Self-service health detection method, device and equipment for user reaching medical standard

Abstract

The invention relates to a self-service health detection method, device and equipment for a user meeting a medical standard, and the method comprises the steps: obtaining a user detection option, generating a corresponding detection instruction according to the user detection option, obtaining a user detection action, and obtaining a user detection parameter under the condition that the user detection action accords with a preset standard detection action; comparing the user detection parameter with a preset human body parameter threshold to obtain a corresponding comparison result, obtaining a user historical detection result, and inputting the user detection parameter and / or the user historical detection result into a preset health detection model to obtain a health prediction result; a health detection report is generated according to the comparison result and the health prediction result, a personnel intervention instruction is generated under the condition that health abnormity occurs in the health detection report, and the health detection report is sent to the management end; and acquiring medical advice input information of the management side, generating a medical advice report according to the medical advice input information and sending the medical advice report to the user side. The method has the effect of improving the health detection accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of health detection, and in particular to a user self-service health detection method, device and equipment that meets medical standards. Background Art

[0002] At present, with the continuous improvement of health awareness and the development of technology, user self-service health testing methods that meet medical standards have gradually become one of the important means of daily health management for people.

[0003] Existing self-help health detection methods that meet medical standards mainly rely on smart devices and applications, through which users can perform simple health indicator tests at home. However, existing self-help health detection methods that meet medical standards still have some problems, such as insufficient standardization of detection actions, resulting in insufficient accuracy and consistency of detection results. In addition, most current health detection models are based on traditional statistical methods, which are difficult to handle complex and changeable health data, affecting the accuracy of health predictions.

[0004] The above-mentioned existing technical solutions have the following defects: the traditional self-service health detection methods have a low degree of standardization, resulting in inaccurate detection, so there is room for improvement. Summary of the invention

[0005] In order to improve the accuracy and efficiency of health testing, the present application provides a user self-service health testing method, device and equipment that meet medical standards.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A user self-help health detection method that meets medical standards, the user self-help health detection method that meets medical standards comprising: Obtaining a user detection option, generating a corresponding detection description message according to the user detection option, and obtaining a user detection action, and obtaining a user detection parameter when the user detection action meets a preset standard detection action; Compare the user detection parameters with preset human body parameter thresholds to obtain corresponding comparison results, obtain user historical detection results, input the user detection parameters and / or user historical detection results into a preset health detection model to obtain health prediction results; Generate a health check report according to the comparison result and the health prediction result, and generate a personnel intervention instruction if a health abnormality appears in the health check report, and send the health check report to the management end; The medical order input information of the management end is obtained, and a medical order report is generated according to the medical order input information and sent to the user end.

[0007] By adopting the above technical solution, by obtaining user detection options and generating corresponding detection instruction messages based on the detection options, users can understand the required steps and precautions before the detection, thereby improving the accuracy of the detection and user experience; by obtaining user detection actions and obtaining user detection parameters when the preset standard detection actions are met, the standardization of the detection process and the accuracy of the data can be ensured, thereby improving the reliability of health detection; by comparing the detection parameters with the preset human parameter thresholds, and combining the user's historical detection results with the preset health detection model, the user's health status can be predicted more accurately, thereby improving the accuracy and scientificity of health prediction; by generating a health detection report based on the comparison results and health prediction results, and generating personnel intervention instructions in the event of abnormal health, potential health problems can be discovered and dealt with in a timely manner, thereby enhancing the timeliness and effectiveness of health management.

[0008] In one example, the present application may be further configured as follows: the acquiring of the user detection action, when the user detection action meets the preset standard detection action, acquiring the user detection parameter, further includes: Acquire detection feature points from the user detection action, and adjust the preset standard detection action based on the detection feature points as reference comparison points; When the user detection action does not match the preset standard detection action within a preset time threshold, an offset analysis is performed according to the reference comparison point, and a user action correction message is generated according to the offset analysis result.

[0009] By adopting the above technical solution, by obtaining detection feature points from the user's detection action and adjusting the preset standard detection action based on the detection feature points as the reference comparison points, it is possible to more flexibly adapt to the user's actual operation situation, thereby improving the fault tolerance of the detection action; when the user's detection action does not match the preset standard detection action within the preset time threshold, by performing offset analysis and generating a user action correction message, the user's detection action can be corrected in time, thereby ensuring the accuracy and reliability of the detection results, and further improving the effectiveness of user self-service health tests that meet medical standards.

[0010] In one example, the present application may be further configured as follows: performing the offset analysis according to the reference comparison point and generating the user action correction message according to the offset analysis result specifically includes: Matching the key feature points with the reference comparison points in the preset standard detection action, and calculating the spatial offset, angular offset and time offset between the user's actual action and the standard action; A motion compensation calculation is performed according to the spatial offset, the angular offset and the temporal offset, and the user motion correction message is generated according to the calculation result.

[0011] By adopting the above technical solution, by matching the key feature points with the reference comparison points in the preset standard detection action, the spatial, angular and temporal offsets between the user's actual action and the standard action can be accurately calculated, thereby ensuring the accuracy of the action correction process; action compensation calculations are performed based on the offsets, and user action correction messages are generated, which can effectively guide users to adjust their actions, thereby improving the accuracy of self-service health detection and the fault tolerance of user operations, and thereby improving the reliability of health detection results.

[0012] In one example, the present application may be further configured as follows: performing an offset analysis according to the reference comparison point, and generating a user action correction message according to the offset analysis result, further comprising: When the user's motion has been adjusted multiple times but still fails to reach the preset standard detection motion, the user's detection motion is three-dimensionally modeled through virtual reality technology, and real-time motion correction is performed based on the constructed user motion three-dimensional model and the standard motion three-dimensional model.

[0013] By adopting the above technical solution, when the user's action has been adjusted multiple times and still fails to reach the preset standard detection action, the user's detection action can be three-dimensionally modeled using virtual reality technology. This can more intuitively show the difference between the user's actual action and the standard action. Combined with the real-time action correction of the three-dimensional model, it can provide users with more accurate adjustment suggestions and further improve the effect of action correction, thereby ensuring the accuracy of the self-service health detection process and the correctness of user operations, and greatly improving the scientificity and effectiveness of health management.

[0014] In one example, the present application may be further configured as follows: the obtaining of the user historical detection results and inputting the user detection parameters and / or the user historical detection results into a preset health detection model specifically includes: Obtaining user login identity information, and performing identity retrieval from a detection database according to the user login identity information; In the case where the user historical detection result corresponding to the user login identity information is not retrieved, inputting the user detection parameter into the preset health detection model; In the case where the user history detection result corresponding to the user login identity information is retrieved, the user detection parameter and the user history detection result are input into the preset health detection model.

[0015] By adopting the above technical solution, by obtaining the user's login identity information and performing identity retrieval from the detection database based on the identity information, the user's historical detection results can be accurately matched, thereby improving data utilization; when the user's historical detection results corresponding to the user's login identity information are not retrieved, the user detection parameters are directly input into the preset health detection model, which can ensure that the detection process of new users is not affected, thereby improving the adaptability of the system; when the user's historical detection results corresponding to the user's login identity information are retrieved, the detection parameters and historical detection results are input into the health detection model, which can combine historical data for more accurate health predictions, thereby improving the reliability and scientificity of the detection results.

[0016] In one example, the present application may be further configured as follows: the construction of the health detection model specifically includes: Acquire clinical test data, and classify the clinical test data according to the age information and gender information of the subjects corresponding to the clinical test data to obtain a model training data set; The preset machine learning algorithm is iteratively trained according to the model training data set to obtain the health detection model.

[0017] By adopting the above-mentioned technical solution, by acquiring clinical test data and classifying it according to the age information and gender information of the subjects corresponding to the clinical test data, it is possible to finely construct the model training data set according to the characteristics of different groups, thereby improving the accuracy and applicability of the health detection model; by iteratively training the model training data set, it is possible to continuously optimize the preset machine learning algorithm, thereby improving the prediction accuracy and generalization ability of the health detection model, and ensuring the reliability and scientificity of the health detection results.

[0018] In one example, the present application may be further configured as follows: after inputting the user detection parameters and / or the user historical detection results into a preset health detection model to obtain a health prediction result, the user self-service health detection method that meets medical standards further includes: Comparing the health prediction result with the user's historical test result, and generating a personnel correction message when the data difference between the health prediction result and the user's historical test result reaches a preset abnormal difference threshold; Perform video source tracing according to the personnel correction message, obtain the video acquisition data corresponding to the user detection action, and manually check the video acquisition data to determine whether the cause of the data difference is an abnormality in the detected action and / or an abnormality in the device; When the cause is abnormality of the inspected action, the user is notified of remote retesting; when the cause is abnormality of the equipment, the user is notified of on-site retesting; when the cause is not abnormality of the inspected action and / or abnormality of the equipment, the data difference is determined to be a normal difference, and the health prediction result is recorded and stored.

[0019] By adopting the above technical solution, by comparing the health prediction results with the user's historical test results, abnormal changes in the user's health status can be effectively identified, thereby improving the accuracy of health prediction; when the data difference between the health prediction results and the user's historical test results reaches a preset abnormal difference threshold, a personnel correction message is generated, and the video acquisition data corresponding to the user's detection action is obtained through video tracing, which can provide an intuitive basis for manual inspection and ensure accurate judgment of the cause of the data difference; when the cause of the data difference is the abnormality of the tested action, the user is notified by remote re-testing, so that errors in the detection process can be corrected in time to ensure data reliability; when the cause is equipment abnormality, the user is notified by on-site re-inspection, so that the normal operation of the equipment can be ensured to avoid false detection; if the cause of the data difference is not the abnormality of the tested action or the equipment, the difference is regarded as a normal difference and the health prediction result is recorded and stored to ensure the integrity of the data and the scientific nature of the analysis, thereby further improving the reliability and comprehensiveness of the user's self-service health detection method that meets medical standards.

[0020] The second object of the invention is achieved by the following technical solutions: A user self-service health detection device that meets medical standards, the user self-service health detection device that meets medical standards comprises: A detection parameter acquisition module is used to acquire a user detection option, generate a corresponding detection description message according to the user detection option, and acquire a user detection action, and acquire a user detection parameter when the user detection action meets a preset standard detection action; A health comparison module is used to compare the user detection parameters with preset human body parameter thresholds to obtain corresponding comparison results, obtain user historical detection results, input the user detection parameters and / or user historical detection results into a preset health detection model to obtain health prediction results; A health report generation module, used to generate a health detection report according to the comparison result and the health prediction result, and generate a personnel intervention instruction when a health abnormality appears in the health detection report, and send the health detection report to the management end; The medical order report generation module is used to obtain the medical order input information of the management end, generate a medical order report according to the medical order input information and send it to the user end.

[0021] By adopting the above technical solution, by obtaining user detection options and generating corresponding detection instruction messages based on the detection options, users can understand the required steps and precautions before the detection, thereby improving the accuracy of the detection and user experience; by obtaining user detection actions and obtaining user detection parameters when the preset standard detection actions are met, the standardization of the detection process and the accuracy of the data can be ensured, thereby improving the reliability of health detection; by comparing the detection parameters with the preset human parameter thresholds, and combining the user's historical detection results with the preset health detection model, the user's health status can be predicted more accurately, thereby improving the accuracy and scientificity of health prediction; by generating a health detection report based on the comparison results and health prediction results, and generating personnel intervention instructions in the event of abnormal health, potential health problems can be discovered and dealt with in a timely manner, thereby enhancing the timeliness and effectiveness of health management.

[0022] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned user self-help health detection method that meets medical standards when executing the computer program.

[0023] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the user self-help health detection method that meets medical standards.

[0024] In summary, this application includes the following beneficial technical effects: 1. By obtaining the user's detection options and generating corresponding detection instructions according to the detection options, the user can understand the required steps and precautions before the test, thereby improving the accuracy of the test and the user experience; by obtaining the user's detection actions and obtaining the user's detection parameters when the preset standard detection actions are met, the standardization of the detection process and the accuracy of the data can be ensured, thereby improving the reliability of health detection; by comparing the detection parameters with the preset human parameter thresholds and combining the user's historical detection results with the preset health detection model, the user's health status can be predicted more accurately, thereby improving the accuracy and scientificity of health prediction; by generating a health detection report based on the comparison results and health prediction results, and generating personnel intervention instructions in the case of abnormal health, potential health problems can be discovered and handled in a timely manner, thereby enhancing the timeliness and effectiveness of health management; 2. By obtaining the user's login identity information and performing identity retrieval from the detection database based on the identity information, the user's historical detection results can be accurately matched to improve data utilization; if the user's historical detection results corresponding to the user's login identity information are not retrieved, the user detection parameters are directly input into the preset health detection model to ensure that the detection process of new users is not affected, thereby improving the adaptability of the system; if the user's historical detection results corresponding to the user's login identity information are retrieved, the detection parameters and historical detection results are input into the health detection model, which can combine historical data to make more accurate health predictions, thereby improving the reliability and scientificity of the detection results; 3. By matching key feature points with reference comparison points in preset standard detection actions, the spatial, angular and temporal offsets between the user's actual actions and the standard actions can be accurately calculated, thereby ensuring the accuracy of the action correction process; action compensation calculations are performed based on the offsets, and user action correction messages are generated, which can effectively guide users to adjust their actions, thereby improving the accuracy of self-service health detection and the fault tolerance of user operations, and thus improving the reliability of health detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a flow chart of a user self-help health detection method that meets medical standards in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S10 in a user self-help health detection method that meets medical standards in one embodiment of the present application; Figure 3 This is a flowchart for implementing step S102 in a user self-help health detection method that meets medical standards in one embodiment of the present application; Figure 4 This is another implementation flow chart after step S102 in the user self-help health detection method that meets medical standards in one embodiment of the present application; Figure 5 This is a flowchart for implementing step S20 in a user self-help health detection method that meets medical standards in one embodiment of the present application; Figure 6 It is a flowchart for implementing the construction of a health detection model in a user self-help health detection method that meets medical standards in one embodiment of the present application; Figure 7 Another implementation flow chart after step S20 in the user self-help health detection method that meets medical standards in one embodiment of the present application Figure 8 This is a principle block diagram of a user self-service health detection device that meets medical standards in one embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application is further described in detail below in conjunction with the accompanying drawings.

[0027] In one embodiment, if Figure 1 As shown, the present application discloses a user self-service health detection method that meets medical standards, which specifically includes the following steps: S10: Obtain user detection options, generate corresponding detection description messages according to the user detection options, and obtain user detection actions. If the user detection actions meet preset standard detection actions, obtain user detection parameters.

[0028] Specifically, the test items selected by the user are obtained through the user interface or preset equipment, including body temperature, blood pressure, 12-lead ECG, body fat, blood sugar, blood oxygen, waist-to-hip ratio, etc., and corresponding test instruction messages are generated according to the user's selection to guide the user how to correctly perform the test. Then, the user's test actions are captured in real time through sensors or other detection devices. For example, during blood pressure testing, the position and posture of the user wearing the cuff are detected, and the static arm movement of the user when the measurement starts is captured through a pressure sensor, or during ECG testing, whether the user has correctly connected all lead electrodes is monitored, and whether the user remains still during the measurement is detected. When the detection action matches the preset standard detection action and reaches a preset threshold, the system considers that the user's action meets the requirements, and then records and stores the user's test parameters, such as blood pressure value, heart rate data or body temperature reading, to ensure the accuracy and reliability of the test data.

[0029] S20: Compare the user detection parameters with the preset human body parameter thresholds to obtain corresponding comparison results, obtain the user's historical detection results, input the user detection parameters and / or the user's historical detection results into a preset health detection model to obtain a health prediction result.

[0030] Specifically, the user's current test parameters are compared with the preset normal human parameter thresholds one by one, such as comparing the blood pressure value with the normal blood pressure range to determine whether the current test result is within the normal range, etc., and the user's historical test data is retrieved from the database. If there is a historical test record, the current test parameters are input into the health detection model together with the historical data. The model compares and analyzes the trends and changes of multiple tests to obtain a predicted result of the user's current health status, so as to reflect whether the user's health status is normal, abnormal, or whether there is a health risk, thereby providing users with more personalized health advice.

[0031] S30: Generate a health check report based on the comparison result and the health prediction result, and if a health abnormality appears in the health check report, generate a personnel intervention instruction and send the health check report to the management end.

[0032] Specifically, after completing the comparison analysis and health prediction, a detailed health check report is generated, including the user's current test parameters, historical test comparison results, and health risk assessment derived from the health prediction model. If the user's health condition is found to be abnormal in the report, such as high blood pressure, abnormal heart rate, etc., it will immediately trigger a personnel intervention instruction, instructing relevant medical or health management personnel to conduct further intervention and inspection, and send the health check report to the management end to ensure that medical personnel can review and take necessary measures in time to help users discover and deal with health problems as early as possible.

[0033] S40: Obtain the medical advice input information from the management end, generate a medical advice report based on the medical advice input information, and send it to the user end.

[0034] Specifically, when the management end receives the health check report, medical personnel can input corresponding medical advice information through the system. The medical advice information may include drug recommendations, suggestions for lifestyle adjustments, or further medical examination arrangements, and integrate these medical advice information into a clear and easy-to-understand medical advice report, which is then sent to the user's mobile device or user interface to remind the user to review and follow the medical advice.

[0035] In one embodiment, if Figure 2 As shown, in step S10, the user detection action is obtained, and when the user detection action meets the preset standard detection action, the user detection parameter is obtained, which also includes: S101: Acquire detection feature points from the user's detection action, and adjust the preset standard detection action based on the detection feature points as reference comparison points.

[0036] Specifically, when the user starts to perform the detection action, sensors or cameras are used to obtain multiple feature points of the user's action, such as the angle of the wrist, the height of the arm, or the posture of the body. These feature points are extracted and compared with the feature points in the standard detection action. If it is found that the user's action deviates from the standard detection action, the system will automatically adjust the comparison benchmark of the standard detection action, making the comparison process more flexible and adaptable to individual differences, thereby improving the accuracy of the detection action and user experience.

[0037] S102: When the user detection action does not match the preset standard detection action within a preset time threshold, an offset analysis is performed according to the reference comparison point, and a user action correction message is generated according to the offset analysis result.

[0038] Specifically, the user's detection actions are monitored. If a significant deviation is found between the user's actions and the standard actions within the set time threshold, an offset analysis will be performed immediately. The direction and magnitude of the deviation will be determined by analyzing the distance and angle between the detection feature points and the standard feature points. A correction message will be generated based on the deviation analysis, and then the user will be guided to adjust their posture or actions through voice prompts, text information or image examples to ensure the accuracy of the detection data.

[0039] In one embodiment, if Figure 3 As shown, in step S102, an offset analysis is performed according to the reference comparison point, and a user action correction message is generated according to the offset analysis result, which specifically includes: S1021: Match the key feature points with the reference comparison points in the preset standard detection action, and calculate the spatial offset, angular offset and time offset between the user's actual action and the standard action.

[0040] Specifically, through precision sensors or image recognition technology, the key feature point data generated by the user during the detection process is captured, including the spatial coordinate information of the hands, elbows, shoulders, etc. These feature points will be matched one by one with the corresponding benchmark comparison points in the preset standard detection action. By calculating the spatial offset between the two, that is, the distance difference between the actual position of the user's key feature points and the corresponding benchmark comparison points in the standard detection action, the angle offset, that is, the angle difference between the actual movement angle of the user's joint points and the benchmark comparison points in the standard detection action, and the time offset, that is, the difference between the time series of each key feature point when the user performs the action and the time benchmark point in the standard detection action, the degree of deviation between the user's actual action and the standard action is determined.

[0041] S1022: Perform motion compensation calculation according to the spatial offset, the angular offset and the temporal offset, and generate a user motion correction message according to the calculation result.

[0042] Specifically, after obtaining the offset between the user's action and the standard action, the system will perform action compensation calculations, and determine the optimal compensation scheme by comprehensively considering the offsets in the three dimensions of space, angle and time. For example, when the spatial offset is large, the system will generate an instruction message to adjust the position; when the angle offset is significant, the system will suggest the user to adjust the posture; and when the time offset exceeds the preset range, the system will prompt the user to speed up or slow down the execution of the action. The generated action correction message will be promptly fed back to the user in the form of text, voice or image, guiding him or her to gradually correct the detection action to meet the expected standard detection requirements and ensure the accuracy of each detection action.

[0043] In one embodiment, if Figure 4As shown, after step S102, the offset analysis is performed according to the reference comparison point, and a user action correction message is generated according to the offset analysis result, and the method further includes: S1023: When the user motion has been adjusted multiple times but still fails to reach the preset standard detection motion, the user detection motion is three-dimensionally modeled through virtual reality technology, and real-time motion correction is performed based on the constructed user motion three-dimensional model and the standard motion three-dimensional model.

[0044] Specifically, when the user fails to match the standard detection action after multiple attempts to adjust the detection action, the system will introduce virtual reality technology to perform three-dimensional modeling of the user's detection action, capture the user's real-time action through high-precision sensors and build its three-dimensional model, and load the preset three-dimensional model of the standard detection action into the system. The three-dimensional spatial difference between the two is then compared, and the deviation of the user's action is displayed in real time. Intuitive visual feedback is provided to the user in the virtual environment, such as through virtual characters or indicator lines to show the correct action path or posture. The user can correct the action according to these real-time visual prompts until the detection action completely overlaps with the standard action in three-dimensional space, thereby ensuring the accuracy of the detection data and the standardization of the action.

[0045] In one embodiment, if Figure 5 As shown, in step S20, the user's historical detection results are obtained, and the user detection parameters and / or the user's historical detection results are input into the preset health detection model, which specifically includes: S21: Obtain the user login identity information, and perform identity retrieval from the detection database according to the user login identity information.

[0046] Specifically, users need to log in to the system before taking the test. The system will verify the user's identity information and confirm the legitimacy of their account. After logging in, the system will search the test database based on the user's identity information to find all previous health test records of the user, including historical test parameters, health prediction results, and any medical data related to the user, etc., to ensure that each test can be associated with the user's health history, thereby providing a more comprehensive health assessment.

[0047] S22: When no user history detection result corresponding to the user login identity information is retrieved, the user detection parameters are input into a preset health detection model.

[0048] Specifically, when the user's historical test records cannot be found in the test database, the current test is regarded as the user's first test. In this case, the user's current test parameters are directly input into the health test model for analysis. The model will preliminarily assess the user's health status based on the comparison of these parameters with standard human parameters, and generate corresponding health prediction results for the user's reference.

[0049] S23: When the user history detection result corresponding to the user login identity information is retrieved, the user detection parameters and the user history detection result are input into a preset health detection model.

[0050] Specifically, after retrieving the user's historical test records, these historical records are input into the health test model together with the current test parameters, which can more accurately assess the user's health trends and potential risks. For example, by detecting continuous changes in certain parameters of the user, possible health risks can be inferred, thereby improving the accuracy of health predictions and enabling users to discover health problems earlier.

[0051] In one embodiment, if Figure 6 As shown, in step S20, the construction of the health detection model specifically includes: S201: Acquire clinical test data, and classify the clinical test data according to the age information and gender information of the subjects corresponding to the clinical test data to obtain a model training data set.

[0052] Specifically, a large amount of test data is extracted from the clinical database, including health parameters of subjects of different age groups and genders, and classified according to these parameters, and the test data of different groups are separated to ensure that the physiological differences of different individuals can be taken into account during model training, generating a diverse and representative model training data set, and providing a data basis for the construction of a health detection model.

[0053] S202: Iteratively train a preset machine learning algorithm according to a model training data set to obtain a health detection model.

[0054] Specifically, the classified model training data set is input into the preset machine learning algorithm for multiple iterative training. After each training, the algorithm will adjust its own weights and parameters according to the training results, and gradually improve its ability to predict health parameters. After multiple iterative training, when the error value between the result obtained from the input data and the established result does not exceed 5%, a health detection model is obtained, which can effectively analyze the input detection parameters and make accurate health predictions based on the rules obtained from the training data.

[0055] In one embodiment, if Figure 7 As shown, after step S20, that is, after the user detection parameters and / or the user historical detection results are input into the preset health detection model to obtain the health prediction results, the user self-service health detection method that meets the medical standards also includes: S24: Compare the health prediction result with the user's historical test results, and generate a personnel correction message when the data difference between the health prediction result and the user's historical test results reaches a preset abnormal difference threshold.

[0056] Specifically, the health prediction results are compared and analyzed with the user's historical test results in detail. First, the data of the two are standardized to ensure the validity of the comparison. Then, a difference analysis algorithm is used to calculate the numerical difference between the health prediction results and the historical test results, and the difference is compared with a preset abnormal difference threshold. When the difference between the two exceeds the set threshold range, it is determined that the user's current health test data may be abnormal. For example, if there is a large difference in heart rate, P wave duration or PR interval between the ECG data of this health test and the historical ECG data, or if the difference between the blood pressure of this health test and the historical blood pressure is large, a personnel correction message is triggered to alert health managers to possible abnormalities to ensure that the user's health status is intervened and adjusted in a timely manner.

[0057] S25: Perform video source tracing based on the personnel correction message, obtain the video acquisition data corresponding to the user detection action, and manually check the video acquisition data to determine whether the cause of the data difference is an abnormality in the detected action and / or an abnormality in the device.

[0058] Specifically, based on the generated personnel correction message, the health management personnel will conduct a comprehensive manual inspection of the user's detection actions by observing whether the user's actions when using the equipment are performed correctly, such as posture during measurement, how to use the equipment, etc. At the same time, they will also check whether the detection equipment is working properly or whether there is external interference, and find out whether the cause of the data difference is abnormality of the tested action and / or abnormality of the equipment, so as to provide users with more accurate health assessments and suggestions.

[0059] S26: When the cause is an abnormality in the inspected action, the user is notified of a remote retest; when the cause is an abnormality in the equipment, the user is notified of an on-site retest; when the cause is not an abnormality in the inspected action and / or an abnormality in the equipment, the data difference is determined to be a normal difference, and the health prediction result is recorded and stored.

[0060] Specifically, when the system detects a user's detection action, it first sends a retest notification to the user through remote communication methods such as telephone, instructing the user to re-perform the detection operation to ensure the accuracy of the detection data; if equipment abnormality is the cause of the data difference, the system will arrange an on-site re-inspection and notify the user to go to the designated location for on-site health testing and to inspect, repair or replace the equipment; when the data difference is not caused by abnormal action or equipment abnormality but is a normal difference, the health prediction result will be recorded and stored as valid data to ensure the integrity and accuracy of the user's health record, providing a reliable basis for subsequent health analysis and diagnosis.

[0061] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0062] In one embodiment, a user self-help health detection device that meets medical standards is provided, and the user self-help health detection device that meets medical standards corresponds one-to-one to the user self-help health detection method that meets medical standards in the above embodiment. Figure 8 As shown, the user self-service health detection device that meets medical standards includes a detection parameter acquisition module, a health comparison module, a health report generation module, and a doctor's order report generation module. The detailed description of each functional module is as follows: A detection parameter acquisition module is used to obtain user detection options, generate corresponding detection description messages according to the user detection options, and obtain user detection actions. If the user detection action meets the preset standard detection action, the user detection parameters are obtained; A health comparison module is used to compare the user's detection parameters with the preset human body parameter thresholds to obtain the corresponding comparison results, obtain the user's historical detection results, input the user's detection parameters and / or the user's historical detection results into a preset health detection model to obtain a health prediction result; The health report generation module is used to generate a health detection report based on the comparison results and health prediction results, and generate a personnel intervention instruction when a health abnormality appears in the health detection report, and send the health detection report to the management end; The medical order report generation module is used to obtain the medical order input information from the management end, generate a medical order report based on the medical order input information, and send it to the user end.

[0063] Optionally, the detection parameter acquisition module also includes: The action correction submodule is used to obtain detection feature points from the user's detection action, and adjust the preset standard detection action based on the detection feature points as reference comparison points; The offset analysis submodule is used to perform offset analysis according to the reference comparison point when the user detection action does not match the preset standard detection action within a preset time threshold, and generate a user action correction message according to the offset analysis result.

[0064] Optionally, the offset analysis submodule specifically includes: An offset calculation unit, used to match the key feature points with the reference comparison points in the preset standard detection action, and calculate the spatial offset, angular offset and time offset between the user's actual action and the standard action; The motion compensation unit is used to perform motion compensation calculation according to the spatial offset, the angular offset and the temporal offset, and generate a user motion correction message according to the calculation result.

[0065] Optionally, the offset analysis submodule also includes: The real-time motion correction unit is used to perform three-dimensional modeling of the user's detection motion through virtual reality technology when the user's motion has been adjusted multiple times but still fails to reach the preset standard detection motion, and to perform real-time motion correction based on the constructed user motion three-dimensional model and the standard motion three-dimensional model.

[0066] Optionally, the health comparison module specifically includes: The identity retrieval submodule is used to obtain the user login identity information and perform identity retrieval from the detection database based on the user login identity information; A direct input submodule, for inputting user detection parameters into a preset health detection model when no user history detection result corresponding to the user login identity information is retrieved; The comprehensive input submodule is used to input the user detection parameters and the user historical detection results into the preset health detection model when the user historical detection results corresponding to the user login identity information are retrieved.

[0067] Optionally, the construction of the health detection model specifically includes: A data preparation module is used to obtain clinical test data and classify the clinical test data according to the age information and gender information of the subjects corresponding to the clinical test data to obtain a model training data set; The model training module is used to iteratively train the preset machine learning algorithm according to the model training data set to obtain a health detection model.

[0068] Optionally, after the health comparison module, also include: A data comparison module is used to compare the health prediction results with the user's historical test results, and generate a personnel correction message when the data difference between the health prediction results and the user's historical test results reaches a preset abnormal difference threshold; The abnormality determination module is used to trace the video source according to the personnel correction message, obtain the video acquisition data corresponding to the user's detection action, and manually check the video acquisition data to determine whether the cause of the data difference is the abnormality of the detected action and / or the abnormality of the equipment; The exception handling module is used to notify the user of remote re-testing when the cause is an abnormality in the inspected action, and to notify the user of on-site re-inspection when the cause is an equipment abnormality. When the cause is not an abnormality in the inspected action and / or equipment abnormality, the data difference is determined to be a normal difference, and the health prediction results are recorded and stored.

[0069] For the specific definition of the user self-service health detection device that meets the medical standards, please refer to the definition of the user self-service health detection method that meets the medical standards above, which will not be repeated here. Each module in the above-mentioned user self-service health detection device that meets the medical standards can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0070] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a user self-service health detection method that meets medical standards is implemented.

[0071] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain user detection options, generate corresponding detection description messages according to the user detection options, and obtain user detection actions. If the user detection actions meet the preset standard detection actions, obtain user detection parameters; Compare the user's detection parameters with the preset human body parameter thresholds to obtain the corresponding comparison results, obtain the user's historical detection results, input the user's detection parameters and / or the user's historical detection results into a preset health detection model to obtain a health prediction result; Generate a health check report based on the comparison results and health prediction results, and generate a personnel intervention instruction if health abnormalities appear in the health check report, and send the health check report to the management end; Obtain the medical order input information from the management end, generate a medical order report based on the medical order input information and send it to the user end.

[0072] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain user detection options, generate corresponding detection description messages according to the user detection options, and obtain user detection actions. If the user detection actions meet the preset standard detection actions, obtain user detection parameters; Compare the user's detection parameters with the preset human body parameter thresholds to obtain the corresponding comparison results, obtain the user's historical detection results, input the user's detection parameters and / or the user's historical detection results into a preset health detection model to obtain a health prediction result; Generate a health check report based on the comparison results and health prediction results, and generate a personnel intervention instruction if health abnormalities appear in the health check report, and send the health check report to the management end; Obtain the medical order input information from the management end, generate a medical order report based on the medical order input information and send it to the user end.

[0073] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0074] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0075] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A user self-help health detection method that meets medical standards, characterized in that: The user self-help health detection method that meets medical standards includes: Obtaining a user detection option, generating a corresponding detection description message according to the user detection option, and obtaining a user detection action, and obtaining a user detection parameter when the user detection action meets a preset standard detection action; Compare the user detection parameters with preset human body parameter thresholds to obtain corresponding comparison results, obtain user historical detection results, input the user detection parameters and / or user historical detection results into a preset health detection model to obtain health prediction results; Generate a health check report according to the comparison result and the health prediction result, and generate a personnel intervention instruction if a health abnormality appears in the health check report, and send the health check report to the management end; The medical order input information of the management end is obtained, and a medical order report is generated according to the medical order input information and sent to the user end.

2. The user self-help health detection method that meets medical standards according to claim 1 is characterized in that: The acquiring of the user detection action, and acquiring the user detection parameters when the user detection action meets the preset standard detection action, further includes: Acquire detection feature points from the user detection action, and adjust the preset standard detection action based on the detection feature points as reference comparison points; When the user detection action does not match the preset standard detection action within a preset time threshold, an offset analysis is performed according to the reference comparison point, and a user action correction message is generated according to the offset analysis result.

3. The user self-help health detection method that meets medical standards according to claim 2 is characterized in that: The performing the offset analysis according to the reference comparison point and generating the user action correction message according to the offset analysis result specifically includes: Matching the key feature points with the reference comparison points in the preset standard detection action, and calculating the spatial offset, angular offset and time offset between the user's actual action and the standard action; A motion compensation calculation is performed according to the spatial offset, the angular offset and the temporal offset, and the user motion correction message is generated according to the calculation result.

4. The user self-help health detection method that meets medical standards according to claim 2 is characterized in that: The performing of the offset analysis according to the reference comparison point and generating the user action correction message according to the offset analysis result also includes: When the user's motion has not reached the preset standard detection motion after multiple adjustments, the user's detection motion is three-dimensionally modeled through virtual reality technology, and real-time motion correction is performed based on the constructed user motion three-dimensional model and the standard motion three-dimensional model.

5. The user self-help health detection method that meets medical standards according to claim 1 is characterized in that: The obtaining of the user's historical detection results and inputting the user detection parameters and / or the user's historical detection results into a preset health detection model specifically includes: Obtaining user login identity information, and performing identity retrieval from a detection database according to the user login identity information; In the case where the user historical detection result corresponding to the user login identity information is not retrieved, inputting the user detection parameter into the preset health detection model; In the case where the user history detection result corresponding to the user login identity information is retrieved, the user detection parameter and the user history detection result are input into the preset health detection model.

6. The user self-help health detection method that meets medical standards according to claim 1 is characterized in that: The construction of the health detection model specifically includes: Acquire clinical test data, and classify the clinical test data according to the age information and gender information of the subjects corresponding to the clinical test data to obtain a model training data set; The preset machine learning algorithm is iteratively trained according to the model training data set to obtain the health detection model.

7. The user self-help health detection method that meets medical standards according to claim 5, characterized in that: After inputting the user detection parameters and / or the user historical detection results into the preset health detection model to obtain the health prediction result, the user self-service health detection method that meets medical standards also includes: Comparing the health prediction result with the user's historical test result, and generating a personnel correction message when the data difference between the health prediction result and the user's historical test result reaches a preset abnormal difference threshold; Perform video source tracing according to the personnel correction message, obtain the video acquisition data corresponding to the user detection action, and manually check the video acquisition data to determine whether the cause of the data difference is an abnormality in the detected action and / or an abnormality in the device; When the cause is abnormality of the inspected action, the user is notified of remote retesting; when the cause is abnormality of the equipment, the user is notified of on-site retesting; when the cause is not abnormality of the inspected action and / or abnormality of the equipment, the data difference is determined to be a normal difference, and the health prediction result is recorded and stored.

8. A user self-service health detection device that meets medical standards, characterized in that: The user self-service health detection device that meets medical standards includes: A detection parameter acquisition module is used to acquire a user detection option, generate a corresponding detection description message according to the user detection option, and acquire a user detection action, and acquire a user detection parameter when the user detection action meets a preset standard detection action; A health comparison module is used to compare the user detection parameters with preset human body parameter thresholds to obtain corresponding comparison results, obtain user historical detection results, input the user detection parameters and / or user historical detection results into a preset health detection model to obtain health prediction results; A health report generation module, used to generate a health detection report according to the comparison result and the health prediction result, and generate a personnel intervention instruction when a health abnormality appears in the health detection report, and send the health detection report to the management end; The medical order report generation module is used to obtain the medical order input information of the management end, generate a medical order report according to the medical order input information and send it to the user end.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the user self-help health detection method that meets medical standards as described in any one of claims 1 to 7 are implemented.

Images