Intelligent physical examination item recommendation and result analysis method, platform and electronic device

Abstract

The present application relates to the technical field of health data processing, and especially relates to a method and platform for intelligent physical examination item recommendation and result analysis and an electronic device, the method comprising: collecting historical physical examination information and historical training data of a target user, and constructing physical fitness features of the target user based on the historical physical examination information; establishing an environment adaptation feature set of the target user based on the historical training data; collecting training data and training environment data of the target user in real time, and determining a real-time physical fitness state based on the training data and the physical fitness features of the target user; updating the real-time physical fitness state of the target user based on the environment adaptation feature set of the target user; extracting a post feature item set according to a post attribute of the target user; and recommending physical examination items to the target user according to the real-time physical fitness state of the target user and the post feature item set within a monitoring period. The present application effectively improves the recommendation efficiency of physical examination items.

Description

Technical Field

[0001] This invention relates to the field of health data processing technology, and in particular to a method, platform, and electronic device for intelligent physical examination item recommendation and result analysis. Background Technology

[0002] Currently, recommendations for physical examination items in the field of intelligent health management are mainly based on two models: one is a rule engine relying on static health records, and the other is a prediction system utilizing general machine learning models. However, these methods have significant shortcomings when dealing with the high-intensity training needs of special groups such as athletes.

[0003] Therefore, there is an urgent need for an intelligent method for recommending physical examination items and analyzing results to solve the above-mentioned technical problems. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent method, platform, and electronic device for recommending and analyzing health checkup items, in order to solve at least one of the problems existing in the prior art.

[0005] To achieve the above objectives, according to one aspect of this application, the present invention provides a method for intelligent health checkup item recommendation and result analysis, comprising: Collect historical physical examination information and historical training data of target users, and construct the physical fitness characteristics of target users based on historical physical examination information; Establish a set of environmental adaptation features for target users using historical training data; Real-time collection of training data and training environment data of target users, and determination of real-time physical fitness status by combining training data with the physical fitness characteristics of target users; The real-time physical fitness status of the target user is updated based on the target user's set of environmental adaptation features; Based on the job attributes of the target users, a set of job characteristic items is extracted, and based on the real-time physical fitness status of the target users and the set of job characteristic items during the monitoring period, physical examination items are recommended for the target users.

[0006] Optionally, historical injury information of the target user is extracted, and an injury timeliness coefficient α(j) is established for the target user. α(j) is set as Σ[S(j)-t(j)] / S(j) / J; where S(j) represents the expected recovery time of the j-th injury site of the target user, t(j) represents the recovery time of the j-th injury site of the target user up to the current time, and J represents the number of injury sites of the target user. Set an injury coefficient threshold and determine the injury status of the target user based on the injury timeliness coefficient of the target user. When the injury timeliness coefficient of the target user is less than the injury coefficient threshold, the injury status of the target user is determined to be normal; otherwise, the injury status of the target user is determined to be abnormal, and the injury timeliness coefficient of the target user at this time is used as the physical fitness correlation factor.

[0007] Optionally, the physical fitness index β of the target user is calculated based on the set of historical physical examination items and the physical examination results of each historical physical examination item, and β is set as β = a1 × (BMR - YBMR) / YBMR + a2 × (qd - QD) / QD; In the formula, BMR represents the target user's basal metabolic rate in historical physical examinations, YBMR represents the routine value of basal metabolic rate, a1 and a2 represent metabolic weight and exercise intensity weight, respectively, and a1+a2=1, qd represents the blood lactate concentration in the target user's exercise intensity range of [80%, 90%] of maximum oxygen uptake, and QD is the blood lactate concentration threshold.

[0008] Optionally, when a physical fitness-related factor exists, the product of the target user's physical fitness-related factor and the user's physical fitness index is used as the target user's physical fitness characteristic; when no physical fitness-related factor exists, the target user's physical fitness index is used as the target user's physical fitness characteristic.

[0009] Optionally, the mean of each fixed data point in the historical training data of the target user is calculated, and the fixed data points are used as the default data set, thereby initializing the adaptive feature data of each fixed data point to 0; The difference before and after training is calculated for each variable data in the historical training data of the target user, and the blood lactate concentration of the target user before and after training for each variable data is retrieved. The deviation rate of the blood lactate concentration of the target user before and after training for each variable data is calculated. Then, the ratio of the deviation rate of blood lactate concentration to the difference before and after training for the variable data is used as the corresponding adaptive feature data for each variable data. An environmental adaptation feature set for the target user is established using adaptation feature data of various fixed and variable data.

[0010] Optionally, the difference ratio of the scores of the training items in the training data is calculated based on historical training data, and the sum of the difference ratios of the scores of each training item is calculated. The calculation result is recorded as Y. When Y is less than the physical fitness characteristic, the real-time physical fitness status of the target user is determined to be good; otherwise, the real-time physical fitness status of the target user is determined to be abnormal.

[0011] Optionally, the real-time adaptation feature data of each variable data in the training environment data of the target user is calculated, and the sum of the ratios of the real-time adaptation feature data and the adaptation feature data of the corresponding variable data in the environmental adaptation feature set is used as the real-time environmental adaptation index of the target user. Set an environmental adaptation threshold and compare it with the real-time environmental adaptation index. When the environmental adaptation threshold is less than the real-time environmental adaptation index, update the target user's physical fitness index to β', and set β'=β×{1-(real-time environmental adaptation index-environmental adaptation threshold) / environmental adaptation threshold}; otherwise, do not update the target user's physical fitness index.

[0012] Optionally, a set of job feature items is extracted based on the job attributes of the target user; the set of job feature items consists of physical examination items for target users of each job attribute, where the abnormality frequency of the physical examination results is higher than 15%. The real-time physical fitness status of target users is statistically monitored during the monitoring period, and the abnormal proportion of real-time physical fitness status is calculated. The calculation result is set as μ. The system collects the physical examination intervals of target users. When μ is less than the interval monitoring ratio threshold and the interval is less than one year, a health warning is issued to the target users, and the set of job characteristic items is set as the recommended physical examination items for the target users. When μ is greater than or equal to the interval monitoring ratio threshold and the interval is less than one year, the 10 physical examination items with the highest frequency in the set of job characteristic items are selected as the recommended physical examination items for the target users. When the physical examination interval is greater than or equal to one year, the set of job characteristic items is set as the recommended physical examination items for the target users.

[0013] According to another aspect of this application, an intelligent health checkup item recommendation and result analysis platform is provided, comprising: The data acquisition unit is used to collect the target user's historical physical examination information and historical training data. Feature building unit, used to build a set of environmental adaptation features for the target user based on historical training data; The status analysis unit is used to collect training data and training environment data of the target user in real time, and to determine the real-time physical status by combining the training data with the physical characteristics of the target user. The machine learning unit is used to construct the real-time environmental adaptation index of the target user by combining the target user's set of environmental adaptation features with training environment data, and then update the target user's real-time physical fitness status with the real-time environmental adaptation index. The project recommendation unit is used to extract a set of job feature projects based on the job attributes of the target user, and to recommend physical examination projects to the target user based on the target user's real-time physical fitness status and the set of job feature projects during the monitoring period.

[0014] According to another aspect of this application, an electronic device is provided, the electronic device comprising: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent physical examination item recommendation and result analysis method.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: by integrating historical physical examination data, real-time training indicators, and environmental parameters, a dynamic physical fitness assessment model is constructed, which, combined with the characteristics of frequently occurring abnormal items in the job, enables accurate recommendations for physical examination items. Its core lies in using real-time environmental data to correct physical fitness status, solving the problem of assessment bias in extreme environments; integrating indicators such as injury recovery, metabolic function, and training performance to comprehensively capture health risks; adaptively adjusting the recommendation strategy according to the proportion of abnormal physical fitness and the interval between physical examinations; and being specifically designed for high-risk occupations (such as combat personnel), identifying occupation-related diseases through a set of job-specific items, thereby improving the efficiency of early intervention. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the intelligent health checkup item recommendation and result analysis method in this embodiment.

[0018] Figure 2 This is a flowchart illustrating the method for constructing the physical fitness characteristics of the target user in this embodiment.

[0019] Figure 3 This is a flowchart illustrating the recommended method for physical examination items in this embodiment.

[0020] Figure 4 This is a schematic diagram of the intelligent physical examination item recommendation and result analysis platform provided in this embodiment.

[0021] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this embodiment. Detailed Implementation

[0022] To more clearly illustrate the present invention, the following description, in conjunction with preferred embodiments and accompanying drawings, further explains the invention. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of the present invention.

[0023] It should be noted that although the terms first, second, third, etc., may be used in the embodiments of this application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of this application, first can also be referred to as second, and similarly, second can also be referred to as first.

[0024] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0025] Specifically, the intelligent physical examination item recommendation and result analysis method described in this application is applied to recommend physical examination items for personnel undergoing high-intensity training in extreme environments. The high-intensity training personnel mentioned in this application are specifically soldiers participating in combat training. This application collects basic health data by wearing a real-time health data acquisition device on the target user, and uses the basic health data combined with historical physical examination information to determine physical examination items with an early warning nature, thereby achieving health early warning and efficient physical examination recommendations.

[0026] To apply the above-mentioned scenarios, this application provides a method for intelligent physical examination item recommendation and result analysis, the flowchart of which can be found in the document. Figure 1 As shown, it includes: Step S101: Collect the target user's historical physical examination information and historical training data, and construct the target user's physical fitness characteristics based on the historical physical examination information.

[0027] Specifically, by systematically integrating users' historical physical examination reports and long-term training records, a personalized health baseline is constructed. This avoids the waste of resources caused by repeated testing, while providing key input parameters for dynamic fitness models and improving the accuracy of subsequent analyses.

[0028] For details, please refer to Figure 2 The diagram shown is a flowchart illustrating the method for constructing the physical fitness characteristics of the target user provided in this application, including: Step S201: Collect the target user's historical physical examination information and historical training data; the target user's historical physical examination information includes: the target user's historical physical examination items set and the physical examination results of each historical physical examination item; the historical training data includes the target user's scores in each historical training item.

[0029] Please continue reading. Figure 2 As shown, the method for constructing the physical fitness characteristics of the target user further includes: Step S202: Construct the target user's injury status and physical fitness index based on the target user's historical physical examination information.

[0030] Specifically, in step S202 of this application, the process of constructing the injury status and physical fitness index is as follows: Extract the historical injury information of the target user and establish the injury timeliness coefficient α(j) of the target user. Set α(j)=Σ[S(j)-t(j)] / S(j) / J; where S(j) represents the expected recovery time of the j-th injury part of the target user, t(j) represents the recovery time of the j-th injury part of the target user up to the current time, and J represents the number of injury parts of the target user. Set an injury coefficient threshold and determine the injury status of the target user based on the injury timeliness coefficient of the target user. When the injury timeliness coefficient of the target user is less than the injury coefficient threshold, the injury status of the target user is determined to be normal; otherwise, the injury status of the target user is determined to be abnormal, and the injury timeliness coefficient of the target user at this time is used as the physical fitness correlation factor. The physical fitness index β of the target user is calculated based on the set of historical physical examination items of the target user and the physical examination results of each historical physical examination item. The formula is β=a1×(BMR-YBMR) / YBMR+a2×(qd-QD) / QD; In the formula, BMR represents the target user's basal metabolic rate in historical physical examinations, YBMR represents the routine value of basal metabolic rate, a1 and a2 represent metabolic weight and exercise intensity weight, respectively, and a1+a2=1, qd represents the blood lactate concentration in the target user's exercise intensity range of [80%, 90%] of maximum oxygen uptake, and QD is the blood lactate concentration threshold.

[0031] For example, this application does not specifically limit the value of the blood lactate concentration threshold. Those skilled in the art can set it themselves, as long as the value requirement of the blood lactate concentration threshold is met. In this application, the optimal value of the blood lactate concentration threshold can be set to 4 mmol / L. At the same time, the optimal value of the injury coefficient threshold in this application can be 0.8, and the optimal values ​​of a1 and a2 in this application are 0.73 and 0.27, respectively.

[0032] Specifically, the injury timeliness coefficient and physical fitness index are integrated for calculation, quantifying the injury recovery progress and metabolic function, and providing multi-dimensional basis for physical fitness characteristics.

[0033] Please continue reading. Figure 2 As shown, the method for constructing the physical fitness characteristics of the target user further includes: Step S203: Establish the physical fitness characteristics of the target user based on the target user's injury status and physical fitness index.

[0034] Specifically, in step S203 of this application, the process of constructing the physical fitness characteristics of the target user is as follows: When a physical fitness-related factor exists, the product of the target user's physical fitness-related factor and the user's physical fitness index is taken as the target user's physical fitness characteristic; when no physical fitness-related factor exists, the target user's physical fitness index is taken as the target user's physical fitness characteristic.

[0035] Specifically, the injury status is linked to the physical fitness index to enhance the sensitivity of physical fitness characteristics to potential health problems (such as automatic weighted early warning when the injury has not healed).

[0036] Please continue reading. Figure 2 As shown, the intelligent health checkup item recommendation and result analysis method also includes: Step S102: Establish a set of environmental adaptation features for the target user using historical training data.

[0037] Specifically, in step S102, the process of establishing the target user's environmental adaptation feature set is as follows: The mean of each fixed data point in the historical training data of the target user is calculated, and the fixed data points are used as the default data set. Then, the adaptive feature data of each fixed data point is initialized to 0. The difference before and after training is calculated for each variable data in the historical training data of the target user, and the blood lactate concentration of the target user before and after training for each variable data is retrieved. The deviation rate of the blood lactate concentration of the target user before and after training for each variable data is calculated. Then, the ratio of the deviation rate of blood lactate concentration to the difference before and after training for the variable data is used as the corresponding adaptive feature data for each variable data. An environmental adaptation feature set for the target user is established using adaptation feature data of various fixed and variable data.

[0038] Specifically, the fixed data mentioned in this application refers to data that is constant or has a low rate of change in the geographical environment, such as altitude, atmospheric pressure, and oxygen content. The variable data refers to data that changes over time, such as temperature, humidity, and ultraviolet radiation intensity.

[0039] Specifically, based on fixed and variable data from historical training, the quantitative correlation between environmental factors and physiological indicators is calculated, providing a scientific basis for predicting physical performance under extreme conditions.

[0040] Please continue reading. Figure 1 As shown, the intelligent health checkup item recommendation and result analysis method also includes: Step S103: Real-time collection of training data and training environment data of the target user, and determination of real-time physical fitness status by combining the training data with the target user's physical fitness characteristics; the training data refers to the target user's scores in various training programs. Specifically, in step S103, the process of determining the real-time physical fitness status of the target user is as follows: Based on historical training data, the difference ratio of the scores of the training items in the training data is calculated, and the sum of the difference ratios of the scores of each training item is calculated. The calculation result is recorded as Y. When Y is less than the physical fitness characteristic, the real-time physical fitness status of the target user is determined to be good; otherwise, the real-time physical fitness status of the target user is determined to be abnormal.

[0041] Specifically, it dynamically compares the difference (Y value) between the current training performance (such as the time to complete a 5km run) and the historical average. When the Y value exceeds the physical fitness characteristic threshold (such as a 15% drop in performance), it is immediately marked as an "abnormal state," enabling millisecond-level early warning of sudden health risks during training (such as myocardial overload).

[0042] Please continue reading. Figure 1 As shown, the intelligent health checkup item recommendation and result analysis method also includes: Step S104: Construct the real-time environmental adaptation index of the target user by combining the target user's environmental adaptation feature set with the target user's training environment data, and then update the target user's real-time physical fitness status using the real-time environmental adaptation index.

[0043] Specifically, in step S104, the process of updating the target user's real-time physical fitness status is as follows: Calculate the real-time adaptation feature data of each variable data in the training environment data of the target user, and use the sum of the ratios of the real-time adaptation feature data and the corresponding adaptation feature data of the variable data in the environmental adaptation feature set as the real-time environmental adaptation index of the target user. Set an environmental adaptation threshold and compare it with the real-time environmental adaptation index. When the environmental adaptation threshold is less than the real-time environmental adaptation index, update the target user's physical fitness index to β', and set β'=β×{1-(real-time environmental adaptation index-environmental adaptation threshold) / environmental adaptation threshold}; otherwise, do not update the target user's physical fitness index.

[0044] For example, this application does not specifically limit the value of the environmental adaptation threshold. Those skilled in the art can set it freely, as long as the value requirement of the environmental adaptation threshold is met. In this application, the optimal value of the environmental adaptation threshold can be set to 1.2.

[0045] Specifically, an adaptation index is calculated using real-time environmental data to dynamically adjust physical fitness assessments. For example, when the environmental adaptation index exceeds a threshold, misjudgments caused by sudden environmental changes are avoided.

[0046] Please continue reading. Figure 1 As shown, the intelligent health checkup item recommendation and result analysis method also includes: Step S105: Extract the set of job feature items based on the job attributes of the target user, and recommend physical examination items for the target user based on the real-time physical fitness status and the set of job feature items within the monitoring period.

[0047] For example, this application does not specifically limit the value of the monitoring period duration. Those skilled in the art can set it freely, as long as the value requirement of the monitoring period duration is met. In this application, the value of the monitoring period duration can be set to 1 day.

[0048] Please see Figure 3 The diagram shown is a flowchart illustrating the recommended method for physical examination items provided in this application, including: Step S301: Extract a set of job feature items based on the job attributes of the target user; the set of job feature items consists of physical examination items for each job attribute whose abnormal frequency of results is higher than 15%.

[0049] Specifically, in this application, the job attribute of the target user refers to the job type of the target user. In the application scenario of this application applied to soldiers, the job attribute can specifically refer to the branch of service to which the soldier belongs. At the same time, the extraction of the set of job feature items in this application can be extracted from the physical examination database.

[0050] Please continue reading. Figure 3 As shown, the recommended methods for the physical examination items also include: Step S302: Recommend physical examination items for the target user based on the target user's real-time physical fitness status and job characteristic items set within the monitoring period.

[0051] Specifically, in step S302, the process of recommending physical examination items to the target user is as follows: The real-time physical fitness status of target users is statistically monitored during the monitoring period, and the abnormal proportion of real-time physical fitness status is calculated. The calculation result is set as μ. The system collects the physical examination intervals of target users. When μ is less than the interval monitoring ratio threshold and the interval is less than one year, a health warning is issued to the target users, and the set of job characteristic items is set as the recommended physical examination items for the target users. When μ is greater than or equal to the interval monitoring ratio threshold and the interval is less than one year, the 10 physical examination items with the highest frequency in the set of job characteristic items are selected as the recommended physical examination items for the target users. When the physical examination interval is greater than or equal to one year, the set of job characteristic items is set as the recommended physical examination items for the target users.

[0052] For example, this application does not specifically limit the value of the interval monitoring ratio threshold. Those skilled in the art can set it freely, as long as the value requirement of the interval monitoring ratio threshold is met. In this application, the optimal value of the interval monitoring ratio threshold can be set to 0.2.

[0053] Specifically, the recommended strategy will be dynamically adjusted based on the proportion of abnormal physical fitness and the interval between physical examinations (e.g., prioritizing high-frequency items) to optimize resource allocation and improve the timeliness of early warning.

[0054] Please see Figure 5 As shown, it is a schematic diagram of the structure of the intelligent physical examination item recommendation and result analysis platform provided in this application, including: The data acquisition unit is used to collect the target user's historical physical examination information and historical training data. Feature building unit, used to build a set of environmental adaptation features for the target user based on historical training data; The status analysis unit is used to collect training data and training environment data of the target user in real time, and to determine the real-time physical status by combining the training data with the physical characteristics of the target user. The machine learning unit is used to construct the real-time environmental adaptation index of the target user by combining the target user's set of environmental adaptation features with training environment data, and then update the target user's real-time physical fitness status with the real-time environmental adaptation index. The project recommendation unit is used to extract a set of job feature projects based on the job attributes of the target user, and to recommend physical examination projects to the target user based on the target user's real-time physical fitness status and the set of job feature projects during the monitoring period.

[0055] The intelligent physical examination item recommendation and result analysis platform provided in this application embodiment can execute the intelligent physical examination item recommendation and result analysis method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the execution method.

[0056] From a hardware perspective, to enable the intelligent health checkup item recommendation and result analysis method to function in a computer, this application also provides an electronic device; please refer to [link to relevant documentation]. Figure 5 As shown, it is a schematic diagram of the structure of the electronic device described in this application, including: The system comprises a processor 1, a memory 2, a communication interface 3, and a bus 4; wherein the processor 1 and the memory 2, and the memory 2 and the communication interface 3, transmit data via the bus 4; the processor is used to process data in the memory and generate commands, the memory is used to store data, the communication interface is used to receive and send data, and the bus is used to realize data transmission between the processor, the memory, and the communication interface.

[0057] In this embodiment, the intelligent physical examination item recommendation and result analysis method can be implemented as a runnable computer program. When the computer program is loaded into the processor or memory and processed by the processor via the bus, one or more steps of the intelligent physical examination item recommendation and result analysis method can be executed.

[0058] This embodiment also provides a computer-readable storage medium for storing the computer-executable instructions. The computer-readable storage medium is a tangible physical storage medium that can store the computer program and various types of data used in the program. The physical storage medium includes, but is not limited to, existing physical storage media or combinations thereof, such as random access memory, read-only memory, optical disk, and hard disk.

[0059] In this application, the computer-readable storage medium is a tangible physical storage medium that can store the aforementioned computer program and various types of data used in the program; the physical storage medium includes, but is not limited to, existing physical storage media or combinations thereof, such as random access memory, read-only memory, optical disk, and hard disk.

[0060] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for intelligent health checkup item recommendation and result analysis, characterized in that, include: Collect historical physical examination information and historical training data of target users, and construct the physical fitness characteristics of target users based on historical physical examination information; Establish a set of environmental adaptation features for target users using historical training data; Real-time collection of training data and training environment data of target users, and determination of real-time physical fitness status by combining training data with the physical fitness characteristics of target users; The real-time physical fitness status of the target user is updated based on the target user's set of environmental adaptation features; Based on the job attributes of the target users, extract a set of job feature items, and recommend physical examination items for the target users based on their real-time physical fitness status and the set of job feature items during the monitoring period; Extract the historical injury information of the target user and establish the injury timeliness coefficient α(j) of the target user. Set α(j)=Σ[S(j)-t(j)] / S(j) / J; where S(j) represents the expected recovery time of the j-th injury part of the target user, t(j) represents the recovery time of the j-th injury part of the target user up to the current time, and J represents the number of injury parts of the target user. Set a damage coefficient threshold and determine the damage status of the target user based on the damage timeliness coefficient of the target user. When the damage timeliness coefficient of the target user is less than the damage coefficient threshold, the damage status of the target user is determined to be normal. Conversely, if the injury status of the target user is determined to be abnormal, the injury timeliness coefficient of the target user at this time is used as the physical fitness correlation factor. The physical fitness index β of the target user is calculated based on the set of historical physical examination items of the target user and the physical examination results of each historical physical examination item. The formula is β=a1×(BMR-YBMR) / YBMR+a2×(qd-QD) / QD; In the formula, BMR represents the target user's basal metabolic rate in historical physical examinations, YBMR represents the conventional value of basal metabolic rate, a1 and a2 represent metabolic weight and exercise intensity weight, respectively, and a1+a2=1, qd represents the target user's blood lactate concentration in the exercise intensity range of [80%, 90%] of maximum oxygen uptake, and QD is the blood lactate concentration threshold. When physical fitness-related factors exist, the product of the target user's physical fitness-related factors and the user's physical fitness index is taken as the target user's physical fitness characteristic. In the absence of physical fitness-related factors, the physical fitness index of the target user is used as the target user's physical fitness characteristic.

2. The intelligent physical examination item recommendation and result analysis method according to claim 1, characterized in that, The mean of each fixed data point in the historical training data of the target user is calculated, and the fixed data points are used as the default data set. Then, the adaptive feature data of each fixed data point is initialized to 0. The difference before and after training is calculated for each variable data in the historical training data of the target user, and the blood lactate concentration of the target user before and after training for each variable data is retrieved. The deviation rate of the blood lactate concentration of the target user before and after training for each variable data is calculated. Then, the ratio of the deviation rate of blood lactate concentration to the difference before and after training for the variable data is used as the corresponding adaptive feature data for each variable data. An environmental adaptation feature set for the target user is established using adaptation feature data of various fixed and variable data.

3. The intelligent physical examination item recommendation and result analysis method according to claim 2, characterized in that, Based on historical training data, the difference ratio of the scores of the training items in the training data is calculated, and the sum of the difference ratios of the scores of each training item is calculated. The calculation result is recorded as Y. When Y is less than the physical fitness characteristic, the real-time physical fitness status of the target user is determined to be good; otherwise, the real-time physical fitness status of the target user is determined to be abnormal.

4. The intelligent physical examination item recommendation and result analysis method according to claim 3, characterized in that, Calculate the real-time adaptation feature data of each variable data in the training environment data of the target user, and use the sum of the ratios of the real-time adaptation feature data and the corresponding adaptation feature data of the variable data in the environmental adaptation feature set as the real-time environmental adaptation index of the target user. Set an environmental adaptation threshold and compare it with the real-time environmental adaptation index. When the environmental adaptation threshold is less than the real-time environmental adaptation index, update the target user's physical fitness index to β', and set β'=β×{1-(real-time environmental adaptation index-environmental adaptation threshold) / environmental adaptation threshold}; otherwise, do not update the target user's physical fitness index.

5. The intelligent physical examination item recommendation and result analysis method according to claim 4, characterized in that, A set of job feature items is extracted based on the job attributes of the target users; the set of job feature items consists of physical examination items for target users of each job attribute, where the abnormality frequency of the examination results is higher than 15%. The real-time physical fitness status of target users is statistically monitored during the monitoring period, and the abnormal proportion of real-time physical fitness status is calculated. The calculation result is set as μ. The system collects the physical examination intervals of target users. When μ is less than the interval monitoring ratio threshold and the interval is less than one year, a health warning is issued to the target users, and the set of job characteristic items is set as the recommended physical examination items for the target users. When μ is greater than or equal to the interval monitoring ratio threshold and the interval is less than one year, the 10 physical examination items with the highest frequency in the set of job characteristic items are selected as the recommended physical examination items for the target users. When the physical examination interval is greater than or equal to one year, the set of job characteristic items is set as the recommended physical examination items for the target users.

6. An intelligent health checkup item recommendation and result analysis platform, applied to the intelligent health checkup item recommendation and result analysis method as described in any one of claims 1-5, characterized in that, include: The data acquisition unit is used to collect the target user's historical physical examination information and historical training data. Feature building unit, used to build a set of environmental adaptation features for the target user based on historical training data; The status analysis unit is used to collect training data and training environment data of the target user in real time, and to determine the real-time physical status by combining the training data with the physical characteristics of the target user. The machine learning unit is used to construct the real-time environmental adaptation index of the target user by combining the target user's set of environmental adaptation features with training environment data, and then update the target user's real-time physical fitness status with the real-time environmental adaptation index. The project recommendation unit is used to extract a set of job feature projects based on the job attributes of the target user, and to recommend physical examination projects to the target user based on the target user's real-time physical fitness status and the set of job feature projects during the monitoring period.

7. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent physical examination item recommendation and result analysis method according to any one of claims 1-5.

Images