module is used to determine the feedback dimension of the physical examination user within the numerical standard range based on the specific physical examination value; the multi-dimensional division determination module is used to determine multiple dimensions of the degree, frequency, and status of the physical examination items accepted by the physical examination user; the sensitive attribute hierarchical output module is used to construct associated sensitivity based on the sensitivity of the identified sensitive attribute itself and the degree of association between the sensitive attributes, and output the sensitive attributes in a hierarchical manner.

4. The big data-based health hierarchical management system according to claim 3 is characterized by: The personalized physical examination recommendation management module includes: a feature keyword module, a two-dimensional array mapping module, a recommended physical examination item set module, and a physical examination cycle and frequency prediction model module. The feature keyword module is used to collect feature data from the personal health assessment questionnaire of the physical examination user, with the characteristics of each physical examination user as the keyword; the two-dimensional array mapping module is used to arrange the physical examination items corresponding to the sensitive attributes output by all hierarchical levels in order, and map them to the established two-dimensional array; the recommended physical examination item set module is used to retrieve the database key fields according to the recommendation pattern array, output the physical examination items that match the key fields, and generate a recommended physical examination item set; the physical examination cycle and frequency prediction model module is used to establish a physical examination cycle and frequency prediction model at the physical examination end, and provide feedback to the physical examination users who need frequency and cycle prediction.

5. The big data-based health hierarchical management system according to claim 4 is characterized by: The step 1 further comprises the following steps: Step 11: The physical examination user who enters the system registers and queries the physical examination information through the physical examination user terminal. Each physical examination user has a personal information record of the physical examination and a mark code of the selected physical examination item. The physical examination system records the personal user information and physical examination data by identifying the mark code; Step 12: Each medical examination item category on the medical examination side forms a medical examination data node. Based on the medical examination user's selection, the corresponding medical examination item category, medical examination item, department, and keyword are obtained. After the medical examination user completes the examination of each item and generates the results, the system automatically summarizes the medical examination data of each item using the medical examination data node; Step 13: Perform intelligent analysis based on the user's physical examination data using the physical examination knowledge base to obtain the physical examination analysis results. Based on the first-level data automatic diagnosis conditions, determine the analysis output or upward transmission of the physical examination data. When the physical examination data node is directly linked to the interface of the health examination system, the physical examination data is automatically transmitted to the health examination system through the physical examination data node according to the link interface.

6. The big data-based health hierarchical management system according to claim 5, characterized in that: The step 2 further comprises the following steps: Step 21: The physical examination terminal in the system synchronously pushes the options corresponding to the content of the physical examination-related indicator data in the set questionnaire to the physical examination user, selects the required fields from the physical examination data source to be processed based on the interpretation and mining objectives of the physical examination items, performs intervention rule mining on the physical examination data to extract the required data, converts the multi-valued attributes of the physical examination data into classified data, replaces the corresponding data information with coding, and constructs an auxiliary analysis model based on the data features of the pre-processed physical examination data; Step 22: Convert the physical examination data of different specifications or distributions to an analytical distribution graph, compare and analyze the physical examination result data with the standard data within the set data feature threshold range, and use the physical examination numerical analysis and expert knowledge base to analyze and judge the single physical examination numerical value in combination with the expert knowledge base to draw conclusions and analytical suggestions; Step 23: When the test data is higher or lower than the reference value, a physical examination report is formed based on the diagnostic value and suggestions, and the normal reference value is attached next to the physical examination data result for comparison. When the data in the physical examination user's physical examination report exceeds or is lower than the normal range, and there is a large gap between the value recorded in the physical examination report and the normal value, the physical examination user's feedback dimension is determined according to the specific physical examination value within the numerical standard range. The feedback dimension includes: data value analysis output based on the normal range, data value analysis based on the value outside the normal range, and linking to the medical terminal for further analysis and interpretation based on the abnormal results. The physical examination user can directly recommend the corresponding doctor or MDT team for analysis of the abnormal physical examination data through the doctor's business card function.

7. The big data-based health hierarchical management system according to claim 6, characterized in that: The step 4 further comprises the following steps: Step 41: Using the characteristic data collected from the personal health assessment questionnaire of the physical examination user, using the characteristics of each physical examination user as keywords, retrieve and extract the physical examination items that have a symptom relationship with the physical examination user from the physical examination data knowledge base, and calculate the physical examination probability associated with the physical examination item, thereby obtaining a recommended ranking list of the physical examination items with a symptom relationship from high to low according to the predicted probability; Step 42: Gather the acquired physical examination item contents, merge synonymous physical examination items based on keyword knowledge, define the fusion of identical physical examination items, confirm the final recommended physical examination item set, arrange the physical examination items corresponding to the sensitive attributes output by all hierarchical levels in order, map them to the established two-dimensional array, convert the sequence to be matched into a two-dimensional array, calculate the matching address of each sequence pattern in the sequence to be matched, and return the matching result; Step 43: Serialize the physical examination data of the physical examination user and perform sequence pattern matching with the recommended pattern. When the physical examination items of the physical examination user are successfully matched with the recommended items, query the physical examination item database, retrieve the database key fields according to the recommended pattern array, output the physical examination items with matching key fields, and generate a recommended physical examination item set.

8. The big data-based health hierarchical management system according to claim 7, characterized in that: After recommending a set of physical examination items corresponding to the characteristic keywords, medical knowledge related to the physical examination items is formed to recommend physical examination users, including the examination parts of the physical examination items, people who are not suitable for the physical examination items, precautions for the physical examination items, and reference values ​​of relevant physical examination indicators. By establishing a knowledge graph of the relationship between characteristic data and physical examination items, combined with the relationship between the examination items and the examination parts, people who are not suitable for the examination, precautions, and reference values ​​of physical examination indicators in the physical examination data of the physical examination users, a physical examination cycle and frequency prediction model for the physical examination end is established, feedback is given to the physical examination users who need frequency and cycle predictions, and the predicted physical examination recommendations and frequency suggestions for the next cycle are output to the physical examination user terminal.

Images