A health consultation service acquisition system

Abstract

The present invention discloses a health consultation service acquisition system, which specifically relates to the field of health service technology, and includes steps of building a health database: step S01, screening out authoritative websites and journals as acquisition sources of health data; step S02, acquiring a maturity parameter ε of constructed information X; step S03, storing information X that meets a maturity threshold into a health database; step S04, screening out information that contradicts information X from the acquired information, when the absolute value of the maturity difference between the contradictory information is greater than a preset value, taking data with a larger maturity parameter and entering it into a health information database, when the absolute value of the maturity difference is less than a preset value, marking the group of paradoxical information to enter the next step; step S05, respectively calculating the actual preference weights of hospitals for contradictory information groups, acquiring a revised maturity parameter, and storing the data with a larger value in a database.

Description

Technical Field

[0001] The present invention relates to the technical field of health services, and more specifically, to a health consultation service acquisition system. Background Art

[0002] Health issues have always been a topic of concern to people. People are exposed to a large amount of health-related information every day. Health data depends on the progress and development of scientific research and technology. Therefore, new health data is constantly being released and past health data is overturned. Based on this, it is believed that the content of health data should also be timely.

[0003] The existing health consultation service system collects health consultations and provides health consultations to users through search engines. However, these health data often transmit outdated and inaccurate information to users in the name of popular science, resulting in users being unable to obtain real and effective health consultations. At the same time, users often do not provide sufficient physical examination information when consulting on health issues. When using the system to retrieve health data, they do not know who the searcher is, resulting in a lack of pertinence in the search results, increasing the search cost, reducing the efficiency of consultation, and causing the health information provided to be inconsistent with the actual situation.

[0004] Based on this, a health consultation service acquisition system is needed that can meet the user's consultation needs and provide users with timely, accurate and actual health data for the user. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a health consultation service acquisition system, which first obtains authoritative and reliable health data through a health database acquisition module, and then establishes a personnel management module. After the user selects the target user, he enters the health problem, and the health consultation service module analyzes the health problem, obtains the health data from the health database, and obtains the risk of the disease sent by the user through the health risk acquisition module, and issues an early warning based on the risk index to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a health consultation service acquisition system, comprising a personnel management module, a health database acquisition module, a health consultation service module, and a health risk acquisition module.

[0007] The personnel management module includes a personnel information input unit, a personnel information update unit, and a personnel information marking unit. The health information of the user is obtained through the personnel information input unit. The health information includes basic personnel information and test item information. The health information of the user is updated in time through the personnel information update unit. The deviation items and floating items in the test item information are marked through the personnel information marking unit.

[0008] The health database acquisition module includes a health data acquisition unit, a data maturity acquisition unit, a contradictory information evaluation unit, and a data update unit, which are used to build a database containing health content, store information that meets the maturity of health data into the health database, screen out contradictory health data, obtain reliable data based on maturity parameters, store the acquired health information in the database according to its category, obtain contradictory information in a timely manner, and update the information in the database;

[0009] The health consultation service module includes a consultation question analysis unit, a relevance evaluation unit, and a health data calling unit, which are used to provide health consultation services to users, input questions and symptoms, and obtain health data from the database;

[0010] The health risk acquisition module is used to evaluate the user's risk and obtain items to be examined.

[0011] Preferably, the personnel information entry unit in the personnel management module is used to enter the basic information and physical examination information of the personnel, and the physical examination information is medical examination items. Assuming that the physical examination items include n items, the normal medical threshold is used as the standard to obtain the deviation degree of each item, which is recorded as Pi; the personnel information update unit is used to obtain the recent user physical examination report, which includes physical examination items and corresponding test data, and obtain the deviation degree and floating degree of the test items.

[0012] Preferably, the deviation degree p1i of the project satisfies the formula , where x0 represents the normal value of the test item, the floating degree of the item is f2i, xb represents the latest data, and xa represents the last test data, satisfying the formula .

[0013] Preferably, the data acquisition unit uses a crawler to crawl health data and a database import method to obtain health information and source information, and transmits the information to a data maturity acquisition unit. The data maturity acquisition unit is used to obtain the maturity of the health data, and obtains the maturity parameters of the health data based on the time of submission, usage time, amount of data in related articles and information entropy of the health information; the contradictory information evaluation unit screens out contradictory health information, obtains the maturity parameters of the contradictory information, calculates the difference in maturity parameters between the contradictory information, and when the difference meets the threshold requirement, takes the contradictory information with a larger maturity parameter as reliable information; when the difference does not meet the threshold requirement, introduces the hospital preference weight, calculates the product of the maturity parameter and the hospital preference weight to obtain the preference-corrected maturity parameter, calculates the difference in preference-corrected maturity parameters between the contradictory information, takes the preference-corrected maturity parameter with a larger value as reliable information, and stores the reliable information in a database.

[0014] Preferably, the health database acquisition module includes the following steps:

[0015] Step S01: divide the health information into m sub-areas according to categories, crawl the health data respectively, select authoritative websites and journals as the sources of health data, mark the authority level parameter of the journal or web page as Q, and take the value as [1,5]. The smaller the value of Q, the higher the authority.

[0016] Step S02, obtain the maturity parameter ε of information X, obtain the actual use time t0 of the information, obtain n articles related to the information content, obtain the initial publication time t of the journal, recorded as ti, obtain the data volume Pi and information entropy S about information X in each article, satisfying the formula , where tj represents the time of crawling information, λ1, λ2, λ3 are coefficient constants, and P0 represents the unit data volume;

[0017] Step S03, data storage: storing the information X that meets the maturity threshold th1 into the health database, where the maturity threshold th1 is a value preset by the system;

[0018] Step S04: Filter out information that contradicts information X from the acquired information, record the contradictory information as -X, obtain m articles that support the contradictory information, evaluate the maturity parameters between the contradictory information, and satisfy the formula , the contradictory information refers to contradictory information that satisfies the formula , when the absolute value of the maturity difference between the contradictory information is greater than the preset value , take the data with large maturity parameters as reliable information and enter it into the health information database. , mark this set of paradoxical information and proceed to the next step;

[0019] Step S05, obtain the hospital set supporting information X, denoted as [y11, y12, ..., y1m], obtain the hospital set supporting information -X [y21, y22, ..., y2m], divide the hospital grades into tertiary, secondary and community hospitals, assign different values ​​to different hospital grades, and denoted as Gi, use ZBi to represent the number of patients treated by the hospital, calculate the actual preference weight YP of the hospital, and satisfy the formula , take the product of maturity parameter and hospital preference parameter to get preference modified maturity parameter, get preference modified maturity parameter to satisfy formula ε*YP, let the preference modified maturity parameter of support information X be XP1, let the preference modified maturity parameter of support information -X be XP2, if , take the support information X as the reliable information, otherwise take the support information -X as the reliable information, and store the reliable information in the database;

[0020] Step S06, data update: store the acquired health information in the database according to the category to which it belongs, obtain the contradictory information in time, and update the information in the database.

[0021] Preferably, the health consultation service module is used to provide health data for users, and extract health data for users from a health database based on user basic information and input consultation questions. It includes a consultation question processing unit, a relevance evaluation unit, and a data calling unit. The consultation question processing unit is used to obtain questions for consultation and extract keywords of the consultation questions. The relevance evaluation unit is used to evaluate the relevance index between the marked items and the consultation questions. The data calling unit is used to retrieve health data from the health database.

[0022] Preferably, the health consultation service module includes the following steps:

[0023] Step S11, consulting question processing: based on the personnel management module, select the targeted personnel mode, input the consulting question, filter the input common words based on the TF-IDF algorithm, retain the important words, the important words refer to the words related to health, record the obtained consulting question keyword set as G=[x1,x2,…,xn], the consulting question is in the form of a statement about health symptoms, and transmit the consulting question keyword set and the health information of the person to the correlation analysis step;

[0024] Step S12, correlation analysis: analyzing the information correlation index between the consulting question and the mark, establishing a two-way mapping table from the abnormal physical examination items to the health problem symptoms, judging the correlation between the health problem symptoms and the marked items based on the two-way mapping table, and obtaining the correlation evaluation index;

[0025] Step S13: recommend health data to the user based on the correlation evaluation index. When the correlation evaluation index is lower than the preset value, indicating that the health question raised by the user is irrelevant to the test item, health data is recommended to the user based on the keywords of the consultation question raised by the user. When the correlation evaluation index meets the preset value, indicating that the health question raised by the user is related to the previous test item, health data is recommended to the user based on the keywords of the consultation question raised by the user plus the test item marked by the user, and a reminder for re-examination of the test item is issued at the same time;

[0026] Step S14, data call: based on the health problem symptoms and the user, using the consultation question keywords as search terms, call data from the health database and output the called data to the user.

[0027] Preferably, the correlation evaluation index satisfies the formula , record the health problem symptoms as set G, based on the mapping table from health symptoms to abnormal indicators, obtain the user's existing problem set as ZW, calculate the relevance XGD1, satisfying the formula Based on the tag information and the mapping table from abnormal indicators to health problem symptoms, the possible symptom set of the user is obtained and recorded as WZ, and the correlation parameter XGD2 is calculated to satisfy the formula , where k1 and k2 are coefficient constants, and their value range is [0.1-1.0].

[0028] Preferably, the health risk acquisition module obtains the correlation function F1 (X) between diseases and indicators and health symptoms through the big data analysis unit, obtains the relationship between population characteristics and indicators, establishes a correlation function from characteristics to diseases, and obtains the user's health risk assessment index based on the user's basic information and physical examination information. The function F1 (X) is a linear regression equation about the feature set. Each disease is related to n independent variables. By obtaining the variance Vi of each feature in the disease and the normal value, the covariance ci between the variables is calculated to obtain the variance-covariance matrix. The dependency relationship between the variables is obtained based on the variance-covariance matrix, and a linear regression equation between the variables is established. The variables are first standardized, and variables with a mean of 0 and a variance of 1 are obtained after standardized processing, and the correlation coefficients of the independent variables are obtained.

[0029] Technical effects and advantages of the present invention:

[0030] The present invention obtains reliable health data through the data maturity acquisition unit and the contradictory information evaluation unit in the health database acquisition module, thereby avoiding the situation where unreliable health data misleads users. The relevance evaluation unit in the health consultation service module evaluates whether the health consultation proposed by the user is related to the user's own situation. If there is a relevance, health data is recommended to the user based on the user's test items and questions raised, which can meet the user's consultation needs and provide the user with timely, accurate and actual health data for the user, thereby solving the problems of the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a system structure block diagram of the present invention.

[0032] Figure 2 A flow chart is constructed for the health database of the present invention.

[0033] Figure 3 This is a flow chart of the health consultation service of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0035] The terms "module", "system", etc. used in this application are intended to include computer-related entities, such as but not limited to hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a module can be, but is not limited to: a process running on a processor, a processor, an object, an executable program, a thread of execution, a program, and / or a computer. For example, an application running on a computing device and the computing device can both be modules. One or more modules can be located within a process and / or thread in execution, and a module can also be located on one computer and / or distributed between two or more computers.

[0036] Example 1

[0037] This embodiment provides Figure 1 A health consultation service acquisition system is shown, comprising a personnel management module, a health database acquisition module, a health consultation service module, and a health risk acquisition module.

[0038] The personnel management module includes a personnel information input unit, a personnel information update unit, and a personnel information marking unit. The health information of the user is obtained through the personnel information input unit. The health information includes basic personnel information and test item information. The health information of the user is updated in time through the personnel information update unit. The deviation items and floating items in the test item information are marked through the personnel information marking unit.

[0039] The health database acquisition module includes a health data acquisition unit, a data maturity acquisition unit, a contradictory information evaluation unit, and a data update unit, which are used to build a database containing health content, store information that meets the maturity of health data into the health database, screen out contradictory health data, obtain reliable data based on maturity parameters, store the acquired health information in the database according to its category, obtain contradictory information in a timely manner, and update the information in the database;

[0040] The health consultation service module includes a consultation question analysis unit, a relevance evaluation unit, and a health data calling unit, which are used to provide health consultation services to users, input questions and symptoms, and obtain health data from the database;

[0041] The health risk acquisition module is used to evaluate the user's risk and obtain items to be examined.

[0042] Furthermore, the personnel information entry unit in the personnel management module is used to enter the basic information and physical examination information of the personnel, the basic information includes name, age, gender, height, weight, region, etc., and the physical examination information includes medical examination items. Assume that the physical examination items include n items, and take the normal medical threshold as the standard to obtain the deviation degree of each item, which is recorded as Pi; the personnel information update unit is used to obtain a recent user physical examination report, which includes physical examination items and corresponding test data, and obtain the deviation degree and floating degree of the test items.

[0043] Set the visitor mode. When the visitor mode is selected, the health consultation service module retrieves data from the health database using the keywords of the consultation questions.

[0044] Furthermore, the deviation degree p1i of the project satisfies the formula , where x0 represents the normal value of the test item, the floating degree of the item is f2i, xb represents the latest data, and xa represents the last test data, satisfying the formula .

[0045] Furthermore, the data collection unit uses a crawler to crawl health data and import databases to obtain health information and source information, and transmits the information to a data maturity acquisition unit. The data maturity acquisition unit is used to obtain the maturity of health data, and obtains maturity parameters of health data based on the time of submission and use of the health information, the amount of data in related articles, and the information entropy. The contradictory information evaluation unit screens out contradictory health information, obtains maturity parameters of contradictory information, calculates the difference in maturity parameters between contradictory information, and when the difference meets the threshold th1 requirement, the maturity threshold th1 is a system preset value, and takes the contradictory information with a larger maturity parameter as reliable information. When the difference does not meet the threshold requirement, the hospital preference weight is introduced, and the product of the maturity parameter and the hospital preference weight is calculated to obtain a preference-corrected maturity parameter. The difference in preference-corrected maturity parameters between contradictory information is calculated, and the preference-corrected maturity parameter with a larger value is taken as reliable information, and the reliable information is stored in a database.

[0046] Furthermore, the health database acquisition module includes the following steps:

[0047] Step S01, divide the health information into m sub-areas according to categories, crawl the health data respectively, select the authoritative websites and journals as the sources of health data, and set the authority level parameter Q of the journals or web pages;

[0048] Step S02, obtaining a maturity parameter ε of the information X based on the actual usage time of the information, the data volume of n articles related to the information content, and the information entropy;

[0049] Step S03, data storage: storing the information X that meets the maturity threshold th1 into the health database;

[0050] Step S04: Filter out information that contradicts information X from the acquired information. When the absolute value of the maturity difference between the contradictory information is greater than a preset value, take the data with a larger maturity parameter and enter it into the health information database. When the absolute value of the maturity difference is less than a preset value, mark the group of paradoxical information and proceed to the next step.

[0051] Step S05, obtain the hospital set supporting information X, obtain the hospital set supporting information -X, record the hospital level as Gi, calculate the actual preference weight YP of the hospital, take the product of the maturity parameter and the hospital preference parameter, satisfy the formula ε*YP, obtain the revised maturity parameter, take the larger value as reliable information, and store it in the database;

[0052] Step S06, data update: store the acquired health information in the database according to the category to which it belongs, obtain the contradictory information in time, and update the information in the database.

[0053] Furthermore, in step S02, the maturity parameter ε is obtained by: obtaining the actual use time t0 of the information, obtaining n articles related to the information content, obtaining the initial publication time t of the journal, recorded as ti, obtaining the data volume Pi and information entropy S about the information X in each article, and satisfying the formula , where tj represents the time for crawling information, λ1, λ2, λ3 are coefficient constants, and P0 represents the unit data volume.

[0054] Furthermore, in step S05, different hospital grades are assigned different values. The hospital grade is recorded as Gi, and ZBi is used to represent the number of patients treated by the hospital. The actual preference weight YP of the hospital is calculated to satisfy the formula , take the product of maturity parameter and hospital preference parameter to get preference modified maturity parameter, get preference modified maturity parameter to satisfy formula ε*YP, let the preference modified maturity parameter of support information X be XP1, let the preference modified maturity parameter of support information -X be XP2, if , take the support information X as the reliable information, otherwise take the support information -X as the reliable information, and store the reliable information in the database.

[0055] Furthermore, the health consultation service module is used to provide health data for users, and extract health data for users from a health database based on user basic information and input consultation questions. It includes a consultation question processing unit, a relevance evaluation unit, and a data calling unit. The consultation question processing unit is used to obtain questions for consultation and extract keywords of the consultation questions. The relevance evaluation unit is used to evaluate the relevance index between the marked items and the consultation questions. The data calling unit is used to retrieve health data from the health database.

[0056] Furthermore, if Figure 3 As shown, the health consultation service module includes the following steps:

[0057] Step S11, consulting question processing: based on the personnel management module, select the targeted personnel mode, input the consulting question, filter the input common words based on the TF-IDF algorithm, retain the important words, the important words refer to the words related to health, record the obtained consulting question keyword set as G=[x1,x2,…,xn], the consulting question is in the form of a statement about health symptoms, and transmit the consulting question keyword set and the health information of the person to the correlation analysis step;

[0058] Step S12, correlation analysis: analyzing the information correlation index between the consulting question and the mark, establishing a two-way mapping table from the abnormal physical examination items to the health problem symptoms, judging the correlation between the health problem symptoms and the marked items based on the two-way mapping table, and obtaining the correlation evaluation index;

[0059] Step S13: recommend health data to the user based on the correlation evaluation index. When the correlation evaluation index is lower than a preset value, recommend health data to the user based on the keywords of the consulting question raised by the user. When the correlation evaluation index meets the preset value, recommend health data to the user based on the keywords of the consulting question raised by the user plus the test items marked by the user, and issue a reminder for re-examination of the test items at the same time;

[0060] Step S14, data call: based on the health problem symptoms and the user, using the consultation question keywords as search terms, call data from the health database and output the called data to the user.

[0061] Furthermore, the correlation evaluation index satisfies the formula , record the health problem symptoms as set G, based on the mapping table from health symptoms to abnormal indicators, obtain the user's existing problem set as ZW, calculate the relevance XGD1, satisfying the formula Based on the tag information and the mapping table from abnormal indicators to health problem symptoms, the possible symptom set of the user is obtained and recorded as WZ, and the correlation parameter XGD2 is calculated to satisfy the formula Among them, k1 and k2 are coefficient constants, and their value range is [0.1-1.0].

[0062] Furthermore, the health risk acquisition module obtains the correlation function F1 (X) between diseases and indicators and health symptoms through the big data analysis unit, obtains the relationship between population characteristics and indicators, establishes a correlation function from characteristics to diseases, and obtains the user's health risk assessment index based on the user's basic information and physical examination information. The function F1 (X) is a linear regression equation about the feature set. Each disease is related to n independent variables. By obtaining the variance Vi of each feature in the disease and the normal value, the covariance ci between the variables is calculated to obtain the variance-covariance matrix. The dependency relationship between the variables is obtained based on the variance-covariance matrix, and a linear regression equation between the variables is established. The variables are first standardized, and variables with a mean of 0 and a variance of 1 are obtained after standardized processing, and the correlation coefficients of the independent variables are obtained.

[0063] The embodiments of the present invention merely provide one implementation mode, rather than specifically limiting the protection scope of the present invention.

[0064] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A health consultation service acquisition system, characterized in that: Including personnel management module, health database acquisition module, health consultation service module, health risk acquisition module, The personnel management module includes a personnel information input unit, a personnel information update unit, and a personnel information marking unit. The health information of the user is obtained through the personnel information input unit. The health information includes basic personnel information and test item information. The health information of the user is updated in time through the personnel information update unit. The deviation items and floating items in the test item information are marked through the personnel information marking unit. The personnel information input unit in the personnel management module is used to input the basic information and physical examination information of the personnel, the physical examination information is the medical examination items, and the physical examination items include n items. The deviation degree of each item is obtained based on the normal threshold of medicine, which is recorded as p1i; the personnel information update unit is used to obtain the recent user physical examination report, which includes the physical examination items and the corresponding test data, and obtain the deviation degree and floating degree of the test items; The deviation degree p1i of the project satisfies the formula , where x0 represents the normal value of the test item, and the floating degree of the item f2i is expressed by x b Indicates the latest data, with x a Represents the last test data, satisfying the formula ; The health database acquisition module includes a health data acquisition unit, a data maturity acquisition unit, a contradictory information evaluation unit, and a data update unit, which are used to build a database containing health content, store information that meets the maturity of health data into the health database, screen out contradictory health data, obtain reliable data based on maturity parameters, store the acquired health information in the database according to its category, obtain contradictory information in a timely manner, and update the information in the database; The data acquisition unit uses a crawler to crawl health data and a database import method to obtain health information and source information, and transmits the information to a data maturity acquisition unit. The data maturity acquisition unit is used to obtain the maturity of the health data, and obtains the maturity parameters of the health data based on the time of presentation of the health information, the time of use, the data volume of related articles, and the information entropy; the contradictory information evaluation unit screens out contradictory health information, obtains the maturity parameters of the contradictory information, calculates the difference in maturity parameters between the contradictory information, and when the difference meets the threshold requirement, takes the contradictory information with a larger maturity parameter value as reliable information, and stores the reliable information in the database; The health database acquisition module includes the following steps: Step S01: divide the health information into m sub-areas according to categories, crawl the health data respectively, select authoritative websites and journals as the sources of health data, mark the authority level parameter of the journal or web page as Q, and take the value as [1,5]. The smaller the value of Q, the higher the authority. Step S02: Obtain the maturity parameter ε of information X x , obtain the actual use time t0 of the information, obtain n articles related to the information content, and obtain the initial publication time t of the journal, recorded as t i , obtain the data volume Pi and information entropy Si about information X in each article, satisfying the formula , where t j represents the time to crawl information, where λ1, λ2, λ3 are coefficient constants, and P0 represents the unit data volume; Step S03, data storage: storing the information X that meets the maturity threshold th1 into the health database; Step S04: Filter out information that contradicts information X from the acquired information, record the contradictory information as -X, obtain m articles that support the contradictory information, evaluate the maturity parameters between the contradictory information, and satisfy the formula , the contradictory information refers to contradictory information that satisfies the formula , when the absolute value of the maturity difference between the contradictory information is greater than the preset value , take the data with large maturity parameters as reliable information and enter it into the health information database. , mark the group of contradictory information and proceed to the next step; Step S05, obtain the hospital set supporting information X, denoted as [y11, y12, ..., y1m], obtain the hospital set supporting information -X [y21, y22, ..., y2m], divide the hospital grades into tertiary, secondary and community hospitals, assign different values ​​to different hospital grades, and denoted as Gi, use ZBi to represent the number of patients treated by the hospital, calculate the actual preference weight YP of the hospital, and satisfy the formula , take the product of maturity parameter and hospital preference parameter to get preference modified maturity parameter, get preference modified maturity parameter to satisfy formula ε*YP, let the preference modified maturity parameter of support information X be XP1, let the preference modified maturity parameter of support information -X be XP2, if , take the support information X as the reliable information, otherwise take the support information -X as the reliable information, and store the reliable information in the database; Step S06, data update: store the acquired health information in the database according to the category to which it belongs, obtain the contradictory information in time, and update the information in the database; The health consultation service module includes a consultation question processing unit, a relevance evaluation unit, and a health data calling unit, and is used to provide health consultation services to users; The consulting question processing unit is used to obtain questions for consultation and extract keywords of the consulting questions; The relevance evaluation unit is used to evaluate the relevance evaluation index between the marked item and the consulting question; the health data calling unit is used to call the health data from the health database; The health consultation service module includes the following steps: Step S11, consulting question processing: based on the personnel management module, select the targeted personnel mode, input the consulting question, filter the input common words based on the TF-IDF algorithm, retain the important words, the important words refer to the words related to health, record the obtained consulting question keyword set as G=[x1,x2,…,xn], the consulting question is in the form of a statement about health symptoms, and transmit the consulting question keyword set and the health information of the person to the correlation analysis step; Step S12, correlation analysis: analyzing the information correlation index between the consulting question and the mark, establishing a two-way mapping table from the abnormal physical examination items to the health problem symptoms, judging the correlation between the health problem symptoms and the marked items based on the two-way mapping table, and obtaining the correlation evaluation index; Step S13: recommend health data to the user based on the correlation evaluation index. When the correlation evaluation index is lower than the preset value, indicating that the health question raised by the user is irrelevant to the test item, health data is recommended to the user based on the keywords of the consultation question raised by the user. When the correlation evaluation index meets the preset value, indicating that the health question raised by the user is related to the previous test item, health data is recommended to the user based on the keywords of the consultation question raised by the user plus the test item marked by the user, and a reminder for re-examination of the test item is issued at the same time; Step S14, health data call: based on health problem symptoms and users, using consulting question keywords as search terms, call data from the health database, and output the called data to the user; The correlation evaluation index satisfies the formula , record the health problem symptoms as set G, based on the mapping table from health symptoms to abnormal indicators, obtain the user's existing problem set as ZW, calculate the relevance XGD1, satisfying the formula Based on the tag information and the mapping table from abnormal indicators to health problem symptoms, the possible symptom set of the user is obtained and recorded as WZ, and the correlation parameter XGD2 is calculated to satisfy the formula , where k1 and k2 are coefficient constants, ranging from [0.1-1.0]; The health risk acquisition module is used to evaluate the user's health risk and obtain items to be examined.

2. A health consultation service acquisition system according to claim 1, characterized in that: The health risk acquisition module obtains the correlation function F1 (X) between diseases and indicators and health symptoms through the big data analysis unit, obtains the relationship between population characteristics and indicators, establishes a correlation function from characteristics to diseases, and obtains the user's health risk assessment index based on the user's basic information and physical examination information. The function F1 (X) is a linear regression equation about the feature set. Each disease is related to n independent variables. By obtaining the variance Vi of each feature in the disease and the normal value, the covariance ci between the variables is calculated to obtain the variance-covariance matrix. The dependency relationship between the variables is obtained based on the variance-covariance matrix, and a linear regression equation between the variables is established. The variables are first standardized, and variables with a mean of 0 and a variance of 1 are obtained after the standardized processing, and the correlation coefficient of the independent variable is obtained.

Images