CN115702775A - Edge computing node and data processing system - Google Patents
Edge computing node and data processing system Download PDFInfo
- Publication number
- CN115702775A CN115702775A CN202110893287.5A CN202110893287A CN115702775A CN 115702775 A CN115702775 A CN 115702775A CN 202110893287 A CN202110893287 A CN 202110893287A CN 115702775 A CN115702775 A CN 115702775A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- layer
- node
- monitoring data
- 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
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The embodiment of the invention is suitable for the technical field of data processing, and provides an edge computing node and a data processing system, wherein the edge computing node comprises: the data processing layer is used for receiving the monitoring data acquired by the monitoring nodes and processing the monitoring data; the memory mapping layer is used for caching the processed monitoring data; the data display layer is used for displaying the monitoring data in the memory mapping layer; the unified control layer is used for responding to the command sent by the monitoring management layer, managing and controlling the monitoring data displayed by the data display layer and the monitoring data cached in the memory mapping layer; and the monitoring management layer is used for receiving the operation instruction sent by the monitoring terminal and sending a corresponding command to the unified control layer according to the operation instruction. The invention improves the timeliness of the monitoring result.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to an edge computing node and a data processing system.
Background
When the related technology carries out sleep monitoring, monitoring data of a monitored person are collected through leads, the monitoring data are transmitted to a monitoring computer, and the monitoring data are processed through the monitoring computer to obtain monitoring results of the sleep quality and the like of the monitored person. In the related art, a monitoring computer is required to process monitoring data, and when the monitoring data volume is large or the correlation degree is high, the monitoring computer cannot quickly obtain a monitoring result, so that the timeliness of the monitoring result is not strong.
Disclosure of Invention
In order to solve the above problem, an embodiment of the present invention provides an edge computing node to at least solve the problem that the timeliness of the monitoring result of the related art is not strong.
The technical scheme of the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides an edge computing node, where the method includes:
the data processing layer is used for receiving the monitoring data acquired by the monitoring nodes and processing the monitoring data;
the memory mapping layer is used for caching the processed monitoring data;
the data display layer is used for displaying the monitoring data in the memory mapping layer;
the unified control layer is used for responding to a command sent by the monitoring management layer, managing and controlling the monitoring data displayed by the data display layer and the monitoring data cached in the memory mapping layer;
and the monitoring management layer is used for receiving an operation instruction sent by the monitoring terminal and sending a corresponding command to the unified control layer according to the operation instruction.
In the above solution, the node further includes:
the data analysis layer is used for carrying out sleep staging on the monitoring data based on the sleep staging model to obtain a sleep staging result of the corresponding monitoring object; the monitoring data characterizes sleep data of the monitored subject.
In the foregoing solution, the data processing layer is configured to:
carrying out variable length coding on the monitoring data;
analyzing the monitoring data after the variable length coding to obtain the monitoring data for displaying on a data display layer.
In the foregoing solution, the unified control layer is configured to:
deleting the monitoring data cached in the memory mapping layer based on a first deletion command sent by the monitoring management layer; or the like, or a combination thereof,
deleting the monitoring data displayed by the data display layer based on a second deletion command sent by the monitoring management layer; or the like, or, alternatively,
and updating the monitoring data displayed by the data display layer based on the monitoring data cached in the memory mapping layer based on the updating command sent by the monitoring management layer.
In the foregoing solution, the memory mapping layer further includes a data interface for communicating between the monitoring node and the edge computing node;
the unified control layer is used for modifying the configuration parameters of the data interface based on the command sent by the monitoring management layer.
In the above scheme, before performing variable length coding on the monitoring data, the data processing layer is further configured to:
and filtering the monitoring data to obtain the monitoring data with noise filtered.
In a second aspect, an embodiment of the present invention provides a data processing system, where the system includes:
in the above solution, the system includes:
at least one edge compute node according to any one of claims 1 to 6;
each edge computing node in the at least one edge computing node is connected with at least one monitoring node, and each monitoring node in the at least one monitoring node is used for collecting monitoring data of a corresponding monitoring object;
and the central computing node is used for receiving the monitoring data sent by the at least one edge computing node and analyzing the data based on the monitoring data.
In the above solution, the monitoring node includes: the system comprises an environment monitoring module and a physical sign monitoring module;
the environment monitoring module is used for acquiring environmental data around a monitored object;
the sign monitoring module is used for acquiring sign data of a monitored object.
In the above solution, the monitoring node includes:
and the data processing module is used for coding and compressing the acquired monitoring data.
In the foregoing solution, when the central computing node performs data analysis based on the monitoring data, the central computing node is configured to:
and upgrading the sleep staging model corresponding to the at least one edge computing node based on the monitoring data of each edge computing node in the at least one edge computing node.
In the embodiment of the invention, the edge computing node receives monitoring data acquired by the monitoring node through the data processing layer and processes the monitoring data; caching the processed monitoring data through a memory mapping layer; displaying the monitoring data in the memory mapping layer through the data display layer; receiving an operation instruction sent by a monitoring terminal through a monitoring management layer, and sending a corresponding command to a unified control layer according to the operation instruction; and the unified control layer responds to a command sent by the monitoring management layer, and manages and controls the monitoring data displayed by the data display layer and the monitoring data cached in the memory mapping layer. According to the embodiment of the invention, the processing and monitoring of the monitoring data are completed through the data interaction among all functional layers in the edge computing assembly, the monitoring result can be quickly obtained, and the timeliness of the monitoring result is improved. And the region limitation when the monitor monitors the data is removed, and the monitor can conveniently check the monitoring data at any time and any place.
Drawings
Fig. 1 is a schematic structural diagram of a first edge computing node according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a second edge computing node according to an embodiment of the present invention;
FIG. 3 is a block diagram of a data processing system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a first monitoring node according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a second monitoring node according to an embodiment of the present invention;
FIG. 6 is a schematic representation of a first lead waveform provided by an applied embodiment of the present invention;
FIG. 7 is a schematic representation of a second lead waveform provided by an applied embodiment of the present invention;
FIG. 8 is a schematic diagram of impedance line segments in a lead waveform diagram provided in accordance with an illustrative embodiment of the present invention;
FIG. 9 is a schematic diagram of statistical information of monitoring data according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a monitoring timeline provided by an embodiment of the present invention;
fig. 11 is a schematic structural diagram of a central computing node according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
According to the sleep monitoring technical scheme in the related art, a tested person wears a multi-lead monitoring device, the monitoring device records characteristics data of the tested person, such as electroencephalogram, eye movement, electrocardio, blood oxygen saturation, related muscle movement and the like, then the characteristics data are transmitted to a monitoring computer, and the sleep quality of the tested person is judged by carrying out sleep analysis on the tested person through software running on the monitoring computer. In the related art, the computer running the software and the monitoring device must be located in the same local area network, and the computer running the software and the monitoring device are in a one-to-one relationship, and other devices cannot be replaced to monitor the monitoring data midway, so that the portability is restricted. And local computing resources are limited, the acquired monitoring data are time sequence continuous signals, the data volume is large, the data association degree is high, and a large amount of computing resources are consumed when the monitoring data are intelligently analyzed, so that a monitoring computer cannot quickly obtain a monitoring result, the timeliness of the monitoring result is not strong, and a monitor cannot obtain a real-time monitoring result.
In view of the above disadvantages of the related art, embodiments of the present invention provide an edge computing node, which can at least improve timeliness of a monitoring result. In order to illustrate the technical means of the present invention, the following description is given by way of specific examples.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an edge computing node according to an embodiment of the present invention, where the edge computing node includes: the device comprises a data processing layer, a memory mapping layer, a data display layer, a unified control layer and a monitoring management layer.
And the data processing layer is used for receiving the monitoring data acquired by the monitoring nodes and processing the monitoring data.
Here, each monitoring node collects monitoring data of a detection object, and each edge calculation node corresponds to at least one monitoring node. For example, an edge computing node is set in a hospital, and the edge computing node is connected with a plurality of monitoring nodes, and each monitoring node collects monitoring data of a patient.
In one embodiment, the data processing layer is configured to:
and carrying out variable length coding on the monitoring data, and analyzing the monitoring data subjected to the variable length coding to obtain the monitoring data for displaying on a data display layer.
Here, the variable length coding is a lossless data compression method, and compresses data to reduce a storage space, and the variable length coding functions to save the storage space of the memory mapping layer. And analyzing the monitoring data subjected to variable length coding to obtain the monitoring data for displaying on the data display layer.
In an embodiment, before performing the variable length coding on the monitoring data, the data processing layer is further configured to: and carrying out filtering processing on the monitoring data to obtain the monitoring data with noise filtered.
Due to the influence of spike noise, the instantaneous highest detection value of the monitored object has an abnormal maximum value. In order to eliminate the peak noise, median filtering processing is carried out on the monitoring data, and noise data in the monitoring data are eliminated.
And the memory mapping layer is used for caching the processed monitoring data.
And the data display layer is used for displaying the monitoring data in the memory mapping layer.
Monitoring data processed by the data processing layer are cached in the memory mapping layer, and the data display layer obtains the monitoring data from the memory mapping layer for display.
In practical application, the data display layer can display the data acquired by each monitoring node in a window mode, and the monitoring data can be displayed in the window in the forms of numerical values, tables, graphs and the like. For example, in a hospital, the data collected by each monitoring node can be distinguished by the name of a patient, the yard and the number, and the monitoring data of each patient is displayed in the form of a plurality of label pages.
For example, if the monitoring data is lead data acquired from a lead, a lead waveform map is generated in the window based on the lead data. And a monitoring time axis is provided in the window, so that a monitor can conveniently determine the time corresponding to the monitoring data.
And the unified control layer is used for responding to a command sent by the monitoring management layer, managing and controlling the monitoring data displayed by the data display layer and the monitoring data cached in the memory mapping layer.
And the monitoring management layer is used for receiving an operation instruction sent by the monitoring terminal and sending a corresponding command to the unified control layer according to the operation instruction.
The monitoring management layer provides a management function for a monitor, and the monitor can log in an edge computing node through a monitoring terminal to manage and control the monitoring data displayed by the data display layer and the monitoring data cached in the memory mapping layer. Here, the monitoring terminal includes a mobile phone, a computer, and the like. A monitor can remotely log in the edge computing node for monitoring without checking monitoring data on a specific terminal, so that the regional limitation is removed, and the monitor can conveniently monitor a monitored object at any time and any place.
A monitor can send a control operation instruction to the monitoring management layer through the monitoring terminal, and the monitoring management layer sends a corresponding command to the unified control layer according to the control operation instruction. The unified control layer responds to the command and executes corresponding operation.
For example, the monitoring data collected by each monitoring node is displayed on the data display layer in a window form, a monitor can send an operation instruction for closing the window to the monitoring management layer through the monitoring terminal, the monitoring management layer sends a command for closing the window to the unified control layer, and the unified control layer responds to the command and closes the corresponding window on the data display layer.
The unified control layer is used for unified management of the data display layer and the memory mapping layer, for example, deleting or updating data displayed in the data display layer, deleting data cached in the memory mapping layer, and the like.
In one embodiment, the unified control layer is configured to:
deleting the monitoring data cached in the memory mapping layer based on a first deletion command sent by the monitoring management layer; or the like, or, alternatively,
deleting the monitoring data displayed by the data display layer based on a second deletion command sent by the monitoring management layer; or the like, or a combination thereof,
and updating the monitoring data displayed by the data display layer based on the monitoring data cached in the memory mapping layer based on the updating command sent by the monitoring management layer.
Because the monitoring data is a time sequence continuous signal, the monitoring data is continuously cached in the memory mapping layer, and the monitoring data displayed by the monitoring data updating data display layer needs to be continuously acquired from the cache to realize the real-time display of the current monitoring data.
When the cache space in the memory mapping layer is insufficient, the historical monitoring data of the cache in the memory mapping layer can be deleted through the unified control layer.
In one embodiment, the memory mapping layer further comprises a data interface for communicating between the monitoring node and the edge computing node; the unified control layer is used for modifying the configuration parameters of the data interface based on the command sent by the monitoring management layer.
Here, the configuration parameters of the data interface refer to the data type, data size, etc. of the received monitoring data, for example, assuming that the monitoring data is lead data, the configuration parameters may be the type of lead, the data size and format collected by each lead. And when the monitoring node collects the monitoring data, the data is collected according to the configuration parameters of the data interface. In practical application, the configuration parameter is an xml file.
Referring to fig. 2, in an embodiment, the node further includes:
the data analysis layer is used for carrying out sleep staging on the monitoring data based on the sleep staging model to obtain a sleep staging result of the corresponding monitoring object; the monitoring data characterizes sleep data of the monitored subject.
The data analysis layer may perform data analysis on the monitoring data, for example, perform sleep analysis on the monitoring data to judge sleep quality.
For example, when the monitored data is sleep data of the monitored object, the data analysis layer may perform sleep staging on the monitored data based on the sleep staging model to obtain a sleep staging result of the monitored object.
During sleep, the electroencephalogram undergoes a variety of different changes, which vary with the depth of sleep. According to different characteristics of electroencephalogram, sleep is divided into two stages: non-ocular fast-moving sleep stages (also known as normal phase sleep, slow wave sleep, synchronous sleep, quiet sleep, NREM sleep) and ocular fast-moving sleep stages (also known as out-of-phase sleep, fast wave sleep, desynchronized sleep, active sleep, REM sleep). The non-eyeball rapid movement sleep stage can also be divided into 4 stages, wherein the 1 st stage is a sleep onset stage, the 2 nd stage is a light sleep stage, the 3 rd stage is a medium sleep stage, and the 4 th stage is a deep sleep stage.
And (4) performing sleep staging on the monitoring data, wherein the sleep staging result can be used for judging the sleep quality of the monitored object.
In the embodiment of the invention, the edge computing node receives monitoring data acquired by the monitoring node through the data processing layer and processes the monitoring data; caching the processed monitoring data through a memory mapping layer; displaying the monitoring data in the memory mapping layer through the data display layer; receiving an operation instruction sent by a monitoring terminal through a monitoring management layer, and sending a corresponding command to a unified control layer according to the operation instruction; and the unified control layer responds to a command sent by the monitoring management layer, and manages and controls the monitoring data displayed by the data display layer and the monitoring data cached in the memory mapping layer. According to the embodiment of the invention, the processing and monitoring of the monitoring data are completed through the data interaction among the functional layers in the edge computing assembly, the monitoring result can be quickly obtained, and the timeliness of the monitoring result is improved. And the regional limitation of the monitor in data monitoring is removed, and the monitor can conveniently check the monitoring data at any time and any place.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a data processing system according to an embodiment of the present invention, where the data processing system includes: the system comprises at least one edge computing node, at least one monitoring node and a central computing node.
Each edge computing node in the at least one edge computing node is connected with at least one monitoring node, and each monitoring node in the at least one monitoring node is used for collecting monitoring data of a corresponding monitoring object.
And the central computing node is used for receiving the monitoring data sent by the at least one edge computing node and analyzing the data based on the monitoring data.
For example, in a medical system scenario of a hospital, it is assumed that a market has 10 hospitals, each hospital has an edge computing node, each hospital has at least one monitoring node, and each monitoring node monitors one patient. The 10 hospitals correspond to a central computing node together, and the central computing node summarizes the monitoring data sent by the 10 hospitals and provides the functions of data analysis and management.
In one embodiment the monitoring node comprises: the system comprises an environment monitoring module and a physical sign monitoring module;
the environment monitoring module is used for acquiring environmental data around a monitored object;
the sign monitoring module is used for acquiring sign data of a monitored object.
For example, the environment monitoring module may be a light intensity sensor, a humidity sensor, a temperature sensor, an air pressure sensor, or the like. The environment monitoring module collects environment data such as light intensity, noise, oxygen concentration, air humidity, air pressure, temperature and the like around a monitored object.
The physical sign monitoring module can be a lead, a body temperature sensor, a body position sensor, a sound sensor and the like. The physical sign monitoring module collects electroencephalogram, myoelectricity, electrocardio, blood oxygen, respiratory state, snore, body position and other physical sign data of a monitored object.
In one embodiment, the monitoring node further comprises:
and the data processing module is used for coding and compressing the acquired monitoring data.
The data processing module encodes the acquired data and then compresses the encoded data according to a compression algorithm.
Here, the monitoring data that the monitoring node can collect is sent to the edge computing node at set time intervals.
In one embodiment, the central computing node, in performing data analysis based on the monitoring data, is configured to:
and upgrading the sleep staging model corresponding to the at least one edge computing node based on the monitoring data of each edge computing node in the at least one edge computing node.
Here, each edge computing node includes a sleep staging model, and the edge computing node may perform sleep staging on the monitoring data by using the sleep staging model.
In the embodiment of the present invention, the central computing node may upgrade the sleep staging model corresponding to the edge computing node according to the monitoring data of each edge computing node, and then issue the upgraded sleep staging model to each edge computing node. Here, the sleep stage model corresponding to each of the at least one edge computing node may be the same or different.
In addition, the central computing node may also manage the monitoring data in each edge computing node, for example, view the monitoring data of a specific monitoring object, modify the system authority of each edge computing node, issue a specific configuration file to each edge computing node, and the like.
The embodiment of the invention combines edge calculation and data monitoring, and realizes data monitoring through three systems, namely a monitoring node, an edge calculation sub-node and a central calculation node. The monitoring data of the monitoring objects are collected at the monitoring nodes, and the monitoring efficiency of a monitor is improved by carrying out cloud monitoring and cloud analysis on a plurality of monitoring objects through the edge computing nodes. The monitoring data is collected and processed at the edge computing node, so that the monitoring portability is greatly improved, a monitor can be connected to the edge computing node through any equipment for operating monitoring terminal software, and the monitoring data which can be obtained in the authority can be obtained through the edge computing node for real-time analysis and display. The whole system carries out unified management and analysis through the central computing node, and realizes decentralized monitoring and unified management.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a monitoring node according to an application embodiment of the present invention, where the monitoring node includes a sign signal acquisition module, an environmental signal acquisition module, a data processing module, an information distribution unit, and a wireless communication module.
The physical sign signal acquisition module is used for acquiring physical sign signals such as electroencephalogram, myoelectricity, electrocardio, blood oxygen, respiratory states, snore, body positions and the like.
The environment signal acquisition module is used for acquiring environment signals such as light intensity, noise, oxygen concentration, carbon dioxide concentration, air humidity, air pressure, temperature and the like around the monitored object.
The data processing module comprises a data coding module and a data compression module, the data coding module is used for coding the collected data, and the data compression module compresses the coded data according to a compression algorithm.
The wireless communication module is used for communicating with the edge computing node.
The information distribution unit sends the acquired data to the wireless communication module, and the wireless communication module sends the acquired data to the edge computing node. The wireless communication module can also receive a control instruction issued by the edge computing node, the wireless communication module sends the control instruction to the information distribution unit, and the information distribution unit issues the control instruction to the sign signal acquisition module, the environment signal acquisition module or the data processing module. For example, the control instructions may be used to adjust a compression algorithm of the data compression module.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an edge computing node according to an application embodiment of the present invention, where the edge computing node includes: the system comprises a view display layer, a memory mapping layer, a data processing layer, a unified control layer, an AI analysis layer and a monitoring management layer.
Wherein the view display layer comprises: lead window, impedance window, function window, merge file, start-stop function. Here, the entities of the monitoring nodes are leads.
The lead window provides lead set up functions including deleting leads, adjusting lead units, adding leads, and inverting waveforms.
The impedance window provides impedance setting functions including deleting impedance, adjusting units of impedance, adding impedance, and the like. Impedance refers to the impedance of the lead, which is also shown in the view display layer.
And a function window for providing selection functions, including options of new and open, view control, automatic interpretation (blood oxygen, apnea, hypopnea, limb movement, cardiac activity), report generation and the like.
And combining files, wherein the data acquired by each lead is stored in a binary file named by the lead by default, and a plurality of acquired data subfiles are combined into a complete binary file by utilizing the function after the acquisition is finished, so that the system can analyze all physiological signals and environmental signals.
And the start-stop function controls the monitoring node to be in a monitoring state or a closing state.
In practical applications, the data collected for each lead is presented in a window where the lead waveforms can be drawn from the lead data. Referring to fig. 6, fig. 6 is a schematic diagram of a lead waveform diagram according to an embodiment of the present invention, which is obtained by analyzing information such as the name, unit, sampling rate, etc. of a lead from a file transmitted from a monitoring node, dividing data into an upper window and a lower window according to the relation between the sampling rate and 256Hz, where the upper window has a length of 30 seconds, the lower window has a length of 2 minutes, and the middle is divided by an impedance lead. The window supports the functions of scaling, displaying and adjusting the maximum and minimum values, reversing the waveform and the like.
Drawing lead waveforms from lead data, referring to fig. 7, fig. 7 is a schematic diagram of a lead waveform diagram according to an embodiment of the present invention. Fixed byte hexadecimal digits are converted to decimal values from the received data packet according to the communication protocol, and the digital values are converted to analog values having units using the parsed values per unit per lead. Noise in the data is filtered out using a low pass filter, a smoothing filter, or the like. The impedance leads are displayed differently from the other leads, with all of the impedance leads being displayed in the same row. The different impedance values are represented by different color line segments, for example, the impedance values are represented by light green line segments in the range of 0-5K omega, dark green line segments in the range of 5K omega-10K omega, red line segments above 10K omega, and the impedance lead refresh frequency is the same as that of other leads.
Referring to fig. 8, fig. 8 is a schematic diagram of impedance line segments in a lead waveform diagram according to an embodiment of the present invention. The impedance line segments for the EMG1 leads are shown in fig. 8.
Referring to fig. 9, fig. 9 is a schematic diagram of statistical information of monitoring data according to an embodiment of the present invention, in which after a lead waveform is drawn, the waveform and data are drawn during a period of being stored every set time, an Epoch is a period, and the number of epochs of data stored in upper and lower windows is counted, for an upper window, an Epoch may be set every 30 seconds, and for a lower window, an Epoch may be set every 2 minutes. In the window, the statistical information may be displayed at the bottom of the window.
Fig. 10 is a schematic view of a monitoring time axis provided by an embodiment of the present invention, in which two time axes are respectively displayed at the topmost ends of upper and lower windows in a lead waveform diagram for determining the current time. The judgment of some events needs to be continued for a certain time, and the time positioning can be conveniently carried out by monitoring the time shaft. The interval between the two times of the time axis of the upper window is 5 seconds, and the interval between the two times of the time axis of the lower window is 20 seconds.
And in the memory mapping layer, the service public data is uniformly managed in the layer, and the structure of the layer is required to process the data change. The functions provided by the memory mapping layer include: data caching, XML updating, configuration management, message management and data interfaces.
Data caching: and for the monitoring data acquired by the monitoring node, caching the monitoring data in a memory by using a dual-cycle cache.
XML updating: and updating the configuration of the monitoring node and the client software during communication.
Configuration management: and managing the configuration state of the memory.
Message management: and uniformly managing the system messages.
A data interface: and configuring and managing the data interface message.
And the data processing layer is responsible for monitoring the unified management of data, receiving and analyzing the data, notifying the data change and the like. The data processing layer has the functions of: data receiving, data coding, data analyzing and data processing.
Data receiving: receiving monitoring data sent by the monitoring node and receiving a control instruction.
Data encoding: and coding the received monitoring data according to a variable length coding mode.
Data analysis: and analyzing the coded monitoring data for displaying the monitoring data by the view display layer.
Data processing: and filtering the received data, and putting the processed data into a cache of a memory mapping layer. In practical applications, in a hospital scenario, as the monitoring data provided by the hospital increases, different sampling frequencies and units of heart rate data appear. In order to enable the heart rate automatic analysis algorithm to adapt to different types of data, the sampling frequency and the unit of the heart rate are set as variables, variable values are read from a data packet header, and different processing methods are used according to different sampling frequencies and data units. The optimized algorithm is suitable for the heart rate data with any sampling frequency and with the data unit of mV or mu V. In addition, due to the influence of spike noise, an abnormal maximum value may occur in the instantaneous maximum detection value of the object. To eliminate spike noise, the detected R-R intervals are median filtered.
The unified control layer is used for managing other layers according to the command of the monitoring management layer, and the main functions comprise: view lifecycle management, lifecycle management of modules, command response, and memory mapping management.
And (3) view life cycle management: unified management of user end views for modular customization needs can respond quickly.
And (3) managing the life cycle of each module: and the life cycle of each functional layer is uniformly managed, including the online and expiration of each layer.
And command response: for responding to user's action instructions.
Memory mapping management: and uniformly managing the system memory mapping relationship, such as deleting cache data in the memory mapping layer.
And a monitoring management layer: the functions of the monitoring management layer include terminal management, data management and session management. The layer can manage and control data in memory mapping management, manage and control monitoring data displayed on the view display layer, receive an operation instruction sent by a monitoring terminal, and send a corresponding command to the unified control layer according to the operation instruction. The unified control layer executes corresponding operations according to the commands, such as deleting the monitoring data cached in the memory mapping layer, updating the monitoring data displayed by the data display layer based on the monitoring data cached in the memory mapping layer, and the like.
And the AI analysis layer intelligently analyzes the monitoring data at the edge element and comprises a sleep staging function. The AI analysis layer includes: the device comprises a filtering module, a Hilbert-Huang (HHT) transformation module, a Support Vector Machine (SVM) processing module and an AI analysis module.
The HHT transformation means that empirical mode decomposition is performed on a signal to obtain an intrinsic mode function, and then hilbert transformation is performed on the intrinsic mode function, so that a hilbert spectrum, a time-frequency energy spectrum and the like of the signal are further obtained, so as to analyze the signal.
Referring to fig. 11, fig. 11 is a schematic structural diagram of a central computing node according to an embodiment of the present invention, where the central computing node includes: the system comprises a data processing layer, an AI analysis layer and a management layer.
The functions of the data processing layer include data reception, data encoding, data processing, and data storage. And the data processing layer receives the data sent by the edge computing node, encodes and analyzes the data, and then stores the data.
The AI analysis layer provides a data analysis function, and performs AI analysis mining on all data with practical significance through big data analysis.
The management layer is used for carrying out unified management on roles of all edge computing nodes, and the unified management comprises information management, report management and data query of monitoring objects.
In a sleep monitoring scene, the application embodiment of the invention combines the capabilities of sleep monitoring hardware, a communication technology, an edge cloud and a center cloud to provide flexible and convenient sleep monitoring capability. The acquisition of physiological signals and sleep environment data of a patient in sleep is realized through monitoring hardware, a six-layer structure is designed in an edge computing node, each layer plays its own role, the intelligent monitoring of the sleep of the patient is completed, and one-to-many client monitoring data collection and management are realized at the edge computing node. And realizing sleep monitoring global data analysis and mining at the central computing node. By utilizing the technology of 5G + edge calculation + center calculation + AI, the intelligent sleep monitoring loosely coupled with a computer can be realized, and the efficiency of monitoring the sleep condition of a patient is fully improved.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In several embodiments provided in the present application, the above-described apparatus embodiment is only illustrative, for example, the division of the layer is only one logical function division, and there may be other division ways in actual implementation, such as: multiple layers or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit may be implemented in the form of hardware, or in the form of hardware plus a software functional unit.
The technical means described in the embodiments of the present application may be arbitrarily combined without conflict.
In addition, in the examples of the present application, "first", "second", and the like are used for distinguishing similar objects, and are not necessarily used for describing a specific order or a sequential order.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An edge computing node, the node comprising:
the data processing layer is used for receiving the monitoring data acquired by the monitoring nodes and processing the monitoring data;
the memory mapping layer is used for caching the processed monitoring data;
the data display layer is used for displaying the monitoring data in the memory mapping layer;
the unified control layer is used for responding to a command sent by the monitoring management layer, managing and controlling the monitoring data displayed by the data display layer and the monitoring data cached in the memory mapping layer;
and the monitoring management layer is used for receiving an operation instruction sent by the monitoring terminal and sending a corresponding command to the unified control layer according to the operation instruction.
2. The node of claim 1, further comprising:
the data analysis layer is used for carrying out sleep staging on the monitoring data based on the sleep staging model to obtain a sleep staging result of the corresponding monitoring object; the monitoring data characterizes sleep data of the monitored subject.
3. The node of claim 1, wherein the data processing layer is configured to:
carrying out variable length coding on the monitoring data;
and analyzing the monitoring data after variable length coding to obtain the monitoring data for displaying on the data display layer.
4. The node of claim 1, wherein the unified control layer is configured to:
deleting the monitoring data cached in the memory mapping layer based on a first deletion command sent by the monitoring management layer; or the like, or, alternatively,
deleting the monitoring data displayed by the data display layer based on a second deleting command sent by the monitoring management layer; or the like, or, alternatively,
and updating the monitoring data displayed by the data display layer based on the monitoring data cached in the memory mapping layer based on the updating command sent by the monitoring management layer.
5. The node of claim 1, wherein the memory mapping layer further comprises a data interface for communicating between the monitoring node and the edge compute node;
the unified control layer is used for modifying the configuration parameters of the data interface based on the command sent by the monitoring management layer.
6. The node of claim 3, wherein the data processing layer, prior to variable length coding the monitor data, is further configured to:
and carrying out filtering processing on the monitoring data to obtain the monitoring data with noise filtered.
7. A data processing system, characterized in that the system comprises:
at least one edge compute node according to any one of claims 1 to 6;
each edge computing node in the at least one edge computing node is connected with at least one monitoring node, and each monitoring node in the at least one monitoring node is used for acquiring monitoring data of a corresponding monitoring object;
and the central computing node is used for receiving the monitoring data sent by the at least one edge computing node and analyzing the data based on the monitoring data.
8. The system of claim 7, wherein the monitoring node comprises: the system comprises an environment monitoring module and a physical sign monitoring module;
the environment monitoring module is used for acquiring environmental data around a monitored object;
the sign monitoring module is used for acquiring sign data of a monitored object.
9. The system of claim 7, wherein the monitoring node comprises:
and the data processing module is used for coding and compressing the acquired monitoring data.
10. The system of claim 7, wherein the central computing node, in performing data analysis based on the monitoring data, is configured to:
and upgrading the sleep staging model corresponding to the at least one edge computing node based on the monitoring data of each edge computing node in the at least one edge computing node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893287.5A CN115702775A (en) | 2021-08-04 | 2021-08-04 | Edge computing node and data processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110893287.5A CN115702775A (en) | 2021-08-04 | 2021-08-04 | Edge computing node and data processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115702775A true CN115702775A (en) | 2023-02-17 |
Family
ID=85178886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110893287.5A Pending CN115702775A (en) | 2021-08-04 | 2021-08-04 | Edge computing node and data processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115702775A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117439853A (en) * | 2023-12-19 | 2024-01-23 | 华章数据技术有限公司 | Cloud edge end-based data operation and maintenance management system |
-
2021
- 2021-08-04 CN CN202110893287.5A patent/CN115702775A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117439853A (en) * | 2023-12-19 | 2024-01-23 | 华章数据技术有限公司 | Cloud edge end-based data operation and maintenance management system |
| CN117439853B (en) * | 2023-12-19 | 2024-04-05 | 华章数据技术有限公司 | Cloud edge end-based data operation and maintenance management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100444788C (en) | Remote mobile electrophysiological data monitoring method and apparatus based on WAN | |
| CN105232032A (en) | Remote electrocardiograph monitoring and early warning system and method based on wavelet analysis | |
| CN104490388A (en) | Extensible human health remote recording, monitoring and diagnosis system | |
| Deshpande et al. | Iot based real time ecg monitoring system using cypress wiced | |
| CN1751656A (en) | Long-distance, radio-electrocardiogram real-time monitoring system, and method therefor | |
| CN106821366A (en) | Intelligent cardiac monitor system | |
| CN108309233A (en) | Sleep quality monitoring method, system, computer equipment and storage medium | |
| CN204336910U (en) | A kind of extendible health remote logging, monitoring and diagnostic system | |
| CN110192842A (en) | System and method is monitored based on the integrated data of physiological index of cloud side end | |
| CN110047575A (en) | A kind of reaction type sleeping system based on Remote Decision-making | |
| CN106963363A (en) | A kind of mobile phone shell of integrated electrocardio and skin pyroelectric monitor | |
| CN104161511A (en) | Portable sleep monitoring system | |
| CN115702775A (en) | Edge computing node and data processing system | |
| CN103932699A (en) | Electrocardiograph monitor | |
| CN204744132U (en) | Long -range health detection and service system | |
| CN115137324A (en) | Human heart health monitoring system based on cloud-edge-end architecture | |
| CN105975758A (en) | Remote auxiliary system terminal of medical device | |
| CN110664394A (en) | Real-time electrocardiogram monitoring system and monitoring method | |
| CN105066359A (en) | Air-conditioning remote control method based on electroencephalograph control | |
| Trobec et al. | Wireless network of bipolar body electrodes | |
| CN1428126A (en) | Multi-parameter portable mobile remote health monitoring apparatus | |
| CN109009209A (en) | A kind of Intelligent stethoscope based on cloud | |
| CN113284592A (en) | Medical equipment integrated management system based on hospital equipment department management | |
| CN106859633A (en) | Mobile ecg telemonitoring early warning system | |
| CN113852879B (en) | Data transmission method and system of wearable device |
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 |