CN112057038A - Big data intelligent health monitoring system based on cloud platform - Google Patents
Big data intelligent health monitoring system based on cloud platform Download PDFInfo
- Publication number
- CN112057038A CN112057038A CN202010519520.9A CN202010519520A CN112057038A CN 112057038 A CN112057038 A CN 112057038A CN 202010519520 A CN202010519520 A CN 202010519520A CN 112057038 A CN112057038 A CN 112057038A
- Authority
- CN
- China
- Prior art keywords
- user
- monitoring
- health
- 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.)
- Withdrawn
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
Abstract
The application requests protection a big data intelligence health monitoring system based on cloud platform, the user passes through the computer access switch, and the switch passes through hot wall access server, and the server is knowledge base server, database server, standby server respectively, and user information exists in each server through this link, accomplishes online intelligent health monitoring function, includes: the system comprises an online intelligent query module, an online real-time interaction module, an intelligent Agent module and a health monitoring management module. The invention realizes the function development of reasoning and monitoring, completes the prototype development of the computer health monitoring system under big data, and can provide a definite solution for the complex computer health. And the system integrates multi-modal and multi-dimensional individual multi-source heterogeneous sensing information, realizes a personalized, refined and long-term effective health management mode, and provides guidance for a user by possibly generating a plurality of health reasons through the idea of multi-Agent.
Description
The prior application: 2019104965001
On the previous filing date: 2019.06.10
Technical Field
The invention relates to the field of electronic information big data analysis, in particular to a big data intelligent health monitoring system based on a cloud platform.
Background
The expert system is an intelligent computer program system, which contains a large amount of knowledge and experience of expert level in a certain field, and can utilize the knowledge of human experts and a problem solving method to process the problem in the field. That is, the expert system is a program system with a great deal of expertise and experience, which employs artificial intelligence technology and computer technology to make inferences and judgments based on knowledge and experience provided by one or more experts in a certain field, and to simulate decision processes of human experts, so as to solve complex problems that need to be handled by human experts.
The data processed by the microcontroller is transmitted to the intelligent terminal in a wireless mode, and all sensor data are collected by the intelligent terminal, further processed and fused and then transmitted to the central monitoring server through a wireless local area network, Bluetooth or a 3G/4G network. The core problem can be attributed to the acquisition, storage, transmission, analysis and utilization of health information. The successive appearance of various mobile monitoring instruments shows that research on mobile health systems has been done with considerable success, but the goal of long-term continuous monitoring has not been achieved overall, nor has the requirement for miniaturization and intelligence of sensor modules been achieved. Especially, a health management system based on an intelligent wearable technology and multisource heterogeneous sensing information is not used for all-weather real-time monitoring, early warning and feedback intervention of individual multi-scenes.
However, most of the existing health care expert systems are designed according to a specific device, and cannot be analyzed in various fields, so that the universality is poor, the knowledge base and the reasoning mechanism of the expert system are greatly different due to different device construction mechanisms in different fields, and different solutions can be provided even if the devices in the same field are different in function, thereby bringing difficulty to the scheme analysis and system design work of the health care expert system.
Therefore, in the vertical field of health data processing, there is a need to design a real-time streaming data intelligent health monitoring system and provide a strong interactive and user-friendly operation mode. In addition, the intelligent data health monitoring system should be well combined with a cloud computing environment to meet the functional requirements of multiple tenants of a data platform.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a cloud platform-based big data intelligent health monitoring system which has certain universality.
The invention relates to a cloud platform-based big data intelligent health monitoring system, wherein a user accesses an exchanger through a computer, the exchanger accesses a server through a firewall, the server is a knowledge base server, a database server and a standby server, user information is stored in each server through a link to complete an online intelligent health monitoring function, and the cloud platform-based big data intelligent health monitoring system is characterized in that the overall structure of the system comprises:
viewing the image layer: the layer is an interactive window between the system and the user and provides a working interface for the user, the system uses a C/S architecture, the presentation of the working interface of the user is realized by software and is an interface between the system and the user
And a service logic layer: providing various services of a system, completing the realization work of various requirements of a user, realizing the requirements of four modules in the system, ensuring the normal work of various services, wherein a service logic layer is the center of all application platforms, and realizing the related operation of data testification, event handling and authority handling services;
physical layer: uniformly managing and distributing bottom hardware resources, respectively starting a proper number of computing nodes, data interfaces and service interface instances, and providing virtual hardware resources for upper application;
the system module comprises:
the online intelligent query module: finishing functions of deterministic health monitoring, uncertain health monitoring and fuzzy query;
an online real-time interaction module: the user can open the interface to communicate with different experts or other users in real time when encountering equipment problems by entering the interactive interface through the related buttons;
the intelligent Agent module: and (3) constructing a characteristic activity matrix by adopting a factor analysis technology, and reserving L principal component factors with the accumulated contribution rate exceeding 90%. Obtaining a factor load matrix
Wherein λ1≥λ2≥...≥λLAnd u1≥u2≥...≥uLRespectively eigenvalues and eigenvectors of the correlation matrix R. Randomly generating a deflection matrix S ∈ RK×dConstructing a characteristic activity matrix AM ∈ RK×dWherein K is a rule number.
Therefore, the rule-level output matrix H ∈ R of the 0-order TSK fuzzy classifierN×KElement h ofikThe description is as follows:
τ is a given threshold.
The health monitoring management module: the system comprises three sub-modules of knowledge base maintenance modification, user monitoring process management and real-time interactive process control, and based on a distributed file system HDFS, the system realizes ultra-large-capacity, expandable and high-fault-tolerance storage of data, can be used for storing data in any format, and provides basic data support for other modules of the system. Furthermore, the intelligent Agent module also comprises difference monitoring among different monitoring methods:
Fdp＝||Hdpβdp-T||2+λ||Hdpβdp-Ydp-1||2where T is the class label and λ is the generalization coefficient, factors that affect the classification performance of the fuzzy classification rule, i.e., the output of the other method and the expected output of the current method and the true label, are considered. Simultaneous square term Hdpβdp-T||2Consistency within the same method is achieved; square term Hdpβdp-Ydp-1||2The consistency among different methods is realized; the sum of the two squared terms achieves comprehensive consistency.
The invention requests to protect an improvement of a cloud platform-based big data intelligent health monitoring system, which also comprises:
the view layer provides a user interface based on a B/S framework, a user configures system parameters, uploads data, submits a task, monitors the execution condition of the task, controls the starting and stopping of each module of the system and checks the execution result of the task through the interface, and the user exchanges data with a background by submitting an Ajax request by using a default Web front end;
the control interface display options and the switching between the main interface and the health recording subsystem interface mainly comprise file management window display, system information window display, output information window display, process information window display, monitoring window display, switching to a main interface mode and switching to the health recording subsystem interface.
The invention requests to protect an improvement of a cloud platform-based big data intelligent health monitoring system, which also comprises:
the method comprises the steps that a user submits own monitoring requirements through an intelligent client in a service logic layer, the intelligent client converts requirement information of the user into JSON information and sends an Ajax request to a background server to serve as a streaming data processing service, the background server sends context information comprising the monitoring requirements and the user information to a scheme processing conversion server in an HTTP post request mode, and the scheme processing conversion server analyzes the request to obtain the monitoring requirements, generates a logic and physical execution plan and stores the logic and physical execution plan locally in the form of an executable file and a configuration file.
The invention requests to protect an improvement of a cloud platform-based big data intelligent health monitoring system, which also comprises:
the physical layer integrates data information in the knowledge archive database and user information in the user database, the integrated data are divided into a training set and a testing set, the physical health data of a user are stored in an intelligent mobile phone APP according to a detailed physical examination report of a hospital, various physiological data of the user such as body temperature, heart rate, pulse and sleep state are monitored in real time through wearable equipment, the prediction model is optimized and adjusted according to the testing set, a final prediction model is obtained, and corresponding early warning analysis results are output according to prediction instructions input by a user side and/or a medical care platform terminal.
The invention requests to protect an improvement of a cloud platform-based big data intelligent health monitoring system, which also comprises:
the online intelligent query module completes functions of deterministic health monitoring, uncertain health monitoring and fuzzy query, and specifically comprises the following steps:
the workflow of the deterministic health monitoring sub-module is as follows: when a user encounters a problem, starting the system, sending the problem to the user by the system, recalculating the computer according to the problem of the user, asking questions for many times, and finally summarizing and analyzing to obtain a conclusion and a scheme;
starting from the health phenomenon, the health monitoring of the computer analyzes the starting process, the running process and the component parts, then analyzes the first-stage reason to the multi-stage reason by using an elimination method respectively, and finally asks questions to a user for selection;
the system asks the user for a question by the exclusion method, and the user can determine or exclude a scheme by selecting 'yes' or 'no'.
The invention requests to protect an improvement of a cloud platform-based big data intelligent health monitoring system, which also comprises:
the online real-time interaction module enters an interaction interface through a related button, and a user can open the interface to communicate with different experts or other users online in real time when encountering an equipment problem, and the method specifically comprises the following steps:
the interactive interface comprises different functions of voice call, real-time chat, remote control, video call and the like, and the user can select the interactive interface according to the self problem.
The invention requests to protect an improvement of a cloud platform-based big data intelligent health monitoring system, which also comprises:
the intelligent Agent module comprises: adopting different monitoring methods of each Agent to monitor the unified health, thereby providing a plurality of conclusions for subsequent analysis, which specifically comprises the following steps:
the method is implemented by adopting a Browser/Server architecture, organically organizes all service objects by designing an intermediate layer, and provides guarantee for Agent to carry out health monitoring;
the system associates users, equipment, knowledge engineers, monitoring systems and monitoring systems distributed in different places, transmits information related to the condition of processing equipment and monitoring decisions in the whole system, and dynamically generates a remote monitoring node for similar equipment. The system network comprises registered equipment users, design and manufacture parties of the equipment, a remote monitoring system, even a third-party operation and maintenance team network and various research and development groups.
The invention requests to protect an improvement of a cloud platform-based big data intelligent health monitoring system, which also comprises:
the health monitoring management module: the system comprises three sub-modules of knowledge base maintenance modification, user monitoring process management and real-time interactive process control, realizes ultra-large capacity, expandable and high fault tolerance storage of data based on a distributed file system (HDFS), can be used for storing data in any format, and provides basic data support for other modules of the system, and specifically comprises the following steps:
the health knowledge base modification module can maintain health phenomena and reasons, can add, delete, modify and check rules, and can enable users to continuously enrich and perfect the knowledge base, thereby achieving the expert level. The user saves the inquiry knowledge in the monitoring process, provides convenience for later use, and can edit, modify and save the user inquiry information database;
adopting a hadoop framework to carry out unified management on distributed resources, adopting Hdfs to provide data storage service, adopting a Spark framework to provide distributed computing service, and using a relational database Mysql to store structured service data;
the modification tool is also used for selecting a health file to be imported into the HDFS and selecting a generated rule file to be imported into the HBase, and meanwhile, for a program which is debugged and compiled on Windows, the file can be imported into a specified directory of the cloud computing platform through a selected program file inlet and the execution of the cloud computing platform is controlled through an execution button.
The invention is based on a Hadoop platform, realizes the function development of reasoning and monitoring, completes the prototype development of the computer health monitoring system under big data, and can provide a determined solution for the complex computer health. And the system integrates multi-modal and multi-dimensional individual multi-source heterogeneous sensing information, including physiological information, psychological information, spatial information and motion information, and combines the influences of subjective and objective factors on the health state to realize a personalized, refined and long-term effective health management mode, and a plurality of health reasons can be possibly generated by using the thought of multiple agents, and are all listed according to the possibility to provide guidance for a user.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a system structure diagram of a cloud platform-based big data intelligent health monitoring system according to the present invention;
fig. 2 is a functional block diagram of a cloud platform-based big data intelligent health monitoring system according to the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, the invention relates to an architecture diagram of a cloud platform-based big data intelligent health monitoring system;
the invention relates to a cloud platform-based big data intelligent health monitoring system, wherein a user accesses an exchanger through a computer, the exchanger accesses a server through a firewall, the server is a knowledge base server, a database server and a standby server, user information is stored in each server through a link to complete an online intelligent health monitoring function, and the cloud platform-based big data intelligent health monitoring system is characterized in that the overall structure of the system comprises:
viewing the image layer: the layer is an interactive window between the system and the user and provides a working interface for the user, the system uses a C/S architecture, the presentation of the working interface of the user is realized by software and is an interface between the system and the user
And a service logic layer: providing various services of a system, completing the realization work of various requirements of a user, realizing the requirements of four modules in the system, ensuring the normal work of various services, wherein a service logic layer is the center of all application platforms, and realizing the related operation of data testification, event handling and authority handling services;
physical layer: uniformly managing and distributing bottom hardware resources, respectively starting a proper number of computing nodes, data interfaces and service interface instances, and providing virtual hardware resources for upper application;
preferably, the view layer provides a user interface based on a B/S architecture, a user configures system parameters, uploads data, submits tasks, monitors task execution conditions, controls starting and stopping of each module of the system, and checks task execution results through the interface, and data are exchanged with the background by submitting an Ajax request by using a default Web front end;
the control interface display options and the switching between the main interface and the health recording subsystem interface mainly comprise file management window display, system information window display, output information window display, process information window display, monitoring window display, switching to a main interface mode and switching to the health recording subsystem interface.
The cloud platform receives the reported state log message and sends the state log message to the data collector through the cloud platform; and acquiring abnormal interruption information of the honeycomb module from the state log message on the data acquisition device, and acquiring a temperature value and/or a signal strength value of the terminal equipment.
Furthermore, a user submits own monitoring requirements through an intelligent client in the service logic layer, the intelligent client converts the requirement information of the user into JSON information and initiates an Ajax request to a background server as a streaming data processing service, the background server sends context information comprising the monitoring requirements and the user information to a scheme processing conversion server in an HTTP post request mode, and the scheme processing conversion server generates a logic and physical execution plan after analyzing the request to obtain the monitoring requirements and locally stores the logic and physical execution plan in the forms of an executable file and a configuration file.
And storing the data set of the health big data subjected to format unification processing by the self-adaptive multi-network health data access module. The platform is designed and developed in a distributed cluster environment, a Map Reduce under Hadoop is adopted by a computing frame, and an HDFS under Hadoop is adopted by a storage platform. In addition, in the foreground display and operation interface, a Struts2 development framework is adopted for developing pages.
And reading the configuration file through an analysis instrument, acquiring program operation parameters, then performing relevant parameter configuration on the Hadoop, and uploading data by using a Hadoop mass log collection system to realize real-time monitoring catalog uploading. Compiling a configuration file of the Hadoop under a Hadoop _ HOME/conf directory, and configuring a formulated directory needing to be monitored in an analysis instrument as a spooldor of the Hadoop; the Hadoop monitors the change of new data in the specified directory by utilizing the self component Source real-time monitoring analyzer, namely, the configured spooldor. And when new data generation is detected, analyzing the content of the new file, writing the content into a component Channel of the Hadoop for caching, and taking out the data cached by the Channel from the component Sink and submitting the data to an HDFS distributed file system in the Hadoop cluster. And simultaneously, printing a complete suffix on the uploaded data in the appointed directory of the analysis instrument, marking that the file is uploaded, and not repeatedly uploading the file next time.
Furthermore, the physical layer integrates data information in a knowledge archive database and user information in a user database, the integrated data are divided into a training set and a testing set, the physical health data of a user are stored in an intelligent mobile phone APP according to a detailed physical examination report of a hospital, various physiological data of the user such as body temperature, heart rate, pulse and sleep state are monitored in real time through wearable equipment, parameters of the prediction model are optimized and adjusted through the testing set, a final prediction model is obtained, and a corresponding early warning analysis result is output according to a prediction instruction input by a user side and/or a medical care platform terminal.
Referring to fig. 2, a functional module diagram of a cloud platform-based big data intelligent health monitoring system according to the present invention;
the system function module of the system comprises:
the online intelligent query module: finishing functions of deterministic health monitoring, uncertain health monitoring and fuzzy query;
an online real-time interaction module: the user can open the interface to communicate with different experts or other users in real time when encountering equipment problems by entering the interactive interface through the related buttons;
the intelligent Agent module: monitoring the unified health by adopting different monitoring methods of each Agent, thereby providing a plurality of conclusions for subsequent analysis;
the health monitoring management module: the system comprises three sub-modules of knowledge base maintenance modification, user monitoring process management and real-time interactive process control, and based on a distributed file system HDFS, the system realizes ultra-large-capacity, expandable and high-fault-tolerance storage of data, can be used for storing data in any format, and provides basic data support for other modules of the system.
Preferably, the online intelligent query module completes functions of deterministic health monitoring, non-deterministic health monitoring and fuzzy query, and specifically includes:
the workflow of the deterministic health monitoring sub-module is as follows: when a user encounters a problem, starting the system, sending the problem to the user by the system, recalculating the computer according to the problem of the user, asking questions for many times, and finally summarizing and analyzing to obtain a conclusion and a scheme;
starting from the health phenomenon, the health monitoring of the computer analyzes the starting process, the running process and the component parts, then analyzes the first-stage reason to the multi-stage reason by using an elimination method respectively, and finally asks questions to a user for selection;
the system asks the user for a question by the exclusion method, and the user can determine or exclude a scheme by selecting 'yes' or 'no'.
The dynamic spatial HDFS query method is adopted in a mobile cloud computing environment and comprises a cloud center service system and an intelligent mobile client system, wherein the cloud center service system provides a spatial grid pruning strategy and continuous network health data monitoring to execute a dynamic HDFS and anti-HDFS algorithm, and the intelligent mobile client needs the degree of attributes, inputs thresholds of the attributes and sends query results to improve the attributes of a hospital.
In the Map process of Spark, health multidimensional data extraction of spatial features is carried out by using network health data monitoring, health space addressing data which do not meet the requirements of users are preprocessed after extraction, key values can also be inconsistent due to over extraction of HDFS in part of results, so hash matching of value values is carried out according to key words at the end of the Map stage, monitoring and extraction are further carried out if matching is unsuccessful, and then the result is sent to Reduce end for further summary processing through the shuffling process. The monitoring method utilizes a Spark distribution processing mechanism. Therefore, the screening time of the user on the hospital data is greatly reduced, and a distribution processing mechanism is more efficiently utilized.
Preferably, the online real-time interaction module enters the interaction interface through a related button, and a user can open the interface to communicate with different experts or other users online in real time when encountering an equipment problem, and the method specifically includes:
the interactive interface comprises different functions of voice call, real-time chat, remote control, video call and the like, and the user can select the interactive interface according to the self problem.
Further, the smart Agent module: adopting different monitoring methods of each Agent to monitor the unified health, thereby providing a plurality of conclusions for subsequent analysis, which specifically comprises the following steps:
the method is implemented by adopting a Browser/Server architecture, organically organizes all service objects by designing an intermediate layer, and provides guarantee for Agent to carry out health monitoring;
the system associates users, equipment, knowledge engineers, monitoring systems and monitoring systems distributed in different places, transmits information related to the condition of processing equipment and monitoring decisions in the whole system, and dynamically generates a remote monitoring node for similar equipment. The system network comprises registered equipment users, design and manufacture parties of the equipment, a remote monitoring system, even a third-party operation and maintenance team network and various research and development groups.
In the process of independent operation of each part, the monitoring of each operation part comprises the following methods: randomly generating a deflection matrix S ∈ RK×dConstructing a characteristic activity matrix AM ∈ RK×dWherein K is a rule number.
Therefore, the rule-level output matrix H ∈ R of the 0-order TSK fuzzy classifierN×KElement h ofikThe description is as follows:
τ is a given threshold.
Taking two values as an example, the value am under each fuzzy rule for each sample featurekjThere are two cases:
(ii) am if the jth feature is not includedkjEach eigenvalue under each fuzzy rule is thus 0:
am otherwisekjEach eigenvalue under each fuzzy rule is thus 1: h isik＝1。
Taking the sleep quality monitoring service of a remote monitoring platform provided by a cloud health service provider as an example, setting a plurality of rules such as total sleep time, deep sleep time, shallow sleep time, eye movement time and the like; in thatAfter the single monitoring is finished, taking the total sleep time as an example, in a 20-25-year-old client group, the requirement that the sleep time is 6-7 hours every day is met, and then h is obtainedik1 (at which time it may be initially assessed as healthy); otherwise, then hik0; of course, the sleep time can be further classified into h when the sleep time per day is more than 8 hoursik1 (which may be initially assessed as sub-healthy) and a sleep time of 6 hours or less per day, for hik0; (mental stress can be preliminarily evaluated at this time). Here, the monitoring, sub-health, mental stress, etc. form a regular output matrix H for sleep quality monitoring. The decision result Y of the classifier is equal to H beta, beta is an output weight, and the conclusion of the monitoring of the part can be obtained through a gradient descent method; after the monitoring results obtained by combining other similar methods are summarized, the complete sleep quality monitoring service is obtained, and reports and suggestions for monitoring the sleep quality of the client are formed. The overall reported accuracy by improvement of this protocol was greater than 99.5% by long-term data comparison.
Aiming at the difference monitoring among different teams, namely different monitoring methods, the following steps are adopted:
Fdp＝||Hdpβdp-T||2+λ||Hdpβdp-Ydp-1||2where T is a true-like label and λ is a generalization coefficient.
The acquired health data are acquired and transmitted to a hospital cloud platform through a Hadoop tool or are stored in a mode of importing data in a database into the hospital cloud platform; the health data are processed through a MapReduce cluster-based high-performance parallel computing platform, namely a parallel computing distributed data processing method, then the processed health data are analyzed through an association rule algorithm to find out the association among diseases, and a corresponding medical pathological model is established through a decision tree. Health data includes health data from wearable smart devices, electronic medical records, medical images, clinical examinations, medical literature, doctor-patient behavior, health insurance industry, pharmaceutical sales enterprises, and the like.
Preferably, the health monitoring management module: the system comprises three sub-modules of knowledge base maintenance modification, user monitoring process management and real-time interactive process control, realizes ultra-large capacity, expandable and high fault tolerance storage of data based on a distributed file system (HDFS), can be used for storing data in any format, and provides basic data support for other modules of the system, and specifically comprises the following steps:
the health knowledge base modification module can maintain health phenomena and reasons, can add, delete, modify and check rules, and can enable users to continuously enrich and perfect the knowledge base, thereby achieving the expert level. The user saves the inquiry knowledge in the monitoring process, provides convenience for later use, and can edit, modify and save the user inquiry information database;
adopting a hadoop framework to carry out unified management on distributed resources, adopting Hdfs to provide data storage service, adopting a Spark framework to provide distributed computing service, and using a relational database Mysql to store structured service data;
the modification tool is also used for selecting a health file to be imported into the HDFS and selecting a generated rule file to be imported into the HBase, and meanwhile, for a program which is debugged and compiled on Windows, the file can be imported into a specified directory of the cloud computing platform through a selected program file inlet and the execution of the cloud computing platform is controlled through an execution button.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (9)
1. The utility model provides a big data intelligence health monitoring system based on cloud platform, the user passes through the computer access switch, and the switch passes through prevents that hot wall inserts the server, and the server is knowledge base server, database server, standby server respectively, and user information exists in each server through this link, accomplishes online intelligent health monitoring function, and its characterized in that, system overall structure includes:
viewing the image layer: the layer is an interactive window between the system and the user and provides a working interface for the user, the system uses a C/S architecture, the presentation of the working interface of the user is realized by software and is an interface between the system and the user
And a service logic layer: providing various services of a system, completing the realization work of various requirements of a user, realizing the requirements of four modules in the system, ensuring the normal work of various services, wherein a service logic layer is the center of all application platforms, and realizing the related operation of data testification, event handling and authority handling services;
physical layer: uniformly managing and distributing bottom hardware resources, respectively starting a proper number of computing nodes, data interfaces and service interface instances, and providing virtual hardware resources for upper application;
the system module comprises:
the online intelligent query module: finishing functions of deterministic health monitoring, uncertain health monitoring and fuzzy query;
an online real-time interaction module: the user can open the interface to communicate with different experts or other users in real time when encountering equipment problems by entering the interactive interface through the related buttons;
the intelligent Agent module: constructing a characteristic activity degree matrix by adopting a factor analysis technology, adjusting the activity degree of each characteristic participating in different rules, reserving L main component factors with the accumulated contribution rate exceeding 90 percent, and acquiring a factor load matrix Ad×L，
Wherein λ1≥λ2≥...≥λLAnd u1≥u2≥...≥uLRespectively are eigenvalues and eigenvectors of the correlation matrix R;
randomly generating a deflection matrix S ∈ RK×dConstructing a characteristic activity matrix AM ∈ RK×dWherein K is the number of rules:
based on the characteristic active matrix, a rule layer output matrix H of a 0-order TSK fuzzy classifier belongs to RN×KCan be obtained by the following formula:
τ is a given threshold; a decision result Y of the TSK fuzzy classifier is equal to H beta, wherein beta is an output weight and is obtained by a gradient descent method;
the health monitoring management module: the system comprises three sub-modules of knowledge base maintenance modification, user monitoring process management and real-time interactive process control, and based on a distributed file system HDFS, the system realizes ultra-large-capacity, expandable and high-fault-tolerance storage of data, can be used for storing data in any format, and provides basic data support for other modules of the system.
2. The cloud platform-based big data intelligent health monitoring system according to claim 1, further comprising:
the view layer provides a user interface based on a B/S framework, a user configures system parameters, uploads data, submits a task, monitors the execution condition of the task, controls the starting and stopping of each module of the system and checks the execution result of the task through the interface, and the user exchanges data with a background by submitting an Ajax request by using a default Web front end;
the control interface display options and the switching between the main interface and the health recording subsystem interface mainly comprise file management window display, system information window display, output information window display, process information window display, monitoring window display, switching to a main interface mode and switching to the health recording subsystem interface.
3. The cloud platform-based big data intelligent health monitoring system according to claim 1, further comprising:
the method comprises the steps that a user submits own monitoring requirements through an intelligent client in a service logic layer, the intelligent client converts requirement information of the user into JSON information and sends an Ajax request to a background server to serve as a streaming data processing service, the background server sends context information comprising the monitoring requirements and the user information to a scheme processing conversion server in an HTTP post request mode, and the scheme processing conversion server analyzes the request to obtain the monitoring requirements, generates a logic and physical execution plan and stores the logic and physical execution plan locally in the form of an executable file and a configuration file.
4. The cloud platform-based big data intelligent health monitoring system according to claim 1, further comprising:
the physical layer integrates data information in the knowledge archive database and user information in the user database, the integrated data are divided into a training set and a testing set, the physical health data of a user are stored in an intelligent mobile phone APP according to a detailed physical examination report of a hospital, various physiological data of the user such as body temperature, heart rate, pulse and sleep state are monitored in real time through wearable equipment, the prediction model is optimized and adjusted according to the testing set, a final prediction model is obtained, and corresponding early warning analysis results are output according to prediction instructions input by a user side and/or a medical care platform terminal.
5. The cloud platform-based big data intelligent health monitoring system according to claim 1, further comprising:
the online intelligent query module completes functions of deterministic health monitoring, uncertain health monitoring and fuzzy query, and specifically comprises the following steps:
the workflow of the deterministic health monitoring sub-module is as follows: when a user encounters a problem, starting the system, sending the problem to the user by the system, recalculating the computer according to the problem of the user, asking questions for many times, and finally summarizing and analyzing to obtain a conclusion and a scheme;
starting from the health phenomenon, the health monitoring of the computer analyzes the starting process, the running process and the component parts, then analyzes the first-stage reason to the multi-stage reason by using an elimination method respectively, and finally asks questions to a user for selection;
the system asks the user for a question by the exclusion method, and the user can determine or exclude a scheme by selecting 'yes' or 'no'.
6. The cloud platform-based big data intelligent health monitoring system according to claim 1, further comprising:
the online real-time interaction module enters an interaction interface through a related button, and a user can open the interface to communicate with different experts or other users online in real time when encountering an equipment problem, and the method specifically comprises the following steps:
the interactive interface comprises different functions of voice call, real-time chat, remote control, video call and the like, and the user can select the interactive interface according to the self problem.
7. The cloud platform-based big data intelligent health monitoring system according to claim 1, further comprising:
the intelligent Agent module comprises: adopting different monitoring methods of each Agent to monitor the unified health, thereby providing a plurality of conclusions for subsequent analysis, which specifically comprises the following steps:
the method is implemented by adopting a Browser/Server architecture, organically organizes all service objects by designing an intermediate layer, and provides guarantee for Agent to carry out health monitoring;
the system associates users, equipment, knowledge engineers, monitoring systems and monitoring systems distributed in different places, transmits information related to the condition of processing equipment and monitoring decisions in the whole system, and dynamically generates a remote monitoring node for similar equipment. The system network comprises registered equipment users, design and manufacture parties of the equipment, a remote monitoring system, even a third-party operation and maintenance team network and various research and development groups.
8. The cloud platform-based big data intelligent health monitoring system according to claim 1, further comprising:
the health monitoring management module: the system comprises three sub-modules of knowledge base maintenance modification, user monitoring process management and real-time interactive process control, realizes ultra-large capacity, expandable and high fault tolerance storage of data based on a distributed file system (HDFS), can be used for storing data in any format, and provides basic data support for other modules of the system, and specifically comprises the following steps:
the health knowledge base modification module can maintain health phenomena and reasons, can add, delete, modify and check rules, and can enable users to continuously enrich and perfect the knowledge base, thereby achieving the expert level. The user saves the inquiry knowledge in the monitoring process, provides convenience for later use, and can edit, modify and save the user inquiry information database;
adopting a hadoop framework to carry out unified management on distributed resources, adopting Hdfs to provide data storage service, adopting a Spark framework to provide distributed computing service, and using a relational database Mysql to store structured service data;
the modification tool is also used for selecting a health file to be imported into the HDFS and selecting a generated rule file to be imported into the HBase, and meanwhile, for a program which is debugged and compiled on Windows, the file can be imported into a specified directory of the cloud computing platform through a selected program file inlet and the execution of the cloud computing platform is controlled through an execution button.
9. The cloud platform-based big data intelligent health monitoring system according to claim 1, wherein the intelligent Agent module further comprises difference monitoring between different monitoring methods:
Fdp＝||Hdpβdp-T||2+λ||Hdpβdp-Ydp-1||2where T is a class label and λ is a generalization coefficient.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2019104965001 | 2019-06-10 | ||
| CN201910496500.1A CN110215189A (en) | 2019-06-10 | 2019-06-10 | A kind of big data size intelligent healthcare system based on cloud platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112057038A true CN112057038A (en) | 2020-12-11 |
Family
ID=67815931
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910496500.1A Pending CN110215189A (en) | 2019-06-10 | 2019-06-10 | A kind of big data size intelligent healthcare system based on cloud platform |
| CN202010519520.9A Withdrawn CN112057038A (en) | 2019-06-10 | 2020-06-09 | Big data intelligent health monitoring system based on cloud platform |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910496500.1A Pending CN110215189A (en) | 2019-06-10 | 2019-06-10 | A kind of big data size intelligent healthcare system based on cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN110215189A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112712865A (en) * | 2020-12-24 | 2021-04-27 | 重庆至道医院管理股份有限公司 | Multi-source heterogeneous doctor-patient experience abnormal data fusion working system and working method |
| CN112947148A (en) * | 2021-01-28 | 2021-06-11 | 王仲楷 | Wisdom thing networking big data cloud platform based on health monitoring |
| CN113990477A (en) * | 2021-10-20 | 2022-01-28 | 上海轻迅信息科技有限公司 | Big data intelligent health monitoring system based on cloud platform |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689956A (en) * | 2019-10-12 | 2020-01-14 | 河北时代电子有限公司 | Intelligent internet big data platform for health monitoring |
| CN116992235A (en) * | 2023-08-09 | 2023-11-03 | 哈尔滨天君科技有限公司 | Big data analysis system and method for computer parallelization synchronization |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140022641A (en) * | 2012-08-14 | 2014-02-25 | 계명대학교 산학협력단 | Health diary service system for chronic disease based on intelligent agent technology, and thereof method |
| KR20140075400A (en) * | 2012-12-11 | 2014-06-19 | 한국전자통신연구원 | A smart agent system for modeling uesr's psychological anomalies based upon user's bio information |
| CN104573862A (en) * | 2015-01-06 | 2015-04-29 | 北京工商大学 | Lake, reservoir and drainage basin water quality monitoring section optimized layout method based on multiple agents |
| CN109065153A (en) * | 2018-07-24 | 2018-12-21 | 广东安家医健科技有限公司 | A kind of wisdom endowment system for management cloud platform of supporting parents |
-
2019
- 2019-06-10 CN CN201910496500.1A patent/CN110215189A/en active Pending
-
2020
- 2020-06-09 CN CN202010519520.9A patent/CN112057038A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140022641A (en) * | 2012-08-14 | 2014-02-25 | 계명대학교 산학협력단 | Health diary service system for chronic disease based on intelligent agent technology, and thereof method |
| KR20140075400A (en) * | 2012-12-11 | 2014-06-19 | 한국전자통신연구원 | A smart agent system for modeling uesr's psychological anomalies based upon user's bio information |
| CN104573862A (en) * | 2015-01-06 | 2015-04-29 | 北京工商大学 | Lake, reservoir and drainage basin water quality monitoring section optimized layout method based on multiple agents |
| CN109065153A (en) * | 2018-07-24 | 2018-12-21 | 广东安家医健科技有限公司 | A kind of wisdom endowment system for management cloud platform of supporting parents |
Non-Patent Citations (4)
| Title |
|---|
| 张晓阳，等: "基于生物免疫机制的复杂系统健康监测与评估", 《系统仿真学报》 * |
| 张莉，等: "飞机电源多Agent预测与健康管理系统研究", 《计算机工程与应用》 * |
| 童海星，等: "基于多Agent系统手术室在线调度研究", 《计算机应用与软件》 * |
| 邹焱飚，等: "基于多Agent 的家庭远程监护系统建模", 《计算机工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112712865A (en) * | 2020-12-24 | 2021-04-27 | 重庆至道医院管理股份有限公司 | Multi-source heterogeneous doctor-patient experience abnormal data fusion working system and working method |
| CN112947148A (en) * | 2021-01-28 | 2021-06-11 | 王仲楷 | Wisdom thing networking big data cloud platform based on health monitoring |
| CN113990477A (en) * | 2021-10-20 | 2022-01-28 | 上海轻迅信息科技有限公司 | Big data intelligent health monitoring system based on cloud platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110215189A (en) | 2019-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112057038A (en) | Big data intelligent health monitoring system based on cloud platform | |
| Greco et al. | An edge-stream computing infrastructure for real-time analysis of wearable sensors data | |
| CN110415831A (en) | A kind of medical treatment big data cloud service analysis platform | |
| Santos et al. | INTCARE: multi-agent approach for real-time intelligent decision support in intensive medicine | |
| Paraschiakos et al. | Activity recognition using wearable sensors for tracking the elderly | |
| Kovalchuk et al. | Distributed data-driven platform for urgent decision making in cardiological ambulance control | |
| CN109508422A (en) | The height of multithreading intelligent scheduling is hidden crawler system | |
| Soltani et al. | A study on siro, solo, compact, and conventional ring-spun yarns. Part III: modeling fiber migration using modular adaptive neuro-fuzzy inference system | |
| Oğur et al. | IoT data analytics architecture for smart healthcare using RFID and WSN | |
| Wu | Optimization of AI-driven communication systems for green hospitals in sustainable cities | |
| Thangaraj et al. | Agent based semantic internet of things (IoT) in smart health care | |
| Buldakova et al. | Multi-agent architecture for medical diagnostic systems | |
| Du et al. | Framework and challenges for wireless body area networks based on big data | |
| Larcher et al. | Event-driven framework for detecting unusual patterns in AAL environments | |
| García-Magariño et al. | Fog computing for assisting and tracking elder patients with neurodegenerative diseases | |
| Balamurugan et al. | Secured cloud computing for medical database monitoring using machine learning techniques | |
| Fanghua et al. | Internet intervention system for elderly hypertensive patients based on hospital community family edge network and personal medical resources optimization | |
| de Souza et al. | Ontology-driven IoT system for monitoring hypertension | |
| JP6783961B1 (en) | Information processing equipment, information processing methods, and programs | |
| Plattner et al. | A multi-sensory approach to acquire and process health and lifestyle information | |
| Cuzzocrea et al. | Intelligent sensor data fusion for supporting advanced smart health processes | |
| Wang et al. | Design of an Intelligent Nursing Information Management System for Critically Ill Patients in Neurosurgery | |
| Lakehal et al. | Real-time ontology-based context-aware situation reasoning framework in pervasive computing | |
| Aladdin et al. | Fitness-Dependent Optimizer for IoT Healthcare Using Adapted Parameters: A Case Study Implementation | |
| Garai et al. | Reflective bio-sensory signal-processing: implementing personal assisted e-Health |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201211 |