WO2023212994A1 - Digital-twin-based data monitoring method and apparatus, and computer device and storage medium - Google Patents

Digital-twin-based data monitoring method and apparatus, and computer device and storage medium Download PDF

Info

Publication number
WO2023212994A1
WO2023212994A1 PCT/CN2022/096644 CN2022096644W WO2023212994A1 WO 2023212994 A1 WO2023212994 A1 WO 2023212994A1 CN 2022096644 W CN2022096644 W CN 2022096644W WO 2023212994 A1 WO2023212994 A1 WO 2023212994A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
monitoring
monitoring data
judgment result
satisfied
Prior art date
Application number
PCT/CN2022/096644
Other languages
French (fr)
Chinese (zh)
Inventor
顾大勇
王莹
黄海彬
Original Assignee
深圳市第二人民医院(深圳市转化医学研究院)
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市第二人民医院(深圳市转化医学研究院) filed Critical 深圳市第二人民医院(深圳市转化医学研究院)
Publication of WO2023212994A1 publication Critical patent/WO2023212994A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • This application relates to a data monitoring method, device, computer equipment, storage medium and computer program product based on digital twins.
  • a digital twin-based data monitoring method device, computer equipment, storage medium and computer program product are provided.
  • a data monitoring method based on digital twins including:
  • the digital twin model is a model formed by modeling the human body;
  • a data monitoring device based on digital twins including:
  • the acquisition module is used to acquire monitoring data related to human health
  • a classification module used to classify the monitoring data according to a digital twin model to obtain at least two data sets;
  • the digital twin model is a model formed by modeling the human body;
  • a selection module for selecting target monitoring conditions corresponding to each of the data sets among the candidate monitoring conditions
  • a judgment module is used to judge whether the monitoring data in the data set meets the target monitoring conditions, obtain a judgment result, and feed back the judgment result to the terminal for display.
  • the computer device includes a memory and a processor.
  • the memory stores a computer program.
  • the processor executes the computer program, it implements the steps of the digital twin-based data monitoring method. .
  • the present application also provides a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the steps of the digital twin-based data monitoring method are implemented.
  • the computer program product includes a computer program that implements the steps of the digital twin-based data monitoring method when executed by a processor.
  • Figure 1 is an application environment diagram of a data monitoring method based on digital twins in one embodiment.
  • Figure 2 is a schematic flowchart of a data monitoring method based on digital twins in one embodiment.
  • Figure 3 is a schematic flowchart of a method for obtaining monitoring data in one embodiment.
  • Figure 4 is a schematic flowchart of a data monitoring method based on digital twins in another embodiment.
  • Figure 5 is a schematic diagram of a digital twin in one embodiment.
  • Figure 6 is a schematic flowchart of a data monitoring method based on digital twins in yet another embodiment.
  • Figure 7 is a structural block diagram of a data monitoring device based on digital twins in one embodiment.
  • Figure 8 is an internal structure diagram of a computer device in one embodiment.
  • the digital twin-based data monitoring method can be applied in the application environment as shown in Figure 1.
  • the terminal 102 communicates with the server 104 through the network.
  • the data storage system may store data that server 104 needs to process.
  • the data storage system can be integrated on the server 104, or placed on the cloud or other network servers.
  • the server 104 obtains monitoring data related to human health; classifies the monitoring data according to the digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body; among the candidate monitoring conditions, select each target monitoring conditions corresponding to each data set; determine whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment result, and feed the judgment result back to the terminal for display.
  • the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices.
  • the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. .
  • Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.
  • the server 104 can be implemented as an independent server or a server cluster composed of multiple servers.
  • a data monitoring method based on digital twins is provided.
  • the application of this method to the server in Figure 1 is used as an example to illustrate, including the following steps:
  • monitoring data refers to data obtained by monitoring the human body, including data collected through wearable devices, human behavior data, data generated during diagnosis and treatment, medical examination data or diagnostic data, etc.
  • Data collected through wearable devices can include heart rate, blood pressure, blood oxygen saturation, etc.
  • Human behavior data includes human body function data, exercise data, diagnosis and treatment data, dietary data, emotional data, etc.
  • Medical test data and diagnostic data are data obtained from LIS (Laboratory Information Management System) or HIS (Hospital Information System).
  • the server can obtain monitoring data from a database, or the server can obtain monitoring data through a socket communication interface, or the server can obtain monitoring data through a file sharing service.
  • S204 Classify the monitoring data according to the digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body.
  • the digital twin model is a model formed by modeling the human body, including geometric model, physical model, physiological model, behavioral model and rule model, etc.
  • a geometric model is a model formed based on the geometric characteristics of the human body's appearance or the geometric characteristics of its internal organs.
  • the geometric characteristics of human body appearance include height, shoulder width, forearm length, thigh length, calf length, head circumference, facial size, etc.
  • the geometric characteristics of the internal organs of the human body include heart size (for example, 18 ⁇ 4.5 ⁇ 3.8cm), heart weight, left and right atrial wall thickness, left ventricular wall thickness, tricuspid valve circumference, pulmonary valve circumference, mitral valve circumference, Kidney size, kidney weight, kidney cortex thickness, etc.
  • the physiological model is a model formed based on the physiological characteristics of the human body.
  • Human physiological characteristics include cell morphology, blood routine, urine routine or gene sequence, protein composition, etc.
  • the physical model is a model based on the physical characteristics of the human body.
  • Human body physical characteristics include neurological characteristics, blood vessel characteristics, muscle characteristics or skeletal characteristics, such as vision, hearing, shallow reflexes, deep reflexes, blood pressure, heartbeat, pulse, body temperature, bone density, age, gender, skeletal muscle data, body fat , vital capacity, etc.
  • a behavioral model is a model based on human behavioral characteristics. Human behavioral characteristics include functional characteristics, movement characteristics, dietary characteristics or emotional characteristics, etc.
  • the rule model is a model formed based on the rules for predicting whether the human body will develop diseases, including disease prediction models, threshold management models or mathematical statistics models, etc.
  • the disease prediction model can be a machine learning model or a deep learning model trained based on characteristic samples when the human body is sick.
  • the threshold management model may be a model used to give an alarm threshold.
  • the threshold management model includes two thresholds. When the monitoring data (for example, the body weight value) exceeds the threshold 1, it is determined that the human body has a first-level health risk. When the monitoring data exceeds threshold 2, it is determined that the human body has a secondary health risk.
  • the mathematical statistical model is a model used to provide statistical analysis algorithms for monitoring data.
  • the mathematical statistical model provides an algorithm for statistical analysis of monitoring data, so that the human body can be analyzed based on the algorithm given by the mathematical statistical model. Perform statistical analysis on the monitoring data within a certain period of time to obtain statistical results. Based on the statistical results, it is judged whether the monitoring data meets the monitoring conditions.
  • the server classifies the monitoring data according to the digital twin model. For example, the server divides the monitoring data related to the human body characteristics represented by the physiological model into a data set corresponding to the physiological model, and divides the monitoring data related to the human body characteristics represented by the physical model into The data set corresponding to the physical model divides the monitoring data related to the human body characteristics represented by the geometric model into a data set corresponding to the geometric model, etc.
  • the server can build geometric models, physical models, physiological models, and behavioral models through relational data tables. For example, the server can use each field in the data table to represent the characteristics represented by the geometric model (for example, height, shoulder width, etc.) to form a geometric model; for another example, the server can use each field in the data table to represent the characteristics represented by the physiological model. Characteristics (for example, protein composition, blood routine, etc.) to form a physiological model.
  • the candidate monitoring conditions are conditions used to monitor whether the human body has health risks.
  • the candidate monitoring condition may be that blood pressure is higher than a preset value, or weight is higher than a preset value, or heart rate is higher than a preset value, etc.
  • the target monitoring condition is one or more monitoring conditions selected from the candidate monitoring conditions.
  • the server targets the data set corresponding to the geometric model.
  • the selected target monitoring condition can be the weight condition, and the weight condition can be that the weight exceeds the preset weight value.
  • the weight condition can also be that the BMI (Body Mass Index, weight) index is within the preset index value range, etc.
  • S208 Determine whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment result, and feed the judgment result back to the terminal for display.
  • the server determines whether the monitoring data in the data set meets the target monitoring conditions. For example, the server determines whether the weight of human body A reaches a preset weight value based on the weight monitoring data of human body A.
  • the judgment result can be "yes” or “no”, or the judgment result can be "satisfied” or “not satisfied”, etc.
  • the server obtains the judgment result and feeds it back to the terminal for display.
  • the terminal may be a wearable device worn by the human body being monitored, or it may be a terminal of a hospital's diagnosis and treatment system. For example, if the judgment result is that monitoring condition 1 is met, the server will feed back the judgment result to the terminal of the diagnosis and treatment system for display.
  • monitoring data related to human health is obtained, and the monitoring data is classified according to a digital twin model formed by modeling the human body to obtain at least two data sets.
  • select the target monitoring conditions corresponding to each data set select the target monitoring conditions corresponding to each data set. Determine whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment results, and feed back the judgment results to the terminal for display.
  • the monitoring data can be automatically judged according to the set monitoring conditions, which improves monitoring efficiency compared to manual analysis and judgment of monitoring data.
  • the accuracy of the judgment results is improved.
  • S202 specifically includes the following steps:
  • Data integration is to logically or physically bring together data from different sources, formats, characteristics and properties.
  • Data integration methods include federated integration methods, integration methods based on middleware models, or integration methods based on data warehouses.
  • Raw monitoring data is uncleaned monitoring data, which may include duplicate or erroneous data.
  • S304 Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data.
  • data cleaning is used to remove duplicate and erroneous data in the original monitoring data. For example, if the third row of data in field A in the digital twin model is the same as the fourth row of data in field A, it is determined that the fourth row of data is duplicate data, and the server deletes the fourth row of data for data cleaning. For another example, if the value of the height field in the geometric model is 180cm, and the value of the leg length field is 20cm, then the value of the leg length field is incorrect data, and the server performs data cleaning on the leg length field.
  • S304 specifically includes: the server performs data cleaning on the original monitoring data by running a SQL (Structured Query Language) script to obtain the cleaned original monitoring data.
  • SQL Structured Query Language
  • S306 Perform data development on the cleaned original monitoring data to obtain development data.
  • data development is the process of processing data to generate new data.
  • the processing process includes calculation, insertion, merging or splitting, etc.
  • performing data development on the A data field and the B data field may be to add the value of the A data field and the value of the B data field to obtain the value of the C data field, and the obtained C data field is the development data.
  • data development for data field A can be performed by splitting data field A into two data fields, A1 and A2.
  • the resulting A1 data field and A2 data field are development data.
  • the server merges the cleaned original monitoring data and development data to form monitoring data, making the obtained monitoring data more comprehensive.
  • the server obtains original monitoring data related to human health through data integration, and performs data cleaning on the original monitoring data, thereby removing duplicate and erroneous data and improving the accuracy of the judgment results. Then, data development is performed on the cleaned original monitoring data to obtain development data, thereby making the monitoring data more comprehensive and further improving the accuracy of the judgment results.
  • S208 specifically includes: starting from the first target monitoring condition, judging the monitoring data through each target monitoring condition in turn, until the obtained judgment result is satisfied, or until the judgment is obtained through the last target monitoring condition. the judgment result.
  • the server first judges the monitoring data through the first target monitoring condition. If the judgment result is satisfied, the judgment result is fed back to the terminal for display. If the judgment result is not satisfied, the monitoring data is judged through the next target monitoring condition. And so on, until the obtained judgment result is satisfied, or until the judgment result obtained is judged by the last target monitoring condition.
  • the server automatically judges the monitoring data through multiple target monitoring conditions, which can realize systematic monitoring of monitoring data and improve the comprehensiveness of monitoring.
  • the judgment results include satisfied, dissatisfied and unable to judge; after S208, it also includes: when the judgment result is satisfied or dissatisfied, feeding back the judgment result to the terminal so that the terminal displays the judgment result; when the judgment is made, When the result is that it cannot be judged, optimize the digital twin model, and after optimizing the digital twin model, return to the steps of classifying the monitoring data according to the digital twin model and iterate until the judgment result is satisfied or not satisfied.
  • the digital twin model is optimized. For example, if the geometric model includes five data fields: height, shoulder width, head circumference, thigh length, and calf length, then the monitoring data in the data set corresponding to the geometric model does not include weight values. If the target monitoring condition is whether the weight reaches the predetermined value, If the weight value is set, it cannot be judged whether the monitoring data meets the target monitoring conditions, and the obtained judgment result is "unable to judge”. At this time, a weight data field is added to the geometric model to optimize the geometric model. Then, the monitoring data is reclassified according to the optimized geometric model, and the resulting data set will include a weight data field, so that it can be judged whether the weight value reaches the preset weight value and the judgment result is obtained.
  • the server starts from the first target monitoring condition and judges the monitoring data through each target monitoring condition in turn. If it passes a certain target monitoring condition (for example, , if the judgment result obtained by the target monitoring condition 3) is satisfied, the judgment result will be fed back to the terminal for display; if the judgment result obtained by the target monitoring condition is not satisfied, the monitoring data will be judged by the next target monitoring condition; If the judgment results obtained by all target monitoring conditions are unable to judge, then optimize the digital twin model, and after optimizing the digital twin model, return to the steps of classifying monitoring data according to the digital twin model and iterate until the judgment result is obtained To be satisfied or dissatisfied.
  • a certain target monitoring condition for example, , if the judgment result obtained by the target monitoring condition 3
  • the judgment result will be fed back to the terminal for display
  • the judgment result obtained by the target monitoring condition is not satisfied, the monitoring data will be judged by the next target monitoring condition; If the judgment results obtained by all target monitoring conditions are unable to judge, then optimize the digital twin model, and
  • the server when the judgment result is satisfied or dissatisfied, the server feeds back the judgment result to the terminal so that the terminal displays the judgment result; when the judgment result is that it cannot be judged, the server optimizes the digital twin model and performs the digital twin model optimization. After the twin model is optimized, it returns to the steps of classifying the monitoring data according to the digital twin model and iterates until the obtained judgment result is satisfied or not satisfied. Therefore, by continuously optimizing the digital twin model, the judgment results can more accurately reflect the health status of the human body and improve the accuracy of the judgment results.
  • S208 specifically includes: scoring the monitoring data in the data set through a prediction model to obtain a score; when the score is greater than or equal to the preset score, determining that the monitoring data meets the target monitoring conditions and obtaining a judgment result. is satisfied; when the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is that it is not satisfied.
  • the prediction model is a machine learning model used to score monitoring data, which can be a CNN (Convolutional Neural Networks) model, a DNN (Deep Neural Networks) model, or a ResNet (Residual Net) model. Difference convolutional neural network) model, etc.
  • the server inputs the monitoring data into the prediction model, scores the monitoring data through the prediction model, and obtains a score. The higher the score, the higher the health risk to the human body.
  • the server can set the target monitoring condition as the score is greater than or equal to the preset score. When the score is greater than or equal to the preset score, the judgment result is satisfied; when the score is less than the preset score, the judgment result is not satisfied. satisfy.
  • the server scores the monitoring data in the data set through the prediction model to obtain a score; when the score is greater than or equal to the preset score, it is determined that the monitoring data meets the target monitoring conditions, and the judgment result is satisfied; when When the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is unsatisfied.
  • the server can automatically score the monitoring data through the prediction model and obtain the judgment results based on the scores. Compared with manual analysis and judgment of the monitoring data, the monitoring efficiency is improved.
  • the target monitoring condition includes at least two monitoring sub-conditions; S208 specifically includes: scoring the monitoring data in the data set according to each monitoring sub-condition to obtain a score; performing a weighted summation of the scores to obtain Total score value; when the total score value is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the total score value is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions.
  • the server scores the monitoring data in the data set according to each monitoring sub-condition and obtains a score.
  • the target monitoring condition includes three monitoring sub-conditions, and the weight values corresponding to the three monitoring sub-conditions are 0.2, 0.3, and 0.5 respectively.
  • the server scores the monitoring data through the first monitoring sub-condition and gets a score of 30. It scores the monitoring data through the second monitoring sub-condition and gets a score of 50. It scores the monitoring data through the third monitoring sub-condition. Rating, the score is 45.
  • the server scores the monitoring data in the data set according to each monitoring sub-condition to obtain a score; performs a weighted sum of the scores to obtain a total score; when the total score is greater than or equal to the preset value, It is determined that the monitoring data meets the target monitoring conditions; when the total score value is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions.
  • the server can comprehensively judge the monitoring data based on multiple monitoring sub-conditions, thereby improving the accuracy of the judgment results.
  • the digital twin space includes multiple digital twins.
  • the data integration unit in the digital twin obtains the original monitoring data related to the health of each physical entity (human body) collected by the monitoring unit, and Store original monitoring data in the physical space corresponding to each physical entity.
  • the original monitoring data collected by the monitoring unit includes wearable device data, third-party data, diagnosis and treatment process data, personal behavior data, data in LIS and HIS, etc.
  • the digital twin performs data cleaning on the original monitoring data, and performs data development on the cleaned original monitoring data to obtain development data.
  • the server combines the cleaned original monitoring data and development data into monitoring data, and classifies the monitoring data according to physical models, geometric models, behavioral models, physiological models and rule models to obtain physical model data sets, geometric model data sets, behavioral models, etc.
  • Model data set, physiological model data set and rule model data set, etc. The digital twin selects the target monitoring conditions corresponding to each data set among the candidate monitoring conditions, determines whether the monitoring data in the data set meets the target monitoring conditions, obtains the judgment results, and feeds the judgment results back to the terminal for display.
  • the digital twin conducts secure and controllable data exchange with other digital twins through the data exchange unit, and provides services to the physical entity through the service unit.
  • the data security unit in the digital twin is used for data security management to ensure the security of data in the digital twin.
  • the data monitoring method based on digital twins includes the following steps:
  • S604 Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data.
  • S606 Perform data development on the cleaned original monitoring data to obtain development data.
  • S608 Combine the cleaned original monitoring data and development data into monitoring data.
  • S610 Classify the monitoring data according to the digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body.
  • S612 Select the target monitoring condition corresponding to each data set among the candidate monitoring conditions.
  • S614 Starting from the first target monitoring condition, the monitoring data is judged by each target monitoring condition in sequence until the obtained judgment result is satisfied, or until the judgment result judged by the last target monitoring condition is obtained.
  • embodiments of the present application also provide a digital twin-based data monitoring device for implementing the above-mentioned digital twin-based data monitoring method.
  • the problem-solving solution provided by this device is similar to the solution recorded in the above method. Therefore, for the specific limitations in one or more digital twin-based data monitoring device embodiments provided below, please refer to the above for digital twin-based data monitoring device. The limitations of twin data monitoring methods will not be described again here.
  • a data monitoring device based on digital twins including: an acquisition module 702, a classification module 704, a selection module 706 and a judgment module 708, wherein:
  • the acquisition module 702 is used to acquire monitoring data related to human health
  • the classification module 704 is used to classify the monitoring data according to the digital twin model to obtain at least two data sets;
  • the digital twin model is a model formed by modeling the human body;
  • the selection module 706 is used to select the target monitoring condition corresponding to each data set among the candidate monitoring conditions
  • the judgment module 708 is used to judge whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment result, and feed the judgment result back to the terminal for display.
  • monitoring data related to human health is obtained, and the monitoring data is classified according to a digital twin model formed by modeling the human body to obtain at least two data sets.
  • select the target monitoring conditions corresponding to each data set select the target monitoring conditions corresponding to each data set. Determine whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment results, and feed back the judgment results to the terminal for display.
  • the monitoring data can be automatically judged according to the set monitoring conditions, which improves monitoring efficiency compared to manual analysis and judgment of monitoring data.
  • the accuracy of the judgment results is improved.
  • the acquisition module 702 is also used to:
  • the cleaned original monitoring data and development data are combined into monitoring data.
  • the judgment results include satisfied, dissatisfied and unable to judge; the judgment module 708 is also used to:
  • the judgment module 708 is also used to:
  • the monitoring data is judged by each target monitoring condition in turn until the judgment result obtained is satisfied, or until the judgment result judged by the last target monitoring condition is obtained.
  • the judgment module 708 is also used to:
  • the target monitoring condition includes at least two monitoring sub-conditions; the judgment module 708 is also used to:
  • Each module in the above-mentioned digital twin-based data monitoring device can be implemented in whole or in part through software, hardware, and combinations thereof.
  • Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may 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.
  • a computer device is provided.
  • the computer device may be a server, and its internal structure diagram may be shown in Figure 8 .
  • the computer device includes a processor, memory, and network interfaces connected through a system bus. Wherein, the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes non-volatile storage media and internal memory.
  • the non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media.
  • the computer device's database is used to store data monitoring data.
  • the network interface of the computer device is used to communicate with external terminals through a network connection.
  • the computer program is executed by the processor to implement a data monitoring method based on digital twins.
  • Figure 8 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied.
  • Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.
  • a computer device including a memory and a processor.
  • a computer program is stored in the memory.
  • the processor executes the computer program, it implements the following steps: obtaining monitoring data related to human health; and following the digital twin model. Classify the monitoring data to obtain at least two data sets; the digital twin model is a model formed by modeling the human body; among the candidate monitoring conditions, select the target monitoring conditions corresponding to each data set; determine the monitoring conditions in the data set Whether the data meets the target monitoring conditions, the judgment result is obtained, and the judgment result is fed back to the terminal for display.
  • the processor also implements the following steps when executing the computer program: obtaining original monitoring data related to human health through data integration; performing data cleaning on the original monitoring data to obtain cleaned original monitoring data; The original monitoring data is developed for data development to obtain development data; the cleaned original monitoring data and development data are combined into monitoring data.
  • the judgment results include satisfied, dissatisfied and unable to judge; when the processor executes the computer program, the following steps are also implemented: when the judgment result is satisfied or dissatisfied, the judgment result is fed back to the terminal so that the terminal can make the judgment The results are displayed; when the judgment result is that it cannot be judged, the digital twin model is optimized, and after optimizing the digital twin model, the steps of classifying the monitoring data according to the digital twin model are returned to iterate until the judgment result is satisfied or not. satisfy.
  • the processor when the processor executes the computer program, it also implements the following steps: starting from the first target monitoring condition, judging the monitoring data through each target monitoring condition in turn, until the obtained judgment result is satisfied, or until the obtained result is passed The judgment result of the last target monitoring condition is judged.
  • the processor also implements the following steps when executing the computer program: scoring the monitoring data in the data set through a prediction model to obtain a score; when the score is greater than or equal to the preset score, determining that the monitoring data satisfies Target monitoring conditions, the judgment result is satisfied; when the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is not satisfied.
  • the target monitoring condition includes at least two monitoring sub-conditions; when the processor executes the computer program, it also implements the following steps: scoring the monitoring data in the data set according to each monitoring sub-condition to obtain a score; The values are weighted and summed to obtain the total score; when the total score is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the total score is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions.
  • a computer-readable storage medium with a computer program stored thereon.
  • the computer program When the computer program is executed by a processor, the following steps are implemented: obtaining monitoring data related to human health; and analyzing the monitoring data according to a digital twin model. Classify and obtain at least two data sets; the digital twin model is a model formed by modeling the human body; among the candidate monitoring conditions, select the target monitoring conditions corresponding to each data set; determine whether the monitoring data in the data set meets The target monitors the conditions, obtains the judgment results, and feeds the judgment results back to the terminal for display.
  • the following steps are also implemented: obtaining original monitoring data related to human health through data integration; performing data cleaning on the original monitoring data to obtain cleaned original monitoring data; Carry out data development on the original monitoring data to obtain development data; combine the cleaned original monitoring data and development data to form monitoring data.
  • the judgment result includes satisfaction, dissatisfaction and inability to judge; when the computer program is executed by the processor, the following steps are also implemented: when the judgment result is satisfied or dissatisfied, the judgment result is fed back to the terminal so that the terminal The judgment result is displayed; when the judgment result is that it cannot be judged, the digital twin model is optimized, and after optimizing the digital twin model, the steps of classifying the monitoring data according to the digital twin model are returned to iterate until the judgment result is satisfied or Not satisfied.
  • the following steps are also implemented: starting from the first target monitoring condition, judging the monitoring data through each target monitoring condition in sequence until the obtained judgment result is satisfied, or until the obtained The judgment result based on the last target monitoring condition.
  • the computer program when executed by the processor, it also implements the following steps: scoring the monitoring data in the data set through a prediction model to obtain a score; when the score is greater than or equal to the preset score, determining the monitoring data If the target monitoring conditions are met, the judgment result is satisfied; when the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is dissatisfied.
  • the target monitoring condition includes at least two monitoring sub-conditions; when executed by the processor, the computer program also implements the following steps: scoring the monitoring data in the data set according to each monitoring sub-condition to obtain a score; The scores are weighted and summed to obtain the total score; when the total score is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the total score is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions .
  • a computer program product including a computer program.
  • the computer program When executed by a processor, the computer program implements the following steps: acquiring monitoring data related to human health; classifying the monitoring data according to a digital twin model to obtain At least two data sets; the digital twin model is a model formed by modeling the human body; among the candidate monitoring conditions, select the target monitoring conditions corresponding to each data set; determine whether the monitoring data in the data set meets the target monitoring conditions, Obtain the judgment result and feed it back to the terminal for display.
  • the following steps are also implemented: obtaining original monitoring data related to human health through data integration; performing data cleaning on the original monitoring data to obtain cleaned original monitoring data; Carry out data development on the original monitoring data to obtain development data; combine the cleaned original monitoring data and development data to form monitoring data.
  • the judgment result includes satisfaction, dissatisfaction and inability to judge; when the computer program is executed by the processor, the following steps are also implemented: when the judgment result is satisfied or dissatisfied, the judgment result is fed back to the terminal so that the terminal The judgment result is displayed; when the judgment result is that it cannot be judged, the digital twin model is optimized, and after optimizing the digital twin model, the steps of classifying the monitoring data according to the digital twin model are returned to iterate until the judgment result is satisfied or Not satisfied.
  • the following steps are also implemented: starting from the first target monitoring condition, judging the monitoring data through each target monitoring condition in sequence until the obtained judgment result is satisfied, or until the obtained The judgment result based on the last target monitoring condition.
  • the computer program when executed by the processor, it also implements the following steps: scoring the monitoring data in the data set through a prediction model to obtain a score; when the score is greater than or equal to the preset score, determining the monitoring data If the target monitoring conditions are met, the judgment result is satisfied; when the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is dissatisfied.
  • the target monitoring condition includes at least two monitoring sub-conditions; when executed by the processor, the computer program also implements the following steps: scoring the monitoring data in the data set according to each monitoring sub-condition to obtain a score; The scores are weighted and summed to obtain the total score; when the total score is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the total score is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions .
  • the user information including but not limited to user equipment information, user personal information, etc.
  • data including but not limited to data used for analysis, stored data, displayed data, etc.
  • the computer program can be stored in a non-volatile computer-readable storage.
  • the computer program when executed, may include the processes of the above method embodiments.
  • Any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory.
  • Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory (MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc.
  • Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory, etc.
  • RAM Random Access Memory
  • RAM random access memory
  • RAM Random Access Memory
  • the databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database.
  • Non-relational databases may include blockchain-based distributed databases, etc., but are not limited thereto.
  • the processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to this.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

A digital-twin-based data monitoring method. The method comprises: classifying monitoring data according to a digital twin model, so as to obtain at least two data sets, wherein the digital twin model is a model formed by modeling a human body; from among candidate monitoring conditions, selecting a target monitoring condition corresponding to each data set; and determining whether the monitoring data in the data set meets the target monitoring condition, so as to obtain a determination result, and feeding the determination result back to a terminal for display.

Description

基于数字孪生的数据监测方法、装置、计算机设备和存储介质Data monitoring methods, devices, computer equipment and storage media based on digital twins 技术领域Technical field
本申请涉及一种基于数字孪生的数据监测方法、装置、计算机设备、存储介质和计算机程序产品。This application relates to a data monitoring method, device, computer equipment, storage medium and computer program product based on digital twins.
背景技术Background technique
随着社会经济发展以及科技进步，人们越来越重视身体健康，怎样对与人体健康相关的数据进行监测成为重要的问题，传统技术中，人工对相关数据进行监测和分析，需要花费大量时间对监测数据进行分析研究，不能及时发现人体的健康风险，监测效率较低。With the development of society and economy and the advancement of science and technology, people pay more and more attention to their health. How to monitor data related to human health has become an important issue. In traditional technology, manual monitoring and analysis of relevant data requires a lot of time. Analysis and research on monitoring data cannot detect human health risks in time, and the monitoring efficiency is low.
发明内容Contents of the invention
根据本申请公开的各种实施例，提供一种基于数字孪生的数据监测方法、装置、计算机设备、存储介质和计算机程序产品。According to various embodiments disclosed in this application, a digital twin-based data monitoring method, device, computer equipment, storage medium and computer program product are provided.
一种基于数字孪生的数据监测方法，包括：A data monitoring method based on digital twins, including:
获取与人体健康相关的监测数据；Obtain monitoring data related to human health;
按照数字孪生模型对所述监测数据进行分类，得到至少两个数据集合；所述数字孪生模型是对人体进行建模所形成的模型；Classify the monitoring data according to a digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body;
在候选监测条件中，选取每个所述数据集合对应的目标监测条件；Among the candidate monitoring conditions, select the target monitoring condition corresponding to each of the data sets;
判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果，并将所述判断结果反馈至终端进行显示。Determine whether the monitoring data in the data set meets the target monitoring condition, obtain a judgment result, and feed the judgment result back to the terminal for display.
一种基于数字孪生的数据监测装置，包括：A data monitoring device based on digital twins, including:
获取模块，用于获取与人体健康相关的监测数据；The acquisition module is used to acquire monitoring data related to human health;
分类模块，用于按照数字孪生模型对所述监测数据进行分类，得到至少两个数据集合；所述数字孪生模型是对人体进行建模所形成的模型；A classification module, used to classify the monitoring data according to a digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body;
选取模块，用于在候选监测条件中，选取每个所述数据集合对应的目标监测条件；A selection module for selecting target monitoring conditions corresponding to each of the data sets among the candidate monitoring conditions;
判断模块，用于判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果，并将所述判断结果反馈至终端进行显示。A judgment module is used to judge whether the monitoring data in the data set meets the target monitoring conditions, obtain a judgment result, and feed back the judgment result to the terminal for display.
本申请还提供了一种计算机设备，所述计算机设备包括存储器和处理器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现所述基于数字孪生的数据监测方法的步骤。This application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, it implements the steps of the digital twin-based data monitoring method. .
本申请还提供了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现所述基于数字孪生的数据监测方法的步骤。The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the digital twin-based data monitoring method are implemented.
本申请还提供了一种计算机程序产品。所述计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现所述基于数字孪生的数据监测方法的步骤。This application also provides a computer program product. The computer program product includes a computer program that implements the steps of the digital twin-based data monitoring method when executed by a processor.
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the application will be apparent from the description, drawings, and claims.
附图说明Description of the drawings
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. Those of ordinary skill in the art can also obtain other drawings based on these drawings without exerting creative efforts.
图1为一个实施例中基于数字孪生的数据监测方法的应用环境图。Figure 1 is an application environment diagram of a data monitoring method based on digital twins in one embodiment.
图2为一个实施例中基于数字孪生的数据监测方法的流程示意图。Figure 2 is a schematic flowchart of a data monitoring method based on digital twins in one embodiment.
图3为一个实施例中获取监测数据方法的流程示意图。Figure 3 is a schematic flowchart of a method for obtaining monitoring data in one embodiment.
图4为另一个实施例中基于数字孪生的数据监测方法的流程示意图。Figure 4 is a schematic flowchart of a data monitoring method based on digital twins in another embodiment.
图5为一个实施例中数字孪生体的示意图。Figure 5 is a schematic diagram of a digital twin in one embodiment.
图6为又一个实施例中基于数字孪生的数据监测方法的流程示意图。Figure 6 is a schematic flowchart of a data monitoring method based on digital twins in yet another embodiment.
图7为一个实施例中基于数字孪生的数据监测装置的结构框图。Figure 7 is a structural block diagram of a data monitoring device based on digital twins in one embodiment.
图8为一个实施例中计算机设备的内部结构图。Figure 8 is an internal structure diagram of a computer device in one embodiment.
具体实施方式Detailed ways
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.
本申请实施例提供的基于数字孪生的数据监测方法，可以应用于如图1所示的应用环境中。其中，终端102通过网络与服务器104进行通信。数据存储***可以存储服务器104需要处理的数据。数据存储***可以集成在服务器104上，也可以放在云上或其他网络服务器上。服务器104获取与人体健康相关的监测数据；按照数字孪生模型对监测数据进行分类，得到至少两个数据集合；数字孪生模型是对人体进行建模所形成的模型；在候选监测条件中，选取每个数据集合对应的目标监测条件；判断数据集合中的监测数据是否满足目标监测条件，得到判断结果，并将判断结果反馈至终端进行显示。The digital twin-based data monitoring method provided by the embodiment of this application can be applied in the application environment as shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system may store data that server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 obtains monitoring data related to human health; classifies the monitoring data according to the digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body; among the candidate monitoring conditions, select each target monitoring conditions corresponding to each data set; determine whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment result, and feed the judgment result back to the terminal for display.
其中，终端102可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑、物联网设备和便携式可穿戴设备，物联网设备可为智能音箱、智能电视、智能空调、智能车载设备等。便携式可穿戴设备可为智能手表、智能手环、头戴设备等。服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. . Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented as an independent server or a server cluster composed of multiple servers.
在一个实施例中，如图2所示，提供了一种基于数字孪生的数据监测方法，以该方法应用于图1中的服务器为例进行说明，包括以下步骤：In one embodiment, as shown in Figure 2, a data monitoring method based on digital twins is provided. The application of this method to the server in Figure 1 is used as an example to illustrate, including the following steps:
S202，获取与人体健康相关的监测数据。S202: Obtain monitoring data related to human health.
其中，监测数据是对人体进行监测所获取的数据，包括通过可穿戴设备采集的数据、人体行为数据、诊疗过程中产生的数据、医学检验数据或者诊断数据等。通过可穿戴设备采集的数据可以包括心率、血压、血氧饱和度等。人体行为数据包括人体机能数据、运动数据、诊疗数据、饮食数据、情绪数据等。医学检验数据和诊断数据是从LIS(Laboratory Information Management System，实验室信息管理***)或者HIS(Hospital Information System，医院信息***)获取的数据。Among them, monitoring data refers to data obtained by monitoring the human body, including data collected through wearable devices, human behavior data, data generated during diagnosis and treatment, medical examination data or diagnostic data, etc. Data collected through wearable devices can include heart rate, blood pressure, blood oxygen saturation, etc. Human behavior data includes human body function data, exercise data, diagnosis and treatment data, dietary data, emotional data, etc. Medical test data and diagnostic data are data obtained from LIS (Laboratory Information Management System) or HIS (Hospital Information System).
在一个实施例中，服务器可以从数据库获取监测数据，或者服务器也可以通过socket(套接字)通信 接口获取监测数据，或者服务器也可以通过文件共享服务获取监测数据。In one embodiment, the server can obtain monitoring data from a database, or the server can obtain monitoring data through a socket communication interface, or the server can obtain monitoring data through a file sharing service.
S204，按照数字孪生模型对监测数据进行分类，得到至少两个数据集合；数字孪生模型是对人体进行建模所形成的模型。S204: Classify the monitoring data according to the digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body.
其中，数字孪生模型是对人体进行建模所形成的模型，包括几何模型、物理模型、生理模型、行为模型和规则模型等。几何模型是根据人体外观的几何特征或内部器官的几何特征进行建模形成的模型。人体外观的几何特征包括身高、肩宽、前臂长、大腿长、小腿长、头围、面部尺寸等。人体内部器官的几何特征包括心脏大小(例如18×4.5×3.8cm)、心脏重量、心脏左右心房壁厚度、左心室壁厚度、三尖瓣周径、肺动脉瓣周径、二尖瓣周径、肾脏大小、肾脏重量、肾脏皮质厚度等。生理模型是根据人体的生理特征进行建模形成的模型。人体生理特征包括细胞形态、血常规、尿常规或者基因序列、蛋白质组成等。物理模型是根据人体物理特征进行建模形成的模型。人体物理特征包括神经特征、血管特征、肌肉特征或者骨骼特征等，例如，视力、听力、浅反射、深反射、血压、心跳、脉搏、体温、骨密度、年龄、性别、骨骼肌数据、体脂肪、肺活量等。行为模型是根据人体行为特征进行建模形成的模型。人体行为特征包括机能特征、运动特征、饮食特征或者情绪特征等。规则模型是根据预测人体是否产生疾病的规则进行建模形成的模型，包括疾病预测模型、阈值管理模型或者数理统计模型等。疾病预测模型可以是根据人体生病时的特征样本进行训练所得的机器学习模型或者深度学习模型。阈值管理模型可以是用于给出告警阈值的模型，例如，阈值管理模型中包括两个阈值，当监测数据(例如，人体的体重值)超过阈值1时，确定人体具有一级健康风险，当监测数据超过阈值2时，确定人体具有二级健康风险。数理统计模型是用于给出对监测数据进行统计分析算法的模型。由于判断人体是否有健康风险时，可能需要根据人体在某个时间段内的特征进行判断，数理统计模型给出对监测数据进行统计分析的算法，从而可以根据数理统计模型给出的算法对人体在某个时间段内的监测数据进行统计分析，得到统计结果，根据统计结果判断监测数据是否满足监测条件。Among them, the digital twin model is a model formed by modeling the human body, including geometric model, physical model, physiological model, behavioral model and rule model, etc. A geometric model is a model formed based on the geometric characteristics of the human body's appearance or the geometric characteristics of its internal organs. The geometric characteristics of human body appearance include height, shoulder width, forearm length, thigh length, calf length, head circumference, facial size, etc. The geometric characteristics of the internal organs of the human body include heart size (for example, 18×4.5×3.8cm), heart weight, left and right atrial wall thickness, left ventricular wall thickness, tricuspid valve circumference, pulmonary valve circumference, mitral valve circumference, Kidney size, kidney weight, kidney cortex thickness, etc. The physiological model is a model formed based on the physiological characteristics of the human body. Human physiological characteristics include cell morphology, blood routine, urine routine or gene sequence, protein composition, etc. The physical model is a model based on the physical characteristics of the human body. Human body physical characteristics include neurological characteristics, blood vessel characteristics, muscle characteristics or skeletal characteristics, such as vision, hearing, shallow reflexes, deep reflexes, blood pressure, heartbeat, pulse, body temperature, bone density, age, gender, skeletal muscle data, body fat , vital capacity, etc. A behavioral model is a model based on human behavioral characteristics. Human behavioral characteristics include functional characteristics, movement characteristics, dietary characteristics or emotional characteristics, etc. The rule model is a model formed based on the rules for predicting whether the human body will develop diseases, including disease prediction models, threshold management models or mathematical statistics models, etc. The disease prediction model can be a machine learning model or a deep learning model trained based on characteristic samples when the human body is sick. The threshold management model may be a model used to give an alarm threshold. For example, the threshold management model includes two thresholds. When the monitoring data (for example, the body weight value) exceeds the threshold 1, it is determined that the human body has a first-level health risk. When the monitoring data exceeds threshold 2, it is determined that the human body has a secondary health risk. The mathematical statistical model is a model used to provide statistical analysis algorithms for monitoring data. Because when judging whether a human body has health risks, it may be necessary to judge based on the characteristics of the human body in a certain period of time. The mathematical statistical model provides an algorithm for statistical analysis of monitoring data, so that the human body can be analyzed based on the algorithm given by the mathematical statistical model. Perform statistical analysis on the monitoring data within a certain period of time to obtain statistical results. Based on the statistical results, it is judged whether the monitoring data meets the monitoring conditions.
服务器按照数字孪生模型对监测数据进行分类，例如，服务器将与生理模型表征的人体特征相关的监测数据划分为与生理模型对应的数据集合，将与物理模型表征的人体特征相关的监测数据划分为与物理模型对应的数据集合，将与几何模型表征的人体特征相关的监测数据划分为与几何模型对应的数据集合等。The server classifies the monitoring data according to the digital twin model. For example, the server divides the monitoring data related to the human body characteristics represented by the physiological model into a data set corresponding to the physiological model, and divides the monitoring data related to the human body characteristics represented by the physical model into The data set corresponding to the physical model divides the monitoring data related to the human body characteristics represented by the geometric model into a data set corresponding to the geometric model, etc.
在一个实施例中，服务器可以通过关系型数据表构建几何模型、物理模型、生理模型和行为模型。例如，服务器可以用数据表中的各字段分别表示几何模型表征的特征(例如，身高、肩宽等)，形成几何模型；又例如，服务器可以用数据表中的各字段分别表示生理模型表征的特征(例如，蛋白质组成、血常规等)，形成生理模型。In one embodiment, the server can build geometric models, physical models, physiological models, and behavioral models through relational data tables. For example, the server can use each field in the data table to represent the characteristics represented by the geometric model (for example, height, shoulder width, etc.) to form a geometric model; for another example, the server can use each field in the data table to represent the characteristics represented by the physiological model. Characteristics (for example, protein composition, blood routine, etc.) to form a physiological model.
S206，在候选监测条件中，选取每个数据集合对应的目标监测条件。S206: Select the target monitoring condition corresponding to each data set among the candidate monitoring conditions.
其中，候选监测条件是用于对人体是否具有健康风险进行监测的条件。例如，候选监测条件可以是血压高于预设值，或者也可以是体重超过预设值，或者也可以是心率高于预设值等。目标监测条件是从候选监测条件中选取的一个或多个监测条件，例如，服务器针对几何模型对应的数据集合，选取的目标监测条件可以是体重条件，体重条件可以是体重超过预设体重值，或者体重条件也可以是BMI(Body Mass Index，体重)指数在预设指数值范围内等。Among them, the candidate monitoring conditions are conditions used to monitor whether the human body has health risks. For example, the candidate monitoring condition may be that blood pressure is higher than a preset value, or weight is higher than a preset value, or heart rate is higher than a preset value, etc. The target monitoring condition is one or more monitoring conditions selected from the candidate monitoring conditions. For example, the server targets the data set corresponding to the geometric model. The selected target monitoring condition can be the weight condition, and the weight condition can be that the weight exceeds the preset weight value. Or the weight condition can also be that the BMI (Body Mass Index, weight) index is within the preset index value range, etc.
S208，判断数据集合中的监测数据是否满足目标监测条件，得到判断结果，并将判断结果反馈至终端进行显示。S208: Determine whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment result, and feed the judgment result back to the terminal for display.
服务器判断数据集合中的监测数据是否满足目标监测条件，例如，服务器根据人体A的体重监测数据判断人体A的体重是否达到预设体重值。判断结果可以为“是”或者“否”，判断结果也可以为“满足”或“不满足”等。服务器获取判断结果，并将判断结果反馈至终端进行显示。终端可以是被监测的人体穿戴的可穿戴设备，或者也可以是医院的诊疗***的终端。例如，判断结果为满足监测条件1，服务器将该判断结果反馈至诊疗***的终端进行显示。The server determines whether the monitoring data in the data set meets the target monitoring conditions. For example, the server determines whether the weight of human body A reaches a preset weight value based on the weight monitoring data of human body A. The judgment result can be "yes" or "no", or the judgment result can be "satisfied" or "not satisfied", etc. The server obtains the judgment result and feeds it back to the terminal for display. The terminal may be a wearable device worn by the human body being monitored, or it may be a terminal of a hospital's diagnosis and treatment system. For example, if the judgment result is that monitoring condition 1 is met, the server will feed back the judgment result to the terminal of the diagnosis and treatment system for display.
上述实施例中，获取与人体健康相关的监测数据，按照对人体进行建模所形成的数字孪生模型对监测数据进行分类，得到至少两个数据集合。在候选监测条件中，选取每个数据集合对应的目标监测条件。判断数据集合中的监测数据是否满足目标监测条件，得到判断结果，并将判断结果反馈至终端进行显示。从而可以通过设置的监测条件自动对监测数据进行判断，相比于人工对监测数据进行分析判断，提高了监测效率。并且，通过按照数字孪生模型对监测数据进行分类，并针对分类所得的每一数据集合有针对性的选取目标监测条件进行监测，提高了判断结果的准确性。In the above embodiment, monitoring data related to human health is obtained, and the monitoring data is classified according to a digital twin model formed by modeling the human body to obtain at least two data sets. Among the candidate monitoring conditions, select the target monitoring conditions corresponding to each data set. Determine whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment results, and feed back the judgment results to the terminal for display. As a result, the monitoring data can be automatically judged according to the set monitoring conditions, which improves monitoring efficiency compared to manual analysis and judgment of monitoring data. Moreover, by classifying the monitoring data according to the digital twin model, and selecting targeted monitoring conditions for monitoring for each data set obtained by classification, the accuracy of the judgment results is improved.
在一个实施例中，如图3所示，S202具体包括如下步骤：In one embodiment, as shown in Figure 3, S202 specifically includes the following steps:
S302，通过数据集成获取与人体健康相关的原始监测数据。S302: Obtain original monitoring data related to human health through data integration.
其中，数据集成是把不同来源、格式、特点和性质的数据在逻辑上或物理上有机地集中在一起。数据集成方法包括联邦式集成方法、基于中间件模型的集成方法或者基于数据仓库的集成方法等。原始监测数据为未经清洗的监测数据，其中可能包括重复的或者错误的数据。Among them, data integration is to logically or physically bring together data from different sources, formats, characteristics and properties. Data integration methods include federated integration methods, integration methods based on middleware models, or integration methods based on data warehouses. Raw monitoring data is uncleaned monitoring data, which may include duplicate or erroneous data.
S304，对原始监测数据进行数据清洗，得到清洗后的原始监测数据。S304: Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data.
其中，数据清洗用于去除原始监测数据中的重复、错误数据。例如，如果数字孪生模型中字段A的第三行数据和字段A的第四行数据相同，则确定第四行数据为重复数据，服务器将第四行数据删除，以进行数据清洗。又例如，如果几何模型中的身高字段的值为180cm，而腿长字段的值为20cm，则腿长字段的值为错误数据，服务器对腿长字段进行数据清洗。Among them, data cleaning is used to remove duplicate and erroneous data in the original monitoring data. For example, if the third row of data in field A in the digital twin model is the same as the fourth row of data in field A, it is determined that the fourth row of data is duplicate data, and the server deletes the fourth row of data for data cleaning. For another example, if the value of the height field in the geometric model is 180cm, and the value of the leg length field is 20cm, then the value of the leg length field is incorrect data, and the server performs data cleaning on the leg length field.
在一个实施例中，S304具体包括：服务器通过运行SQL(Structured Query Language，结构化查询语言)脚本对原始监测数据进行数据清洗，得到清洗后的原始监测数据。In one embodiment, S304 specifically includes: the server performs data cleaning on the original monitoring data by running a SQL (Structured Query Language) script to obtain the cleaned original monitoring data.
S306，对清洗后的原始监测数据进行数据开发，得到开发数据。S306: Perform data development on the cleaned original monitoring data to obtain development data.
其中，数据开发是对数据进行处理以生成新的数据的过程。处理过程包括计算、***、合并或者拆分等。例如，对A数据字段和B数据字段进行数据开发可以是将A数据字段的值和B数据字段的值相加，得到C数据字段的值，所得到的C数据字段为开发数据。又例如，对A数据字段进行数据开发可以将A数据字段拆分为A1和A2两个数据字段，所得到的A1数据字段和A2数据字段为开发数据。Among them, data development is the process of processing data to generate new data. The processing process includes calculation, insertion, merging or splitting, etc. For example, performing data development on the A data field and the B data field may be to add the value of the A data field and the value of the B data field to obtain the value of the C data field, and the obtained C data field is the development data. For another example, data development for data field A can be performed by splitting data field A into two data fields, A1 and A2. The resulting A1 data field and A2 data field are development data.
S308，将清洗后的原始监测数据和开发数据组成监测数据。S308: Combine the cleaned original monitoring data and development data into monitoring data.
服务器将清洗后的原始监测数据和开发数据合并在一起，组成监测数据，使所得到的监测数据更加全面。The server merges the cleaned original monitoring data and development data to form monitoring data, making the obtained monitoring data more comprehensive.
上述实施例中，服务器通过数据集成获取与人体健康相关的原始监测数据，并对原始监测数据进行数据清洗，从而可以去除重复和错误的数据，提高了判断结果的准确性。然后对清洗后的原始监测数据进行数据开发，得到开发数据，从而使监测数据更加全面，进一步提高了判断结果的准确性。In the above embodiment, the server obtains original monitoring data related to human health through data integration, and performs data cleaning on the original monitoring data, thereby removing duplicate and erroneous data and improving the accuracy of the judgment results. Then, data development is performed on the cleaned original monitoring data to obtain development data, thereby making the monitoring data more comprehensive and further improving the accuracy of the judgment results.
在一个实施例中，S208具体包括：从首个目标监测条件开始，依次通过每个目标监测条件对监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个目标监测条件进行判断的判断结果。In one embodiment, S208 specifically includes: starting from the first target monitoring condition, judging the monitoring data through each target monitoring condition in turn, until the obtained judgment result is satisfied, or until the judgment is obtained through the last target monitoring condition. the judgment result.
服务器首先通过首个目标监测条件对监测数据进行判断，如果判断结果为满足，则将判断结果反馈到终端进行显示，如果判断结果为不满足，则通过下一个目标监测条件对监测数据进行判断，依次类推，直到得到的判断结果为满足，或者直到得到通过最后一个目标监测条件进行判断的判断结果。服务器自动通过多个目标监测条件对监测数据进行判断，可以实现对监测数据的***性监测，提高了监测的全面性。The server first judges the monitoring data through the first target monitoring condition. If the judgment result is satisfied, the judgment result is fed back to the terminal for display. If the judgment result is not satisfied, the monitoring data is judged through the next target monitoring condition. And so on, until the obtained judgment result is satisfied, or until the judgment result obtained is judged by the last target monitoring condition. The server automatically judges the monitoring data through multiple target monitoring conditions, which can realize systematic monitoring of monitoring data and improve the comprehensiveness of monitoring.
在一个实施例中，判断结果包括满足、不满足和无法判断；S208之后还包括：当判断结果为满足或者不满足时，将判断结果反馈至终端，以使终端对判断结果进行显示；当判断结果为无法判断时，优化数字孪生模型，并在对数字孪生模型进行优化后返回按照数字孪生模型对监测数据进行分类的步骤进行迭代，直到得到的判断结果为满足或者不满足。In one embodiment, the judgment results include satisfied, dissatisfied and unable to judge; after S208, it also includes: when the judgment result is satisfied or dissatisfied, feeding back the judgment result to the terminal so that the terminal displays the judgment result; when the judgment is made, When the result is that it cannot be judged, optimize the digital twin model, and after optimizing the digital twin model, return to the steps of classifying the monitoring data according to the digital twin model and iterate until the judgment result is satisfied or not satisfied.
其中，当判断结果为无法判断时，优化数字孪生模型。例如，几何模型中包括身高、肩宽、头围、大腿长和小腿长五个数据字段，则与几何模型对应的数据集合中的监测数据不包括体重值，若目标监测条件为体重是否达到预设体重值，则无法判断监测数据是否满足该目标监测条件，所得到的判断结果为“无法判断”，此时在几何模型中添加体重数据字段以对几何模型进行优化。然后，根据优化后的几何模型重新对监测数据进行分类，所得到的数据集合中将包括体重数据字段，从而可以判断体重值是否达到预设体重值，得到判断结果。Among them, when the judgment result is that it cannot be judged, the digital twin model is optimized. For example, if the geometric model includes five data fields: height, shoulder width, head circumference, thigh length, and calf length, then the monitoring data in the data set corresponding to the geometric model does not include weight values. If the target monitoring condition is whether the weight reaches the predetermined value, If the weight value is set, it cannot be judged whether the monitoring data meets the target monitoring conditions, and the obtained judgment result is "unable to judge". At this time, a weight data field is added to the geometric model to optimize the geometric model. Then, the monitoring data is reclassified according to the optimized geometric model, and the resulting data set will include a weight data field, so that it can be judged whether the weight value reaches the preset weight value and the judgment result is obtained.
在一个实施例中，如图4所示，目标监测条件为多个，服务器从首个目标监测条件开始，依次通过每个目标监测条件对监测数据进行判断，如果通过某个目标监测条件(例如，目标监测条件3)所得的判断结果为满足，则将判断结果反馈至终端进行显示；如果通过该目标监测条件所得的判断结果为不满足，则通过下一个目标监测条件对监测数据进行判断；如果通过所有目标监测条件所得的判断结果均为无法判断，则优化数字孪生模型，并在对数字孪生模型进行优化后返回按照数字孪生模型对监测数据进行分类的步骤进行迭代，直到得到的判断结果为满足或者不满足。In one embodiment, as shown in Figure 4, there are multiple target monitoring conditions. The server starts from the first target monitoring condition and judges the monitoring data through each target monitoring condition in turn. If it passes a certain target monitoring condition (for example, , if the judgment result obtained by the target monitoring condition 3) is satisfied, the judgment result will be fed back to the terminal for display; if the judgment result obtained by the target monitoring condition is not satisfied, the monitoring data will be judged by the next target monitoring condition; If the judgment results obtained by all target monitoring conditions are unable to judge, then optimize the digital twin model, and after optimizing the digital twin model, return to the steps of classifying monitoring data according to the digital twin model and iterate until the judgment result is obtained To be satisfied or dissatisfied.
上述实施例中，当判断结果为满足或者不满足时，服务器将判断结果反馈至终端，以使终端对判断结果进行显示；当判断结果为无法判断时，服务器优化数字孪生模型，并在对数字孪生模型进行优化后返回按照数字孪生模型对监测数据进行分类的步骤进行迭代，直到得到的判断结果为满足或者不满足。从而可以通过不断优化数字孪生模型，使判断结果更加准确的反映人体的健康状况，提高了判断结果的准确性。In the above embodiment, when the judgment result is satisfied or dissatisfied, the server feeds back the judgment result to the terminal so that the terminal displays the judgment result; when the judgment result is that it cannot be judged, the server optimizes the digital twin model and performs the digital twin model optimization. After the twin model is optimized, it returns to the steps of classifying the monitoring data according to the digital twin model and iterates until the obtained judgment result is satisfied or not satisfied. Therefore, by continuously optimizing the digital twin model, the judgment results can more accurately reflect the health status of the human body and improve the accuracy of the judgment results.
在一个实施例中，S208具体包括：通过预测模型对数据集合中的监测数据进行评分，得到分值；当分值大于或等于预设分值时，确定监测数据满足目标监测条件，得到判断结果为满足；当分值小于预设分值时，确定监测数据不满足目标监测条件，得到判断结果为不满足。In one embodiment, S208 specifically includes: scoring the monitoring data in the data set through a prediction model to obtain a score; when the score is greater than or equal to the preset score, determining that the monitoring data meets the target monitoring conditions and obtaining a judgment result. is satisfied; when the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is that it is not satisfied.
其中，预测模型是用于对监测数据进行评分的机器学习模型，可以是CNN(Convolutional Neural Networks，卷积神经网络)模型、DNN(Deep Neural Networks，深度神经网络)模型、ResNet(Residual Net，残差卷积神经网络)模型等。服务器将监测数据输入预测模型，通过预测模型对监测数据进行评分，得到分值，分值越高表示人体的健康风险越高。服务器可以设置目标监测条件为分值大于或等于预设分值，当分值大于或等于预设分值时，得到判断结果为满足；当分值小于预设分值时，得到判断结果为不满足。Among them, the prediction model is a machine learning model used to score monitoring data, which can be a CNN (Convolutional Neural Networks) model, a DNN (Deep Neural Networks) model, or a ResNet (Residual Net) model. Difference convolutional neural network) model, etc. The server inputs the monitoring data into the prediction model, scores the monitoring data through the prediction model, and obtains a score. The higher the score, the higher the health risk to the human body. The server can set the target monitoring condition as the score is greater than or equal to the preset score. When the score is greater than or equal to the preset score, the judgment result is satisfied; when the score is less than the preset score, the judgment result is not satisfied. satisfy.
上述实施例中，服务器通过预测模型对数据集合中的监测数据进行评分，得到分值；当分值大于或等于预设分值时，确定监测数据满足目标监测条件，得到判断结果为满足；当分值小于预设分值时，确定监测数据不满足目标监测条件，得到判断结果为不满足。从而服务器可以通过预测模型自动对监测数据进行评分，并根据评分得到判断结果，相比于人工对监测数据进行分析判断，提高了监测效率。In the above embodiment, the server scores the monitoring data in the data set through the prediction model to obtain a score; when the score is greater than or equal to the preset score, it is determined that the monitoring data meets the target monitoring conditions, and the judgment result is satisfied; when When the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is unsatisfied. As a result, the server can automatically score the monitoring data through the prediction model and obtain the judgment results based on the scores. Compared with manual analysis and judgment of the monitoring data, the monitoring efficiency is improved.
在一个实施例中，目标监测条件中包括至少两个监测子条件；S208具体包括：根据各监测子条件对数据集合中的监测数据进行评分，得到分值；对分值进行加权求和，得到总分值；当总分值大于或等于预设值时，确定监测数据满足目标监测条件；当总分值小于预设值时，确定监测数据不满足目标监测条件。In one embodiment, the target monitoring condition includes at least two monitoring sub-conditions; S208 specifically includes: scoring the monitoring data in the data set according to each monitoring sub-condition to obtain a score; performing a weighted summation of the scores to obtain Total score value; when the total score value is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the total score value is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions.
服务器根据各监测子条件对数据集合中的监测数据进行评分，得到分值。例如目标监测条件中包括三个监测子条件，三个监测子条件对应的权重值分别为0.2、0.3、0.5。服务器通过第一个监测子条件对监测数据进行评分，得到分值为30，通过第二个监测子条件对监测数据进行评分，得到分值为50，通过第三个监测子条件对监测数据进行评分，得到分值为45。服务器对各分值进行加权求和，得到总分值为0.2×30+0.3×50+0.5×45＝43.5。当总分值大于或等于预设值时，确定监测数据满足目标监测条件；当分值小于预设值时，确定监测数据不满足目标监测条件。The server scores the monitoring data in the data set according to each monitoring sub-condition and obtains a score. For example, the target monitoring condition includes three monitoring sub-conditions, and the weight values corresponding to the three monitoring sub-conditions are 0.2, 0.3, and 0.5 respectively. The server scores the monitoring data through the first monitoring sub-condition and gets a score of 30. It scores the monitoring data through the second monitoring sub-condition and gets a score of 50. It scores the monitoring data through the third monitoring sub-condition. Rating, the score is 45. The server performs a weighted sum of each score, and the total score is 0.2×30+0.3×50+0.5×45=43.5. When the total score is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the score is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions.
上述实施例中，服务器根据各监测子条件对数据集合中的监测数据进行评分，得到分值；对分值进行加权求和，得到总分值；当总分值大于或等于预设值时，确定监测数据满足目标监测条件；当总分值小于预设值时，确定监测数据不满足目标监测条件。从而服务器可以根据多个监测子条件对监测数据进行综合判断，提高了判断结果的准确性。In the above embodiment, the server scores the monitoring data in the data set according to each monitoring sub-condition to obtain a score; performs a weighted sum of the scores to obtain a total score; when the total score is greater than or equal to the preset value, It is determined that the monitoring data meets the target monitoring conditions; when the total score value is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions. As a result, the server can comprehensively judge the monitoring data based on multiple monitoring sub-conditions, thereby improving the accuracy of the judgment results.
在一个实施例中，如图5所示，数字孪生空间中包括多个数字孪生体，数字孪生体中的数据集成单元获取监控单元采集的各物理实体(人体)健康相关的原始监测数据，并将原始监测数据存储在各物理实体对应的物理空间。监控单元采集的原始监测数据包括可穿戴设备数据、第三方数据、诊疗过程数据、个人行为数据、LIS和HIS中的数据等。数字孪生体对原始监测数据进行数据清洗，并对清洗后的原始监测数据进行数据开发，得到开发数据。服务器将清洗后的原始监测数据和开发数据组成监测数据，并按照物理模型、几何模型、行为模型、生理模型和规则模型等对监测数据进行分类，得到物理模型数据集、几何模型数据集、行为模型数据集、生理模型数据集和规则模型数据集等。数字孪生体在候选监测条件中，选取每个数据集合对应的目标监测条件，判断数据集合中的监测数据是否满足目标监测条件，得到判断结果，并将判断结果反馈至终端进行显示。数字孪生体通过数据交换单元与其他数字孪生体进行安全可控的数据交换，通过服务单元向物理实体提供服务。数字孪生体中的数据安全单元用于进行数据安全管理，保障数字孪生体中数据的安全。In one embodiment, as shown in Figure 5, the digital twin space includes multiple digital twins. The data integration unit in the digital twin obtains the original monitoring data related to the health of each physical entity (human body) collected by the monitoring unit, and Store original monitoring data in the physical space corresponding to each physical entity. The original monitoring data collected by the monitoring unit includes wearable device data, third-party data, diagnosis and treatment process data, personal behavior data, data in LIS and HIS, etc. The digital twin performs data cleaning on the original monitoring data, and performs data development on the cleaned original monitoring data to obtain development data. The server combines the cleaned original monitoring data and development data into monitoring data, and classifies the monitoring data according to physical models, geometric models, behavioral models, physiological models and rule models to obtain physical model data sets, geometric model data sets, behavioral models, etc. Model data set, physiological model data set and rule model data set, etc. The digital twin selects the target monitoring conditions corresponding to each data set among the candidate monitoring conditions, determines whether the monitoring data in the data set meets the target monitoring conditions, obtains the judgment results, and feeds the judgment results back to the terminal for display. The digital twin conducts secure and controllable data exchange with other digital twins through the data exchange unit, and provides services to the physical entity through the service unit. The data security unit in the digital twin is used for data security management to ensure the security of data in the digital twin.
在一个实施例中，如图6所示，基于数字孪生的数据监测方法包括如下步骤：In one embodiment, as shown in Figure 6, the data monitoring method based on digital twins includes the following steps:
S602，通过数据集成获取与人体健康相关的原始监测数据。S602: Obtain original monitoring data related to human health through data integration.
S604，对原始监测数据进行数据清洗，得到清洗后的原始监测数据。S604: Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data.
S606，对清洗后的原始监测数据进行数据开发，得到开发数据。S606: Perform data development on the cleaned original monitoring data to obtain development data.
S608，将清洗后的原始监测数据和开发数据组成监测数据。S608: Combine the cleaned original monitoring data and development data into monitoring data.
S610，按照数字孪生模型对监测数据进行分类，得到至少两个数据集合；数字孪生模型是对人体进行 建模所形成的模型。S610: Classify the monitoring data according to the digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body.
S612，在候选监测条件中，选取每个数据集合对应的目标监测条件。S612: Select the target monitoring condition corresponding to each data set among the candidate monitoring conditions.
S614，从首个目标监测条件开始，依次通过每个目标监测条件对监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个目标监测条件进行判断的判断结果。S614: Starting from the first target monitoring condition, the monitoring data is judged by each target monitoring condition in sequence until the obtained judgment result is satisfied, or until the judgment result judged by the last target monitoring condition is obtained.
S616，当判断结果为满足或者不满足时，将判断结果反馈至终端，以使终端对判断结果进行显示。S616: When the judgment result is satisfied or not satisfied, the judgment result is fed back to the terminal so that the terminal displays the judgment result.
S618，当判断结果为无法判断时，优化数字孪生模型，并在对数字孪生模型进行优化后返回按照数字孪生模型对监测数据进行分类的步骤进行迭代，直到得到的判断结果为满足或者不满足。S618: When the judgment result is that it cannot be judged, optimize the digital twin model, and after optimizing the digital twin model, return to the steps of classifying the monitoring data according to the digital twin model to iterate until the obtained judgment result is satisfied or not satisfied.
上述S602至S618的具体内容可以参考上文所述的具体实现过程。For the specific contents of S602 to S618, please refer to the specific implementation process described above.
应该理解的是，虽然如上所述的各实施例所涉及的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，如上所述的各实施例所涉及的流程图中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or stages. These steps or stages are not necessarily executed at the same time, but may be completed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.
基于同样的发明构思，本申请实施例还提供了一种用于实现上述所涉及的基于数字孪生的数据监测方法的基于数字孪生的数据监测装置。该装置所提供的解决问题的实现方案与上述方法中所记载的实现方案相似，故下面所提供的一个或多个基于数字孪生的数据监测装置实施例中的具体限定可以参见上文中对于基于数字孪生的数据监测方法的限定，在此不再赘述。Based on the same inventive concept, embodiments of the present application also provide a digital twin-based data monitoring device for implementing the above-mentioned digital twin-based data monitoring method. The problem-solving solution provided by this device is similar to the solution recorded in the above method. Therefore, for the specific limitations in one or more digital twin-based data monitoring device embodiments provided below, please refer to the above for digital twin-based data monitoring device. The limitations of twin data monitoring methods will not be described again here.
在一个实施例中，如图7所示，提供了一种基于数字孪生的数据监测装置，包括：获取模块702、分类模块704、选取模块706和判断模块708，其中：In one embodiment, as shown in Figure 7, a data monitoring device based on digital twins is provided, including: an acquisition module 702, a classification module 704, a selection module 706 and a judgment module 708, wherein:
获取模块702，用于获取与人体健康相关的监测数据；The acquisition module 702 is used to acquire monitoring data related to human health;
分类模块704，用于按照数字孪生模型对监测数据进行分类，得到至少两个数据集合；数字孪生模型是对人体进行建模所形成的模型；The classification module 704 is used to classify the monitoring data according to the digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body;
选取模块706，用于在候选监测条件中，选取每个数据集合对应的目标监测条件；The selection module 706 is used to select the target monitoring condition corresponding to each data set among the candidate monitoring conditions;
判断模块708，用于判断数据集合中的监测数据是否满足目标监测条件，得到判断结果，并将判断结果反馈至终端进行显示。The judgment module 708 is used to judge whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment result, and feed the judgment result back to the terminal for display.
上述实施例中，获取与人体健康相关的监测数据，按照对人体进行建模所形成的数字孪生模型对监测数据进行分类，得到至少两个数据集合。在候选监测条件中，选取每个数据集合对应的目标监测条件。判断数据集合中的监测数据是否满足目标监测条件，得到判断结果，并将判断结果反馈至终端进行显示。从而可以通过设置的监测条件自动对监测数据进行判断，相比于人工对监测数据进行分析判断，提高了监测效率。并且，通过按照数字孪生模型对监测数据进行分类，并针对分类所得的每一数据集合有针对性的选取目标监测条件进行监测，提高了判断结果的准确性。In the above embodiment, monitoring data related to human health is obtained, and the monitoring data is classified according to a digital twin model formed by modeling the human body to obtain at least two data sets. Among the candidate monitoring conditions, select the target monitoring conditions corresponding to each data set. Determine whether the monitoring data in the data set meets the target monitoring conditions, obtain the judgment results, and feed back the judgment results to the terminal for display. As a result, the monitoring data can be automatically judged according to the set monitoring conditions, which improves monitoring efficiency compared to manual analysis and judgment of monitoring data. Moreover, by classifying the monitoring data according to the digital twin model, and selecting targeted monitoring conditions for monitoring for each data set obtained by classification, the accuracy of the judgment results is improved.
在一个实施例中，获取模块702，还用于：In one embodiment, the acquisition module 702 is also used to:
通过数据集成获取与人体健康相关的原始监测数据；Obtain original monitoring data related to human health through data integration;
对原始监测数据进行数据清洗，得到清洗后的原始监测数据；Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data;
对清洗后的原始监测数据进行数据开发，得到开发数据；Perform data development on the cleaned original monitoring data to obtain development data;
将清洗后的原始监测数据和开发数据组成监测数据。The cleaned original monitoring data and development data are combined into monitoring data.
在一个实施例中，判断结果包括满足、不满足和无法判断；判断模块708还用于：In one embodiment, the judgment results include satisfied, dissatisfied and unable to judge; the judgment module 708 is also used to:
当判断结果为满足或者不满足时，将判断结果反馈至终端，以使终端对判断结果进行显示；When the judgment result is satisfied or not satisfied, the judgment result is fed back to the terminal so that the terminal displays the judgment result;
当判断结果为无法判断时，优化数字孪生模型，并在对数字孪生模型进行优化后返回按照数字孪生模型对监测数据进行分类的步骤进行迭代，直到得到的判断结果为满足或者不满足。When the judgment result is that it cannot be judged, optimize the digital twin model, and after optimizing the digital twin model, return to the steps of classifying the monitoring data according to the digital twin model and iterate until the judgment result is satisfied or not satisfied.
在一个实施例中，判断模块708，还用于：In one embodiment, the judgment module 708 is also used to:
从首个目标监测条件开始，依次通过每个目标监测条件对监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个目标监测条件进行判断的判断结果。Starting from the first target monitoring condition, the monitoring data is judged by each target monitoring condition in turn until the judgment result obtained is satisfied, or until the judgment result judged by the last target monitoring condition is obtained.
在一个实施例中，判断模块708，还用于：In one embodiment, the judgment module 708 is also used to:
通过预测模型对数据集合中的监测数据进行评分，得到分值；Score the monitoring data in the data set through the prediction model to obtain a score;
当分值大于或等于预设分值时，确定监测数据满足目标监测条件，得到判断结果为满足；When the score is greater than or equal to the preset score, it is determined that the monitoring data meets the target monitoring conditions, and the judgment result is that it is satisfied;
当分值小于预设分值时，确定监测数据不满足目标监测条件，得到判断结果为不满足。When the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is unsatisfied.
在一个实施例中，目标监测条件中包括至少两个监测子条件；判断模块708，还用于：In one embodiment, the target monitoring condition includes at least two monitoring sub-conditions; the judgment module 708 is also used to:
根据各监测子条件对数据集合中的监测数据进行评分，得到分值；Score the monitoring data in the data set according to each monitoring sub-condition to obtain a score;
对分值进行加权求和，得到总分值；Perform a weighted sum of the scores to obtain the total score;
当总分值大于或等于预设值时，确定监测数据满足目标监测条件；When the total score value is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions;
当总分值小于预设值时，确定监测数据不满足目标监测条件。When the total score value is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions.
上述基于数字孪生的数据监测装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。Each module in the above-mentioned digital twin-based data monitoring device can be implemented in whole or in part through software, hardware, and combinations thereof. Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may 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.
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图8所示。该计算机设备包括通过***总线连接的处理器、存储器和网络接口。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质和内存储器。该非易失性存储介质存储有操作***、计算机程序和数据库。该内存储器为非易失性存储介质中的操作***和计算机程序的运行提供环境。该计算机设备的数据库用于存储数据监测数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种基于数字孪生的数据监测方法。In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be shown in Figure 8 . The computer device includes a processor, memory, and network interfaces connected through a system bus. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The computer device's database is used to store data monitoring data. The network interface of the computer device is used to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a data monitoring method based on digital twins.
本领域技术人员可以理解，图8中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。Those skilled in the art can understand that the structure shown in Figure 8 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.
在一个实施例中，提供了一种计算机设备，包括存储器和处理器，存储器中存储有计算机程序，该处理器执行计算机程序时实现以下步骤：获取与人体健康相关的监测数据；按照数字孪生模型对监测数据进行分类，得到至少两个数据集合；数字孪生模型是对人体进行建模所形成的模型；在候选监测条件中，选取每个数据集合对应的目标监测条件；判断数据集合中的监测数据是否满足目标监测条件，得到判断结果， 并将判断结果反馈至终端进行显示。In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements the following steps: obtaining monitoring data related to human health; and following the digital twin model. Classify the monitoring data to obtain at least two data sets; the digital twin model is a model formed by modeling the human body; among the candidate monitoring conditions, select the target monitoring conditions corresponding to each data set; determine the monitoring conditions in the data set Whether the data meets the target monitoring conditions, the judgment result is obtained, and the judgment result is fed back to the terminal for display.
在一个实施例中，处理器执行计算机程序时还实现以下步骤：通过数据集成获取与人体健康相关的原始监测数据；对原始监测数据进行数据清洗，得到清洗后的原始监测数据；对清洗后的原始监测数据进行数据开发，得到开发数据；将清洗后的原始监测数据和开发数据组成监测数据。In one embodiment, the processor also implements the following steps when executing the computer program: obtaining original monitoring data related to human health through data integration; performing data cleaning on the original monitoring data to obtain cleaned original monitoring data; The original monitoring data is developed for data development to obtain development data; the cleaned original monitoring data and development data are combined into monitoring data.
在一个实施例中，判断结果包括满足、不满足和无法判断；处理器执行计算机程序时还实现以下步骤：当判断结果为满足或者不满足时，将判断结果反馈至终端，以使终端对判断结果进行显示；当判断结果为无法判断时，优化数字孪生模型，并在对数字孪生模型进行优化后返回按照数字孪生模型对监测数据进行分类的步骤进行迭代，直到得到的判断结果为满足或者不满足。In one embodiment, the judgment results include satisfied, dissatisfied and unable to judge; when the processor executes the computer program, the following steps are also implemented: when the judgment result is satisfied or dissatisfied, the judgment result is fed back to the terminal so that the terminal can make the judgment The results are displayed; when the judgment result is that it cannot be judged, the digital twin model is optimized, and after optimizing the digital twin model, the steps of classifying the monitoring data according to the digital twin model are returned to iterate until the judgment result is satisfied or not. satisfy.
在一个实施例中，处理器执行计算机程序时还实现以下步骤：从首个目标监测条件开始，依次通过每个目标监测条件对监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个目标监测条件进行判断的判断结果。In one embodiment, when the processor executes the computer program, it also implements the following steps: starting from the first target monitoring condition, judging the monitoring data through each target monitoring condition in turn, until the obtained judgment result is satisfied, or until the obtained result is passed The judgment result of the last target monitoring condition is judged.
在一个实施例中，处理器执行计算机程序时还实现以下步骤：通过预测模型对数据集合中的监测数据进行评分，得到分值；当分值大于或等于预设分值时，确定监测数据满足目标监测条件，得到判断结果为满足；当分值小于预设分值时，确定监测数据不满足目标监测条件，得到判断结果为不满足。In one embodiment, the processor also implements the following steps when executing the computer program: scoring the monitoring data in the data set through a prediction model to obtain a score; when the score is greater than or equal to the preset score, determining that the monitoring data satisfies Target monitoring conditions, the judgment result is satisfied; when the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is not satisfied.
在一个实施例中，目标监测条件中包括至少两个监测子条件；处理器执行计算机程序时还实现以下步骤：根据各监测子条件对数据集合中的监测数据进行评分，得到分值；对分值进行加权求和，得到总分值；当总分值大于或等于预设值时，确定监测数据满足目标监测条件；当总分值小于预设值时，确定监测数据不满足目标监测条件。In one embodiment, the target monitoring condition includes at least two monitoring sub-conditions; when the processor executes the computer program, it also implements the following steps: scoring the monitoring data in the data set according to each monitoring sub-condition to obtain a score; The values are weighted and summed to obtain the total score; when the total score is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the total score is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions.
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现以下步骤：获取与人体健康相关的监测数据；按照数字孪生模型对监测数据进行分类，得到至少两个数据集合；数字孪生模型是对人体进行建模所形成的模型；在候选监测条件中，选取每个数据集合对应的目标监测条件；判断数据集合中的监测数据是否满足目标监测条件，得到判断结果，并将判断结果反馈至终端进行显示。In one embodiment, a computer-readable storage medium is provided, with a computer program stored thereon. When the computer program is executed by a processor, the following steps are implemented: obtaining monitoring data related to human health; and analyzing the monitoring data according to a digital twin model. Classify and obtain at least two data sets; the digital twin model is a model formed by modeling the human body; among the candidate monitoring conditions, select the target monitoring conditions corresponding to each data set; determine whether the monitoring data in the data set meets The target monitors the conditions, obtains the judgment results, and feeds the judgment results back to the terminal for display.
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：通过数据集成获取与人体健康相关的原始监测数据；对原始监测数据进行数据清洗，得到清洗后的原始监测数据；对清洗后的原始监测数据进行数据开发，得到开发数据；将清洗后的原始监测数据和开发数据组成监测数据。In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining original monitoring data related to human health through data integration; performing data cleaning on the original monitoring data to obtain cleaned original monitoring data; Carry out data development on the original monitoring data to obtain development data; combine the cleaned original monitoring data and development data to form monitoring data.
在一个实施例中，判断结果包括满足、不满足和无法判断；计算机程序被处理器执行时还实现以下步骤：当判断结果为满足或者不满足时，将判断结果反馈至终端，以使终端对判断结果进行显示；当判断结果为无法判断时，优化数字孪生模型，并在对数字孪生模型进行优化后返回按照数字孪生模型对监测数据进行分类的步骤进行迭代，直到得到的判断结果为满足或者不满足。In one embodiment, the judgment result includes satisfaction, dissatisfaction and inability to judge; when the computer program is executed by the processor, the following steps are also implemented: when the judgment result is satisfied or dissatisfied, the judgment result is fed back to the terminal so that the terminal The judgment result is displayed; when the judgment result is that it cannot be judged, the digital twin model is optimized, and after optimizing the digital twin model, the steps of classifying the monitoring data according to the digital twin model are returned to iterate until the judgment result is satisfied or Not satisfied.
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：从首个目标监测条件开始，依次通过每个目标监测条件对监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个目标监测条件进行判断的判断结果。In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: starting from the first target monitoring condition, judging the monitoring data through each target monitoring condition in sequence until the obtained judgment result is satisfied, or until the obtained The judgment result based on the last target monitoring condition.
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：通过预测模型对数据集合中的监测数据进行评分，得到分值；当分值大于或等于预设分值时，确定监测数据满足目标监测条件，得到判断结果 为满足；当分值小于预设分值时，确定监测数据不满足目标监测条件，得到判断结果为不满足。In one embodiment, when the computer program is executed by the processor, it also implements the following steps: scoring the monitoring data in the data set through a prediction model to obtain a score; when the score is greater than or equal to the preset score, determining the monitoring data If the target monitoring conditions are met, the judgment result is satisfied; when the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is dissatisfied.
在一个实施例中，目标监测条件中包括至少两个监测子条件；计算机程序被处理器执行时还实现以下步骤：根据各监测子条件对数据集合中的监测数据进行评分，得到分值；对分值进行加权求和，得到总分值；当总分值大于或等于预设值时，确定监测数据满足目标监测条件；当总分值小于预设值时，确定监测数据不满足目标监测条件。In one embodiment, the target monitoring condition includes at least two monitoring sub-conditions; when executed by the processor, the computer program also implements the following steps: scoring the monitoring data in the data set according to each monitoring sub-condition to obtain a score; The scores are weighted and summed to obtain the total score; when the total score is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the total score is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions .
在一个实施例中，提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现以下步骤：获取与人体健康相关的监测数据；按照数字孪生模型对监测数据进行分类，得到至少两个数据集合；数字孪生模型是对人体进行建模所形成的模型；在候选监测条件中，选取每个数据集合对应的目标监测条件；判断数据集合中的监测数据是否满足目标监测条件，得到判断结果，并将判断结果反馈至终端进行显示。In one embodiment, a computer program product is provided, including a computer program. When executed by a processor, the computer program implements the following steps: acquiring monitoring data related to human health; classifying the monitoring data according to a digital twin model to obtain At least two data sets; the digital twin model is a model formed by modeling the human body; among the candidate monitoring conditions, select the target monitoring conditions corresponding to each data set; determine whether the monitoring data in the data set meets the target monitoring conditions, Obtain the judgment result and feed it back to the terminal for display.
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：通过数据集成获取与人体健康相关的原始监测数据；对原始监测数据进行数据清洗，得到清洗后的原始监测数据；对清洗后的原始监测数据进行数据开发，得到开发数据；将清洗后的原始监测数据和开发数据组成监测数据。In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining original monitoring data related to human health through data integration; performing data cleaning on the original monitoring data to obtain cleaned original monitoring data; Carry out data development on the original monitoring data to obtain development data; combine the cleaned original monitoring data and development data to form monitoring data.
在一个实施例中，判断结果包括满足、不满足和无法判断；计算机程序被处理器执行时还实现以下步骤：当判断结果为满足或者不满足时，将判断结果反馈至终端，以使终端对判断结果进行显示；当判断结果为无法判断时，优化数字孪生模型，并在对数字孪生模型进行优化后返回按照数字孪生模型对监测数据进行分类的步骤进行迭代，直到得到的判断结果为满足或者不满足。In one embodiment, the judgment result includes satisfaction, dissatisfaction and inability to judge; when the computer program is executed by the processor, the following steps are also implemented: when the judgment result is satisfied or dissatisfied, the judgment result is fed back to the terminal so that the terminal The judgment result is displayed; when the judgment result is that it cannot be judged, the digital twin model is optimized, and after optimizing the digital twin model, the steps of classifying the monitoring data according to the digital twin model are returned to iterate until the judgment result is satisfied or Not satisfied.
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：从首个目标监测条件开始，依次通过每个目标监测条件对监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个目标监测条件进行判断的判断结果。In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: starting from the first target monitoring condition, judging the monitoring data through each target monitoring condition in sequence until the obtained judgment result is satisfied, or until the obtained The judgment result based on the last target monitoring condition.
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：通过预测模型对数据集合中的监测数据进行评分，得到分值；当分值大于或等于预设分值时，确定监测数据满足目标监测条件，得到判断结果为满足；当分值小于预设分值时，确定监测数据不满足目标监测条件，得到判断结果为不满足。In one embodiment, when the computer program is executed by the processor, it also implements the following steps: scoring the monitoring data in the data set through a prediction model to obtain a score; when the score is greater than or equal to the preset score, determining the monitoring data If the target monitoring conditions are met, the judgment result is satisfied; when the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring conditions, and the judgment result is dissatisfied.
在一个实施例中，目标监测条件中包括至少两个监测子条件；计算机程序被处理器执行时还实现以下步骤：根据各监测子条件对数据集合中的监测数据进行评分，得到分值；对分值进行加权求和，得到总分值；当总分值大于或等于预设值时，确定监测数据满足目标监测条件；当总分值小于预设值时，确定监测数据不满足目标监测条件。In one embodiment, the target monitoring condition includes at least two monitoring sub-conditions; when executed by the processor, the computer program also implements the following steps: scoring the monitoring data in the data set according to each monitoring sub-condition to obtain a score; The scores are weighted and summed to obtain the total score; when the total score is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring conditions; when the total score is less than the preset value, it is determined that the monitoring data does not meet the target monitoring conditions .
需要说明的是，本申请所涉及的用户信息(包括但不限于用户设备信息、用户个人信息等)和数据(包括但不限于用于分析的数据、存储的数据、展示的数据等)，均为经用户授权或者经过各方充分授权的信息和数据。It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all It is information and data authorized by the user or fully authorized by all parties.
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、数据库或其它介质的任何引用，均可包括非易失性和易失性存储器中的至少一种。非易失性存储器可包括只读存储器(Read-Only Memory，ROM)、磁带、软盘、闪存、光存储器、高密度嵌入式非易失性存储器、 阻变存储器(ReRAM)、磁变存储器(Magnetoresistive Random Access Memory，MRAM)、铁电存储器(Ferroelectric Random Access Memory，FRAM)、相变存储器(Phase Change Memory，PCM)、石墨烯存储器等。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或外部高速缓冲存储器等。作为说明而非局限，RAM可以是多种形式，比如静态随机存取存储器(Static Random Access Memory，SRAM)或动态随机存取存储器(Dynamic Random Access Memory，DRAM)等。本申请所提供的各实施例中所涉及的数据库可包括关系型数据库和非关系型数据库中至少一种。非关系型数据库可包括基于区块链的分布式数据库等，不限于此。本申请所提供的各实施例中所涉及的处理器可为通用处理器、中央处理器、图形处理器、数字信号处理器、可编程逻辑器、基于量子计算的数据处理逻辑器等，不限于此。Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage. In the media, when executed, the computer program may include the processes of the above method embodiments. Any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory (MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in many forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include blockchain-based distributed databases, etc., but are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to this.
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。The technical features of the above embodiments can be combined in any way. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, all possible combinations should be used. It is considered to be within the scope of this manual.
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本申请专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请的保护范围应以所附权利要求为准。The above-described embodiments only express several implementation modes of the present application, and their descriptions are relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all fall within the protection scope of the present application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims (20)

  1. 一种基于数字孪生的数据监测方法，其特征在于，所述方法包括：A data monitoring method based on digital twins, characterized in that the method includes:
    获取与人体健康相关的监测数据；Obtain monitoring data related to human health;
    按照数字孪生模型对所述监测数据进行分类，得到至少两个数据集合；所述数字孪生模型是对人体进行建模所形成的模型；Classify the monitoring data according to a digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body;
    在候选监测条件中，选取每个所述数据集合对应的目标监测条件；Among the candidate monitoring conditions, select the target monitoring condition corresponding to each of the data sets;
    判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果，并将所述判断结果反馈至终端进行显示。Determine whether the monitoring data in the data set meets the target monitoring condition, obtain a judgment result, and feed the judgment result back to the terminal for display.
  2. 根据权利要求1所述的方法，其特征在于，所述获取与人体健康相关的监测数据包括：The method according to claim 1, characterized in that said obtaining monitoring data related to human health includes:
    通过数据集成获取与人体健康相关的原始监测数据；Obtain original monitoring data related to human health through data integration;
    对所述原始监测数据进行数据清洗，得到清洗后的所述原始监测数据；Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data;
    对清洗后的所述原始监测数据进行数据开发，得到开发数据；Perform data development on the cleaned original monitoring data to obtain development data;
    将清洗后的所述原始监测数据和所述开发数据组成所述监测数据。The cleaned original monitoring data and the development data are combined into the monitoring data.
  3. 根据权利要求1所述的方法，其特征在于，所述判断结果包括满足、不满足和无法判断；所述方法还包括：The method according to claim 1, characterized in that the judgment results include satisfied, dissatisfied and unable to judge; the method further includes:
    当所述判断结果为满足或者不满足时，将所述判断结果反馈至终端，以使所述终端对所述判断结果进行显示；When the judgment result is satisfied or not satisfied, the judgment result is fed back to the terminal so that the terminal displays the judgment result;
    当所述判断结果为无法判断时，优化所述数字孪生模型，并在对所述数字孪生模型进行优化后返回所述按照数字孪生模型对所述监测数据进行分类的步骤进行迭代，直到得到的所述判断结果为满足或者不满足。When the judgment result is that it cannot be judged, optimize the digital twin model, and after optimizing the digital twin model, return to the step of classifying the monitoring data according to the digital twin model and iterate until the obtained The judgment result is satisfied or not satisfied.
  4. 根据权利要求1所述的方法，其特征在于，所述判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果包括：The method of claim 1, wherein determining whether the monitoring data in the data set satisfies the target monitoring condition and obtaining the determination result includes:
    从首个所述目标监测条件开始，依次通过每个所述目标监测条件对所述监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个所述目标监测条件进行判断的判断结果。Starting from the first target monitoring condition, the monitoring data is judged by each target monitoring condition in turn until the obtained judgment result is satisfied, or until the judgment is obtained based on the last target monitoring condition. result.
  5. 根据权利要求1所述的方法，其特征在于，所述判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果包括：The method of claim 1, wherein determining whether the monitoring data in the data set satisfies the target monitoring condition and obtaining the determination result includes:
    通过预测模型对所述数据集合中的监测数据进行评分，得到分值；Score the monitoring data in the data set through a prediction model to obtain a score;
    当所述分值大于或等于预设分值时，确定所述监测数据满足所述目标监测条件，得到判断结果为满足；When the score is greater than or equal to the preset score, it is determined that the monitoring data satisfies the target monitoring condition, and the judgment result is that it is satisfied;
    当所述分值小于所述预设分值时，确定所述监测数据不满足所述目标监测条件，得到所述判断结果为不满足。When the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring condition, and the judgment result is obtained as dissatisfaction.
  6. 根据权利要求1所述的方法，其特征在于，所述目标监测条件中包括至少两个监测子条件；所述判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果包括：The method according to claim 1, characterized in that the target monitoring condition includes at least two monitoring sub-conditions; the judgment of whether the monitoring data in the data set satisfies the target monitoring condition, and the judgment result includes: :
    根据各所述监测子条件对所述数据集合中的监测数据进行评分，得到分值；Score the monitoring data in the data set according to each of the monitoring sub-conditions to obtain a score;
    对所述分值进行加权求和，得到总分值；Perform a weighted sum of the scores to obtain a total score;
    当所述总分值大于或等于预设值时，确定所述监测数据满足所述目标监测条件；When the total score value is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring condition;
    当所述总分值小于所述预设值时，确定所述监测数据不满足所述目标监测条件。When the total score value is less than the preset value, it is determined that the monitoring data does not meet the target monitoring condition.
  7. 一种基于数字孪生的数据监测装置，其特征在于，所述装置包括：A data monitoring device based on digital twins, characterized in that the device includes:
    获取模块，用于获取与人体健康相关的监测数据；The acquisition module is used to acquire monitoring data related to human health;
    分类模块，用于按照数字孪生模型对所述监测数据进行分类，得到至少两个数据集合；所述数字孪生模型是对人体进行建模所形成的模型；A classification module, used to classify the monitoring data according to a digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body;
    选取模块，用于在候选监测条件中，选取每个所述数据集合对应的目标监测条件；A selection module for selecting target monitoring conditions corresponding to each of the data sets among the candidate monitoring conditions;
    判断模块，用于判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果，并将所述判断结果反馈至终端进行显示。A judgment module is used to judge whether the monitoring data in the data set meets the target monitoring conditions, obtain a judgment result, and feed back the judgment result to the terminal for display.
  8. 根据权利要求7所述的装置，其特征在于，所述获取模块，还用于：The device according to claim 7, characterized in that the acquisition module is also used to:
    通过数据集成获取与人体健康相关的原始监测数据；Obtain original monitoring data related to human health through data integration;
    对所述原始监测数据进行数据清洗，得到清洗后的所述原始监测数据；Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data;
    对清洗后的所述原始监测数据进行数据开发，得到开发数据；Perform data development on the cleaned original monitoring data to obtain development data;
    将清洗后的所述原始监测数据和所述开发数据组成所述监测数据。The cleaned original monitoring data and the development data are combined into the monitoring data.
  9. 根据权利要求7所述的装置，其特征在于，所述判断结果包括满足、不满足和无法判断；所述判断模块，还用于：The device according to claim 7, characterized in that the judgment results include satisfied, dissatisfied and unable to judge; the judgment module is also used to:
    当所述判断结果为满足或者不满足时，将所述判断结果反馈至终端，以使所述终端对所述判断结果进行显示；When the judgment result is satisfied or not satisfied, the judgment result is fed back to the terminal so that the terminal displays the judgment result;
    当所述判断结果为无法判断时，优化所述数字孪生模型，并在对所述数字孪生模型进行优化后返回所述按照数字孪生模型对所述监测数据进行分类的步骤进行迭代，直到得到的所述判断结果为满足或者不满足。When the judgment result is that it cannot be judged, optimize the digital twin model, and after optimizing the digital twin model, return to the step of classifying the monitoring data according to the digital twin model and iterate until the obtained The judgment result is satisfied or not satisfied.
  10. 根据权利要求7所述的装置，其特征在于，所述判断模块，还用于：The device according to claim 7, characterized in that the judgment module is also used to:
    从首个所述目标监测条件开始，依次通过每个所述目标监测条件对所述监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个所述目标监测条件进行判断的判断结果。Starting from the first target monitoring condition, the monitoring data is judged by each target monitoring condition in turn until the obtained judgment result is satisfied, or until the judgment is obtained based on the last target monitoring condition. result.
  11. 根据权利要求7所述的装置，其特征在于，所述判断模块，还用于：The device according to claim 7, characterized in that the judgment module is also used to:
    通过预测模型对所述数据集合中的监测数据进行评分，得到分值；Score the monitoring data in the data set through a prediction model to obtain a score;
    当所述分值大于或等于预设分值时，确定所述监测数据满足所述目标监测条件，得到判断结果为满足；When the score is greater than or equal to the preset score, it is determined that the monitoring data satisfies the target monitoring condition, and the judgment result is that it is satisfied;
    当所述分值小于所述预设分值时，确定所述监测数据不满足所述目标监测条件，得到所述判断结果为不满足。When the score is less than the preset score, it is determined that the monitoring data does not meet the target monitoring condition, and the judgment result is obtained as dissatisfaction.
  12. 根据权利要求7所述的装置，其特征在于，所述目标监测条件中包括至少两个监测子条件；所述判断模块，还用于：The device according to claim 7, characterized in that the target monitoring condition includes at least two monitoring sub-conditions; the judgment module is also used to:
    根据各所述监测子条件对所述数据集合中的监测数据进行评分，得到分值；Score the monitoring data in the data set according to each of the monitoring sub-conditions to obtain a score;
    对所述分值进行加权求和，得到总分值；Perform a weighted sum of the scores to obtain a total score;
    当所述总分值大于或等于预设值时，确定所述监测数据满足所述目标监测条件；When the total score value is greater than or equal to the preset value, it is determined that the monitoring data meets the target monitoring condition;
    当所述总分值小于所述预设值时，确定所述监测数据不满足所述目标监测条件。When the total score value is less than the preset value, it is determined that the monitoring data does not meet the target monitoring condition.
  13. 一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，其特征在于，所述处理器执行所述计算机程序时实现以下步骤：A computer device includes a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, it implements the following steps:
    获取与人体健康相关的监测数据；Obtain monitoring data related to human health;
    按照数字孪生模型对所述监测数据进行分类，得到至少两个数据集合；所述数字孪生模型是对人体进行建模所形成的模型；Classify the monitoring data according to a digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body;
    在候选监测条件中，选取每个所述数据集合对应的目标监测条件；Among the candidate monitoring conditions, select the target monitoring condition corresponding to each of the data sets;
    判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果，并将所述判断结果反馈至终端进行显示。Determine whether the monitoring data in the data set meets the target monitoring condition, obtain a judgment result, and feed the judgment result back to the terminal for display.
  14. 根据权利要求13所述的计算机设备，其特征在于，所述处理器执行所述计算机程序时还实现以下步骤：The computer device according to claim 13, characterized in that when the processor executes the computer program, it also implements the following steps:
    通过数据集成获取与人体健康相关的原始监测数据；Obtain original monitoring data related to human health through data integration;
    对所述原始监测数据进行数据清洗，得到清洗后的所述原始监测数据；Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data;
    对清洗后的所述原始监测数据进行数据开发，得到开发数据；Perform data development on the cleaned original monitoring data to obtain development data;
    将清洗后的所述原始监测数据和所述开发数据组成所述监测数据。The cleaned original monitoring data and the development data are combined into the monitoring data.
  15. 根据权利要求13所述的计算机设备，其特征在于，所述判断结果包括满足、不满足和无法判断；所述处理器执行所述计算机程序时还实现以下步骤：The computer device according to claim 13, characterized in that the judgment results include satisfied, dissatisfied and unable to judge; when the processor executes the computer program, it also implements the following steps:
    当所述判断结果为满足或者不满足时，将所述判断结果反馈至终端，以使所述终端对所述判断结果进行显示；When the judgment result is satisfied or not satisfied, the judgment result is fed back to the terminal so that the terminal displays the judgment result;
    当所述判断结果为无法判断时，优化所述数字孪生模型，并在对所述数字孪生模型进行优化后返回所述按照数字孪生模型对所述监测数据进行分类的步骤进行迭代，直到得到的所述判断结果为满足或者不满足。When the judgment result is that it cannot be judged, optimize the digital twin model, and after optimizing the digital twin model, return to the step of classifying the monitoring data according to the digital twin model and iterate until the obtained The judgment result is satisfied or not satisfied.
  16. 根据权利要求13所述的计算机设备，其特征在于，所述处理器执行所述计算机程序时还实现以下步骤：The computer device according to claim 13, characterized in that when the processor executes the computer program, it also implements the following steps:
    从首个所述目标监测条件开始，依次通过每个所述目标监测条件对所述监测数据进行判断，直到得到的判断结果为满足，或者直到得到通过最后一个所述目标监测条件进行判断的判断结果。Starting from the first target monitoring condition, the monitoring data is judged by each target monitoring condition in turn until the obtained judgment result is satisfied, or until the judgment is obtained based on the last target monitoring condition. result.
  17. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现以下步骤：A computer-readable storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, the following steps are implemented:
    获取与人体健康相关的监测数据；Obtain monitoring data related to human health;
    按照数字孪生模型对所述监测数据进行分类，得到至少两个数据集合；所述数字孪生模型是对人体进行建模所形成的模型；Classify the monitoring data according to a digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body;
    在候选监测条件中，选取每个所述数据集合对应的目标监测条件；Among the candidate monitoring conditions, select the target monitoring condition corresponding to each of the data sets;
    判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果，并将所述判断结果反馈至终端进行显示。Determine whether the monitoring data in the data set meets the target monitoring condition, obtain a judgment result, and feed the judgment result back to the terminal for display.
  18. 根据权利要求17所述的存储介质，所述计算机程序被所述处理器执行时还实现以下步骤：According to the storage medium of claim 17, when the computer program is executed by the processor, it also implements the following steps:
    通过数据集成获取与人体健康相关的原始监测数据；Obtain original monitoring data related to human health through data integration;
    对所述原始监测数据进行数据清洗，得到清洗后的所述原始监测数据；Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data;
    对清洗后的所述原始监测数据进行数据开发，得到开发数据；Perform data development on the cleaned original monitoring data to obtain development data;
    将清洗后的所述原始监测数据和所述开发数据组成所述监测数据。The cleaned original monitoring data and the development data are combined into the monitoring data.
  19. 一种计算机程序产品，包括计算机程序，其特征在于，所述计算机程序被处理器执行时实现以下 步骤：A computer program product, including a computer program, characterized in that the computer program implements the following steps when executed by a processor:
    获取与人体健康相关的监测数据；Obtain monitoring data related to human health;
    按照数字孪生模型对所述监测数据进行分类，得到至少两个数据集合；所述数字孪生模型是对人体进行建模所形成的模型；Classify the monitoring data according to a digital twin model to obtain at least two data sets; the digital twin model is a model formed by modeling the human body;
    在候选监测条件中，选取每个所述数据集合对应的目标监测条件；Among the candidate monitoring conditions, select the target monitoring condition corresponding to each of the data sets;
    判断所述数据集合中的监测数据是否满足所述目标监测条件，得到判断结果，并将所述判断结果反馈至终端进行显示。Determine whether the monitoring data in the data set meets the target monitoring condition, obtain a judgment result, and feed the judgment result back to the terminal for display.
  20. 根据权利要求19所述的计算机程序产品，其特征在于，所述计算机程序被所述处理器执行时还实现以下步骤：The computer program product according to claim 19, characterized in that when the computer program is executed by the processor, it also implements the following steps:
    通过数据集成获取与人体健康相关的原始监测数据；Obtain original monitoring data related to human health through data integration;
    对所述原始监测数据进行数据清洗，得到清洗后的所述原始监测数据；Perform data cleaning on the original monitoring data to obtain the cleaned original monitoring data;
    对清洗后的所述原始监测数据进行数据开发，得到开发数据；Perform data development on the cleaned original monitoring data to obtain development data;
    将清洗后的所述原始监测数据和所述开发数据组成所述监测数据。The cleaned original monitoring data and the development data are combined into the monitoring data.
PCT/CN2022/096644 2022-05-06 2022-06-01 Digital-twin-based data monitoring method and apparatus, and computer device and storage medium WO2023212994A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210483969.3A CN114822849B (en) 2022-05-06 2022-05-06 Digital twinning-based data monitoring method, device, equipment and storage medium
CN202210483969.3 2022-05-06

Publications (1)

Publication Number Publication Date
WO2023212994A1 true WO2023212994A1 (en) 2023-11-09

Family

ID=82511793

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/096644 WO2023212994A1 (en) 2022-05-06 2022-06-01 Digital-twin-based data monitoring method and apparatus, and computer device and storage medium

Country Status (2)

Country Link
CN (1) CN114822849B (en)
WO (1) WO2023212994A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190005200A1 (en) * 2017-06-28 2019-01-03 General Electric Company Methods and systems for generating a patient digital twin
CN110503338A (en) * 2019-08-26 2019-11-26 江苏方天电力技术有限公司 A kind of ubiquitous electric power Internet of Things monitoring method
CN110600132A (en) * 2019-08-31 2019-12-20 深圳市广宁股份有限公司 Digital twin intelligent health prediction method and device based on vibration detection
CN113035353A (en) * 2021-01-30 2021-06-25 周浩 Digital twin health management system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190005200A1 (en) * 2017-06-28 2019-01-03 General Electric Company Methods and systems for generating a patient digital twin
CN110709938A (en) * 2017-06-28 2020-01-17 通用电气公司 Method and system for generating a digital twin of patients
CN110503338A (en) * 2019-08-26 2019-11-26 江苏方天电力技术有限公司 A kind of ubiquitous electric power Internet of Things monitoring method
CN110600132A (en) * 2019-08-31 2019-12-20 深圳市广宁股份有限公司 Digital twin intelligent health prediction method and device based on vibration detection
WO2021036635A1 (en) * 2019-08-31 2021-03-04 深圳市广宁股份有限公司 Digital twin intelligent health prediction method and device based on vibration detection
CN113035353A (en) * 2021-01-30 2021-06-25 周浩 Digital twin health management system

Also Published As

Publication number Publication date
CN114822849A (en) 2022-07-29
CN114822849B (en) 2023-09-05

Similar Documents

Publication Publication Date Title
Ambekar et al. Disease risk prediction by using convolutional neural network
Karthiga et al. Early prediction of heart disease using decision tree algorithm
Boukenze et al. Predictive analytics in healthcare system using data mining techniques
JP2020518050A (en) Learning and applying contextual similarity between entities
Sankaranarayanan et al. A predictive approach for diabetes mellitus disease through data mining technologies
CN114220549A (en) Effective physiological feature selection and medical causal reasoning method based on interpretable machine learning
US20210089965A1 (en) Data Conversion/Symptom Scoring
Kwakye et al. Machine learning-based classification algorithms for the prediction of coronary heart diseases
Suryani et al. The cost-based feature selection model for coronary heart disease diagnosis system using deep neural network
WO2023212994A1 (en) Digital-twin-based data monitoring method and apparatus, and computer device and storage medium
Navaz et al. The use of data mining techniques to predict mortality and length of stay in an ICU
Kundu et al. Predicting autism spectrum disorder in infants using machine learning
Brown et al. Estimating average treatment effects with propensity scores estimated with four machine learning procedures: simulation results in high dimensional settings and with time to event outcomes
Frize et al. Integration of outcome estimations with a clinical decision support system: Application in the neonatal intensive care unit (NICU)
Selvan et al. [Retracted] An Image Processing Approach for Detection of Prenatal Heart Disease
Alaria et al. Design Simulation and Assessment of Prediction of Mortality in Intensive Care Unit Using Intelligent Algorithms
Dhanamithra et al. A Comparison Study on Machine Learning Approaches for Thyroid Disease Prediction
Quellec et al. Multimedia medical case retrieval using decision trees
Miao et al. Cardiovascular Disease Prediction Based on Soft Voting Ensemble Model
Kour et al. An Advance Approach for Diabetes Detection by Implementing Machine Learning Algorithms
Ambrews et al. Ensemble based machine learning model for heart disease prediction
Momo et al. Length of stay prediction for hospital management using domain adaptation
Oliveira et al. Towards an intelligent systems to predict nosocomial infections in intensive care
CN111048192B (en) Obstetric and research management method for medical couplet based on mobile terminal
Kaur et al. Assessing Machine Learning Approaches for Imputing Missing Values in Cardiovascular Dataset

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22940688

Country of ref document: EP

Kind code of ref document: A1