Citizen physical health risk prediction method and system based on artificial intelligence

Abstract

The invention discloses a citizen physical health risk prediction method and system based on artificial intelligence, and relates to the technical field of data analysis processing, and the method comprises the steps: carrying out the data matching processing of the to-be-analyzed physical data of citizens, and determining the to-be-verified unqualified standard physical data; and performing verification processing on the to-be-verified unqualified standard physique data, and determining the physique data which really does not meet the standard. According to the method, integrity analysis is firstly performed on the to-be-analyzed constitution data of the citizens, whether the to-be-analyzed data is complete or not is determined, the integrity of the analysis result is ensured, in addition, the to-be-analyzed constitution data of the citizens is verified by improving the related movement table of the constitution data, and the accuracy of the verification result is improved. According to the method, whether part of data exceeding normal data in the to-be-analyzed physique data of the citizens is normal or not is determined, the situation that misjudgment occurs on the to-be-analyzed physique data of the citizens who often move is avoided, the accuracy of data analysis is improved, meanwhile, the situation that the citizens carry misjudgment results to hospitals for examination is avoided, and the daily expenditure of the citizens is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis and processing, and in particular to a method and system for predicting citizens' physical health risks based on artificial intelligence. Background Art

[0002] Citizen physical fitness data typically includes various statistical information related to residents' health and physical fitness. This data can be used to analyze the overall health level, exercise habits, and dietary habits of city or regional residents, thereby helping to formulate public health policies and improve residents' quality of life.

[0003] Some of the physical data of citizens who exercise regularly are higher than those of normal people. If the physical data of citizens who exercise regularly are compared with those of normal people, misjudgment may occur. If citizens who exercise regularly go for examination based on the misjudged report, it will waste their money and increase their daily expenses. Summary of the Invention

[0004] In order to solve the above technical problems, a method and system for predicting the physical health risks of citizens based on artificial intelligence are provided. This technical solution solves the problem raised in the above background technology that some physical data of citizens who exercise regularly are higher than those of normal people. If the physical data of citizens who exercise regularly are compared with the physical data of normal people, misjudgment may occur. If citizens who exercise regularly go for examination based on the misjudged reports, it will waste their money and increase their daily expenses.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] A citizen's physical health risk prediction method based on artificial intelligence, including:

[0007] Obtain the physical data of citizens to be analyzed, perform data matching processing on the physical data to be analyzed based on the data analysis terminal, and determine the physical data to be verified as unqualified;

[0008] Based on the data analysis terminal, the physical data that fails to meet the verification standards are verified and processed to determine the physical data that truly does not meet the standards;

[0009] If there is physical data that does not meet the standards in the physical data to be analyzed, the citizen is unhealthy and there is a risk. Based on the data analysis terminal, information indicating that the citizen needs a physical examination will be sent to the citizen's electronic device.

[0010] Preferably, the steps of obtaining the physical data of the citizen to be analyzed, performing data matching processing on the physical data of the citizen to be analyzed based on the data analysis terminal, and determining the physical data to be verified as unqualified specifically include the following steps:

[0011] Based on the data analysis terminal, the data of smart wearable devices is read and processed to obtain the physical data of citizens to be analyzed;

[0012] Based on the data analysis terminal, the completeness of the physical data of citizens to be analyzed is analyzed to determine whether there are any data types that fail the test;

[0013] If there are data types that fail the test, reselect smart wearable devices to collect data on the data types that fail the test within the test period to obtain complete physical data of the citizens to be analyzed;

[0014] Based on the data analysis terminal, the complete physical data of citizens to be analyzed are compared and analyzed to determine the physical data that does not meet the standards to be verified.

[0015] Preferably, the completeness analysis of the physical fitness data of the citizen to be analyzed based on the data analysis terminal to determine whether there is any data type that fails the test specifically includes the following steps:

[0016] Based on the data analysis terminal, information analysis and processing are performed on the physical data of the citizen to be analyzed to determine a detection window; wherein the size of the detection window is the same as the detection frequency of the physical data of the citizen to be analyzed;

[0017] Based on the data analysis terminal, the detection window is controlled according to the detection step length to perform data missing detection processing on the physical data of the citizen to be analyzed, and the window data missing rate is determined; wherein the detection step length is the same as the size of the detection window;

[0018] Based on the data analysis terminal, the window data missing rate is compared and analyzed to determine whether there are any data types that fail the test;

[0019] The specific calculation formula for determining the window data missing rate is:

[0020]

[0021] Wherein, the W d is the window data missing rate; D1 is the number of missing data within the window; α is the detection step size.

[0022] Preferably, the comparative analysis of the window data missing rate based on the data analysis terminal to determine whether there is a data type that fails the detection specifically includes the following steps:

[0023] Based on the data analysis terminal, the window data missing rate is counted based on the set data missing rate threshold. The number of occurrences of the window data missing rate greater than or equal to the set data missing rate threshold is recorded and set as the number of occurrences of the data unqualified window.

[0024] Based on the data analysis terminal, the detection frequency of the citizens' physical data to be analyzed is calculated and processed to determine the detection frequency of the smart wearable device;

[0025] Based on the data analysis terminal, the number of occurrences of data-unqualified windows and the number of detections by the smart wearable device are calculated and processed to determine the window data unqualified rate;

[0026] Based on the data analysis terminal, the window data failure rate and the set data failure rate threshold are judged and processed;

[0027] If the window data unqualified rate is greater than or equal to the set data unqualified rate threshold, the data type corresponding to the window data unqualified rate greater than or equal to the set data unqualified rate threshold is set as the detection unqualified data type;

[0028] If the window data failure rate is less than the set data failure rate threshold, there is no data type that fails the test;

[0029] The specific calculation formula for determining the number of detection times of the smart wearable device is:

[0030]

[0031] In the formula, F1 is the number of detections of the smart wearable device; T1 is the detection cycle of the smart wearable device, which is one day; and T2 is the detection frequency of the citizen's physical data to be analyzed.

[0032] Preferably, the comparative analysis and processing of the complete physical data of the citizen to be analyzed based on the data analysis terminal to determine the physical data to be verified as not meeting the standards specifically includes the following steps:

[0033] Based on the data analysis terminal, the complete data of the physical condition of the citizens to be analyzed is retrieved and processed to determine the age data of the citizens;

[0034] Based on the data analysis terminal, the database system is processed to extract data and obtain the physical fitness data reference table;

[0035] Based on the data analysis terminal, data is extracted and processed from the physical fitness data reference table based on the citizen's age data to obtain a reference interval for normal physical fitness data; wherein the age data corresponding to the reference interval for normal physical fitness data is the same as the citizen's age data;

[0036] Based on the data analysis terminal, the complete data of the physical condition to be analyzed and the reference interval of the normal physical condition data of the citizen are judged and processed;

[0037] If there is data in the complete physical data of the citizen to be analyzed that is not within the reference range of normal physical data, the data will be set as physical data to be verified as not meeting the standards;

[0038] If all the data in the complete physical data to be analyzed of the citizen are within the reference range of normal physical data, the complete physical data to be analyzed of the citizen all meet the standards.

[0039] Preferably, the method of verifying the physical data that fails the verification standard based on the data analysis terminal and determining the physical data that truly does not meet the standard specifically includes the following steps:

[0040] Based on the data analysis terminal, the database system is processed to extract data and obtain the relevant exercise table for improving physical fitness data;

[0041] Based on the data analysis terminal, a comparative analysis is conducted between the physical fitness data that fails to meet the verification standards and the related exercise tables for improving the physical fitness data, and the physical fitness data that does not meet the standards and needs to be re-verified is determined;

[0042] Based on the data analysis terminal, secondary verification is performed on the non-standard physical data that needs secondary verification to determine whether there is any physical data that truly does not meet the standards among the non-standard physical data that needs secondary verification.

[0043] Preferably, the comparative analysis of the physical fitness data to be verified as unqualified and the related exercise tables for improving the physical fitness data based on the data analysis terminal to determine the physical fitness data that does not meet the standards and needs secondary verification specifically includes the following steps:

[0044] Based on the data analysis terminal, the physical fitness data that fails to meet the verification standards and the related exercise tables for improving the physical fitness data are judged and processed;

[0045] If the physical data in the physical data to be verified as unqualified is completely different from the physical data in the exercise table related to the physical data for improving the physical data, the physical data to be verified as unqualified is set as the physical data that actually does not meet the standards;

[0046] If the physical data in the unqualified physical data to be verified have some of the same data types as the physical data in the related exercise table of the improved physical data, the unqualified physical data to be verified corresponding to the same data type will be set as the unqualified physical data that needs secondary verification, and the remaining unqualified physical data to be verified will be set as the physical data that truly does not meet the standards;

[0047] If the physical data in the physical data to be verified as unqualified are of the same type as the physical data in the relevant exercise table for improving the physical data, the physical data to be verified as unqualified physical data requiring secondary verification will be set as unqualified physical data.

[0048] Preferably, the method of performing secondary verification on the non-standard physical data requiring secondary verification based on the data analysis terminal and determining whether there is any physical data that truly does not meet the standards among the non-standard physical data requiring secondary verification specifically comprises the following steps:

[0049] Based on the data analysis terminal, information is extracted and processed from the exercise table related to the physical fitness data to obtain the exercise method for improving the physical fitness data; wherein the physical fitness data type corresponding to the exercise method for improving the physical fitness data is the same as the physical fitness data type that does not meet the standards and requires secondary verification;

[0050] Based on the data analysis terminal, data extraction and processing are performed on smart wearable devices to obtain citizens' exercise information;

[0051] Based on the data analysis terminal, the citizens' exercise information and the exercise methods used to improve their physical fitness data are compared and analyzed to obtain the normal range of physical fitness data;

[0052] Based on the data analysis terminal, the normal range of physical fitness data and the physical fitness data that does not meet the standards and needs secondary verification are judged and processed;

[0053] If the physical data that does not meet the standards and needs secondary verification is within the normal range of physical data, the physical data that does not meet the standards and needs secondary verification meets the standards;

[0054] If the non-standard physical data requiring secondary verification is not within the normal range of the physical data, the non-standard physical data requiring secondary verification is set as truly non-standard physical data.

[0055] Preferably, the comparative analysis of the citizen's exercise information and the exercise mode for improving physical fitness data based on the data analysis terminal to obtain the normal range of physical fitness data specifically includes the following steps:

[0056] Based on the data analysis terminal, the citizens' exercise information and exercise methods to improve their physical fitness data are judged and processed;

[0057] If the citizen's exercise information does not contain any exercise methods that can improve their physical fitness data, the physical fitness data that does not meet the standards and needs secondary verification will be set as physical fitness data that does not meet the standards;

[0058] If the citizen's exercise information contains exercise methods that improve physical data, based on the data analysis terminal, the physical data in the relevant exercise table for improving physical data is extracted and processed with the exercise methods that improve physical data as the characteristics to obtain the normal range of the physical data.

[0059] Furthermore, an intelligent citizen physical health risk prediction system is proposed, which is used to implement the above-mentioned citizen physical health risk prediction method based on artificial intelligence, including:

[0060] A data analysis terminal is used to control each module to perform integrity analysis, data comparison analysis, and data verification processing on the physical fitness data to be analyzed by the citizen, so as to determine whether the citizen is physically healthy; the data analysis terminal is used to control data transmission and information exchange between each module;

[0061] A database system for storing a reference table of physical fitness data and a table of related exercises for improving physical fitness data;

[0062] Smart wearable devices, which are used to collect data on citizens' bodies and obtain physical data to be analyzed;

[0063] A data integrity analysis module is used to perform data missing detection, data comparison, data calculation, and data judgment on the physical fitness data of citizens to be analyzed to determine whether there are any data types that fail the test;

[0064] A data analysis module, which is used to compare and analyze the complete physical data of citizens to be analyzed, and determine the physical data to be verified as not meeting the standards;

[0065] A data verification module, the data verification module is used to perform two data verifications on the physical fitness data to be verified as not meeting the standards, to determine the physical fitness data that truly does not meet the standards;

[0066] An information sending module sends information indicating that a physical examination is needed to a citizen's electronic device based on the physical data that does not meet the standards.

[0067] Compared with the existing technology, the present invention provides a citizen's physical health risk prediction method and system based on artificial intelligence, which has the following beneficial effects:

[0068] The present invention first performs a completeness analysis on the physical fitness data to be analyzed by the citizens to determine whether the data to be analyzed is complete, thereby ensuring the integrity of the analysis results. In addition, the physical fitness data to be analyzed by the citizens is verified by improving the relevant exercise table of the physical fitness data to determine whether some data exceeding the normal data in the physical fitness data to be analyzed by the citizens is normal, thereby avoiding misjudgment of the physical fitness data to be analyzed of citizens who exercise regularly, improving the accuracy of data analysis, and at the same time, avoiding the situation where citizens go to the hospital for examination with misjudgment results, thereby reducing the daily expenses of citizens. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 This is a flow chart of steps S100-S300 in a citizen's physical health risk prediction method based on artificial intelligence proposed in the present invention;

[0070] Figure 2 This is a structural block diagram of the intelligent citizen physical health risk prediction system proposed by the present invention. DETAILED DESCRIPTION

[0071] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0072] Reference Figure 1 As shown, a citizen's physical health risk prediction method based on artificial intelligence includes:

[0073] S100, obtaining the physical fitness data of the citizen to be analyzed, performing data matching processing on the physical fitness data to be analyzed based on the data analysis terminal, and determining the physical fitness data to be verified as unqualified;

[0074] S200: Based on the data analysis terminal, verify the physical data that fails the verification standard and determine the physical data that truly does not meet the standard;

[0075] S300: If the citizen's physical data to be analyzed does not meet the standards, the citizen's physical condition is unhealthy and there is a risk. The data analysis terminal sends a message to the citizen's electronic device indicating that a physical examination is needed.

[0076] Those skilled in the art can understand that, there are differences in the physical data to be analyzed of different citizens, but the physical data to be analyzed of normal citizens are within the normal range even if there are differences. However, some citizens like to run, and the physical fitness of citizens who run regularly is relatively good, and some of their physical data may be higher than the data within the normal range. However, data exceeding the normal range is normal for citizens who exercise regularly, and abnormal for citizens who do not exercise regularly. In order to avoid comparing the physical data of citizens who exercise regularly with the data within the normal range, and then judging that the physical data of the citizens are abnormal, the physical data to be analyzed of the citizens are verified multiple times to ensure that there will be no misjudgment of the physical data of citizens who exercise regularly, avoid the situation where citizens who exercise regularly go to the hospital for examination with misjudgment reports, and reduce the daily expenses of citizens.

[0077] Example 1

[0078] S100, obtaining the physical data of the citizen to be analyzed, performing data matching processing on the physical data of the citizen to be analyzed based on the data analysis terminal, and determining the physical data to be verified as unqualified, specifically includes the following steps:

[0079] S101. Based on the data analysis terminal, data is read and processed from the smart wearable device to obtain the physical fitness data of the citizen to be analyzed;

[0080] S102. Based on the data analysis terminal, the completeness of the physical fitness data of the citizen to be analyzed is analyzed to determine whether there is any data type that fails the test;

[0081] It is understandable that if a citizen's physical data to be analyzed is incomplete, the results of the physical data analysis may be incomplete. As a result, a citizen may be reported as healthy even though they are in poor health due to incomplete data. As a result, the citizen may not go to the hospital for examination, thus delaying treatment.

[0082] S103. If there is any data type that fails the test, reselect the smart wearable device to collect data on the data type that fails the test within the test period to obtain complete physical fitness data of the citizen to be analyzed;

[0083] It is understandable that when it is found that the physical data of citizens to be analyzed is incomplete, in order to improve the accuracy of data analysis, it is necessary to wear other smart wearable devices again to collect the missing data of citizens and ensure the integrity of the data;

[0084] S104. Based on the data analysis terminal, a comparative analysis is performed on the complete physical data of the citizen to be analyzed, and physical data to be verified as not meeting the standards is determined;

[0085] S102, based on the data analysis terminal, performs a completeness analysis on the physical fitness data of the citizen to be analyzed to determine whether there is any data type that fails the test, specifically including the following steps:

[0086] S1021. Analyze and process the citizen's physical fitness data to be analyzed based on the data analysis terminal, and determine a detection window; wherein the size of the detection window is the same as the detection frequency of the citizen's physical fitness data to be analyzed;

[0087] It is understandable that the data collected by the smart wearable device is collected at a fixed time interval. For example, if the smart wearable device is set to test the heart rate of a citizen every 10 minutes, the detection frequency is the fixed time interval for data collection.

[0088] S1022. Based on the data analysis terminal, control the detection window according to the detection step length to perform data missing detection processing on the physical fitness data of the citizen to be analyzed, and determine the window data missing rate; wherein the detection step length is the same as the size of the detection window;

[0089] It is understandable that the smart wearable device may be interfered with by external factors during a certain period of time, resulting in the failure to collect physical data during a certain period of time, thereby causing physical data to be missing. For example, a citizen may remove the smart wearable device from the body during a certain period of time, resulting in the smart wearable device not collecting data during this period of time. However, data missing may also be caused by damage to a component of the smart wearable device. Therefore, it is necessary to verify the missing data to determine whether the smart wearable device has malfunctioned.

[0090] S1023. Based on the data analysis terminal, comparative analysis is performed on the window data missing rate to determine whether there is any data type that fails the test;

[0091] The specific calculation formula for determining the window data missing rate is:

[0092]

[0093] Wherein, the W d is the window data missing rate; D1 is the number of missing data within the window; α is the detection step size.

[0094] Among them, S1023, based on the data analysis terminal, comparative analysis of the window data missing rate to determine whether there is any data type that fails the detection specifically includes the following steps:

[0095] S10231. Based on the data analysis terminal, count the window data missing rate based on the set data missing rate threshold as a feature, record the number of occurrences of the window data missing rate greater than or equal to the set data missing rate threshold, and set it as the number of occurrences of data unqualified windows;

[0096] S10232. Calculate and process the detection frequency of the citizen's physical fitness data to be analyzed based on the data analysis terminal, and determine the number of detection times of the smart wearable device;

[0097] S10233. Calculate the number of occurrences of data-unqualified windows and the number of detections by the smart wearable device based on the data analysis terminal to determine a window data unqualified rate.

[0098] S10234. Based on the data analysis terminal, determine and process the window data failure rate and the set data failure rate threshold;

[0099] S10235: If the window data unqualified rate is greater than or equal to the set data unqualified rate threshold, set the data type corresponding to the window data unqualified rate greater than or equal to the set data unqualified rate threshold as the detection unqualified data type;

[0100] S10236: If the window data failure rate is less than the set data failure rate threshold, there is no data type that fails the test;

[0101] The specific calculation formula for determining the number of detection times of the smart wearable device is:

[0102]

[0103] Wherein, F1 is the number of detections of the smart wearable device; T1 is the detection cycle of the smart wearable device, which is one day; T2 is the detection frequency of the citizen's physical data to be analyzed;

[0104] It is understandable that when there is an abnormality inside the smart wearable device, the data collected within a detection time may also be discontinuous, that is, the collected data is intermittent. For example, the data collection time is 1 minute, and 40 data need to be collected within this 1 minute. Due to a fault inside the smart wearable device, only 26 data are collected. Therefore, the window data missing rate includes not only complete data loss, but also partial data loss. The above-mentioned calculation formula for the window data missing rate is for partial data loss. Therefore, if the window data is completely missing, the missing rate is 100%, and the designed window data missing rate is for partial data loss. Because, when the data is missing less, there is no need to re-collect the data, and the physical data changes are regular. For example, there are 40 collected data and only 2 missing data. These two data can be supplemented according to the change law of physical data. When there are more missing data, the data collected within this time period may not be able to see its change law, and it cannot be supplemented. Then this data cannot be used and needs to be re-collected.

[0105] Among them, S104, based on the data analysis terminal, compares and analyzes the complete physical data of the citizen to be analyzed, and determines the physical data to be verified as not meeting the standards, specifically includes the following steps:

[0106] S1041. Based on the data analysis terminal, perform information retrieval processing on the complete physical data of the citizen to be analyzed to determine the citizen's age data;

[0107] S1042. Based on the data analysis terminal, extract data from the database system to obtain a reference table of physical fitness data;

[0108] S1043. Using the data analysis terminal, extract data from the physical fitness data reference table using the citizen's age data as a feature to obtain a reference interval for normal physical fitness data; wherein the age data corresponding to the reference interval for normal physical fitness data is the same as the citizen's age data;

[0109] S1044. Based on the data analysis terminal, a judgment is made on the complete physical data to be analyzed and the reference interval of the normal physical data of the citizen;

[0110] S1045. If there is data in the complete physical data to be analyzed of the citizen that is not within the reference range of normal physical data, the data is set as physical data to be verified as not meeting the standards;

[0111] S1046. If all data in the complete physical data to be analyzed of the citizen are within the reference range of normal physical data, the complete physical data to be analyzed of the citizen all meet the standards;

[0112] It is understandable that the reference ranges of physical data of citizens of different ages are different. For example, some physical data of teenagers may be higher than those of the elderly. If the physical data of the elderly are compared with those of teenagers, the physical data of teenagers may be abnormal. Therefore, it is necessary to first determine the age data of the citizens, and then determine the corresponding reference range of normal physical data based on the age data of the citizens. Finally, compare the complete physical data of the citizens to be analyzed with the reference range of normal physical data to determine whether there is abnormal data.

[0113] Example 2

[0114] S200: Based on the data analysis terminal, verify the physical data that fails the verification standard, and determine the physical data that does not meet the standard. Specifically, the steps include:

[0115] S201: extracting data from a database system based on a data analysis terminal to obtain a table of exercises related to improving physical fitness data;

[0116] S202: Comparing and analyzing the physical fitness data that fails the verification and the related exercise tables for improving the physical fitness data based on the data analysis terminal, and determining the physical fitness data that does not meet the standards and needs secondary verification;

[0117] S203: performing secondary verification on the physical fitness data that does not meet the standards and needs secondary verification based on the data analysis terminal to determine whether there is any physical fitness data that truly does not meet the standards among the physical fitness data that does not meet the standards and needs secondary verification;

[0118] S202, based on the data analysis terminal, compares and analyzes the physical fitness data that fails the verification standard and the related exercise tables for improving the physical fitness data, and determines the physical fitness data that does not meet the standard and needs secondary verification, specifically includes the following steps:

[0119] S2021. Based on the data analysis terminal, judging and processing the physical fitness data that fails the verification standard and the related exercise tables for improving the physical fitness data;

[0120] S2022. If the physical fitness data in the physical fitness data to be verified as unqualified is completely different from the physical fitness data in the exercise table related to the physical fitness data to be improved, the physical fitness data to be verified as unqualified is set as physical fitness data that truly does not meet the standards.

[0121] It is understandable that some physical fitness data cannot be changed by exercise. Therefore, when the data is abnormal, it means that the citizen's physical health is abnormal. Therefore, first verify the physical fitness data that fails the verification standard based on the data in the relevant exercise table for improving physical fitness data to determine whether there is data that cannot be changed by exercise. If so, it means that the citizen's physical health is abnormal and needs to go to the hospital for examination.

[0122] S2023. If the physical data in the unqualified physical data to be verified have some of the same data type as the physical data in the exercise table related to the improved physical data, the unqualified physical data to be verified corresponding to the same data type are set as unqualified physical data requiring secondary verification, and the remaining unqualified physical data to be verified are set as truly unqualified physical data.

[0123] S2024. If the physical data in the physical data to be verified as unqualified is of the same type as the physical data in the exercise table related to the physical data for improving the physical data, the physical data to be verified as unqualified is set as physical data that does not meet the standards and requires secondary verification;

[0124] It is understandable that when there are types of physical fitness data that can be changed by exercise in the physical fitness data to be verified as unqualified, it is necessary to analyze the citizen's exercise information to determine whether the citizen exercises. If the citizen does not perform the corresponding exercise method, it means that the citizen's body has an abnormality. If the citizen performs the corresponding exercise method, it means that the citizen's data is normal.

[0125] Among them, S203, based on the data analysis terminal, performing secondary verification processing on the physical fitness data that does not meet the standards and needs secondary verification, and determining whether there is physical fitness data that does not meet the standards and needs secondary verification, specifically includes the following steps:

[0126] S2031. Extracting information from a table of exercises related to improving the physical fitness data using the data analysis terminal to obtain an exercise method for improving the physical fitness data; wherein the physical fitness data type corresponding to the exercise method for improving the physical fitness data is the same as the physical fitness data type that does not meet the standards and requires secondary verification;

[0127] S2032. Extract and process data from the smart wearable device based on the data analysis terminal to obtain citizens' exercise information;

[0128] S2033. Comparative analysis is performed on the citizen's exercise information and exercise methods for improving physical fitness data based on the data analysis terminal to obtain a normal range for the physical fitness data.

[0129] S2034: Based on the data analysis terminal, the normal range of the physical fitness data and the physical fitness data that does not meet the standards and requires secondary verification are judged and processed;

[0130] S2035. If the physical data that does not meet the standards and needs secondary verification is within the normal range of physical data, the physical data that does not meet the standards and needs secondary verification meets the standards;

[0131] S2036: If the non-standard physical data requiring secondary verification is not within the normal range of physical data, the non-standard physical data requiring secondary verification is set as truly non-standard physical data;

[0132] It is understandable that after some citizens exercise according to the exercise method that improves their physical fitness data, the physical fitness data corresponding to this method is higher than the normal range, but this physical fitness data is not necessarily normal, because improving physical fitness data through exercise can only increase the data within a certain range. If it exceeds this range, then even if they exercise according to this method, the physical fitness data of the citizens will be abnormal. Therefore, by analyzing the exercise method that improves physical fitness data, the normal range of the physical fitness data after exercise is determined. Then, based on the normal range of the physical data, the physical data that does not meet the standards and needs secondary verification is verified to determine whether there is any abnormality in the citizens' physical health.

[0133] Among them, S2033, based on the data analysis terminal, comparative analysis is performed on the citizen's exercise information and the exercise method for improving physical fitness data to obtain the normal range of physical fitness data, specifically including the following steps:

[0134] S20331. Based on the data analysis terminal, determine and process citizens' exercise information and exercise methods for improving physical fitness data;

[0135] S20332. If the citizen's exercise information does not contain any exercise methods that can improve their physical fitness data, the physical fitness data that does not meet the standards and requires secondary verification will be set as physical fitness data that truly does not meet the standards;

[0136] S20333. If the citizen's exercise information contains exercise methods that improve physical fitness data, based on the data analysis terminal, the physical fitness data in the relevant exercise table for improving physical fitness data is extracted and processed with the exercise methods that improve physical fitness data as the characteristics to obtain the normal range of the physical fitness data.

[0137] Reference Figure 2 As shown, the intelligent citizen physical health risk prediction system is used to implement the above-mentioned citizen physical health risk prediction method based on artificial intelligence, including:

[0138] A data analysis terminal is used to control each module to perform integrity analysis, data comparison analysis, and data verification processing on the physical fitness data to be analyzed by the citizen, so as to determine whether the citizen is physically healthy; the data analysis terminal is used to control data transmission and information exchange between each module;

[0139] A database system for storing a reference table of physical fitness data and a table of related exercises for improving physical fitness data;

[0140] Smart wearable devices, which are used to collect data on citizens' bodies and obtain physical data to be analyzed;

[0141] A data integrity analysis module is used to perform data missing detection, data comparison, data calculation, and data judgment on the physical fitness data of citizens to be analyzed to determine whether there are any data types that fail the test;

[0142] A data analysis module, which is used to compare and analyze the complete physical data of citizens to be analyzed, and determine the physical data to be verified as not meeting the standards;

[0143] A data verification module, the data verification module is used to perform two data verifications on the physical fitness data to be verified as not meeting the standards, and determine the physical fitness data that truly does not meet the standards;

[0144] An information sending module sends information indicating that a physical examination is needed to a citizen's electronic device based on the physical data that does not meet the standards.

[0145] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A citizen's physical health risk prediction method based on artificial intelligence, characterized by: include: Obtain the physical data of citizens to be analyzed, perform data matching processing on the physical data to be analyzed based on the data analysis terminal, and determine the physical data to be verified as unqualified; Based on the data analysis terminal, the physical data that fails to meet the verification standards are verified and processed to determine the physical data that truly does not meet the standards; If there is physical data that does not meet the standards in the physical data to be analyzed, the citizen is unhealthy and there is a risk. Based on the data analysis terminal, information indicating that the citizen needs a physical examination will be sent to the citizen's electronic device.

2. The method for predicting citizens' physical health risks based on artificial intelligence according to claim 1, characterized in that: The steps of obtaining the physical data of the citizen to be analyzed, performing data matching processing on the physical data of the citizen to be analyzed based on the data analysis terminal, and determining the physical data to be verified as unqualified include the following steps: Based on the data analysis terminal, the data of smart wearable devices is read and processed to obtain the physical data of citizens to be analyzed; Based on the data analysis terminal, the completeness of the physical data of citizens to be analyzed is analyzed to determine whether there are any data types that fail the test; If there are data types that fail the test, reselect smart wearable devices to collect data on the data types that fail the test within the test period to obtain complete physical data of the citizens to be analyzed; Based on the data analysis terminal, the complete physical data of citizens to be analyzed are compared and analyzed to determine the physical data that does not meet the standards to be verified.

3. The method for predicting citizens' physical health risks based on artificial intelligence according to claim 2, characterized in that: The method of performing a completeness analysis on the physical fitness data of the citizen to be analyzed based on the data analysis terminal to determine whether there is any data type that fails the test specifically includes the following steps: Based on the data analysis terminal, information analysis and processing are performed on the physical data of the citizen to be analyzed to determine a detection window; wherein the size of the detection window is the same as the detection frequency of the physical data of the citizen to be analyzed; Based on the data analysis terminal, the detection window is controlled according to the detection step length to perform data missing detection processing on the physical data of the citizen to be analyzed, and the window data missing rate is determined; wherein the detection step length is the same as the size of the detection window; Based on the data analysis terminal, the window data missing rate is compared and analyzed to determine whether there are any data types that fail the test; The specific calculation formula for determining the window data missing rate is: Wherein, the W d is the window data missing rate; D1 is the number of missing data within the window; α is the detection step size.

4. The method for predicting citizens' physical health risks based on artificial intelligence according to claim 3 is characterized in that: The comparative analysis of the window data missing rate based on the data analysis terminal to determine whether there is any data type that fails the detection specifically includes the following steps: Based on the data analysis terminal, the window data missing rate is counted based on the set data missing rate threshold. The number of occurrences of the window data missing rate greater than or equal to the set data missing rate threshold is recorded and set as the number of occurrences of the data unqualified window. Based on the data analysis terminal, the detection frequency of the citizens' physical data to be analyzed is calculated and processed to determine the detection frequency of the smart wearable device; Based on the data analysis terminal, the number of occurrences of data-unqualified windows and the number of detections by the smart wearable device are calculated and processed to determine the window data unqualified rate; Based on the data analysis terminal, the window data failure rate and the set data failure rate threshold are judged and processed; If the window data unqualified rate is greater than or equal to the set data unqualified rate threshold, the data type corresponding to the window data unqualified rate greater than or equal to the set data unqualified rate threshold is set as the detection unqualified data type; If the window data failure rate is less than the set data failure rate threshold, there is no data type that fails the test; The specific calculation formula for determining the number of detection times of the smart wearable device is: In the formula, F1 is the number of detections of the smart wearable device; T1 is the detection cycle of the smart wearable device, which is one day; and T2 is the detection frequency of the citizen's physical data to be analyzed.

5. The method for predicting citizens' physical health risks based on artificial intelligence according to claim 2, characterized in that: The method of performing comparative analysis on the complete physical data of the citizen to be analyzed based on the data analysis terminal and determining the physical data to be verified as not meeting the standards specifically includes the following steps: Based on the data analysis terminal, the complete data of the physical condition of the citizens to be analyzed is retrieved and processed to determine the age data of the citizens; Based on the data analysis terminal, the database system is processed to extract data and obtain the physical fitness data reference table; Based on the data analysis terminal, data is extracted and processed from the physical fitness data reference table based on the citizen's age data to obtain a reference interval for normal physical fitness data; wherein the age data corresponding to the reference interval for normal physical fitness data is the same as the citizen's age data; Based on the data analysis terminal, the complete data of the physical condition to be analyzed and the reference interval of the normal physical condition data of the citizen are judged and processed; If there is data in the complete physical data of the citizen to be analyzed that is not within the reference range of normal physical data, the data will be set as physical data to be verified as not meeting the standards; If all the data in the complete physical data to be analyzed of the citizen are within the reference range of normal physical data, the complete physical data to be analyzed of the citizen all meet the standards.

6. The method for predicting citizens' physical health risks based on artificial intelligence according to claim 1, characterized in that: The method of verifying the physical data that fails the verification standard based on the data analysis terminal and determining the physical data that does not meet the standard specifically includes the following steps: Based on the data analysis terminal, the database system is processed to extract data and obtain the relevant exercise table for improving physical fitness data; Based on the data analysis terminal, a comparative analysis is conducted between the physical fitness data that fails to meet the verification standards and the related exercise tables for improving the physical fitness data, and the physical fitness data that does not meet the standards and needs to be re-verified is determined; Based on the data analysis terminal, secondary verification is performed on the non-standard physical data that needs secondary verification to determine whether there is any physical data that truly does not meet the standards among the non-standard physical data that needs secondary verification.

7. The method for predicting citizens' physical health risks based on artificial intelligence according to claim 6, characterized in that: The method of comparing and analyzing the physical fitness data that fails to meet the verification standards and the related exercise tables for improving the physical fitness data based on the data analysis terminal to determine the physical fitness data that does not meet the standards and needs secondary verification specifically includes the following steps: Based on the data analysis terminal, the physical fitness data that fails to meet the verification standards and the related exercise tables for improving the physical fitness data are judged and processed; If the physical data in the physical data to be verified as unqualified is completely different from the physical data in the exercise table related to the physical data for improving the physical data, the physical data to be verified as unqualified is set as the physical data that actually does not meet the standards; If the physical data in the unqualified physical data to be verified have some of the same data types as the physical data in the related exercise table of the improved physical data, the unqualified physical data to be verified corresponding to the same data type will be set as the unqualified physical data that needs secondary verification, and the remaining unqualified physical data to be verified will be set as the physical data that truly does not meet the standards; If the physical data in the physical data to be verified as unqualified are of the same type as the physical data in the relevant exercise table for improving the physical data, the physical data to be verified as unqualified physical data requiring secondary verification will be set as unqualified physical data.

8. The method for predicting citizens' physical health risks based on artificial intelligence according to claim 6 is characterized in that: The method of performing secondary verification on the non-standard physical data requiring secondary verification based on the data analysis terminal and determining whether there is any physical data that truly does not meet the standards among the non-standard physical data requiring secondary verification specifically includes the following steps: Based on the data analysis terminal, information is extracted and processed from the exercise table related to the physical fitness data to obtain the exercise method for improving the physical fitness data; wherein the physical fitness data type corresponding to the exercise method for improving the physical fitness data is the same as the physical fitness data type that does not meet the standards and requires secondary verification; Based on the data analysis terminal, data extraction and processing are performed on smart wearable devices to obtain citizens' exercise information; Based on the data analysis terminal, the citizens' exercise information and the exercise methods used to improve their physical fitness data are compared and analyzed to obtain the normal range of physical fitness data; Based on the data analysis terminal, the normal range of physical fitness data and the physical fitness data that does not meet the standards and needs secondary verification are judged and processed; If the physical data that does not meet the standards and needs secondary verification is within the normal range of physical data, the physical data that does not meet the standards and needs secondary verification meets the standards; If the non-standard physical data requiring secondary verification is not within the normal range of the physical data, the non-standard physical data requiring secondary verification is set as truly non-standard physical data.

9. The method for predicting citizens' physical health risks based on artificial intelligence according to claim 8, characterized in that: The comparative analysis of the citizen's exercise information and the exercise methods for improving physical fitness data based on the data analysis terminal to obtain the normal range of physical fitness data specifically includes the following steps: Based on the data analysis terminal, the citizens' exercise information and exercise methods to improve their physical fitness data are judged and processed; If the citizen's exercise information does not contain any exercise methods that can improve their physical fitness data, the physical fitness data that does not meet the standards and needs secondary verification will be set as physical fitness data that does not meet the standards; If the citizen's exercise information contains exercise methods that improve physical data, based on the data analysis terminal, the physical data in the relevant exercise table for improving physical data is extracted and processed with the exercise methods that improve physical data as the characteristics to obtain the normal range of the physical data.

10. An intelligent citizen physical health risk prediction system, used to implement the citizen physical health risk prediction method based on artificial intelligence as described in any one of claims 1 to 9, characterized in that: include: A data analysis terminal is used to control each module to perform integrity analysis, data comparison analysis, and data verification processing on the physical fitness data to be analyzed by the citizen, so as to determine whether the citizen is physically healthy; the data analysis terminal is used to control data transmission and information exchange between each module; A database system for storing a reference table of physical fitness data and a table of related exercises for improving physical fitness data; Smart wearable devices, which are used to collect data on citizens' bodies and obtain physical data to be analyzed; A data integrity analysis module is used to perform data missing detection, data comparison, data calculation, and data judgment on the physical fitness data of citizens to be analyzed to determine whether there are any data types that fail the test; A data analysis module, which is used to compare and analyze the complete physical data of citizens to be analyzed, and determine the physical data to be verified as not meeting the standards; A data verification module, the data verification module is used to perform two data verifications on the physical fitness data to be verified as not meeting the standards, to determine the physical fitness data that truly does not meet the standards; An information sending module sends information indicating that a physical examination is needed to a citizen's electronic device based on the physical data that does not meet the standards.

Images