CN115579140A - Self-service health monitoring method and system based on campus health management system - Google Patents
Self-service health monitoring method and system based on campus health management system Download PDFInfo
- Publication number
- CN115579140A CN115579140A CN202211256093.5A CN202211256093A CN115579140A CN 115579140 A CN115579140 A CN 115579140A CN 202211256093 A CN202211256093 A CN 202211256093A CN 115579140 A CN115579140 A CN 115579140A
- Authority
- CN
- China
- Prior art keywords
- health
- user
- data
- monitoring data
- health monitoring
- 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
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a self-service health monitoring method and system based on a campus health management system, and relates to the technical field of self-service health monitoring. The invention starts the self-service health monitoring function after the user successfully authorizes; then acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of a user based on a campus health management system; acquiring an explicit health state score of the user based on the explicit health monitoring data, acquiring a implicit health state score of the user based on the implicit health monitoring data, and acquiring an emotional health state score based on the emotional monitoring data; and finally, visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user. The invention does not need to invest extra resources and facilities, and is simple and easy to implement; secondly, the health state of the school user is monitored from different dimensions, and the accuracy of the final detection result is ensured.
Description
Technical Field
The invention relates to the technical field of self-service health monitoring, in particular to a self-service health monitoring method and system based on a campus health management system.
Background
The assessment of physical and mental health of students is an important link of campus management. In recent years, the conditions of poor physical quality of students, substandard physical testing and the like tend to be normalized gradually; meanwhile, events such as campus conflicts and building jumps caused by the mental health problem of students also occur occasionally. These phenomena are not only detrimental to the healthy growth of students, but also hinder the scientific management of the entire campus.
At present, most of campuses mainly adopt post-remedial measures for monitoring physical and mental health of students, namely, the students can go to a school hospital to see a doctor when obvious symptoms appear on the bodies of the students, or the students can seek help for a nursing assistant when more obvious abnormal conditions appear on the psychology of the students. However, most of the post-event remedies are late, which cause irreversible damage to physical and mental health of students and lead to campus tragedy.
However, the number of students in a campus is large, and limited school managers cannot give consideration to physical and psychological health monitoring of each student; secondly, campus health monitoring equipment and supporting facilities are limited, and real-time accurate monitoring of physical and mental health of most students cannot be met simultaneously; moreover, students do not have professional physical and mental health monitoring and judging standards, and cannot fast and accurately grasp their own physical and mental health conditions. Therefore, it is desirable to provide a simple and feasible self-service health monitoring method that can be implemented by students themselves to solve the above problems.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a self-service health monitoring method and system based on a campus health management system, and solves the problem that the prior art cannot realize self-service health accurate monitoring of campus users through a simple and feasible method.
(II) technical scheme
In order to realize the purpose, the invention is realized by the following technical scheme:
in a first aspect, the present invention first provides a self-service health monitoring method based on a campus health management system, the method including:
starting a self-service health monitoring function after the user successfully authorizes;
acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of a user based on a campus health management system;
obtaining a dominant health status score of the user based on the dominant health monitoring data, a recessive health status score of the user based on the recessive health monitoring data, and an emotional health status score based on the emotional monitoring data;
and visually displaying the explicit health state score, the implicit health state score and the emotional health state score of the user.
Preferably, the user authorization includes identifying the user identity authority by using a user identity authority identification unit.
Preferably, the acquiring of dominant health monitoring data and emotion monitoring data required for self-service health monitoring of the user based on the campus health management system and the implicit health monitoring data include:
directly acquiring the dominant health monitoring data of the user based on a campus health gate, a campus intelligent workbench and a campus self-service health station, and indirectly calling the dominant health monitoring data of the user from a city and district health platform, a hospital and a disease control center which are connected with a campus health management platform;
acquiring emotion monitoring data of a user in real time based on video acquisition and bracelet equipment integrated on a school doctor intelligent workbench and a campus self-service health station;
the method comprises the steps of obtaining implicit health monitoring data of a user based on a campus card management system.
Preferably, the explicit health monitoring data comprises body temperature detection numerical value text data of the user, a chief complaint of the user, a current medical history, past medical history text data and disease treatment record text data; lung images, electrocardiograms, ultrasonic endoscope data image data and audio-video data of a user;
the emotion monitoring data comprises facial video data and physiological signal data of the user; the physiological signal data includes: heart rate variability signal, respiration variability signal and skin electrical signal;
the recessive health monitoring data comprises dietary consumption record data of a user, card swiping record data of a sport place, attendance data and library attendance record data.
Preferably, the obtaining an explicit health status score of the user based on the explicit health monitoring data, obtaining an implicit health status score of the user based on the implicit health monitoring data, and obtaining a mood health status score based on the mood monitoring data includes:
acquiring an explicit health state score of the user by utilizing a multi-mode fusion method based on the explicit health monitoring data;
constructing a current user case based on the recessive health monitoring data, calculating the final similarity between the current user case and a preset labeled user case, and acquiring the recessive health state score of the user based on the final similarity;
and acquiring face video data and physiological signal data of the user based on the emotion monitoring data, performing feature fusion on the face video data and the physiological signal data through a data layer and semantic layer feature verification and fusion mechanism based on a deep neural network and transfer learning, and finally inputting the fused features into a dynamic Bayesian network to obtain the emotion health state score of the user.
In a second aspect, the present invention further provides a self-service health monitoring system based on the campus health management system, the system includes:
the authorization and function starting module is used for obtaining user authorization and starting a self-service health monitoring function of the self-service health monitoring system after obtaining the user authorization;
the data acquisition module is used for acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of the user based on the campus health management system;
a single health status score acquisition module for acquiring a dominant health status score of the user based on the dominant health monitoring data, acquiring a recessive health status score of the user based on the recessive health monitoring data, and acquiring a mood health status score based on the mood monitoring data;
and the health state monitoring score display module is used for visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user.
Preferably, the authorization and function starting module is integrated with a user identity authority identification unit, and is used for identifying the user identity authority.
Preferably, the data acquisition module acquires dominant health monitoring data and emotion monitoring data required by self-service health monitoring of the user based on the campus health management system, and the recessive health monitoring data includes:
directly acquiring the dominant health monitoring data of a user based on a campus health gate, a campus medical intelligent workbench and a campus self-service health station, and indirectly calling the dominant health monitoring data of the user from a city and district health platform, a hospital and a disease control center which are connected with a campus health management platform;
acquiring emotion monitoring data of a user in real time based on video acquisition and bracelet equipment integrated on a school doctor intelligent workbench and a campus self-service health station;
campus card management system-based implicit health monitoring data of user
Preferably, the explicit health monitoring data comprises body temperature detection numerical text data of the user, a user chief complaint, a present medical history, past medical history text data and disease treatment record text data; the method comprises the steps that lung images, electrocardiograms, ultrasonic endoscope data image data and audio-video data of a user are obtained;
the emotion monitoring data comprises facial video data and physiological signal data of the user; the physiological signal data includes: heart rate variability signal, respiration variability signal and skin electrical signal;
the recessive health monitoring data comprises dietary consumption record data of a user, card swiping record data of a sport place, attendance data of a class and attendance record data of a library
Preferably, the acquiring module of the single-item health status score acquires an explicit health status score of the user based on the explicit health monitoring data, acquires an implicit health status score of the user based on the implicit health monitoring data, and acquires an emotional health status score based on the emotional monitoring data includes:
acquiring an explicit health state score of the user by utilizing a multi-mode fusion method based on the explicit health monitoring data;
constructing a current user case based on the recessive health monitoring data, calculating the final similarity between the current user case and a preset labeled user case, and acquiring the recessive health state score of the user based on the final similarity;
and acquiring facial video data and physiological signal data of the user based on the emotion monitoring data, performing feature fusion on the facial video data and the physiological signal data through a data layer based on a deep neural network and transfer learning, a semantic layer feature verification and fusion mechanism, and finally inputting the fused features into a dynamic Bayesian network to obtain the emotion health state score of the user.
(III) advantageous effects
The invention provides a self-service health monitoring method and system based on a campus health management system. Compared with the prior art, the method has the following beneficial effects:
1. the invention provides a self-service health monitoring method based on a campus health management system, which starts a self-service health monitoring function after a user successfully authorizes; then acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of the user based on the campus health management system; then acquiring an explicit health state score of the user based on the explicit health monitoring data, acquiring a implicit health state score of the user based on the implicit health monitoring data, and acquiring an emotional health state score based on the emotional monitoring data; and finally, visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user. The self-service health state monitoring of school users is carried out by utilizing the existing campus health management system, no additional resources and facilities are required to be invested, and the method is simple and easy to implement; in addition, the invention monitors the health state of the school user from different dimensions by utilizing the dominant health monitoring data, emotion monitoring data and recessive health monitoring data of the school user, thereby ensuring the accuracy of the final detection result.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of a campus health management system according to the present invention;
FIG. 2 is a flow chart of a self-service health monitoring method based on a campus health management system according to the present invention;
fig. 3 is a schematic structural diagram of a self-service health monitoring system based on a campus health management system according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The self-service health monitoring method and system based on the campus health management system solve the problem that self-service health accurate monitoring of campus users cannot be achieved through a simple and feasible method in the prior art, and achieve self-service health detection of all members of the campus users by means of existing resources.
In order to solve the technical problems, the general idea of the embodiment of the present application is as follows:
in order to realize self-service health detection of all members of a campus user in a simple and feasible mode on the basis of the existing campus infrastructure, the invention utilizes a campus health management system to start a self-service health monitoring function after the authorization of the user is successful; then acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of a user based on a campus health management system; then acquiring an explicit health state score of the user based on the explicit health monitoring data, acquiring a implicit health state score of the user based on the implicit health monitoring data, and acquiring an emotional health state score based on the emotional monitoring data; and finally, visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user. The invention does not need to invest extra resources and facilities, and is simple and easy to implement; secondly, the health state of the school user is monitored from different dimensions, and the accuracy of the final detection result is ensured.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
In order to save resources and supporting facilities, the campus health management system in the campus is utilized, and the re-investment of related supporting facilities is saved.
Referring to fig. 1, the campus health management system includes a health management platform, which is connected to a downtown health management platform and can import health data about users in hospitals and disease control centers after being authorized. In addition, the health management platform is connected with a campus health door, a campus intelligent working table, a campus self-service health station and the like. Wherein:
the campus health door is arranged on a school door and a floor passageway and is used for real-time body temperature monitoring, infectious epidemic disease identification, face identification attendance checking, repeated detection a day, automatic alarm and the like;
the school doctor intelligent workbench is arranged in a school doctor room and is used for body detection, automatic filing, trend prediction, abnormal alarm, remote medical treatment and the like;
the campus self-service health station is arranged in a school district passage or a medical office and used for teachers and students to perform normalized self-service detection on physiological and psychological indexes, file inquiry and the like.
Based on the campus health management system, the following two specific embodiments are used to describe the implementation process of the self-service health monitoring method and system based on the campus health management system.
Example 1:
in a first aspect, the present invention first provides a self-service health monitoring method based on a campus health management system, and referring to fig. 2, the method includes:
s1, starting a self-service health monitoring function after successful authorization of a user;
s2, acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of a user based on a campus health management system;
s3, acquiring an explicit health state score of the user based on the explicit health monitoring data, acquiring a implicit health state score of the user based on the implicit health monitoring data, and acquiring an emotional health state score based on the emotional monitoring data;
and S4, visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user.
Therefore, according to the self-service health monitoring method based on the campus health management system, the self-service health monitoring function is started after the user is successfully authorized; then acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of a user based on a campus health management system; then acquiring an explicit health state score of the user based on the explicit health monitoring data, acquiring a implicit health state score of the user based on the implicit health monitoring data, and acquiring an emotional health state score based on the emotional monitoring data; and finally, visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user. In the embodiment, the self-service health state monitoring of school users is carried out by utilizing the existing campus health management system, no additional resources and facilities are required to be invested, and the method is simple and feasible; secondly, the embodiment utilizes the dominant health monitoring data, emotion monitoring data and recessive health monitoring data of school users to monitor the health state of the school users from different dimensions, and the accuracy of the final detection result is ensured.
The following describes the implementation of an embodiment of the present invention in detail with reference to fig. 1-2 and the explanation of the specific steps of S1-S4.
S1, starting a self-service health monitoring function after successful authorization of a user.
In order to ensure that the health information of each school user is not leaked, before the self-service health monitoring function is started, a user identity authority identification step is set, namely when a certain user wants to acquire the health condition of the user, the self-service health monitoring system needs to be authorized to start the self-service health monitoring function, and data related to the user is acquired and only acquired for determining the final health score. In particular, the method comprises the following steps of,
an authorization and function starting module is integrated on instruments such as a school doctor intelligent workbench and a campus self-service health station, a user can identify the user identity authority through the authorization and function starting module, and an authorization self-service health monitoring system starts a self-service health monitoring function and obtains related data.
The user identification step includes but is not limited to password login, fingerprint identification, face identification, iris identification and the like. For example, when the user identity authority is authenticated by fingerprint identification, the user inputs his fingerprint through the integrated fingerprint input device, and when the identity verification passes, the data related to the user and used for determining the final health score can be retrieved from the related system.
S2, acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of the user based on the campus health management system.
After the user passes the authorization, acquiring or indirectly acquiring health data related to the user through a connected campus health management system, wherein the data comprises: explicit health monitoring data of the user, emotional monitoring data of the user, and implicit health monitoring data of the user.
The explicit health monitoring data is data which has a definite meaning and can directly reflect the physical health condition of the user, and includes but is not limited to numerical text data such as body temperature detection data of the user, disease treatment recording data of medical institutions such as in-school hospitals and out-of-school hospitals and the like, text data such as chief complaints, current medical history and past medical history of the user, image data such as lung images, electrocardiograms and ultrasonic endoscope data, audio and video data and the like. The dominant health monitoring data can be acquired by a sensor from a campus health door, a campus medical intelligent workbench and a campus self-service health station directly through a campus health management system, or can be indirectly acquired from a city and district health platform, a hospital and a disease control center which are connected with the campus health management platform.
In addition, when the authorization system starts the self-service health monitoring function, the data acquisition device integrated on the school intelligent workbench and the campus self-service health station acquires emotion monitoring data of the user, wherein the emotion monitoring data comprises but is not limited to facial video data of the user and physiological signal data of the user. Utilize integrated video acquisition equipment (like the camera) can gather user's facial video in real time, utilize integrated bracelet record user's physiological signal data simultaneously, wherein, user's physiological signal data include: heart rate variability signal, respiration variability signal and skin electrical signal.
The implicit health monitoring data refer to data indirectly reflecting the physical health of the user, and include, but are not limited to, life consumption habit data of the user and the like, such as user canteen diet consumption record data acquired through a campus one-card management system, sports frequency data of a gymnasium (school gym), and the like.
S3, acquiring an explicit health state score of the user based on the explicit health monitoring data, acquiring a implicit health state score of the user based on the implicit health monitoring data, and acquiring an emotional health state score based on the emotional monitoring data.
In particular, the method comprises the following steps of,
1) And acquiring the dominant health state score of the user by utilizing a multi-mode fusion method based on the dominant health monitoring data.
And carrying out data conversion and cleaning on the acquired user numerical value text data, image data, audio and video data and the like, standardizing and discretizing the data, carrying out feature extraction on the data through minimum absolute shrinkage and selection of an LASSO algorithm, and selecting features by combining the extracted features and doctor labeling to determine data features.
And then, fusing the multi-modal data features in a feature level by using a multi-modal fusion method, and obtaining a health evaluation index of the user based on the feature fusion.
By using a multi-modal fusion method, for example, a multi-kernel learning algorithm can be selected to fuse the modal data, weights are distributed to the indexes through automatic learning, and linear weighting is carried out to obtain the health evaluation index. Specifically, the multi-modal feature vectors such as the extracted text features, the extracted image features, the extracted audio-video features and the like are mapped to a high-dimensional space by using a multi-kernel learning algorithm, and then fusion is performed in the high-dimensional space.
And finally, taking the health evaluation index as the explicit health state score of the user.
2) And constructing a current user case based on the implicit health monitoring data, calculating the final similarity between the current user case and a preset labeling user case, and acquiring the implicit health status score of the user based on the final similarity.
The method comprises the steps of calling life consumption habit data of a user within one year, for example, the life consumption habit data can be classified into drinking consumption record data, sport place card swiping record data, class attendance data, library attendance record data and the like according to categories, then carrying out data conversion and cleaning on the data, screening and removing abnormal value data and the like, and finally packaging the data to be used as a case and defining the case as a current user case.
In addition, a labeled user case is constructed in advance, life consumption habit data of the standard user case within one year, such as diet consumption record data, exercise place card swiping record data, class attendance data, library attendance record data and the like, are formulated according to the consumption habit data of healthy students, namely all the life consumption habits of the user are standard health values.
And finally, calculating the similarity between the current user case and the labeled user case respectively by utilizing the cosine similarity and the Pearson similarity, and matching the calculation results of the two similarities according to a certain weight so as to obtain the final similarity between the current user case and the labeled user case.
The higher the final similarity is, the healthier the consumption behavior habit of the current user is; the lower the final similarity, the less healthy the consumption behavior habits of the current user. The user implicit health status score is set to be 10, the system obtains the user implicit health status score through the value of the final similarity, for example, the user implicit health status score is 9 when the similarity is larger than a certain threshold value, and the user implicit health status score is 3 when the similarity is smaller than another threshold value.
3) And acquiring facial video data and physiological signal data of the user based on the emotion monitoring data, performing feature fusion on the facial video data and the physiological signal data through a data layer based on a deep neural network and transfer learning, a semantic layer feature verification and fusion mechanism, and finally inputting the fused features into a dynamic Bayesian network to obtain the emotion health state score of the user.
3.1 Detecting a face from an acquired user face video view column by using a face feature point positioning and face detection algorithm, cutting the face in the video by using a digital Dlib face feature point positioning model and a face edge monitoring mechanism based on a Gaussian difference filter, segmenting the face from a background picture, and completing a series of operations such as face calibration, alignment, light supplement and the like to obtain a high-definition face image set;
a data enhancement algorithm based on an antagonistic learning mechanism, a face feature analysis method based on LBP-TOP eye movement track, head pose, micro expression and the like and a visual feature calibration technology give full play to the advantages of multi-task learning, a deep double-flow neural network model for excavating convolution feature image flow and optical flow information of AU motion units is further designed, meanwhile, aiming at the problem that the region of the face motion unit in the traditional algorithm is difficult to locate, a deep face segmentation network based on U-NET (the segmentation network consists of series Aures-block attention residual blocks) directly transmits input information to a subsequent layer, and the problem of gradient disappearance caused by stacking of network layers is avoided. Extraction of AU motion units is for certain regions of the face (e.g., regions of eyes, mouth, etc.), these regions can be segmented using a U-NET based deep facial segmentation network, and then information of AU motion units can be extracted from these segmented facial regions using a deep dual-flow neural model. Information about extracting a plurality of facial motion units (AUs) can be acquired in the above manner, and then values are first normalized using min-max normalization in order to avoid the feature values being too large or too small. Finally, in order to reduce the interference of other irrelevant features and make the corresponding features more prominent, the normalized result is squared, thereby realizing more accurate classification. The specific process can be seen in the following formula:
since each emotion state corresponds to multiple AU motion units, in order to more accurately identify emotion, the above AUs are combined into 6 combinations by analyzing the relation between different emotions and AU motion units, and we can obtain the characteristic value of the combination by the following formula:
where m represents the number of AU motion units in each AU motion unit combination. Where k denotes the kth of 6 AU motion combinations, AU i ' means AU in each combinationThe value of the motion unit.
3.2 Extracting a PPG signal from the contact type equipment, eliminating a trend item of the signal and removing low-frequency and high-frequency interference signals so as to better extract emotion related characteristics, and finally extracting time domain and frequency domain indexes related to emotion recognition from the obtained PPG signal for subsequent state recognition;
according to the frequency range of the respiratory signal (the respiratory signal frequency of a normal person is 0-0.35 Hz), a Butterworth low-pass filter is selected to remove interference, the cut frequency is 0.4Hz, and a relatively pure signal can be obtained after filtering. From which respiratory variability indicators related to emotion recognition can be extracted for subsequent state recognition. The butterworth filter is defined as:
wherein, ω is p And ω is the cut-off frequency of the upper and lower limits of the passband, and N is the order of the Butterworth filter. Typically, the maximum attenuation allowed by the passband is chosen to be 3dB, when e =1.
The effective frequency range of the human skin electric signal is within 0.02-0.20 Hz, is lower than the frequency of most interference signals, and does not overlap with the spectrum of other physiological signals such as noise, so the frequency bands of the noise and the SCR reaction signal are separated, therefore, the noise outside the frequency band of the skin electric signal can be removed by using a Butterworth low-pass filter, the interference of high frequency is eliminated, and the removal of high frequency component signals is part of signal smoothing processing. The useless noise signals can be removed to the maximum extent through the Butterworth low-pass filter, and finally, the pure skin electric signals are obtained. A electrodermal indicator associated with emotion recognition can then be extracted from the clean electrodermal signal for subsequent state recognition.
3.3 Carrying out feature fusion on the obtained facial motion unit, the processed heart rate variability signal, the processed respiratory variability signal, the processed skin electrical signal and the like through a data layer and a semantic layer feature verification and fusion mechanism based on a deep neural network and transfer learning;
then, the fused features are input into a dynamic Bayesian network, POMS emotion components are input as emotion recognition results, and a reverse reasoning process is added, namely the POMS emotion components are used as input to recognize the corresponding relation between the POMS emotion components and the fused features. Finally, after the emotion recognition architecture model based on the dynamic Bayesian network is trained, the POMS emotion component input into the model is used as an emotion state recognition result of the user, then the emotion recognition result is used as an emotion health state score of the user, the specific principle is that the score is carried out from-5 to 5 according to negative and positive emotions, the highest positive emotion score is 5, the lowest negative emotion score is-5, and the like.
And S4, visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user.
User's dominant health state score, recessive health state score that acquire through above-mentioned module to and mood health state score back, show several above-mentioned scores for the user through visual show interface, make the user can be clear know the health status condition of oneself current body and mind.
In addition, preferably, the explicit health status score, the implicit health status score, and the emotional health status score of the user may be output as a total health status monitoring score through weighting to characterize the health status of the user as a whole and visually display the health status of the user.
In addition, in order to facilitate the detailed and specific understanding of the self health state monitoring scoring condition of the user, the health state monitoring scoring display module is integrated into a health state monitoring scoring self-service downloading unit, and the unit is provided with a downloading port and printing equipment and can download and print the health state monitoring scoring result of the user.
Example 2:
in a second aspect, the present invention further provides a self-service health monitoring system based on the campus health management system, referring to fig. 3, the system includes:
the authorization and function starting module is used for obtaining user authorization and starting a self-service health monitoring function of the self-service health monitoring system after obtaining the user authorization;
the data acquisition module is used for acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of the user based on the campus health management system;
the single health state score acquisition module is used for acquiring an explicit health state score of the user based on the explicit health monitoring data, acquiring a implicit health state score of the user based on the implicit health monitoring data, and acquiring a mood health state score based on the mood monitoring data;
and the health state monitoring score display module is used for visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user.
Optionally, the authorization and function starting module is integrated with a user identity authority identification unit, and is configured to identify the user identity authority.
Optionally, the data acquisition module acquires dominant health monitoring data and emotion monitoring data required by self-service health monitoring of the user based on the campus health management system, and the recessive health monitoring data includes:
directly acquiring the dominant health monitoring data of a user based on a campus health gate, a campus medical intelligent workbench and a campus self-service health station, and indirectly calling the dominant health monitoring data of the user from a city and district health platform, a hospital and a disease control center which are connected with a campus health management platform;
acquiring emotion monitoring data of a user in real time based on video acquisition and bracelet equipment integrated on a school doctor intelligent workbench and a campus self-service health station;
campus card management system-based implicit health monitoring data of user
Optionally, the explicit health monitoring data includes body temperature detection numerical text data of the user, a user chief complaint, a current medical history, a past medical history text data, and a disease treatment record text data; the method comprises the steps that lung images, electrocardiograms, ultrasonic endoscope data image data and audio-video data of a user are obtained;
the emotion monitoring data comprises facial video data and physiological signal data of the user; the physiological signal data includes: heart rate variability signal, respiration variability signal and skin electrical signal;
the recessive health monitoring data comprises dietary consumption record data of a user, card swiping record data of a sport place, attendance data of a class and attendance record data of a library
Optionally, the obtaining, by the single-item health status score obtaining module, a dominant health status score of the user based on the dominant health monitoring data, a recessive health status score of the user based on the recessive health monitoring data, and a emotional health status score based on the emotional monitoring data includes:
acquiring an explicit health state score of the user by utilizing a multi-mode fusion method based on the explicit health monitoring data;
constructing a current user case based on the recessive health monitoring data, calculating the final similarity between the current user case and a preset labeled user case, and acquiring the recessive health state score of the user based on the final similarity;
and acquiring face video data and physiological signal data of the user based on the emotion monitoring data, performing feature fusion on the face video data and the physiological signal data through a data layer and semantic layer feature verification and fusion mechanism based on a deep neural network and transfer learning, and finally inputting the fused features into a dynamic Bayesian network to obtain the emotion health state score of the user.
It can be understood that the self-service health monitoring system based on the campus health management system provided in the embodiments of the present invention corresponds to the self-service health monitoring method based on the campus health management system, and the explanation, examples, and beneficial effects of the relevant contents may refer to the corresponding contents in the self-service health monitoring method based on the campus health management system, which are not described herein again.
In summary, compared with the prior art, the method has the following beneficial effects:
1. the self-service health monitoring method based on the campus health management system provided by the invention has the advantages that the self-service health monitoring function is started after the authorization of a user is successful; then acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of the user based on the campus health management system; then acquiring an explicit health state score of the user based on the explicit health monitoring data, acquiring a implicit health state score of the user based on the implicit health monitoring data, and acquiring an emotional health state score based on the emotional monitoring data; and finally, visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user. The self-service health state monitoring of school users is carried out by utilizing the existing campus health management system, no additional resources and facilities are required to be invested, and the method is simple and easy to implement; in addition, the invention monitors the health state of the school user from different dimensions by utilizing the dominant health monitoring data, emotion monitoring data and recessive health monitoring data of the school user, thereby ensuring the accuracy of the final detection result.
2. The method and the device have the advantages that the multi-mode fusion method is utilized to fuse the data characteristics of the obtained multi-mode dominant health monitoring data of the user on the characteristic level, the health evaluation index of the user is obtained on the basis of the fusion method, the dominant health state score of the user is obtained on the basis of the health evaluation index, and the obtained data contain multi-mode data with rich forms such as texts, videos and audios, so that the result is more accurate.
3. According to the method, the current user case is constructed based on the acquired implicit health monitoring data of the user to be monitored, the final similarity between the current user case and the preset labeling user case is calculated, the implicit health state score of the user is acquired based on the final similarity, the method focuses on the influence of the life consumption habits of the user on health, and the final health monitoring result is more comprehensive and accurate.
4. The method obtains emotion monitoring data such as facial video data and physiological signal data of a user, performs feature fusion on the facial video data and the physiological signal data through a data layer and semantic layer feature verification and fusion mechanism based on a deep neural network and transfer learning, and finally inputs the fused features into a dynamic Bayesian network to obtain the emotion health state score of the user.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A self-service health monitoring method based on a campus health management system is characterized by comprising the following steps:
starting a self-service health monitoring function after the user successfully authorizes;
acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of a user based on a campus health management system;
obtaining a dominant health status score of the user based on the dominant health monitoring data, a recessive health status score of the user based on the recessive health monitoring data, and an emotional health status score based on the emotional monitoring data;
and visually displaying the explicit health state score, the implicit health state score and the emotional health state score of the user.
2. The method of claim 1, wherein the user authorization comprises identifying a user identity authority using a user identity authority identification unit.
3. The method of claim 1, wherein the obtaining explicit health monitoring data, emotion monitoring data, and implicit health monitoring data needed for user self-service health monitoring based on the campus health management system comprises:
directly acquiring the dominant health monitoring data of the user based on a campus health gate, a campus intelligent workbench and a campus self-service health station, and indirectly calling the dominant health monitoring data of the user from a city and district health platform, a hospital and a disease control center which are connected with a campus health management platform;
acquiring emotion monitoring data of a user in real time based on video acquisition and bracelet equipment integrated on a school doctor intelligent workbench and a campus self-service health station;
the method comprises the steps of obtaining implicit health monitoring data of a user based on a campus card management system.
4. The method of claim 3, wherein the overt health monitoring data comprises body temperature detection numerical textual data of the user, user complaints, current medical history, past history textual data, disease treatment record textual data; lung images, electrocardiograms, ultrasonic endoscope data image data and audio-video data of a user;
the emotion monitoring data comprises facial video data and physiological signal data of the user; the physiological signal data includes: a heart rate variability signal, a respiratory variability signal and a skin electrical signal;
the recessive health monitoring data comprises dietary consumption record data of a user, card swiping record data of a sport place, attendance data and library attendance record data.
5. The method of claim 1, wherein the obtaining an explicit health status score for the user based on the explicit health monitoring data, obtaining an implicit health status score for the user based on the implicit health monitoring data, and obtaining an emotional health status score based on the emotional monitoring data comprises:
acquiring an explicit health state score of the user by utilizing a multi-mode fusion method based on the explicit health monitoring data;
constructing a current user case based on the recessive health monitoring data, calculating the final similarity between the current user case and a preset labeled user case, and acquiring the recessive health state score of the user based on the final similarity;
and acquiring facial video data and physiological signal data of the user based on the emotion monitoring data, performing feature fusion on the facial video data and the physiological signal data through a data layer based on a deep neural network and transfer learning, a semantic layer feature verification and fusion mechanism, and finally inputting the fused features into a dynamic Bayesian network to obtain the emotion health state score of the user.
6. A self-service health monitoring system based on a campus health management system, the system comprising:
the authorization and function starting module is used for obtaining user authorization and starting a self-service health monitoring function of the self-service health monitoring system after obtaining the user authorization;
the data acquisition module is used for acquiring dominant health monitoring data, emotion monitoring data and recessive health monitoring data required by self-service health monitoring of the user based on the campus health management system;
a single health status score acquisition module for acquiring a dominant health status score of the user based on the dominant health monitoring data, acquiring a recessive health status score of the user based on the recessive health monitoring data, and acquiring a mood health status score based on the mood monitoring data;
and the health state monitoring score display module is used for visually displaying the dominant health state score, the recessive health state score and the emotional health state score of the user.
7. The system of claim 6, wherein the authorization and function initiation module integrates a user authentication unit for identifying user authentication.
8. The system of claim 6, wherein the data acquisition module acquires explicit health monitoring data, emotion monitoring data required for user self-service health monitoring based on the campus health management system, and implicit health monitoring data comprises:
directly acquiring the dominant health monitoring data of the user based on a campus health gate, a campus intelligent workbench and a campus self-service health station, and indirectly calling the dominant health monitoring data of the user from a city and district health platform, a hospital and a disease control center which are connected with a campus health management platform;
acquiring emotion monitoring data of a user in real time based on video acquisition and bracelet equipment integrated on a school doctor intelligent workbench and a campus self-service health station;
the method includes the steps that implicit health monitoring data of a user are obtained based on a campus card management system.
9. The system of claim 8, wherein the overt health monitoring data includes body temperature detection numerical textual data of a user, a user's chief complaints, a current medical history, a past history textual data, a disease treatment record textual data; the method comprises the steps that lung images, electrocardiograms, ultrasonic endoscope data image data and audio-video data of a user are obtained;
the emotion monitoring data comprises facial video data and physiological signal data of the user; the physiological signal data includes: heart rate variability signal, respiration variability signal and skin electrical signal;
the recessive health monitoring data comprises dietary consumption record data of a user, card swiping record data of a sport place, attendance data and library attendance record data.
10. The system of claim 6, wherein the single item health status score acquisition module acquires an explicit health status score for the user based on the explicit health monitoring data, acquires an implicit health status score for the user based on the implicit health monitoring data, and acquires a emotional health status score based on the emotional monitoring data comprises:
acquiring an explicit health state score of the user by utilizing a multi-mode fusion method based on the explicit health monitoring data;
constructing a current user case based on the recessive health monitoring data, calculating the final similarity between the current user case and a preset labeling user case, and acquiring the recessive health state score of the user based on the final similarity;
and acquiring facial video data and physiological signal data of the user based on the emotion monitoring data, performing feature fusion on the facial video data and the physiological signal data through a data layer based on a deep neural network and transfer learning, a semantic layer feature verification and fusion mechanism, and finally inputting the fused features into a dynamic Bayesian network to obtain the emotion health state score of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211256093.5A CN115579140A (en) | 2022-10-13 | 2022-10-13 | Self-service health monitoring method and system based on campus health management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211256093.5A CN115579140A (en) | 2022-10-13 | 2022-10-13 | Self-service health monitoring method and system based on campus health management system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115579140A true CN115579140A (en) | 2023-01-06 |
Family
ID=84585307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211256093.5A Pending CN115579140A (en) | 2022-10-13 | 2022-10-13 | Self-service health monitoring method and system based on campus health management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115579140A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116434955A (en) * | 2023-03-20 | 2023-07-14 | 吉林金域医学检验所有限公司 | Staff health state evaluation method and device |
-
2022
- 2022-10-13 CN CN202211256093.5A patent/CN115579140A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116434955A (en) * | 2023-03-20 | 2023-07-14 | 吉林金域医学检验所有限公司 | Staff health state evaluation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gjoreski et al. | Machine learning and end-to-end deep learning for the detection of chronic heart failure from heart sounds | |
| US20210145306A1 (en) | Managing respiratory conditions based on sounds of the respiratory system | |
| CN106725532B (en) | Depression automatic evaluation system and method based on phonetic feature and machine learning | |
| CN110570941B (en) | System and device for assessing psychological state based on text semantic vector model | |
| CN111920420B (en) | Patient behavior multi-modal analysis and prediction system based on statistical learning | |
| CN113197579A (en) | Intelligent psychological assessment method and system based on multi-mode information fusion | |
| CN109346164A (en) | A kind of automatic acquisition equipment and method of tcm clinical practice case | |
| CN111568445B (en) | Delirium risk monitoring method and system based on delirium dynamic prediction model | |
| CN114898860A (en) | Cross-modal transformer-based multi-modal anxiety disorder detection method and system | |
| CN115579140A (en) | Self-service health monitoring method and system based on campus health management system | |
| CN115329818A (en) | Multi-modal fusion attention assessment method, system and storage medium based on VR | |
| CN116230234A (en) | Multi-mode feature consistency psychological health abnormality identification method and system | |
| CN116665845A (en) | User emotion self-testing system based on multi-mode data | |
| Li et al. | Improvement on speech depression recognition based on deep networks | |
| KR102321520B1 (en) | Depression identification and care system through voice analysis | |
| An et al. | Mental health detection from speech signal: A convolution neural networks approach | |
| Pale et al. | Importance of methodological choices in data manipulation for validating epileptic seizure detection models | |
| CN111243728A (en) | Intelligent traditional Chinese medicine four-diagnosis information fusion system, method and storage medium | |
| CN115497621A (en) | Old person cognitive status evaluation system | |
| Touahria et al. | Feature selection algorithms highlight the importance of the systolic segment for normal/murmur PCG beat classification | |
| CN115240241A (en) | Emotion recognition method and device for road and bridge engineering scene | |
| CN208985716U (en) | A kind of automatic acquisition equipment of tcm clinical practice case | |
| CN114463671A (en) | User personality identification method based on video data | |
| Jo et al. | Diagnosis of depression based on four-stream model of bi-LSTM and CNN from audio and text information | |
| Jiang et al. | Mmda: A multimodal dataset for depression and anxiety detection |
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 |