CN117789995A - Health management online service system based on data classification algorithm - Google Patents
Health management online service system based on data classification algorithm Download PDFInfo
- Publication number
- CN117789995A CN117789995A CN202311552226.8A CN202311552226A CN117789995A CN 117789995 A CN117789995 A CN 117789995A CN 202311552226 A CN202311552226 A CN 202311552226A CN 117789995 A CN117789995 A CN 117789995A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- user
- health
- module
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 121
- 238000007635 classification algorithm Methods 0.000 title claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 71
- 230000002159 abnormal effect Effects 0.000 claims abstract description 68
- 238000000605 extraction Methods 0.000 claims abstract description 59
- 238000012545 processing Methods 0.000 claims abstract description 49
- 238000012937 correction Methods 0.000 claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- 238000007726 management method Methods 0.000 claims abstract description 38
- 238000013523 data management Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims description 62
- 230000006399 behavior Effects 0.000 claims description 30
- 238000011157 data evaluation Methods 0.000 claims description 26
- 238000000034 method Methods 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 22
- 238000007781 pre-processing Methods 0.000 claims description 21
- 230000005856 abnormality Effects 0.000 claims description 19
- 238000007405 data analysis Methods 0.000 claims description 17
- 238000011049 filling Methods 0.000 claims description 16
- 238000009499 grossing Methods 0.000 claims description 16
- 238000010801 machine learning Methods 0.000 claims description 16
- 230000004044 response Effects 0.000 claims description 15
- 238000007619 statistical method Methods 0.000 claims description 14
- 238000013500 data storage Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000013213 extrapolation Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 10
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 8
- 238000007418 data mining Methods 0.000 claims description 7
- 238000013145 classification model Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 239000003814 drug Substances 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 5
- 230000006872 improvement Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000012067 mathematical method Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000012300 Sequence Analysis Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 229940079593 drug Drugs 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000011426 transformation method Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 8
- 230000000875 corresponding effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a health management on-line service system based on a data classification algorithm, which relates to the technical field of big data processing and mainly solves the problems that prediction and processing of the health state of a user cannot be realized, the management range is incomplete and abnormal processing is not timely, the health management on-line service system comprises a cloud server, a data acquisition module, a data management module, a health prediction module, a habit tracking module and a system reminding module, abnormal data conditions in a prediction model are detected and processed through a data correction algorithm, and the stability of the health management on-line service system is improved; the useful data information in the physiological data of the user is extracted through a data classification extraction algorithm to reveal the habit mode and the behavior mode of the user, so that the diversity of health management of the user is increased; the system reminding module sends the emergency notice to the user, so that the on-line service data information analysis capability of the health management line is greatly improved.
Description
Technical Field
The invention relates to the technical field of big data processing, in particular to a health management online service system based on a data classification algorithm.
Background
The on-line health management service system based on the data classification algorithm is an innovative application combining artificial intelligence and health management, and utilizes big data and machine learning algorithms to classify, analyze and predict health data of users so as to provide personalized health management service. The health management system can classify, analyze and predict health data of the user by utilizing a data mining and machine learning algorithm, and meanwhile, by means of intelligent hardware and a sensing technology, the health management system can collect health data of the user, such as heart rate, step number, sleep quality and the like. The intelligent equipment can monitor and record the health condition of the user in real time, provide more accurate data support for health management, and provide more accurate and personalized health management service for the user by the on-line health management service system. The on-line service system for health management has wide development prospect and future trend, and the system is continuously developed and innovated in the future, so that the requirement of users on personalized health management is met, and the popularization and promotion of healthy life style are promoted. In the field of medical health, the on-line health management service system plays an important role, provides a comprehensive and convenient health management scheme, and promotes the health and happy life of people.
The traditional health management online service system has no prediction and processing functions on physiological data information of the user, and is not beneficial to the development of the health state of the user; if the on-line health management service system cannot classify the data and extract the data for use, the health state of the user cannot be accurately estimated, the large data processing capacity is lagged, and the user health needs to be correctly managed; if the health management online service system cannot timely remind and inform the user when the emergency abnormality of the physiological data of the user is detected, great loss is caused to the health of the user.
Disclosure of Invention
Aiming at the defects of the technology, the invention discloses a health management on-line service system based on a data classification algorithm, which detects and processes abnormal data conditions in a prediction model through a data correction algorithm, so that the stability of the health management on-line service system is improved; the useful data information in the physiological data of the user is extracted through a data classification extraction algorithm to reveal the habit mode and the behavior mode of the user, so that the diversity of health management of the user is increased; and the system reminding module sends an emergency notification to the user, so that the user safety is comprehensively protected.
In order to achieve the technical effects, the invention adopts the following technical scheme:
a health management online service system based on a data classification algorithm comprises a cloud server, and a data acquisition module, a data management module, a health prediction module, a habit tracking module and a system reminding module which are connected with the cloud server;
the cloud server is used for maintaining the system to stably run;
the data acquisition module is used for acquiring and recording physiological data of a user;
the data management module is used for processing and analyzing the acquired physiological data;
the health prediction module predicts the health state of the user according to the processed physiological data; the health prediction module comprises a health prediction unit, an abnormality processing unit and a result display unit, wherein the health prediction unit predicts the health state of a user according to collected physiological data of the user through statistical analysis and time sequence analysis; the abnormal processing unit detects and processes abnormal data conditions in the prediction model through a data correction algorithm; the result display unit displays the prediction result to the client in a line graph and report mode, the output end of the health prediction unit is connected with the input end of the abnormality processing unit, and the output end of the abnormality processing unit is connected with the input end of the result display unit;
The habit tracking module is used for evaluating the influence of the habit of the user on the healthy development; the habit tracking module comprises a feature extraction unit, a data evaluation unit and an opinion feedback unit, wherein the feature extraction unit extracts useful data information in physiological data of a user through a data classification extraction algorithm so as to reveal a habit mode and a behavior mode of the user; the data evaluation unit analyzes and evaluates the extracted characteristic values through mining and recognition to realize the understanding of habits, behaviors and potential factors of the user; the opinion feedback unit provides personalized feedback and advice for a user, the output end of the characteristic extraction unit is connected with the input end of the data evaluation unit, and the output end of the data evaluation unit is connected with the input end of the opinion feedback unit;
the system reminding module is used for sending reminding and informing a reminding user of paying attention to the health state;
the output end of the cloud server is respectively connected with the input ends of the data acquisition module, the data management module, the health prediction module, the habit tracking module and the system reminding module, the output end of the data acquisition module is connected with the input end of the data management module, the output end of the data management module is connected with the input end of the health prediction module, the output end of the health prediction module is connected with the input end of the habit tracking module, and the output end of the habit tracking module is connected with the input end of the system reminding module.
As a further description of the above technical solution, the cloud server includes a computing unit, a network unit, a control unit and a security unit, where the computing unit implements computation of health data through ALU arithmetic logic; the network unit transmits physiological data of the user to the cloud server by adopting a WIFI wireless communication protocol and receives response and results from the server; the control unit manages and controls the operation and scheduling of the cloud server through the central processing unit and monitors the operation state and performance of the system; the security unit realizes the setting of user health data security and privacy through a firewall, the output end of the calculation unit is connected with the input end of the network unit, the output end of the network unit is connected with the input end of the control unit, and the output end of the control unit is connected with the input end of the security unit.
As a further description of the above technical solution, the data acquisition module includes a sensor, a data entry unit, a data storage unit and a data uploading unit, where the sensor detects physiological data of a user through an intelligent wearable device and a signal sensor to acquire the data; the data input unit converts the acquired physiological data into digital data which can be analyzed by the system through an API interface; the data storage unit records and stores the processed data through the ROM memory so as to realize the storage of the data; the data uploading unit uploads data information to the cloud server through an API interface to achieve uploading of data, the output end of the sensor is connected with the input end of the data input unit, the output end of the data input unit is connected with the input end of the data storage unit, and the output end of the data storage unit is connected with the input end of the data uploading unit.
As a further description of the above technical solution, the data management module includes a data preprocessing unit, a data analysis unit and a data query unit, where the data preprocessing unit performs preprocessing on data through cleaning, denoising and missing value filling operations; the data analysis unit analyzes the preprocessed data through machine learning and data mining; the data query unit is used for realizing the retrieval, modification and deletion of the health data information by a user through the SQL database query language, the output end of the data preprocessing unit is connected with the input end of the data analysis unit, and the output end of the data analysis unit is connected with the input end of the data query unit.
As a further description of the above technical solution, the working method of the data correction algorithm is as follows:
1) Abnormal data detection: firstly, detecting abnormal data of the output of a prediction model, and identifying abnormal values in a prediction result by using a statistical method, threshold detection and deviation analysis;
2) Abnormal data marking: once abnormal data is detected, the data is marked for further analysis and processing, and the marking can take on specific identifiers and values for subsequent steps to identify and process the abnormal data;
3) And (3) abnormal data analysis: before processing the abnormal data, further analyzing the data according to an abnormal analysis function, including deleting the abnormal data, interpolating and filling, smoothing, extrapolation estimation and algorithm adjustment, wherein the expression of the abnormal analysis function is:
in the expression (1), aa represents an abnormality analysis function, α i Representing the data value to be analyzed, beta i And the standard data value of comparison is represented, gamma represents an abnormality analysis function analysis factor, and delta represents a data expansion processing factor.
4) Data correction strategy selection: deleting the abnormal data, interpolating and filling, smoothing, extrapolation estimation and algorithm adjustment operation are carried out on the data according to the characteristics of the abnormal data and the characteristics of the prediction model;
5) The data correction is performed: according to the selected correction strategy, the data correction algorithm performs actual correction operation on the abnormal data, which may involve deleting the abnormal data, filling the missing values by using an interpolation method, smoothing the data by applying a smoothing algorithm, and the like;
6) Evaluation of corrected data: after the data correction is completed, the corrected data is evaluated according to a data evaluation function to check the effect of the correction and the influence on the prediction model, an evaluation index can be calculated, and the difference before and after the correction is compared, wherein the formula expression of the data evaluation function is as follows:
In equation (2), de represents a data evaluation function, δ i Represents the data value to be evaluated, zeta represents the evaluation index factor epsilon i Representing defined function standard evaluation values, η represents a data evaluation function difference factor.
As a further description of the above technical solution, the working method of the data classification extraction algorithm is as follows:
1) Data preprocessing: firstly, preprocessing and cleaning the collected original physiological data, including noise removal, smoothing and data standardization operation, so as to improve the data quality and accuracy;
2) Feature selection: based on domain knowledge and feature selection algorithms, features related to habit patterns and behavior patterns are selected from the preprocessed data, and statistical methods, information gain and correlation analysis can be used to evaluate the importance and correlation of features;
3) Feature extraction: feature extraction is carried out according to a feature extraction function through a mathematical and statistical method, wherein the feature extraction function comprises mean value, variance, peak value, power spectrum density and frequency band energy, and features are extracted mainly through wavelet transformation and Fourier transformation methods, and the formula expression of the feature extraction function is as follows:
in equation (3), ce represents a feature extraction function, Representing the extracted feature factor value, θ i Iota represents a characteristic relation coefficient of the characteristic extraction function, and phi represents an extraction reference value of the characteristic extraction function;
4) The characteristic is represented as follows: after feature extraction, the extracted features are converted into feature representations, such as vector representations and matrix representations, that can be used by machine learning algorithms for further classification and analysis;
5) Data classification: classifying the data represented by the features to obtain a habit mode and a behavior mode of a user, and training and constructing a classification model by using a machine learning algorithm Support Vector Machine (SVM);
6) Model evaluation: evaluating the data according to a model analysis function to check the accuracy and generalization capability of the data on sample data, wherein the formula expression of the model processing function is as follows:
in equation (4), mh represents a model processing function, κ i Representing the data value to be evaluated lambda i Representing the standard evaluation value defined by the model, wherein xi represents the data integration coefficient value, and ρ represents the extrapolation estimation factor value;
7) Interpretation and application of results: according to the result and analysis of the classification model, the habit mode and the behavior mode of the user are interpreted, and corresponding application is performed, so that personalized suggestions, behavior recommendation and decision support can be provided to promote health improvement and behavior adjustment of the user.
As a further description of the above technical solution, the system reminder module includes a reminder setting unit, a trigger unit, a notification sending unit, and a user response unit, where the reminder setting unit implements setting medication reminders, sports reminders, and regularly recorded health data through a timer and a user setting interface; the triggering unit triggers the reminding event according to the reminding time and the conditions set by the user; the notification sending unit sends a reminding message to a user in the forms of an application program interface, a short message and an email through WIFI wireless communication; the user response unit confirms the received reminding event through the operating system, the output end of the reminding setting unit is connected with the input end of the triggering unit, the output end of the triggering unit is connected with the input end of the notification sending unit, and the output end of the notification sending unit is connected with the input end of the user response unit.
The invention has the beneficial technical effects that compared with the prior art: the invention discloses a health management on-line service system based on a data classification algorithm, which detects and processes abnormal data conditions in a prediction model through a data correction algorithm, so that the stability of the health management on-line service system is improved; the useful data information in the physiological data of the user is extracted through a data classification extraction algorithm to reveal the habit mode and the behavior mode of the user, so that the diversity of health management of the user is increased; and the system reminding module sends an emergency notification to the user, so that the user safety is comprehensively protected.
Drawings
In order to more intuitively and clearly understand and understand the technical solution, when describing the embodiment of the present invention or the prior art, the drawings are often used for supplementing and describing, it should be noted that the drawing is only an expression mode of the embodiment of the present invention or the prior art, and in fact, the technical solution may also have other implementation modes and changes, which are all within the scope of protection of the present invention, so that a skilled person can design other drawings as needed to implement the technical solution of the present invention, where,
FIG. 1 is a schematic diagram of the overall architecture of the present invention;
FIG. 2 is a schematic diagram of a cloud server according to the present invention;
FIG. 3 is a schematic diagram of a data acquisition module according to the present invention;
FIG. 4 is a schematic diagram of a health prediction module according to the present invention;
fig. 5 is a schematic diagram of a habit tracking module structure according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made more apparent and fully by reference to the accompanying drawings, in which it is shown, by way of illustration, only some, but not all embodiments of the embodiments described. Meanwhile, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present invention.
1-5, a health management online service system based on a data classification algorithm comprises a cloud server, a data acquisition module, a data management module, a health prediction module, a habit tracking module and a system reminding module;
the cloud server is used for maintaining the system to stably run;
the data acquisition module is used for acquiring and recording physiological data of a user;
the data management module is used for processing and analyzing the acquired physiological data;
the health prediction module predicts the health state of the user according to the processed physiological data; the health prediction module comprises a health prediction unit, an abnormality processing unit and a result display unit, wherein the health prediction unit predicts the health state of a user according to collected physiological data of the user through statistical analysis and time sequence analysis; the abnormal processing unit detects and processes abnormal data conditions in the prediction model through a data correction algorithm; the result display unit displays the prediction result to the client in a line graph and report mode, the output end of the health prediction unit is connected with the input end of the abnormality processing unit, and the output end of the abnormality processing unit is connected with the input end of the result display unit;
The habit tracking module is used for evaluating the influence of the habit of the user on the healthy development; the habit tracking module comprises a feature extraction unit, a data evaluation unit and an opinion feedback unit, wherein the feature extraction unit extracts useful data information in physiological data of a user through a data classification extraction algorithm so as to reveal a habit mode and a behavior mode of the user; the data evaluation unit analyzes and evaluates the extracted characteristic values through mining and recognition to realize the understanding of habits, behaviors and potential factors of the user; the opinion feedback unit provides personalized feedback and advice for a user, the output end of the characteristic extraction unit is connected with the input end of the data evaluation unit, and the output end of the data evaluation unit is connected with the input end of the opinion feedback unit;
the system reminding module is used for sending reminding and informing a reminding user of paying attention to the health state;
the system comprises a cloud server, a data acquisition module, a data management module, a health prediction module, a habit tracking module and a system reminding module, wherein the output end of the cloud server is connected with the data acquisition module, the data management module, the health prediction module, the habit tracking module and the system reminding module respectively, the output end of the data acquisition module is connected with the input end of the data management module, the output end of the data management module is connected with the input end of the health prediction module, the output end of the health prediction module is connected with the input end of the habit tracking module, and the output end of the habit tracking module is connected with the input end of the system reminding module.
In a further embodiment, the cloud server includes a computing unit, a network unit, a control unit and a security unit, where the computing unit is configured to implement computing health data through ALU arithmetic logic; the network unit transmits physiological data of the user to the cloud server by adopting a WIFI wireless communication protocol and receives response and results from the server; the control unit manages and controls the operation and scheduling of the cloud server through the central processing unit and monitors the operation state and performance of the system; the security unit realizes the setting of user health data security and privacy through a firewall, the output end of the calculation unit is connected with the input end of the network unit, the output end of the network unit is connected with the input end of the control unit, and the output end of the control unit is connected with the input end of the security unit.
The cloud server has the following working principle: the calculation unit calculates and processes the health data of the user through high-efficiency arithmetic logic, and the cloud server can rapidly and accurately calculate the health data of the user, thereby providing comprehensive health reports and suggestions for the user, wherein the real-time monitoring of body indexes and the analysis of historical data are realized; the WIFI wireless communication protocol is adopted by the network unit, physiological data of a user can be conveniently transmitted to the cloud server through the wireless communication technology, and response and calculation results of the server are obtained, and compared with traditional wired communication, the WIFI technology has higher flexibility and convenience, so that the user can perform data interaction with the cloud server at any time and any place; the control unit is a brain of the cloud server and consists of a central processing unit and is responsible for managing and controlling the operation and scheduling of the whole server; through the efficient central processing unit, the control unit can optimize and adjust the system, so that the operation of the cloud server is more stable and high, and meanwhile, the control unit also provides monitoring on the operation state and performance of the system, and the server is ensured to be always in an optimal state; the security unit adopts a powerful firewall technology, the firewall can realize the strict protection of user health data, unauthorized access and data leakage are prevented, and the cloud server can effectively protect privacy and personal information of a user by reasonably setting firewall rules.
In a further embodiment, the data acquisition module includes a sensor, a data input unit, a data storage unit and a data uploading unit, and the sensor detects physiological data of the user through the intelligent wearable device and the signal sensor to acquire the data; the data input unit converts the acquired physiological data into digital data which can be analyzed by the system through an API interface; the data storage unit records and stores the processed data through the ROM memory so as to realize the storage of the data; the data uploading unit uploads data information to the cloud server through an API interface to achieve uploading of data, the output end of the sensor is connected with the input end of the data input unit, the output end of the data input unit is connected with the input end of the data storage unit, and the output end of the data storage unit is connected with the input end of the data uploading unit.
The working principle of the data acquisition module is as follows: the sensor is a core component of the data acquisition module, physiological data of a user, such as heart rate, blood pressure, blood oxygen saturation and the like, can be detected through the intelligent wearing equipment and the signal sensor, and the sensor can timely capture physiological changes of the user through a high-precision measurement technology and convert the physiological changes into analog signals; in the data acquisition process, the data input unit plays a vital role in converting physiological data acquired by the sensor through an API interface and converting analog signals into digital data which can be analyzed by the system, so that the data becomes more accurate and standardized, and powerful support is provided for subsequent data analysis and processing; the data storage unit is an important link for guaranteeing data safety, and can record and store processed digital data through the ROM memory, and the storage mode can ensure the reliability and stability of the data, save space and prolong the storage time of the data; the data uploading unit realizes remote transmission and sharing of data, and can upload the processed and stored data information to the cloud server through the API interface so as to realize uploading and sharing of the data, so that no matter where a user is, the user can acquire and share own physiological data in real time as long as the user is connected with the network.
In a further embodiment, the data management module includes a data preprocessing unit, a data analysis unit and a data query unit, where the data preprocessing unit performs preprocessing on data through operations of cleaning, denoising and filling missing values; the data analysis unit analyzes the preprocessed data through machine learning and data mining; the data query unit is used for realizing the retrieval, modification and deletion of the health data information by a user through the SQL database query language, the output end of the data preprocessing unit is connected with the input end of the data analysis unit, and the output end of the data analysis unit is connected with the input end of the data query unit.
The working principle of the data management module is as follows: the data preprocessing unit can effectively process original healthy data through cleaning, denoising and missing value filling operations, unnecessary information such as repeated data, error data or incomplete data is deleted through cleaning operations, the denoising operations are performed by identifying and removing interference data, the accuracy and reliability of the data are guaranteed, the missing value filling operations are performed by reasonably filling missing parts of the data to process the missing data, and the integrity of the data is guaranteed; after the data analysis unit is subjected to data preprocessing, the unit uses the technology of machine learning and data mining to deeply analyze the preprocessed data, the machine learning can build a model through training data, the future trend is predicted through analyzing the mode and the trend, for example, the prediction of the development potential of a certain disease is predicted, and the data mining extracts valuable information through finding knowledge hidden behind massive data, for example, comprehensive analysis and evaluation of the health condition of a patient and the like; the data query unit provides an interface for the user to interact with the health data information, the user can conveniently search, modify and delete the health data through the SQL database query language, and the user can flexibly query in the data management module according to the self requirements so as to obtain the required health data information, so that the health condition of the user can be better known.
In a further embodiment, the working method of the data correction algorithm is as follows:
1) Abnormal data detection: firstly, detecting abnormal data of the output of a prediction model, and identifying abnormal values in a prediction result by using a statistical method, threshold detection and deviation analysis;
2) Abnormal data marking: once abnormal data is detected, the data is marked for further analysis and processing, and the marking can take on specific identifiers and values for subsequent steps to identify and process the abnormal data;
3) And (3) abnormal data analysis: before processing the abnormal data, further analyzing the data according to an abnormal analysis function, including deleting the abnormal data, interpolating and filling, smoothing, extrapolation estimation and algorithm adjustment, wherein the expression of the abnormal analysis function is:
in the expression (1), aa represents an abnormality analysis function, α i Representing the data value to be analyzed, beta i And the standard data value of comparison is represented, gamma represents an abnormality analysis function analysis factor, and delta represents a data expansion processing factor.
4) Data correction strategy selection: deleting the abnormal data, interpolating and filling, smoothing, extrapolation estimation and algorithm adjustment operation are carried out on the data according to the characteristics of the abnormal data and the characteristics of the prediction model;
5) The data correction is performed: according to the selected correction strategy, the data correction algorithm performs actual correction operation on the abnormal data, which may involve deleting the abnormal data, filling the missing values by using an interpolation method, smoothing the data by applying a smoothing algorithm, and the like;
6) Evaluation of corrected data: after the data correction is completed, the corrected data is evaluated according to a data evaluation function to check the effect of the correction and the influence on the prediction model, an evaluation index can be calculated, and the difference before and after the correction is compared, wherein the formula expression of the data evaluation function is as follows:
in equation (2), de represents a data evaluation function, δ i Represents the data value to be evaluated, zeta represents the evaluation index factor epsilon i Representing defined function standard evaluation values, wherein eta represents a data evaluation function difference factor;
the working principle of the data correction algorithm is as follows: the data correction algorithm has the effects that abnormal data are detected and corrected on the output of the prediction model, so that the data are more in line with the actual situation, the accuracy and the reliability of the data are improved, the problem that abnormal data possibly occur in the prediction process, such as abnormal values in a prediction result, data with larger deviation and the like, can be solved, the accuracy and the reliability of the prediction model can be improved through detecting and correcting the abnormal data, and the influence of the abnormal data on subsequent analysis and decision making is avoided; firstly, detecting abnormal data of the output of a prediction model, and identifying the abnormal data through the technical means of a statistical method, threshold detection, deviation analysis and the like; secondly, marking the abnormal data for further analysis and processing; then, the data is further analyzed according to the anomaly analysis function, and the data value alpha to be analyzed and processed is obtained i And standard data value beta i Comparative analysis was performed by sin (. Alpha. i +β i ) 2 Analysis is carried out, and the gamma abnormal analysis function analysis factor and delta expansion processing factor are combined for passingFurther analyzing the data, including deleting abnormal data, interpolating and filling, smoothing, extrapolation estimation, algorithm adjustment and the like; then, selecting a proper data correction strategy according to the nature of the abnormal data and the characteristics of the prediction model; finally, according to the selected correction strategy, carrying out actual correction operation on the abnormal data; number of digitsAfter the correction is completed, the corrected data is evaluated according to a data evaluation function, and the data value delta to be evaluated is combined i And defined function standard evaluation value epsilon i By->Comparing the data difference before and after correction, and combining the evaluation index factor zeta and the data evaluation function difference factor eta to pass +.>The modified data is evaluated, meanwhile, a large amount of data can be stored and processed by means of a big data platform, cloud computing and distributed computing technology, abnormal data are identified by means of data mining and machine learning algorithms, and differences exist among the different data modification algorithms, as shown in table 1:
differences between the data correction algorithms described in Table 1
In summary, the algorithm searching efficiency, the algorithm changing efficiency and the algorithm accuracy of the data correction algorithm are respectively 98.45%, 96.25% and 98.36%, and the response time of the data correction algorithm is faster than that of the outlier rejection algorithm and the data correction algorithm, so that the data correction algorithm is the best choice of the invention.
In a further embodiment, the working method of the data classification and extraction algorithm is as follows:
1) Data preprocessing: firstly, preprocessing and cleaning the collected original physiological data, including noise removal, smoothing and data standardization operation, so as to improve the data quality and accuracy;
2) Feature selection: based on domain knowledge and feature selection algorithms, features related to habit patterns and behavior patterns are selected from the preprocessed data, and statistical methods, information gain and correlation analysis can be used to evaluate the importance and correlation of features;
3) Feature extraction: feature extraction is carried out according to a feature extraction function through a mathematical and statistical method, wherein the feature extraction function comprises mean value, variance, peak value, power spectrum density and frequency band energy, and features are extracted mainly through wavelet transformation and Fourier transformation methods, and the formula expression of the feature extraction function is as follows:
In equation (3), ce represents a feature extraction function,representing the extracted feature factor value, θ i Iota represents a characteristic relation coefficient of the characteristic extraction function, and phi represents an extraction reference value of the characteristic extraction function;
4) The characteristic is represented as follows: after feature extraction, the extracted features are converted into feature representations, such as vector representations and matrix representations, that can be used by machine learning algorithms for further classification and analysis;
5) Data classification: classifying the data represented by the features to obtain a habit mode and a behavior mode of a user, and training and constructing a classification model by using a machine learning algorithm Support Vector Machine (SVM);
6) Model evaluation: evaluating the data according to a model analysis function to check the accuracy and generalization capability of the data on sample data, wherein the formula expression of the model processing function is as follows:
in equation (4), mh represents a model processing function, κ i Representing the data value to be evaluated lambda i Representing the standard evaluation value defined by the model, wherein xi represents the data integration coefficient value, and ρ represents the extrapolation estimation factor value;
7) Interpretation and application of results: according to the result and analysis of the classification model, the habit mode and the behavior mode of the user are interpreted, and corresponding application is performed, so that personalized suggestions, behavior recommendation and decision support can be provided to promote health improvement and behavior adjustment of the user.
The working principle of the data classification extraction algorithm is as follows: the data classification extraction algorithm is used for revealing the habit mode and the behavior mode of the user through extraction and classification analysis according to the collected physiological data; the problem solved by the algorithm is that the habit mode and the behavior mode of the user are identified and predicted by analyzing the physiological data, so that the behavior rule of the user can be known, corresponding personalized suggestions and decision support are provided, and the health improvement and behavior adjustment of the user are promoted; firstly, pretreatment and cleaning are needed to improve the quality and accuracy of data; then, selecting the characteristics related to the habit pattern and the behavior pattern from the preprocessed data for further processing, extracting the characteristics by using mathematical and statistical methods, and detecting the data value theta by using the data value theta to be detected i And extracting characteristic factorsCarry out the operation->Calculating the characteristic value of the data, and then passing through the characteristic relation coefficient iota and extracting the reference value +.>Multiplication to obtain->To extract features including calculating mean, variance, peak, power spectral density, band energy, etc.; after feature extraction, the features are converted into feature representations, such as vector representations and matrix representations, which can be used by machine learning algorithms to facilitate further classification and analysis, by classifying the data of the feature representations, one can obtain Habit patterns and behavior patterns of users; by classifying the data, the behavior characteristics and trends of the user can be identified, and finally, the data are evaluated by a model analysis function, and the data value to be evaluated and the standard evaluation value are subjected to integral operation>Detecting the difference between the two, and calculating according to the integration coefficient xi and the extrapolation estimation factor rhoIn order to check the accuracy and generalization capability of the algorithm on sample data, this step is crucial to the performance of the verification and optimization algorithm, and meanwhile, the machine learning algorithm and the statistical model can be utilized to perform data classification and feature extraction, and the difference between the data classification extraction algorithm and the data feature selection algorithm is shown in table 2:
table 2 data classification extraction algorithm and data feature selection algorithm
Therefore, the average classification efficiency, extraction efficiency and data accuracy of the data classification algorithm are respectively as follows: 98.22%, 97.90% and 97.86%; the average classification efficiency, extraction efficiency and data accuracy of the data feature selection algorithm are respectively as follows: 94.52%, 94.13% and 94.91%, from which it can be derived that the data classification extraction algorithm is the best choice for the present invention.
In a further embodiment, the system reminding module includes a reminding setting unit, a triggering unit, a notification sending unit and a user response unit, wherein the reminding setting unit realizes setting of medication reminding, exercise reminding and timing record health data through a timer and a user setting interface; the triggering unit triggers the reminding event according to the reminding time and the conditions set by the user; the notification sending unit sends a reminding message to a user in the forms of an application program interface, a short message and an email through WIFI wireless communication; the user response unit confirms the received reminding event through the operating system, the output end of the reminding setting unit is connected with the input end of the triggering unit, the output end of the triggering unit is connected with the input end of the notification sending unit, and the output end of the notification sending unit is connected with the input end of the user response unit.
The working principle of the system reminding module is as follows: the reminding setting unit is used for setting a reminding function through a timer and a user setting interface, a user can set the time and the frequency of taking medicine, reminding in sports and regularly recording health data according to own needs, for example, the user can set 8 hours in the morning every day to remind the user to take medicine or 3 hours in the afternoon every three weeks to remind the user to do sports; the triggering unit triggers corresponding reminding events through reminding time and conditions set by a user, and when the reminding time reaches or the set triggering conditions are met, the system automatically triggers the corresponding reminding events; the notification sending unit sends a reminding message to a user in the form of an application program interface, a short message and an email through WIFI wireless communication, the user has various optional modes for receiving the reminding, and the reminding message can be obtained through the mobile phone application program interface, the short message or the email, so that the user can select the receiving mode which is most suitable for the user according to the habit and the use scene of the user; and the user response unit confirms the received reminding event through the operating system, and once the user receives the reminding message, the system waits for the confirmation operation of the user so as to ensure that the user notices the reminding and takes corresponding action.
In a specific embodiment, firstly, providing infrastructure and computing resources of a system through the cloud server, wherein the infrastructure and computing resources are used for storing and processing user health data and supporting the operation of each module of the system; then, the data acquisition module is responsible for collecting health data of a user, acquiring heart rate, blood pressure, step number, sleep and other data of the user in a mode of a sensor, health equipment, a mobile application program and the like, and the data management module is responsible for preprocessing, cleaning and storing the acquired data for improving data quality, analyzing the data and accessing the user data; and the system comprises a health prediction module, an abnormality processing unit and a result display unit, wherein the health detection module comprises a health prediction unit, an abnormality processing unit and a result display unit and is used for generating health prediction, processing prediction abnormality and displaying a prediction result to the user, meanwhile, the data correction algorithm corrects and optimizes the prediction result through a self-adaptive mechanism or a data correction algorithm to improve the accuracy and reliability of prediction, and the habit tracking module can track and analyze the life habits of the user according to daily habit data and data classification extraction algorithm of the user, including diet, movement, sleep and the like, so as to provide personalized habit assessment, optimization suggestion and schedule arrangement.
While the invention has been described in terms of the above specific embodiments, it will be appreciated by those skilled in the art that these embodiments are provided by way of example only and do not limit the scope and application of the invention. Various omissions, substitutions and changes in the form and details of the invention may be made by those skilled in the art to achieve substantially similar results without departing from the spirit and scope of the invention. Accordingly, the scope of the invention is limited only by the following claims.
Claims (7)
1. The utility model provides a service system on health management line based on data classification algorithm, includes high in the clouds server and with data acquisition module, data management module, health prediction module, habit tracking module and the system of being connected of high in the clouds server reminds the module, its characterized in that:
the cloud server is used for maintaining the system to stably run;
the data acquisition module is used for acquiring and recording physiological data of a user;
the data management module is used for processing and analyzing the acquired physiological data;
the health prediction module predicts the health state of the user according to the processed physiological data; the health prediction module comprises a health prediction unit, an abnormality processing unit and a result display unit, wherein the health prediction unit predicts the health state of a user according to collected physiological data of the user through statistical analysis and time sequence analysis; the abnormal processing unit detects and processes abnormal data conditions in the prediction model through a data correction algorithm; the result display unit displays the prediction result to the client in a line graph and report mode, the output end of the health prediction unit is connected with the input end of the abnormality processing unit, and the output end of the abnormality processing unit is connected with the input end of the result display unit;
The habit tracking module is used for evaluating the influence of the habit of the user on the healthy development; the habit tracking module comprises a feature extraction unit, a data evaluation unit and an opinion feedback unit, wherein the feature extraction unit extracts useful data information in physiological data of a user through a data classification extraction algorithm so as to reveal a habit mode and a behavior mode of the user; the data evaluation unit analyzes and evaluates the extracted characteristic values through mining and recognition to realize the understanding of habits, behaviors and potential factors of the user; the opinion feedback unit provides personalized feedback and advice for a user, the output end of the characteristic extraction unit is connected with the input end of the data evaluation unit, and the output end of the data evaluation unit is connected with the input end of the opinion feedback unit;
the system reminding module is used for sending reminding and informing a reminding user of paying attention to the health state;
the output end of the cloud server is respectively connected with the input ends of the data acquisition module, the data management module, the health prediction module, the habit tracking module and the system reminding module, the output end of the data acquisition module is connected with the input end of the data management module, the output end of the data management module is connected with the input end of the health prediction module, the output end of the health prediction module is connected with the input end of the habit tracking module, and the output end of the habit tracking module is connected with the input end of the system reminding module.
2. The data classification algorithm-based health management online service system of claim 1, wherein: the cloud server comprises a computing unit, a network unit, a control unit and a safety unit, wherein the computing unit is used for computing health data through ALU arithmetic logic; the network unit transmits physiological data of the user to the cloud server by adopting a WIFI wireless communication protocol and receives response and results from the server; the control unit manages and controls the operation and scheduling of the cloud server through the central processing unit and monitors the operation state and performance of the system; the security unit realizes the setting of user health data security and privacy through a firewall, the output end of the calculation unit is connected with the input end of the network unit, the output end of the network unit is connected with the input end of the control unit, and the output end of the control unit is connected with the input end of the security unit.
3. The data classification algorithm-based health management online service system of claim 1, wherein: the data acquisition module comprises a sensor, a data input unit, a data storage unit and a data uploading unit, wherein the sensor detects physiological data of a user through intelligent wearing equipment and a signal sensor so as to acquire the data; the data input unit converts the acquired physiological data into digital data which can be analyzed by the system through an API interface; the data storage unit records and stores the processed data through the ROM memory so as to realize the storage of the data; the data uploading unit uploads data information to the cloud server through an API interface to achieve uploading of data, the output end of the sensor is connected with the input end of the data input unit, the output end of the data input unit is connected with the input end of the data storage unit, and the output end of the data storage unit is connected with the input end of the data uploading unit.
4. The data classification algorithm-based health management online service system of claim 1, wherein: the data management module comprises a data preprocessing unit, a data analysis unit and a data query unit, wherein the data preprocessing unit is used for preprocessing data through cleaning, denoising and missing value filling operations; the data analysis unit analyzes the preprocessed data through machine learning and data mining; the data query unit is used for realizing the retrieval, modification and deletion of the health data information by a user through the SQL database query language, the output end of the data preprocessing unit is connected with the input end of the data analysis unit, and the output end of the data analysis unit is connected with the input end of the data query unit.
5. The data classification algorithm-based health management online service system of claim 1, wherein: the working method of the data correction algorithm comprises the following steps:
1) Abnormal data detection: firstly, detecting abnormal data of the output of a prediction model, and identifying abnormal values in a prediction result by using a statistical method, threshold detection and deviation analysis;
2) Abnormal data marking: once abnormal data is detected, the data is marked for further analysis and processing, and the marking can take on specific identifiers and values for subsequent steps to identify and process the abnormal data;
3) And (3) abnormal data analysis: before processing the abnormal data, further analyzing the data according to an abnormal analysis function, including deleting the abnormal data, interpolating and filling, smoothing, extrapolation estimation and algorithm adjustment, wherein the expression of the abnormal analysis function is:
in the formula (1), aa represents an abnormality analysis functionNumber, alpha i Representing the data value to be analyzed, beta i And the standard data value of comparison is represented, gamma represents an abnormality analysis function analysis factor, and delta represents a data expansion processing factor.
4) Data correction strategy selection: deleting the abnormal data, interpolating and filling, smoothing, extrapolation estimation and algorithm adjustment operation are carried out on the data according to the characteristics of the abnormal data and the characteristics of the prediction model;
5) The data correction is performed: according to the selected correction strategy, the data correction algorithm performs actual correction operation on the abnormal data, which may involve deleting the abnormal data, filling the missing values by using an interpolation method, smoothing the data by applying a smoothing algorithm, and the like;
6) Evaluation of corrected data: after the data correction is completed, the corrected data is evaluated according to a data evaluation function to check the effect of the correction and the influence on the prediction model, an evaluation index can be calculated, and the difference before and after the correction is compared, wherein the formula expression of the data evaluation function is as follows:
in equation (2), de represents a data evaluation function, δ i Represents the data value to be evaluated, zeta represents the evaluation index factor epsilon i Representing defined function standard evaluation values, η represents a data evaluation function difference factor.
6. The data classification algorithm-based health management online service system of claim 1, wherein: the working method of the data classification extraction algorithm comprises the following steps:
1) Data preprocessing: firstly, preprocessing and cleaning the collected original physiological data, including noise removal, smoothing and data standardization operation, so as to improve the data quality and accuracy;
2) Feature selection: based on domain knowledge and feature selection algorithms, features related to habit patterns and behavior patterns are selected from the preprocessed data, and statistical methods, information gain and correlation analysis can be used to evaluate the importance and correlation of features;
3) Feature extraction: feature extraction is carried out according to a feature extraction function through a mathematical and statistical method, wherein the feature extraction function comprises mean value, variance, peak value, power spectrum density and frequency band energy, and features are extracted mainly through wavelet transformation and Fourier transformation methods, and the formula expression of the feature extraction function is as follows:
in equation (3), ce represents a feature extraction function, θ represents an extracted feature factor value, θ i Representing the data value to be detected of the feature extraction function, iota representing the feature relation coefficient of the feature extraction function,extracting reference values representing feature extraction functions;
4) The characteristic is represented as follows: after feature extraction, the extracted features are converted into feature representations, such as vector representations and matrix representations, that can be used by machine learning algorithms for further classification and analysis;
5) Data classification: classifying the data represented by the features to obtain a habit mode and a behavior mode of a user, and training and constructing a classification model by using a machine learning algorithm Support Vector Machine (SVM);
6) Model evaluation: evaluating the data according to a model analysis function to check the accuracy and generalization capability of the data on sample data, wherein the formula expression of the model processing function is as follows:
In equation (4), mh represents a model processing function, κ i Representing the data value to be evaluated lambda i Representing the standard evaluation value defined by the model, wherein xi represents the data integration coefficient value, and ρ represents the extrapolation estimation factor value;
7) Interpretation and application of results: according to the result and analysis of the classification model, the habit mode and the behavior mode of the user are interpreted, and corresponding application is performed, so that personalized suggestions, behavior recommendation and decision support can be provided to promote health improvement and behavior adjustment of the user.
7. The data classification algorithm-based health management online service system of claim 1, wherein: the system reminding module comprises a reminding setting unit, a triggering unit, a notification sending unit and a user response unit, wherein the reminding setting unit is used for setting medication reminding, sports reminding and timing record health data through a timer and a user setting interface; the triggering unit triggers the reminding event according to the reminding time and the conditions set by the user; the notification sending unit sends a reminding message to a user in the forms of an application program interface, a short message and an email through WIFI wireless communication; the user response unit confirms the received reminding event through the operating system, the output end of the reminding setting unit is connected with the input end of the triggering unit, the output end of the triggering unit is connected with the input end of the notification sending unit, and the output end of the notification sending unit is connected with the input end of the user response unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311552226.8A CN117789995A (en) | 2023-11-18 | 2023-11-18 | Health management online service system based on data classification algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311552226.8A CN117789995A (en) | 2023-11-18 | 2023-11-18 | Health management online service system based on data classification algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117789995A true CN117789995A (en) | 2024-03-29 |
Family
ID=90389950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311552226.8A Pending CN117789995A (en) | 2023-11-18 | 2023-11-18 | Health management online service system based on data classification algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117789995A (en) |
-
2023
- 2023-11-18 CN CN202311552226.8A patent/CN117789995A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10265029B2 (en) | Methods and systems for calculating and using statistical models to predict medical events | |
| US20150127595A1 (en) | Modeling and detection of anomaly based on prediction | |
| Zhang et al. | Epilepsy prediction through optimized multidimensional sample entropy and Bi-LSTM | |
| US20190117143A1 (en) | Methods and Apparatus for Assessing Depression | |
| US11037022B2 (en) | Discovery of shifting patterns in sequence classification | |
| Page et al. | Research directions in cloud-based decision support systems for health monitoring using Internet-of-Things driven data acquisition | |
| US20220039729A1 (en) | Electrocardiogram processing system for detecting and/or predicting cardiac events | |
| US8805484B2 (en) | System, apparatus and method for diagnosing seizures | |
| CN116451848A (en) | Satellite telemetry data prediction method and device based on space-time attention mechanism | |
| KU et al. | A Wavelet-based hybrid multi-step Wind Speed Forecasting model using LSTM and SVR | |
| US20230141496A1 (en) | Computer-based systems and devices configured for deep learning from sensor data non-invasive seizure forecasting and methods thereof | |
| Shi et al. | mAAS--a mobile ambulatory assessment system for alcohol craving studies | |
| CN117789995A (en) | Health management online service system based on data classification algorithm | |
| Jayanthi et al. | Automated ECG Arrhythmia classification using Resnet and AutoML Learning Model | |
| Sun et al. | Ada-automatic detection of alcohol usage for mobile ambulatory assessment | |
| Gad et al. | Communication-efficient privacy-preserving federated learning via knowledge distillation for human activity recognition systems | |
| CN111931798B (en) | Method for classifying and detecting cold head state and predicting service life | |
| Orpa et al. | An IoT based healthcare solution with ESP32 using machine learning model | |
| Tazarv et al. | Active reinforcement learning for personalized stress monitoring in everyday settings | |
| de la Cal et al. | An autonomous fallers monitoring kit: release 0.0 | |
| Huang et al. | Analyzing entropy features in time-series data for pattern recognition in neurological conditions | |
| US20230386672A1 (en) | Computer-based systems configured for condition measurement prediction and methods thereof | |
| US20230190204A1 (en) | Statistical dependence-aware biological predictive system | |
| Rameshbabu et al. | Machine Learning Approach for Diagnosis and Prognosis of Cardiac Arrhythmia Condition Using a Minimum Feature Set and Auto-Segmentation-Based Window Optimisation | |
| Gao et al. | Research on Bidirectional Recurrent Imputation of Multivariate Time Series for Clinical Outcomes Prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |