CN116612892A - Health monitoring method and system of wearable device - Google Patents
Health monitoring method and system of wearable device Download PDFInfo
- Publication number
- CN116612892A CN116612892A CN202310871681.8A CN202310871681A CN116612892A CN 116612892 A CN116612892 A CN 116612892A CN 202310871681 A CN202310871681 A CN 202310871681A CN 116612892 A CN116612892 A CN 116612892A
- Authority
- CN
- China
- Prior art keywords
- health
- monitoring
- compensation
- health analysis
- scheme
- 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.)
- Granted
Links
- 230000036541 health Effects 0.000 title claims abstract description 226
- 238000012544 monitoring process Methods 0.000 title claims abstract description 112
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 155
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims description 37
- 238000001228 spectrum Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 22
- 238000010276 construction Methods 0.000 claims description 18
- 210000001124 body fluid Anatomy 0.000 claims description 9
- 239000010839 body fluid Substances 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 230000003238 somatosensory effect Effects 0.000 claims description 9
- 238000003745 diagnosis Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 abstract description 4
- 230000006978 adaptation Effects 0.000 abstract 1
- 230000009467 reduction Effects 0.000 description 7
- 230000029058 respiratory gaseous exchange Effects 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000002330 Congenital Heart Defects Diseases 0.000 description 1
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 208000008784 apnea Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000037219 healthy weight Effects 0.000 description 1
- 230000005831 heart abnormality Effects 0.000 description 1
- 239000005556 hormone Substances 0.000 description 1
- 229940088597 hormone Drugs 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002207 metabolite Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000008035 nerve activity Effects 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 210000004243 sweat Anatomy 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Veterinary Medicine (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application provides a health monitoring method and a health monitoring system of a wearable device, which relate to the technical field of data processing, and are used for monitoring and acquiring multi-element sensing signals of a target user, inputting the multi-element sensing signals into a health analysis model and acquiring health analysis results; the method comprises the steps of building a compensation knowledge graph, carrying out matching on a health analysis result to determine a health compensation scheme, feeding back the health compensation scheme to a user side, generating a scheme execution popup window, carrying out execution monitoring and early warning of the health compensation scheme based on a scheme monitoring instruction, solving the technical problems that the health monitoring method of a wearable device in the prior art is insufficient in monitoring completeness and accuracy and cannot carry out self-adaptive correction analysis and user supervision based on the monitoring result, taking a received monitoring feedback signal as an analysis data source, directly carrying out processing and modeling analysis, effectively guaranteeing the accuracy and completeness of the analysis result, carrying out compensation scheme decision by building the graph, guaranteeing the validity of the scheme and the user adaptation and carrying out targeted execution supervision.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a health monitoring method and system of a wearable device.
Background
Along with the development of flexible electronic technology, based on wearable medical equipment, daily health's sustainable monitoring weakens the dependence to large-scale medical equipment, and the guarantee user can know self health condition at any time to carry out intelligent prevention and control of disease.
At present, the health monitoring method based on the wearable device is mainly based on isolated monitoring of different monitoring dimensions, has certain limitations, leads to insufficient monitoring completeness and accuracy, and cannot perform self-adaptive correction analysis and user supervision based on monitoring results.
Disclosure of Invention
The application provides a health monitoring method and system of a wearable device, which are used for solving the technical problems that the health monitoring method of the wearable device in the prior art is insufficient in monitoring completeness and accuracy and cannot perform self-adaptive correction analysis and user supervision based on monitoring results.
In view of the above, the present application provides a method and a system for health monitoring of a wearable device.
In a first aspect, the present application provides a method of health monitoring of a wearable device, the method comprising:
based on the wearable device, monitoring and acquiring multi-element sensing signals of a target user, wherein the multi-element sensing signals comprise three dimensions of somatosensory monitoring, body fluid monitoring and electrophysiological monitoring;
inputting the multi-element sensing signals into a health analysis model, and outputting a health analysis result;
configuring a map triplet, interactively publishing collected data to extract information, and constructing a compensation knowledge map, wherein the compensation knowledge map has timeliness updating;
traversing the compensation knowledge graph, matching the health analysis result, and determining a health compensation scheme;
feeding back the health analysis result and the health compensation scheme to a user side, and generating a scheme execution popup window;
based on the scheme execution popup window, a scheme monitoring instruction is generated, and the target user is subjected to execution monitoring and early warning of the health compensation scheme.
In a second aspect, the present application provides a health monitoring system for a wearable device, the system comprising:
the signal monitoring module is used for monitoring and acquiring multi-element sensing signals of a target user based on the wearable device, wherein the multi-element sensing signals comprise three dimensions of somatosensory monitoring, body fluid monitoring and electrophysiological monitoring;
the signal analysis module is used for inputting the multi-element sensing signals into a health analysis model and outputting health analysis results;
the map construction module is used for configuring a map triplet, interactively and publicly collecting data to extract information, and constructing a compensation knowledge map which has timeliness updating property;
the scheme determining module is used for traversing the compensation knowledge graph, matching the health analysis result and determining a health compensation scheme;
the information feedback module is used for feeding back the health analysis result and the health compensation scheme to the user side and generating a scheme execution popup;
and the execution monitoring module is used for executing popup window based on the scheme, generating a scheme monitoring instruction, and performing execution monitoring and early warning of the health compensation scheme on the target user.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
according to the health monitoring method of the wearable device, based on the wearable device, multiple sensing signals of a target user are monitored and obtained, wherein the multiple sensing signals comprise three dimensions of somatosensory monitoring, body fluid monitoring and electrophysiological monitoring, and the three dimensions are input into a health analysis model to obtain health analysis results; the method comprises the steps of configuring a map triplet, interactively publishing collected data to extract information, building a compensation knowledge map, traversing the compensation knowledge map, matching the health analysis result, determining a health compensation scheme, feeding back the health analysis result to a user side, generating a scheme execution popup, executing a popup generation scheme monitoring instruction based on the scheme, and carrying out the health compensation scheme execution monitoring and early warning on a target user.
Drawings
Fig. 1 is a schematic flow chart of a health monitoring method of a wearable device;
fig. 2 is a schematic diagram of a health analysis result obtaining process in a health monitoring method of a wearable device according to the present application;
fig. 3 is a schematic diagram of a compensating knowledge graph construction flow in a health monitoring method of a wearable device;
fig. 4 is a schematic structural diagram of a health monitoring system of a wearable device according to the present application.
Reference numerals illustrate: the system comprises a signal monitoring module 11, a signal analysis module 12, a map construction module 13, a scheme determination module 14, an information feedback module 15 and an execution monitoring module 16.
Detailed Description
The application provides a health monitoring method and a health monitoring system for a wearable device, wherein the health monitoring method and the health monitoring system monitor and acquire multi-element sensing signals of a target user, and input the multi-element sensing signals into a health analysis model to acquire health analysis results; the method comprises the steps of configuring a map triplet, interactively publishing collected data to extract information, building a compensation knowledge map, matching a health analysis result to determine a health compensation scheme, feeding back to a user side, generating a scheme execution popup window, and performing monitoring and early warning of the health compensation scheme based on a scheme monitoring instruction, so that the technical problems that the health monitoring method for the wearable device in the prior art is insufficient in monitoring completeness and accuracy and cannot perform self-adaptive correction analysis and user supervision based on the monitoring result are solved.
Example 1
As shown in fig. 1, the present application provides a health monitoring method of a wearable device, the method comprising:
step S100: based on the wearable device, monitoring and acquiring multi-element sensing signals of a target user, wherein the multi-element sensing signals comprise three dimensions of somatosensory monitoring, body fluid monitoring and electrophysiological monitoring;
specifically, with the development of flexible electronic technology, based on wearable medical equipment for daily health continuous monitoring, the dependence on large-scale medical equipment is weakened, and the user can know the health condition at any time so as to perform intelligent prevention and control of diseases. According to the health monitoring method of the wearable device, provided by the application, the analysis of the monitoring received signals is performed by modeling, the health analysis result is obtained, the result matching and the determination of the health compensation scheme are performed based on the constructed compensation knowledge graph, so that the fit optimization scheme is configured aiming at the health condition of the user, meanwhile, the execution process of the scheme is monitored and warned, and the follow-up compensation analysis and execution management are performed on the basis of improving the accuracy of the health analysis result, so that the functionality is ensured to the greatest extent.
Specifically, the target user is a user to be subjected to health monitoring management, the wearable device is equipment for sensing physical energy information of the user, and the wearable device is worn on the target user. Determining specific monitoring dimensions, including the somatosensory monitoring, the body fluid monitoring, and the electrophysiological monitoring, may be based on a multi-dimensional sensor configured with the wearable device, or the like. For example, the somatosensory monitoring includes body surface temperature, respiration, limb behavior, etc., and can be acquired based on a temperature sensor, an image monitoring device, etc.; the body measurement monitoring comprises sweat, blood and the like, and body fluid contains substances such as electrolyte, metabolite, hormone and the like, can be used for determining the physiological state of a user and can be acquired based on a chemical sensor and the like; the electrophysiological monitoring comprises organs, nerve activities, tissues and the like, can be obtained based on electrophysiological sensors and the like, is based on the wearable device, monitors and collects the target user in real time, receives and integrates sensing signals as the multi-element sensing signals, and the multi-element sensing signals are collection source data for health analysis of the target user.
Step S200: inputting the multi-element sensing signals into a health analysis model, and outputting a health analysis result;
further, as shown in fig. 2, the outputting the health analysis result in step S200 of the present application further includes:
step S210: transmitting the multi-element sensing signals to a server, and carrying out signal time sequence integration to determine multi-element time sequence signals;
step S220: performing signal preprocessing on the multi-element time sequence signals to obtain N groups of abnormal signal sources;
step S230: inputting the N groups of abnormal signal sources into the health analysis model, matching with a target health analysis unit, and analyzing and outputting the health analysis result, wherein the health analysis result comprises a health diagnosis and treatment list and abnormal warning information.
Further, the step S220 of the present application further includes performing signal preprocessing on the multiple timing signals to obtain N sets of abnormal signal sources:
step S221: sampling and denoising the multi-element time sequence signals based on a preset frame frequency to generate multi-element signal frequency spectrums;
step S222: global normalization processing is carried out on the multi-element signal spectrum, and a multi-element target spectrum is determined;
step S223: and configuring a multi-element hard threshold for the multi-element target frequency spectrum, and mining the N groups of abnormal signal sources by combining an permutation entropy algorithm, wherein the hard threshold refers to a signal amplitude limiting value, and the N groups of abnormal signal sources are marked with signal positions, signal amplitudes and duration.
Further, the health analysis model is built, and step S230 of the present application further includes:
step S231: determining a type of user mode, and calling a sample data set, wherein the sample data set comprises a sample abnormal signal set and a sample health analysis result set;
step S232: mapping and associating the sample abnormal signal group with the sample health analysis result set, and constructing a first health analysis sub-model as a training sample;
step S233: performing a verification test of the first health analysis sub-model based on the training sample, and determining that the reconstructed training sample trains a second health analysis sub-model;
step S234: performing sample iterative training, determining an Nth health analysis sub-model, and generating a health analysis unit for the first health analysis sub-model and the second health analysis sub-model until the Nth health analysis sub-model are configured in parallel;
step S235: based on the M-class user mode, building M health analysis units;
step S236: and integrating the M health analysis sub-models to generate the health analysis model.
Specifically, the server is a back-end processing module of the wearable device, is in communication connection with the user end, and transmits the acquired multi-element sensing signals to the server for analysis and processing of monitoring data. The server receives the multiple sensing signals and performs time sequence integration to determine a time sequence signal sequence of each sensing signal, for example, electrocardiosignals with time sequence in a preset time interval, and determine multiple time sequence signals. And further performing signal preprocessing on the multi-element time sequence signals to extract abnormal signals.
Specifically, the multiple time sequence signals are extracted based on the preset frame frequency, where the preset frame frequency signal is a signal extraction frequency which is set in a self-defining manner and meets the information extraction requirement, for example, signal extraction is performed every 1 second. Due to the fact that noise influence exists in the signal acquisition and transmission processes, signal accuracy deviates, noise reduction processing is carried out on the extracted signals, for example, the noise reduction processing is carried out on the basis of a wavelet noise reduction mode, the signal spectrum is visualized, and the multi-element signal spectrum is obtained. And due to the fluctuation of the body position, limb movement and the like of the target user, the amplitude of the signals before and after the fluctuation has a certain influence, global normalization processing is carried out on the multi-element signal spectrum, and the processed standard spectrum is determined as the multi-element target spectrum. And positioning abnormal signals based on the multi-element target frequency spectrum.
Specifically, after signal spectrum normalization processing is performed, the amplitudes of normal signals tend to be consistent, and the amplitudes of abnormal signals are more prominent. And determining normal signal definition amplitude values of the signal spectrums aiming at the multi-element target spectrums, wherein the normal signal definition amplitude values respectively comprise an amplitude interval defined by an amplitude upper bound and an amplitude lower bound, the amplitude intervals are used as the multi-element hard threshold, for example, the target spectrums based on breathing signals, the amplitude of the normal breathing signals are in an interval of 0 to 1, when the breathing signals tend to 0, the breathing signals have an apnea, and the amplitude ranges of 0 to 1 are used as the hard threshold of the breathing signal spectrums. And taking the multi-element hard threshold as a limit, and combining an permutation entropy algorithm to position mutation time and determine mutation time delay intervals of the multi-element target frequency spectrum, so that the recognition accuracy of abnormal signals can be effectively improved. And determining the signal position corresponding to the target frequency spectrum based on the abrupt change moment, identifying the signal amplitude of the signal position, determining the duration based on the abrupt change time delay interval, and acquiring the N groups of abnormal signal sources, wherein the N groups of abnormal signal sources are in one-to-one correspondence with the multiple target frequency spectrum.
Further, the health analysis model is constructed. In the process of monitoring the target user, the actual state difference of the user is related to the real-time monitoring information, M types of user modes such as a sleep mode, a movement mode and the like are determined, and health analysis units are respectively constructed for different user modes so as to perform targeted analysis processing of the real-time information. Specifically, one of the user patterns is randomly extracted based on the multiple types of user patterns to serve as the one type of user patterns. And collecting historical monitoring information under the user mode, identifying and extracting the sample abnormal signal group and the sample health analysis result set, and calling the sample abnormal signal group and the sample health analysis result set to serve as one sample data group, wherein the one sample data group is the once-monitored data, and can be directly identified and determined. The abnormal signal groups are in one-to-one correspondence with the sample health analysis result sets, corresponding association is carried out based on mapping association, and the first health analysis sub-model is generated by training a neural network as the training sample. And further inputting the abnormal signal group into the first health analysis sub-model, matching and calculating a difference between an output result and the sample health analysis result, and extracting a sample with a result difference greater than or equal to a deviation threshold value in the training sample as the reconstruction training sample, wherein the deviation threshold value is a critical deviation value which is self-defined and set based on a model processing accuracy requirement.
And further performing neural network training based on the reconstructed training sample to generate the second health analysis sub-model. And further, performing verification test and deviation threshold analysis on the second health analysis sub-model based on the reconstructed training sample, and repeating the training verification step until a verification test result meets the deviation threshold, thereby completing construction of the Nth health analysis sub-model. The first health analysis sub-model and the second health analysis sub-model are further integrated, and are arranged in parallel until the Nth health analysis sub-model is achieved, so that the one health analysis unit is generated, the analysis accuracy of the first health analysis unit can be effectively improved, and the one health analysis unit is suitable for an independent analysis unit based on the user mode. Similarly, aiming at the M types of user modes, health analysis units are respectively constructed, the M health analysis units are obtained, the construction modes of the M health analysis units are the same, specific construction data are different, the M health analysis units are integrated, the health analysis model is generated, the health analysis model has mode independence, targeted analysis processing can be carried out based on the real-time state of a user, and the accuracy of analysis results is ensured to the greatest extent.
Further, the N groups of abnormal signal sources are input into the health analysis model, and based on the collected user states of the N groups of abnormal signal sources, the health analysis units in corresponding modes are matched to serve as the target health analysis units. Based on the target health analysis unit, processing and analyzing the N groups of abnormal signal sources to obtain a plurality of focus features and a plurality of correlation signal source arrays corresponding to the focus features, and mapping and correlating to determine a plurality of diagnosis and treatment sequences as the health diagnosis and treatment list; and configuring suitability early-warning grades based on the severity of the focus characteristics, taking the suitability early-warning grades as the abnormality early-warning information, and outputting the health diagnosis and treatment list and the abnormality early-warning information as the health analysis result. And further configuring an adaptive scheme for the health analysis result to perform health compensation analysis.
Step S300: configuring a map triplet, interactively publishing collected data to extract information, and constructing a compensation knowledge map, wherein the compensation knowledge map has timeliness updating;
further, as shown in fig. 3, the building of the compensation knowledge graph, step S300 of the present application further includes:
step S310: determining a map triplet by taking focus characteristics as an entity, taking a multi-element data type as an attribute and taking a multi-element data value as a target value;
step S320: retrieving big data to obtain public acquisition data;
step S330: based on the public acquisition data, carrying out data extraction by taking the map triples as index elements to obtain extraction data sets;
step S340: and constructing the compensation knowledge graph based on the extraction data set.
Further, the step S340 of the present application further includes:
step S341: performing entity disambiguation and coreference resolution on the extracted data set to obtain a built data set;
step S342: configuring a map main body structure, and performing structure attribution filling on the constructed data set to generate a primary knowledge map;
step S343: optimizing the primary knowledge graph based on an inter-group relationship, and determining an optimized knowledge graph, wherein the inter-group relationship comprises a parallel relationship and an upper-lower relationship;
step S344: and configuring a preset health compensation scheme for the optimized knowledge graph to generate the compensation knowledge graph.
Further, the configuring a preset health compensation scheme for the optimized knowledge graph to generate the compensated knowledge graph, and step S344 of the present application further includes:
step S3441: identifying frame selection condition information based on the optimized knowledge graph, wherein one piece of condition information corresponds to at least one focus feature;
step S3442: respectively configuring the preset health compensation schemes for the condition information;
step S3443: in the optimized knowledge graph, carrying out position matching resetting and frame selection target linking on the preset health compensation scheme to generate the compensation knowledge graph;
step S3444: and setting a map management rule, and executing the self-adaptive management of the compensation knowledge maps.
Specifically, performing map construction requirement analysis, wherein the focus features are taken as entities, such as heart rate abnormality; taking the multivariate data type as an attribute, such as a plurality of data source types causing heart rate abnormality; and taking the multivariate data value as a target value, for example, specific numerical values corresponding to a plurality of data source types, and taking the focus characteristic-multivariate data type-multivariate data numerical value as the map triplet. And carrying out big data retrieval, for example, taking a medical database as a retrieval target, and carrying out acquisition and calling on the associated data for executing health monitoring as the public acquisition data. And in the public acquisition data, the map triples are used as index elements, and the related element data are retrieved and extracted to be used as the extraction data set. And taking the extracted data set as construction source data to construct the compensation knowledge graph.
Specifically, as different meanings may exist in different pathological directions of the same focus, in order to eliminate data ambiguity and ensure construction accuracy, entity disambiguation is performed on the extracted data set, and for example, based on a clustering processing mode, meaning analysis processing is performed on each clustering result respectively for a plurality of clustering results of the extracted data set so as to eliminate data ambiguity; because multiple feature expressions may refer to the same focus, in order to ensure the construction simplicity, eliminate redundant data, perform coreference resolution on the extracted data set after entity disambiguation, for example, based on a synonymous manner of an entity, perform consistency on multiple features corresponding to the focus, or perform marking processing based on the same identification information, so as to eliminate data redundancy, acquire the constructed data set to be subjected to map construction, and ensure the quality of map construction data.
The map main framework is further configured, and the map main framework can be subjected to self-defining configuration in combination with construction requirements, such as a tree space framework and the like. And determining the arrangement condition of the data of each element in the construction data set in the map main structure, positioning and filling the data structure, generating the primary knowledge map, and further adjusting if certain deviation exists for the primary construction result. The parallel relationship and the upper-lower relationship are used as the relationships among the groups, components with the parallel relationship are identified, and parallel adjustment of the architecture position is carried out; and identifying components with upper and lower relationships, performing sequential association adjustment on the architecture positions, and acquiring the optimized knowledge graph so as to improve the order and the regularity of the graph and facilitate rapid association identification. And further configuring the preset health compensation scheme to perfect the optimized knowledge graph.
Specifically, the main body correlation analysis is performed on the optimized knowledge graph, that is, at least one focus characteristic, such as heart abnormality, possibly including heart rate characteristics, electrocardio characteristics, muscle tissue characteristics, blood flow characteristics and the like, which causes occurrence of the condition is determined, and the optimized knowledge graph is subjected to division frame selection based on the focus characteristic, so that a plurality of condition information are determined and frame selection for covering the focus characteristic is performed. For each condition information, a plurality of feasibility compensation schemes are respectively collected, fitness analysis is carried out on the condition information, for example, an adaptive user duty ratio, compensation effect and the like are used as fitness evaluation indexes, a feasibility compensation scheme corresponding to the maximum fitness of each condition information is selected and used as the preset health compensation scheme, the preset health compensation scheme corresponds to the condition information one by one, and the preset health compensation schemes are all configuration schemes which take nutrition, exercise, three health (salt reduction, oil reduction, sugar reduction, healthy weight, healthy bones, healthy oral cavity), smoke control and the like as compensation execution targets and limit compensation amounts. And in the optimized knowledge graph, matching, corresponding and linking the preset compensation scheme and the condition information, and generating the compensation knowledge graph by taking the neighborhood position of the corresponding condition information as a scheme resetting position, wherein the compensation knowledge graph has information completeness and authority.
Further, setting the map management rule, for example, setting an update period, and performing optimization adjustment of map data and a framework by performing regular processing information of a period time zone on an update node; and receiving scheme execution feedback information, periodically adjusting the scheme in the compensation knowledge graph, and executing periodic self-adaptive management on the compensation knowledge graph based on the graph management rule to ensure the timeliness of the compensation knowledge graph.
Step S400: traversing the compensation knowledge graph, matching the health analysis result, and determining a health compensation scheme;
step S500: feeding back the health analysis result and the health compensation scheme to a user side, and generating a scheme execution popup window;
step S600: based on the scheme execution popup window, a scheme monitoring instruction is generated, and the target user is subjected to execution monitoring and early warning of the health compensation scheme.
Specifically, in the compensation knowledge graph, the health analysis result is subjected to frequency spectrum, condition information covered by a health diagnosis and treatment list included in the health analysis result is determined, an associated preset health compensation scheme is determined based on the link relation of the compensation knowledge graph, and the health compensation scheme is extracted and used as the health compensation scheme, wherein the health compensation scheme is a health management scheme matched with the target user. Further, the health analysis result and the health compensation scheme are transmitted to a user side of the wearable device, visual display is performed based on a display component of the user side, the visual display is used for inquiring by the target user, meanwhile, a scheme execution popup window, namely a user confirmation window used for performing scheme execution supervision is generated, if the target user selects confirmation, the wearable device is required to be relied on to perform subsequent scheme execution supervision, a scheme monitoring instruction is generated, namely a starting instruction for controlling the wearable device supervision scheme to be executed, the target user is monitored for executing the health compensation scheme, and if the self-control strength of the target user is insufficient, warning reminding is performed for the target user, so that the execution effect of the health compensation scheme is guaranteed.
Example two
Based on the same inventive concept as the health monitoring method of a wearable device in the foregoing embodiments, as shown in fig. 4, the present application provides a health monitoring system of a wearable device, the system comprising:
the signal monitoring module 11 is used for monitoring and acquiring multi-element sensing signals of a target user based on the wearable device, wherein the multi-element sensing signals comprise three dimensions of somatosensory monitoring, body fluid monitoring and electrophysiological monitoring;
the signal analysis module 12 is used for inputting the multi-element sensing signals into a health analysis model and outputting health analysis results;
the map construction module 13 is used for configuring a map triplet, interactively and publicly collecting data to extract information, and constructing a compensation knowledge map which has timeliness updating property;
the solution determining module 14 is configured to traverse the compensation knowledge graph, match the health analysis result, and determine a health compensation solution;
the information feedback module 15 is configured to feedback the health analysis result and the health compensation scheme to the user side, and generate a scheme execution popup;
and the execution monitoring module 16 is used for generating a scheme monitoring instruction based on the scheme execution popup, and performing execution monitoring and early warning of the health compensation scheme on the target user.
Further, the system further comprises:
the signal time sequence integration module is used for transmitting the multi-element sensing signals to a server to perform signal time sequence integration and determine multi-element time sequence signals;
the signal preprocessing module is used for performing signal preprocessing on the multi-element time sequence signals to obtain N groups of abnormal signal sources;
the health analysis result output module is used for inputting the N groups of abnormal signal sources into the health analysis model, matching with a target health analysis unit, analyzing and outputting the health analysis result, wherein the health analysis result comprises a health diagnosis and treatment list and abnormal warning information.
Further, the system further comprises:
the sampling noise reduction module is used for sampling and reducing noise of the multi-element time sequence signals based on a preset frame frequency to generate multi-element signal frequency spectrums;
the normalization processing module is used for executing global normalization processing on the multi-element signal spectrum and determining a multi-element target spectrum;
the abnormal signal source mining module is used for configuring a multi-element hard threshold value for the multi-element target frequency spectrum, mining the N groups of abnormal signal sources by combining an permutation entropy algorithm, wherein the hard threshold value refers to a signal amplitude limiting value, and the N groups of abnormal signal sources are marked with signal positions, signal amplitudes and duration.
Further, the system further comprises:
the sample calling module is used for determining a type of user mode and calling a sample data set, wherein the sample data set comprises a sample abnormal signal set and a sample health analysis result set;
the first health analysis sub-model training module is used for mapping and associating the sample abnormal signal group with the sample health analysis result set and constructing a first health analysis sub-model as a training sample;
the second health analysis sub-model training module is used for carrying out verification test on the first health analysis sub-model based on the training sample and determining a reconstructed training sample to train a second health analysis sub-model;
the health analysis unit building module is used for performing sample iterative training, determining an Nth health analysis sub-model, and generating a health analysis unit by configuring the first health analysis sub-model and the second health analysis sub-model in parallel until the Nth health analysis sub-model;
the M health analysis unit building module is used for building M health analysis units based on M types of user modes;
and the health analysis model generation module is used for integrating the M health analysis sub-models to generate the health analysis model.
Further, the system further comprises:
the map triplet determination module is used for determining a map triplet by taking a focus characteristic as an entity, taking a multi-element data type as an attribute and taking a multi-element data value as a target value;
the public acquisition data acquisition module is used for carrying out big data retrieval to acquire public acquisition data;
the data extraction module is used for carrying out data extraction by taking the map triples as index elements based on the public acquired data to obtain an extracted data set;
the compensation knowledge graph construction module is used for constructing the compensation knowledge graph based on the extraction data set.
Further, the system further comprises:
the group data acquisition module is used for performing entity disambiguation and coreference resolution on the extracted data group to acquire a group data group;
the primary knowledge graph generation module is used for configuring a graph main body structure, and performing structure attribution filling on the constructed data set to generate a primary knowledge graph;
the optimization knowledge graph determining module is used for optimizing the primary knowledge graph based on an inter-group relationship, and determining an optimization knowledge graph, wherein the inter-group relationship comprises a parallel relationship and an upper-lower relationship;
the scheme configuration module is used for configuring a preset health compensation scheme for the optimized knowledge graph and generating the compensation knowledge graph.
Further, the system further comprises:
the condition information frame selection module is used for identifying frame selection condition information based on the optimized knowledge graph, wherein one piece of condition information corresponds to at least one focus characteristic;
the preset health compensation scheme configuration module is used for respectively configuring the preset health compensation schemes for the condition information;
the compensation knowledge graph generation module is used for carrying out position matching and resetting and frame selection target link on the preset health compensation scheme in the optimized knowledge graph to generate the compensation knowledge graph;
and the map management module is used for setting map management rules and executing the self-adaptive management of the compensation knowledge maps.
The foregoing detailed description of a method for monitoring health of a wearable device will be clear to those skilled in the art, and the method and system for monitoring health of a wearable device in this embodiment are relatively simple for the device disclosed in the embodiments, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method of health monitoring of a wearable device, the method comprising:
based on the wearable device, monitoring and acquiring multi-element sensing signals of a target user, wherein the multi-element sensing signals comprise three dimensions of somatosensory monitoring, body fluid monitoring and electrophysiological monitoring;
inputting the multi-element sensing signals into a health analysis model, and outputting a health analysis result;
configuring a map triplet, interactively publishing collected data to extract information, and constructing a compensation knowledge map, wherein the compensation knowledge map has timeliness updating;
traversing the compensation knowledge graph, matching the health analysis result, and determining a health compensation scheme;
feeding back the health analysis result and the health compensation scheme to a user side, and generating a scheme execution popup window;
based on the scheme execution popup window, a scheme monitoring instruction is generated, and the target user is subjected to execution monitoring and early warning of the health compensation scheme.
2. The method of claim 1, wherein the outputting the health analysis results, the method comprising:
transmitting the multi-element sensing signals to a server, and carrying out signal time sequence integration to determine multi-element time sequence signals;
performing signal preprocessing on the multi-element time sequence signals to obtain N groups of abnormal signal sources;
inputting the N groups of abnormal signal sources into the health analysis model, matching with a target health analysis unit, and analyzing and outputting the health analysis result, wherein the health analysis result comprises a health diagnosis and treatment list and abnormal warning information.
3. The method of claim 2, wherein the performing signal preprocessing on the plurality of timing signals obtains N sets of abnormal signal sources, the method comprising:
sampling and denoising the multi-element time sequence signals based on a preset frame frequency to generate multi-element signal frequency spectrums;
global normalization processing is carried out on the multi-element signal spectrum, and a multi-element target spectrum is determined;
and configuring a multi-element hard threshold for the multi-element target frequency spectrum, and mining the N groups of abnormal signal sources by combining an permutation entropy algorithm, wherein the hard threshold refers to a signal amplitude limiting value, and the N groups of abnormal signal sources are marked with signal positions, signal amplitudes and duration.
4. The method of claim 2, wherein building a health analysis model, the method comprising:
determining a type of user mode, and calling a sample data set, wherein the sample data set comprises a sample abnormal signal set and a sample health analysis result set;
mapping and associating the sample abnormal signal group with the sample health analysis result set, and constructing a first health analysis sub-model as a training sample;
performing a verification test of the first health analysis sub-model based on the training sample, and determining that the reconstructed training sample trains a second health analysis sub-model;
performing sample iterative training, determining an Nth health analysis sub-model, and generating a health analysis unit for the first health analysis sub-model and the second health analysis sub-model until the Nth health analysis sub-model are configured in parallel;
based on the M-class user mode, building M health analysis units;
and integrating the M health analysis sub-models to generate the health analysis model.
5. The method according to claim 1, wherein the building of the compensation knowledge graph comprises:
determining a map triplet by taking focus characteristics as an entity, taking a multi-element data type as an attribute and taking a multi-element data value as a target value;
retrieving big data to obtain public acquisition data;
based on the public acquisition data, carrying out data extraction by taking the map triples as index elements to obtain extraction data sets;
and constructing the compensation knowledge graph based on the extraction data set.
6. The method of claim 5, wherein constructing the compensation knowledge-graph based on the extracted data set, the method comprising:
performing entity disambiguation and coreference resolution on the extracted data set to obtain a built data set;
configuring a map main body structure, and performing structure attribution filling on the constructed data set to generate a primary knowledge map;
optimizing the primary knowledge graph based on an inter-group relationship, and determining an optimized knowledge graph, wherein the inter-group relationship comprises a parallel relationship and an upper-lower relationship;
and configuring a preset health compensation scheme for the optimized knowledge graph to generate the compensation knowledge graph.
7. The method of claim 6, wherein configuring a preset health compensation scheme for the optimized knowledge-graph, generating the compensated knowledge-graph, comprises:
identifying frame selection condition information based on the optimized knowledge graph, wherein one piece of condition information corresponds to at least one focus feature;
respectively configuring the preset health compensation schemes for the condition information;
in the optimized knowledge graph, carrying out position matching resetting and frame selection target linking on the preset health compensation scheme to generate the compensation knowledge graph;
and setting a map management rule, and executing the self-adaptive management of the compensation knowledge maps.
8. A health monitoring system for a wearable device, the system comprising:
the signal monitoring module is used for monitoring and acquiring multi-element sensing signals of a target user based on the wearable device, wherein the multi-element sensing signals comprise three dimensions of somatosensory monitoring, body fluid monitoring and electrophysiological monitoring;
the signal analysis module is used for inputting the multi-element sensing signals into a health analysis model and outputting health analysis results;
the map construction module is used for configuring a map triplet, interactively and publicly collecting data to extract information, and constructing a compensation knowledge map which has timeliness updating property;
the scheme determining module is used for traversing the compensation knowledge graph, matching the health analysis result and determining a health compensation scheme;
the information feedback module is used for feeding back the health analysis result and the health compensation scheme to the user side and generating a scheme execution popup;
and the execution monitoring module is used for executing popup window based on the scheme, generating a scheme monitoring instruction, and performing execution monitoring and early warning of the health compensation scheme on the target user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310871681.8A CN116612892B (en) | 2023-07-17 | 2023-07-17 | Health monitoring method and system of wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310871681.8A CN116612892B (en) | 2023-07-17 | 2023-07-17 | Health monitoring method and system of wearable device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116612892A true CN116612892A (en) | 2023-08-18 |
| CN116612892B CN116612892B (en) | 2023-09-26 |
Family
ID=87682095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310871681.8A Active CN116612892B (en) | 2023-07-17 | 2023-07-17 | Health monitoring method and system of wearable device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612892B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105808931A (en) * | 2016-03-03 | 2016-07-27 | 北京大学深圳研究生院 | Knowledge graph based acupuncture and moxibustion decision support method and apparatus |
| US20160217565A1 (en) * | 2015-01-28 | 2016-07-28 | Sensory, Incorporated | Health and Fitness Monitoring via Long-Term Temporal Analysis of Biometric Data |
| CN110911009A (en) * | 2019-11-14 | 2020-03-24 | 南京医科大学 | Clinical diagnosis aid decision-making system and medical knowledge map accumulation method |
| CN112133445A (en) * | 2020-10-21 | 2020-12-25 | 万达信息股份有限公司 | Cardiovascular disease management service method and system |
| CN112242187A (en) * | 2020-10-26 | 2021-01-19 | 平安科技（深圳）有限公司 | Medical scheme recommendation system and method based on knowledge graph representation learning |
| CN113345587A (en) * | 2021-06-16 | 2021-09-03 | 北京邮电大学 | Man-machine collaborative health case matching method and system based on chronic disease big data |
| CN113806553A (en) * | 2021-09-08 | 2021-12-17 | 曲剑 | Traditional Chinese and western medicine health knowledge map system and construction method |
| CN116110577A (en) * | 2022-11-16 | 2023-05-12 | 荣科科技股份有限公司 | Health monitoring analysis method and system based on big data |
-
2023
- 2023-07-17 CN CN202310871681.8A patent/CN116612892B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160217565A1 (en) * | 2015-01-28 | 2016-07-28 | Sensory, Incorporated | Health and Fitness Monitoring via Long-Term Temporal Analysis of Biometric Data |
| CN105808931A (en) * | 2016-03-03 | 2016-07-27 | 北京大学深圳研究生院 | Knowledge graph based acupuncture and moxibustion decision support method and apparatus |
| CN110911009A (en) * | 2019-11-14 | 2020-03-24 | 南京医科大学 | Clinical diagnosis aid decision-making system and medical knowledge map accumulation method |
| CN112133445A (en) * | 2020-10-21 | 2020-12-25 | 万达信息股份有限公司 | Cardiovascular disease management service method and system |
| CN112242187A (en) * | 2020-10-26 | 2021-01-19 | 平安科技（深圳）有限公司 | Medical scheme recommendation system and method based on knowledge graph representation learning |
| CN113345587A (en) * | 2021-06-16 | 2021-09-03 | 北京邮电大学 | Man-machine collaborative health case matching method and system based on chronic disease big data |
| CN113806553A (en) * | 2021-09-08 | 2021-12-17 | 曲剑 | Traditional Chinese and western medicine health knowledge map system and construction method |
| CN116110577A (en) * | 2022-11-16 | 2023-05-12 | 荣科科技股份有限公司 | Health monitoring analysis method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116612892B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109087706B (en) | Human health assessment method and system based on sleep big data | |
| CN101365378A (en) | Residual-based monitoring of human health | |
| KR20190105163A (en) | Patient condition predicting apparatus based on artificial intelligence and predicting method using the same | |
| CN113647939B (en) | Artificial intelligence rehabilitation evaluation and training system for spinal degenerative diseases | |
| CN105279362A (en) | Personal health monitoring system | |
| AU2018285950A1 (en) | Mental state indicator | |
| CN114616632A (en) | System and method for automatic detection of clinical outcome measures | |
| Banerjee et al. | Deep neural network based missing data prediction of electrocardiogram signal using multiagent reinforcement learning | |
| CN113241196A (en) | Remote medical treatment and grading monitoring system based on cloud-terminal cooperation | |
| CN113384241B (en) | Wearable device assisted chronic patient clinical monitoring platform and method | |
| KR102552787B1 (en) | Method for snoring analysis service providing snoring analysis and disease diagnosis prediction service based on snoring sound analysis | |
| CN116612892B (en) | Health monitoring method and system of wearable device | |
| CN106650206A (en) | Prediction method of high blood pressure based on incremental neural network model and prediction system | |
| Scheffer et al. | Inertial motion capture in conjunction with an artificial neural network can differentiate the gait patterns of hemiparetic stroke patients compared with able-bodied counterparts | |
| CN109300546A (en) | A kind of individual sub-health state appraisal procedure based on big data and artificial intelligence | |
| US20220287564A1 (en) | An Interactive Health-Monitoring Platform for Wearable Wireless Sensor Systems | |
| CN117133464A (en) | Intelligent monitoring system and monitoring method for health of old people | |
| CN116313029B (en) | Method, system and device for dynamic control optimization of digital acupuncture | |
| CN116570283A (en) | Perioperative patient emotion monitoring system and method | |
| CN116434979A (en) | Physiological state cloud monitoring method, monitoring system and storage medium | |
| CN116369853A (en) | Olfactory function standardized evaluation device and method based on brain-computer interaction technology | |
| Rahman et al. | A field study to capture events of interest (EoI) from living labs using wearables for spatiotemporal monitoring towards a framework of smart health (sHealth) | |
| Karimi Moridani | An automated method for sleep apnoea detection using HRV | |
| CN111696011B (en) | System and method for monitoring, regulating and controlling student autonomous learning | |
| KR20220021989A (en) | Method and device for monitoring correlation between snoring and posture based on snoring sound and sleep posture analysis during sleep |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |