CN112349404A - Multi-center medical equipment big data cloud platform based on cloud-edge-end architecture - Google Patents
Multi-center medical equipment big data cloud platform based on cloud-edge-end architecture Download PDFInfo
- Publication number
- CN112349404A CN112349404A CN202011207990.8A CN202011207990A CN112349404A CN 112349404 A CN112349404 A CN 112349404A CN 202011207990 A CN202011207990 A CN 202011207990A CN 112349404 A CN112349404 A CN 112349404A
- Authority
- CN
- China
- Prior art keywords
- data
- cloud
- medical
- platform
- layer
- 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
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000005516 engineering process Methods 0.000 claims abstract description 19
- 230000005540 biological transmission Effects 0.000 claims abstract description 17
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 238000010223 real-time analysis Methods 0.000 claims abstract description 7
- 230000036541 health Effects 0.000 claims abstract description 6
- 238000003860 storage Methods 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims description 21
- 238000007726 management method Methods 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 16
- 238000012423 maintenance Methods 0.000 claims description 13
- 238000013500 data storage Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013523 data management Methods 0.000 claims description 6
- 230000008901 benefit Effects 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000013499 data model Methods 0.000 claims description 4
- 238000002059 diagnostic imaging Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 claims description 2
- 235000019580 granularity Nutrition 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000004044 response Effects 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 7
- 238000007689 inspection Methods 0.000 description 7
- 238000007619 statistical method Methods 0.000 description 6
- 230000002776 aggregation Effects 0.000 description 5
- 238000004220 aggregation Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000013475 authorization Methods 0.000 description 3
- 238000013075 data extraction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000011068 loading method Methods 0.000 description 3
- 238000012800 visualization Methods 0.000 description 3
- 241001448301 Ficus variegata Blume, 1825 Species 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000001631 haemodialysis Methods 0.000 description 2
- 230000000322 hemodialysis Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 206010002091 Anaesthesia Diseases 0.000 description 1
- 244000207667 Rumex vesicarius Species 0.000 description 1
- 235000002905 Rumex vesicarius Nutrition 0.000 description 1
- 206010048669 Terminal state Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000037005 anaesthesia Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011058 failure modes and effects analysis Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 238000011165 process development Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
一种基于云‑边‑端架构的多中心医疗设备大数据云平台，其包括：端层、边层、云层；端层包括多个医疗设备及医疗设备采集终端；医疗设备采集终端自医疗终端采集医疗数据；端层将其医疗数据传输至边层；边层为多个边服务器构成的边服务器集群，其包括：数据流集群模块和数据展示模块，用于医疗设备数据接入、数据解析、数据结构化、实时分析处理、数据展示、数据传输，并提供医院信息系统数据接入接口；边层将其医疗数据传输至云层；云层包括：医疗设备物联网业务中心、数据AI平台、技术平台、数据湖集群，用于支持多种数据类型标准化接入，实现多模态、不同时间颗粒度的健康与医疗数据海量存储，并提供易于扩展的离线计算和批处理架构。
A multi-center medical equipment big data cloud platform based on a cloud-side-terminal architecture, which includes: an end layer, an edge layer, and a cloud layer; the end layer includes a plurality of medical equipment and medical equipment collection terminals; the medical equipment collection terminal is from the medical terminal Collect medical data; the end layer transmits its medical data to the side layer; the side layer is a side server cluster composed of multiple side servers, which includes: a data stream cluster module and a data display module, which are used for medical equipment data access and data analysis. , data structure, real-time analysis and processing, data display, data transmission, and provide hospital information system data access interface; the side layer transmits its medical data to the cloud layer; the cloud layer includes: medical equipment IoT business center, data AI platform, technology The platform and data lake cluster are used to support standardized access of various data types, realize mass storage of health and medical data of multi-modality and different time granularity, and provide an easily scalable offline computing and batch processing architecture.
Description
Technical Field
The application relates to the field of Internet of things, in particular to a cloud-edge-end architecture-based multi-center medical equipment big data cloud platform.
Background
Currently, with the rapid development of medical information technology, the shift to informatization is gradually being accomplished by each medical institution. Hospital information systems, laboratory information management systems, medical image archiving and communication systems, and radiology information management systems have been widely used in medical institutions to assist the medical institutions in their daily operations. As the awareness of medical personnel increases, finding data generated by medical devices also has extremely important research value. The medical equipment Internet of things big data cloud platform is built by using big data technology, data of different data sources are collected, the data are analyzed and displayed in real time, meanwhile, offline processing and analysis are carried out, data value is mined, and hospital service operation is assisted.
At present, the following technical problems exist:
firstly, the data volume is large in consumed space and various in kinds when stored in a local disk; traditional data storage is stored in a local disk, and the disk needs to be continuously replaced along with the accumulation of time, so that the economic consumption is huge.
Second, traditional data storage and consolidation drawbacks; conventional data storage and arrangement is directed to structured data. Most of the data generated by the medical device is unstructured data. The unstructured data processing refers to processing of text information such as inspection description and inspection conclusion, the whole text description needs to extract key information, otherwise, effective scientific research utilization cannot be carried out, the information quantity contained in the large amount of text data is huge, the comprehensiveness of information extraction needs to be guaranteed while the key and effective information is extracted, and the loss of any useful information is a huge loss of data integrity.
Third, each application generates and stores large amounts of data that cannot be used by other applications, which results in the creation of data islands. Meanwhile, the problems of data management, data ownership, access control and the like are lacked.
Disclosure of Invention
In view of the above problems, the present application aims to provide a cloud platform for big data of a multi-center medical device based on a cloud-edge-end architecture.
The utility model provides a multicenter medical equipment big data cloud platform based on cloud-limit-end architecture, it includes: end layers, side layers and cloud layers; each center is at least provided with an end layer and an edge layer; a cloud layer disposed in one of the multiple centers;
each end layer comprises a plurality of medical devices and medical device acquisition terminals; each medical equipment acquisition terminal corresponds to at least one medical terminal; the medical equipment acquisition terminal acquires medical data from the medical terminal; the end layer transmits the medical data to the edge layer which is positioned at the same center with the end layer;
each edge layer is an edge server cluster formed by a plurality of edge servers, and the edge server cluster comprises: the data flow clustering module and the data display module are used for data access, data analysis, data structuring, real-time analysis and processing, data display and data transmission of the medical equipment and providing a data access interface of a hospital information system; the boundary layer transmits the medical data to the cloud layer;
the cloud layer comprises: the medical equipment Internet of things system comprises a medical equipment Internet of things service center, a data AI platform, a technical platform and a data lake cluster, wherein the medical equipment Internet of things service center, the data AI platform, the technical platform and the data lake cluster are used for supporting standardized access of various data types, realizing multi-mode health and medical data mass storage with different time granularities and providing an off-line calculation and batch processing framework which is easy to expand; the data AI platform provides intelligent data analysis capability and provides data management, algorithm and model construction; the medical equipment Internet of things service center provides authority distribution for all service process management and control and service data; the data lake cluster is used for data access, data storage and data query; the technical platform is built by utilizing cloud services, consists of micro services, cloud middleware and a software development cloud, and provides various technical services.
Preferably, the medical device acquisition terminal is used for acquiring medical data from the medical device through a serial port or a network port.
Preferably, the data stream cluster module is built by using a big data technology on the edge server cluster; the data stream cluster module is connected with medical equipment data, provides real-time analysis and data processing services, and can push the processed data to a data display module for visual display or to a cloud layer for secondary analysis and utilization of the data;
the hospital information system data access interface is used for accessing hospital information system data, following a Webservice protocol, and acquiring data fields required by the hospital information system in a request-response mode.
Preferably, the cloud layer is composed of a plurality of servers in the same center;
the data lake cluster is built through a big data technology and a cloud computing technology;
the technical platform and the data AI platform are built through cloud service and artificial intelligence technology.
Preferably, the data stream cluster module is built by using at least one big data component technology of Nifi, Kafka and Spark; and the data stream cluster module performs structured processing on the original data according to the constructed data model and the data standard protocol so as to complete data analysis.
Preferably, the medical equipment comprises an ICU equipment and a medical imaging equipment; for ICU equipment, the data stream cluster module analyzes according to HL7 standard; the medical imaging device is analyzed according to a protocol according to the device.
Preferably, the construction of the data lake cluster uses at least one of Hadoop, HDFS, Kafka, Hive and drive big data technologies; the cloud service comprises at least one of infrastructure as a service (IaaS), platform as a service (PaaS) and software as a service (SaaS);
the data AI platform provides massive data preprocessing, semi-automatic labeling, large-scale distributed training, automatic model generation and cloud-edge-end architecture deployment capability as required for machine learning and deep learning, helps a user to quickly create and deploy the cloud-edge-end architecture, manages a full-period AI workflow, and provides data management service.
Preferably, the management and control of the service center of the internet of things of the medical equipment comprises: daily equipment management, central monitoring, an intensive care information management system, real-time large-screen equipment, equipment efficiency analysis, equipment benefit analysis and equipment maintenance analysis.
According to the multi-center medical equipment big data cloud platform based on the cloud-edge-end architecture, an end layer is responsible for bottom layer data acquisition; the side layer is responsible for data access, data analysis and real-time processing, provides edge computing service and can be made into lightweight application development and deployment; the cloud layer is mainly responsible for data offline processing and large-scale storage, supports a technical platform and a data AI platform through cloud services SaaS, Paas and Iaas, and deploys a medical equipment Internet of things service center.
Drawings
Fig. 1 is a cloud platform architecture of a cloud-edge-end architecture for a multi-center medical device big data provided by an embodiment of the present invention.
Fig. 2 is a technical architecture of a data flow platform according to an embodiment of the present invention.
Fig. 3 is a functional architecture of an application presentation module according to an embodiment of the present invention.
Fig. 4 is an example of real-time monitoring of a NiFi data stream according to an embodiment of the present invention.
Fig. 5 is a data flow monitoring management system according to an embodiment of the present invention.
Fig. 6 is a big data ETL technical architecture provided by an embodiment of the present invention.
Fig. 7 is a data warehouse data model for emergency services according to an embodiment of the present invention.
Fig. 8 is a flowchart illustrating steps of a big data ETL according to an embodiment of the present invention.
FIG. 9 is a diagram of a data administration architecture provided by an embodiment of the present invention.
Fig. 10 is a diagram of a security architecture provided by an embodiment of the present invention.
Fig. 11 is a flow of managing rights by a security system when a user uses a platform according to an embodiment of the present invention.
Fig. 12 is a flowchart of data AI platform application formation according to an embodiment of the present invention.
FIG. 13 is a flowchart of an algorithm for a system for detecting an abnormal state of a patient according to an embodiment of the present invention.
Fig. 14 is a flowchart of an algorithm of a prediction and early warning model based on a key part of a log of a large-scale image device according to an embodiment of the present invention.
Fig. 15 is a schematic structural view of the present invention.
Detailed Description
The cloud-edge-end architecture-based multi-center medical equipment big data cloud platform of the present application is described in detail below with reference to the accompanying drawings.
The software and hardware architecture of the medical big data cloud service analysis platform is described as follows:
1. the system adopts a cloud-edge-end structure
As shown in fig. 1, based on geographical location distribution, edge servers are deployed in each center to ensure low-delay data transmission and work such as real-time service data analysis, and display. And deploying a cloud platform, uniformly issuing services and models, ensuring the cooperation of edge clouds, and forming an architecture system with uniform management, flexible deployment and high automation operation and maintenance.
2. Principles of System design
1) The equipment operation information and the clinical information are repeated, all relevant data generated by the terminal equipment are concerned, and the hospital information system is connected to cover all relevant data of the equipment.
2) The method completely supports the functional requirements of the system, supports continuous operation for 7 days by 24 hours, has enough disk capacity, supports the operation speed of a large amount of real-time business processing, manages the capability of a database table in a complex relation, and has the advantages of safety, fault tolerance, support of friendly design of a user interface and the like.
3) The system operation environment and the system structure have strong flexibility, scalability, expandability and openness, not only need to fully consider and meet the current requirements, but also need to be convenient for the later expansion and expansion, and need to protect the existing investment for a long time.
4) The deployment and data synchronization interface of third-party products can be supported.
As shown in fig. 1, the cloud platform for big data of a multi-center medical device according to an embodiment of the present invention includes: the system comprises terminal medical equipment, a terminal medical equipment data acquisition module, an edge data stream cluster, an edge data display module, a cloud platform data lake cluster, a cloud platform technology platform, a cloud platform data AI platform and a cloud platform medical equipment Internet of things service center.
First, acquiring the bottom raw data of the medical equipment
Specifically, medical devices that may be classified as emergency ICU-type medical devices include: monitor, breathing machine, anesthesia machine etc. and large-scale image class medical equipment include: CT, MR, ultrasound, etc. The original data comprises sign data, waveform data, alarm data and log data. The method is compatible with various acquisition transmission protocols such as TCP, UDP, HTTP, local file systems and the like, and supports various structured, semi-structured and unstructured data acquisition such as hl7, xml, json, binary files, pictures, videos and the like.
The original data of the first-aid ICU medical equipment is acquired by integrating a communication protocol through a data acquisition terminal, and the medical equipment is connected with a serial port or a network port.
The large-scale image equipment can directly transmit equipment operation logs, equipment alarm logs and the like in a log file form through the internet access through the authority.
Second, edge server cluster
As shown in fig. 2, the edge server cluster deploys a large data stream platform, which covers a data acquisition server (Nifi), a distributed message engine (Kafka), a Streaming data real-time analysis engine (Spark Streaming), and the like, and implements real-time acquisition, parsing and collecting, stable transmission, and efficient analysis of data.
And displaying the service management and statistical chart information in real time through a data large screen by application display.
1. Real-time management of data streams
The data flow platform deploys distributed data acquisition service (Nifi) key functions including flow management, usability, safety, an extensible architecture and a flexible scaling model, and dynamically establishes connection with an acquisition client of a terminal through visual configuration to realize multi-path concurrent acquisition of mass data;
a platform deploys a data flow monitoring and management system to track basic information and data transmission conditions of medical equipment bound by each terminal in real time; presenting data flow statistical indexes, terminal states, alarm information and the like in real time; each node in the NiFi cluster performs the same task on the data, but each node operates on a different set of data. One node is selected by the ZooKeeper as the cluster coordinator and failover is handled automatically by the ZooKeeper. All cluster nodes report heartbeat and status information to the cluster coordinator. The cluster coordinator is responsible for disconnecting and connecting nodes. In addition, the cluster has a master node, which is also selected by ZooKeeper. As a dataslow manager, a user may interact with the NiFi cluster through a User Interface (UI) of any node. Any changes made will be replicated to all nodes in the cluster, allowing multiple entry points.
Data stream deployment and arrangement: the method solves the problems of terminal deployment and edge acquisition of the IoT application through a flow orchestration deployment model. And the visual arrangement and the release of the original flow are supported, and the deployment and the arrangement of an IoT application edge end are simplified.
Data flow monitoring: the data flow platform provides full-chain data tracking and flow monitoring from the source end to the tail end, and can trace the source end of each piece of data, and can automatically position terminal equipment when transmission faults, data quality problems and the like occur.
2. Analytic collection
The data analysis of the emergency treatment ICU medical equipment is analyzed and structured according to the HL7 standard, and HL7 original messages can be disassembled through a Java framework Hapi.
According to the regulations of manufacturers, the large-scale image medical equipment can analyze log data into structured data and transmit the structured data to the message middleware for data transmission and collection.
Data aggregation is the first step in the entry of various data from different data sources into a big data system. The performance of this step will directly determine the ability of a large data system to process the amount of data in a given time period. The data aggregation process is based on the personalized requirements of the system, but some commonly performed steps are-parsing incoming data, making necessary verifications, data clearness, e.g. data deduplication, format conversion, etc.
The transmissions from the different data sources are made asynchronously. May be transferred using files or implemented using message-oriented middleware. Due to the asynchronous transmission of data, the throughput of the data acquisition process can be much higher than the processing power of large data systems. Asynchronous data transmission can likewise be decoupled between the big data system and different data sources. The design of a big data infrastructure enables the big data infrastructure to be easily dynamically scaled, and the peak flow of data acquisition is safe for a big data system. Through testing, the data platform can process hundred million data levels per second, the data throughput of the platform is guaranteed, and message blocking is prevented.
3. Data transmission
After data is acquired and analyzed by the data acquisition service, a distributed message engine (Kafka) is accessed, the message engine provides distributed caching and parallel transmission of streaming data, one-time and only one-time semantics are realized, and the integrity and uniqueness of the message are ensured; the message engine has the functions of message caching, message distribution, low-delay delivery, data oriented distribution and the function of relieving the production and consumption speed mismatch problem of an upstream producer and a downstream consumer.
4. High efficiency assay
The distributed message engine is in butt joint with a downstream real-time data analysis system (Spark streaming), the real-time analysis system provides parallel consumption and real-time calculation of streaming data, and a calculation result is pushed to downstream dynamic presentation.
5. Application demonstration
By deploying and configuring the Superset, visualization of real-time query and statistical analysis of equipment time sequence data and medical service data is provided. For complex statistical analysis and visualization of machine learning calculation results, interactive presentation of Spark, Pyspark, Spark R and Python machine learning tasks is achieved through Zeppelin, Jupyter notewood and expansion thereof. For visualizations that require a high degree of customization, separate development and deployment is performed by zeppelin + Javascript. The front end is connected with a data large screen, and real-time display is realized based on the web and the like.
Three, cloud platform
Specifically, the cloud platform comprises a data lake cluster, a technical platform, a data AI platform and a medical equipment Internet of things service center.
1. Data lake cluster
Specifically, the data lake cluster maintains all platform data, constructs a data warehouse, completes the ETL work of the data, and stores the data.
1) The application technology is as follows:
hive: a data warehouse tool based on Hadoop is used for data extraction, transformation and loading, and is a mechanism capable of storing, inquiring and analyzing large-scale data stored in Hadoop. The hive data warehouse tool can map the structured data file into a database table, provide SQL query function and convert SQL sentences into MapReduce tasks for execution. For accessing structured device clinical data and device operational data.
Druid: the Druid is a distributed data processing system that supports real-time multidimensional OLAP analysis. The method supports high-speed real-time data intake processing and real-time and flexible multi-dimensional data analysis and query.
HDFS (Hadoop distributed File System): the HDFS is a Hadoop Distributed File System (Hadoop Distributed File System) and realizes reliable Distributed reading and writing of large-scale data. The HDFS aims at the use scene that data read and write have the characteristics of writing once and reading many times. HDFS ensures that a file is written to by only one caller at a time, but can be read by multiple callers. And the functions of reading, writing and storing unstructured data are carried.
sparkSQL: spark SQL is a module used by Spark to process structured data that provides a programming abstraction called DataFrame and acts as a distributed SQL query engine. Has the following characteristics: 1. easy integration 2. unified data access 3. compatible with Hive 4. standard data connection;
2) big data ETL
Referring to fig. 6, the big data platform ETL covers three contents of data collection, data storage and data conversion.
The data acquisition layer is connected with a service system and other associated external data, and supports various heterogeneous data sources such as a relational database, a NoSQL database, files, streaming data and the like. The layer is responsible for efficient and stable data acquisition and transmission, and integrity and consistency of data are guaranteed as far as possible.
The data acquisition layer adopts different technical schemes aiming at the difference of data sources.
For the business data with a relatively complex structure and synchronized regularly, a scheme for starting a timing acquisition task through a data ETL tool (such as Sqoop and Kettle) is adopted.
For data with higher real-time synchronization requirements, a streaming data acquisition scheme (such as Nifi/Flume/Logstash + Kafka, StreamSets) is adopted.
The big data platform stores data by adopting a layered scheme, and divides a data storage part into a source data layer, a data warehouse layer and a data application layer according to different data use scenes. The source data layer stores data reported by the acquisition service, keeps isomorphism of the data with the source system, and synchronizes with the source system data regularly/in real time in an increment/full loading mode. And the data warehouse layer is used for cleaning and processing the data of the source pasting layer and performing extraction and conversion according to the coarse-grained service scene to form a standardized data structure facing the theme. The data application layer organizes data for specific service applications (such as data retrieval, statistical analysis, iterative computation and the like) on the basis of the warehouse layer, and the service applications directly interact with the corresponding data table of the data application layer through an access layer API.
The data storage mode adopts different technical schemes according to the difference of the structure, the application and the source of the data and the requirements of real-time performance, integrity, consistency and the like.
Structured service data (such as HIS system data) for offline calculation is considered to be stored in the HDFS in a Hive table manner; storing time series data (such as equipment data) for real-time query and statistical analysis into the Druid; data (such as intermediate result data of a computing task) with real-time query and real-time update requirements are considered to be stored in the HDFS; and adopting Hive to solve the association operation between the heterogeneous data storages.
The data conversion model mainly undertakes the tasks of data extraction, cleaning, processing and the like of the layered storage model among layers. A set of extensible data conversion model based on a plug-in mode is designed, a model component provides a general data conversion process, and for data conversion requirements of different service types, custom rules can be developed according to interface specifications provided by the model and are accessed into the conversion model in the plug-in mode.
The technical scheme of the data conversion model is as follows: sqoop custom functions or a Kettle extension plug-in.
After the data passes through the ETL, a data warehouse or database for different subjects is formed, including a medical device business database comprising: an ICU equipment clinical database, a large-scale image log database, a large-scale image fault maintenance database, an electronic medical record document library, an operation management database and the like in each department.
The following description is given with reference to specific examples, the structured data of the ICU-like device of the present example is fused with the hospital information system to form an emergency ICU data warehouse, a data model, and a flowchart is shown in fig. 8.
The IO access of multiple data sources uses spark SQL, and the data sources comprise original HL7 message data streams of a monitor and xml messages of a hospital information system;
the data cleaning, the conversion and the extraction are completed by using distributed computation, an ETL tool is formed by configuring codes, the data cleaning is mainly implemented by setting a threshold value and an abnormal value to filter data, and screening and discarding null values;
the structured loading of the data is realized through spark SQL, and the structured processing is carried out after the data in the two data sources are matched;
hive provides meta and data warehouse operations, with data stored at hdfs at all.
The concrete configuration is as follows:
1) extracting data
2) Conversion
Select column names
Non-null processing and outlier processing
Data type conversion
df＝df.withColumn('order_type',df.order_type.cast(IntegerType()))
df＝df.withColumn('cost_count',df.cost_count.cast(IntegerType()))
df＝df.withColumn('is_comb',df.is_comb.cast(IntegerType()))
#dfc＝dfc.withColumn('is_insurup',dft.is_insurup.cast(IntegerType()))
df＝df.withColumn('tsort',df.tsort.cast(IntegerType()))
df＝df.withColumn('tstatus',df.tstatus.cast(IntegerType()))
df＝df.withColumn('cost_tstatus',df.cost_tstatus.cast(IntegerType()))
df＝df.withColumn('payment_tstatus',df.payment_tstatus.cast(IntegerType()))
df＝df.withColumn('is_append',df.is_append.cast(IntegerType()))
#dfc＝dfc.withColumn('send_mtl_flag',dft.send_mtl_flag.cast(IntegerType()))
df＝df.withColumn('comb_cost_count',
df.comb_cost_count.cast(IntegerType()))
Polymerisation
# aggregation grouping aggregation by cost traffic type
df_order＝df.groupBy("order_type").agg(F.sum(df.cost_money-df.prefer_money),F.max(df.cost_money-df.prefer_money))
df_order＝df_order.withColumnRenamed("sum((cost_money-prefer_money))","sum_group_order")
df_order＝df_order.withColumnRenamed("max((cost_money-prefer_money))","max_group_order")
df_order.show(200,truncate＝False)
# polymerization: grouping aggregation by diagnostics department
df_depart＝df.groupBy("op_depart_code").agg(F.sum(df.cost_money-df.prefer_money),F.max(df.cost_money-df.prefer_money))
df_depart＝df_depart.withColumnRenamed("sum((cost_money-prefer_money))","sum_group_depart")
df_depart＝df_depart.withColumnRenamed("max((cost_money-prefer_money))","max_group_depart")
df_depart.show(200,truncate＝False)
3) Store and load
2. Technical platform
The technical platform provides technical services required by the platform in a micro-service mode, and mainly comprises data governance and safety control.
Data governance is mainly accomplished by deploying a data governance platform, and the framework is shown in fig. 9.
Through data management, an open and universal data acquisition interface can be constructed, and the data acquisition efficiency is improved; data standards are unified, and data are easily fused; establishing cross-platform data extraction and data tracing, realizing open sharing and getting through an information isolated island; and protecting private data and constructing credible data.
Referring to fig. 10, the platform integrates LDAP, KDC Kerberos, range to implement user and service account management, authorization, authentication, service cluster protection, data access permission control, etc.
The transmission data is encrypted based on the KMS key management service.
The data security transmission and access control are realized by combining the authorization authentication strategy and the security channel, and the security use of the data and the service is ensured.
Referring to fig. 11, the platform security architecture includes: Kerberos/LDAP is used for identity authentication, Ranger is used for authorization audit, Knox is responsible for cluster security, the same account number sharing is met after integration (for example, a user1 can use the user in linux, ambari, anger, Kerberos and the like), the user and administrator information is responsible for maintaining all users and administrator information, the Ranger can synchronize the users in the LDAP and carry out uniform user authority management, and the LDAP user can be configured as a system user of the linux; knox is used as an alternative scheme of an API security gateway, users created in LDAP and Kerberos can be shared, and illegal access Host is intercepted; thereby constituting a security architecture for the data stream and data lake platform.
3. Data AI platform
Platform integration is a service for ModelArts platforms. The ModelArts is a one-stop development platform and can support the full-process development process from data to AI application for developers. As shown in fig. 12, operations including data processing, model training, model management, model deployment, etc. are provided, and AI market functions are provided that enable sharing of models with other developers within the market. The ModelArts supports a plurality of AI application scenes such as image classification, image detection, video analysis, voice recognition, product recommendation and anomaly detection.
4. Medical equipment internet of things service center
The big data analysis of the integrated medical equipment thing networking of medical equipment thing networking service center forms unified supervision system, includes: cost effectiveness, service supervision, guarantee analysis, quality safety and use analysis.
1. Single machine benefit analysis
Selecting representative equipment for single machine benefit analysis, comprising: the device has high value and has great influence on the hospital income, such as CT, DSA, DR, MR, color Doppler ultrasound, biochemical analyzers and the like in outpatient medical technical departments; secondly, equipment which occupies a large amount and is widely distributed in a hospital, such as a multi-parameter monitor, is generally analyzed by selecting the equipment in a certain department as a whole; and devices which are not high in use rate but are necessary for rescuing patients, such as a defibrillator, a breathing machine and the like. The following indices were calculated: average charging standard, average unit variable cost, average unit income, periodic warranty income, warranty point (namely the minimum business volume which must be reached each year for avoiding the loss of equipment), hospital return year, the net income created by the equipment in the specified year, annual investment earning rate and the like, and are displayed on a data large screen in a tabular form.
2. Medical equipment performance prediction model based on data mining technology
The data mining technology is utilized to fuse operation log and maintenance log data generated by large-scale image equipment with data such as equipment maintenance cost, income cost, depreciation cost and the like. And constructing a predictive performance model of each medical device by using a decision tree algorithm to obtain a device performance score.
3. Reservation/inspection person number statistical analysis for large-scale image equipment
The method comprises the steps of monitoring the current reservation times and the inspection times of large-scale image medical equipment such as CT, MR and the like in real time, wherein the current reservation times and the inspection times comprise statistics of the times, department ranking, monthly reservation times/inspection times trend broken lines and monthly reservation waiting time statistics.
4. Intelligent report form of large-scale image medical equipment
Through scientific and reasonable evaluation and analysis of equipment operation logs, maintenance and key part scanning data, report statistics is formed on the operation condition of the medical equipment, and the report statistics can be directly displayed through system calling. The main indexes comprise: the method comprises the steps of key part monthly error reporting frequency statistics, medical equipment utilization rate statistical analysis, medical equipment daily/monthly inspection part change statistics, medical equipment monthly maintenance frequency statistics and key part damage rate.
5. Accurate preventive maintenance of hemodialysis machine
And predicting the running data of the hemodialysis machine equipment based on a BP neural network algorithm, prompting equipment maintenance in advance, and providing a preventive maintenance scheme.
6. Health degree evaluation standard system for large-scale image equipment
And (3) combining the experience of a maintenance engineer, obtaining an FTA chart and an FMEA chart of the equipment by using fault tree analysis and fault mode and influence analysis methods, establishing an equipment fault experience database, judging the health distribution type of the equipment, estimating the distribution friction number, and completing the health measurement analysis with high confidence level.
7. Patient abnormal state detection system
A patient abnormal state detection algorithm is developed for the vital sign monitoring data of the department patient, as shown in fig. 13, a real-time patient state score is obtained, and a threshold value is set. When the alarm exceeds the threshold value or the trend rises, the alarm is generated to assist medical personnel in carrying out rescue measures.
8. Prediction and early warning model based on large-scale image equipment log key parts
Based on data fusion of large-scale image equipment log data and equipment maintenance system data (MEIS), training the feature data through a machine learning algorithm to obtain a classification result, judging whether the equipment fails in a T +1 time period, and early warning in time, as shown in FIG. 14.
Unless defined otherwise, all technical and/or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The materials, methods, and examples set forth in this application are illustrative only and not intended to be limiting.
Although the present invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications, and variations will be apparent to those skilled in the art in light of the teachings of this application and yet remain within the scope of this application.
Claims (8)
1. A cloud-edge-end architecture based multicenter medical device big data cloud platform comprising: end layers, side layers and cloud layers; each center is at least provided with an end layer and an edge layer; a cloud layer disposed in one of the multiple centers;
each end layer comprises a plurality of medical devices and medical device acquisition terminals; each medical equipment acquisition terminal corresponds to at least one medical terminal; the medical equipment acquisition terminal acquires medical data from the medical terminal; the end layer transmits the medical data to the edge layer which is positioned at the same center with the end layer;
each edge layer is an edge server cluster formed by a plurality of edge servers, and the edge server cluster comprises: the data flow clustering module and the data display module are used for data access, data analysis, data structuring, real-time analysis and processing, data display and data transmission of the medical equipment and providing a data access interface of a hospital information system; the boundary layer transmits the medical data to the cloud layer;
the cloud layer comprises: the medical equipment Internet of things system comprises a medical equipment Internet of things service center, a data AI platform, a technical platform and a data lake cluster, wherein the medical equipment Internet of things service center, the data AI platform, the technical platform and the data lake cluster are used for supporting standardized access of various data types, realizing multi-mode health and medical data mass storage with different time granularities and providing an off-line calculation and batch processing framework which is easy to expand; the data AI platform provides intelligent data analysis capability and provides data management, algorithm and model construction; the medical equipment Internet of things service center provides authority distribution for all service process management and control and service data; the data lake cluster is used for data access, data storage and data query; the technical platform is built by utilizing cloud services, consists of micro services, cloud middleware and a software development cloud, and provides various technical services.
2. The cloud-edge-end architecture based multicenter medical device big data cloud platform of claim 1, wherein:
the medical equipment acquisition terminal is communicated with and acquires medical data from the medical equipment through a serial port or a network port.
3. The cloud-edge-end architecture based multicenter medical device big data cloud platform of claim 1, wherein:
the data stream cluster module is built by using a big data technology on the edge server cluster; the data stream cluster module is connected with medical equipment data, provides real-time analysis and data processing services, and can push the processed data to a data display module for visual display or to a cloud layer for secondary analysis and utilization of the data;
the hospital information system data access interface is used for accessing hospital information system data, following a Webservice protocol, and acquiring data fields required by the hospital information system in a request-response mode.
4. The cloud-edge-end architecture based multicenter medical device big data cloud platform of claim 1, wherein:
the cloud layer consists of a plurality of servers in the same center;
the data lake cluster is built through a big data technology and a cloud computing technology;
the technical platform and the data AI platform are built through cloud service and artificial intelligence technology.
5. The cloud-edge-end architecture based multicenter medical device big data cloud platform of claim 1, wherein:
the data flow cluster module is built by using at least one big data assembly technology of Nifi, Kafka and Spark; and the data stream cluster module performs structured processing on the original data according to the constructed data model and the data standard protocol so as to complete data analysis.
6. The cloud-edge-end architecture based multicenter medical device big data cloud platform of claim 5, wherein:
the medical equipment comprises an ICU (intensive care unit) equipment and a medical imaging equipment; for ICU equipment, the data stream cluster module analyzes according to HL7 standard; the medical imaging device is analyzed according to a protocol according to the device.
7. The cloud-edge-end architecture based multicenter medical device big data cloud platform of claim 4, wherein:
the data lake cluster is built by using at least one of Hadoop, HDFS, Kafka, Hive and drive big data technologies; the cloud service comprises at least one of infrastructure as a service (IaaS), platform as a service (PaaS) and software as a service (SaaS);
the data AI platform provides massive data preprocessing, semi-automatic labeling, large-scale distributed training, automatic model generation and cloud-edge-end architecture deployment capability as required for machine learning and deep learning, helps a user to quickly create and deploy the cloud-edge-end architecture, manages a full-period AI workflow, and provides data management service.
8. The cloud-edge-end architecture based multicenter medical device big data cloud platform of claim 4, wherein:
the management and control of the medical equipment internet of things service center comprises the following steps: daily equipment management, central monitoring, an intensive care information management system, real-time large-screen equipment, equipment efficiency analysis, equipment benefit analysis and equipment maintenance analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011207990.8A CN112349404A (en) | 2020-11-03 | 2020-11-03 | Multi-center medical equipment big data cloud platform based on cloud-edge-end architecture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011207990.8A CN112349404A (en) | 2020-11-03 | 2020-11-03 | Multi-center medical equipment big data cloud platform based on cloud-edge-end architecture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112349404A true CN112349404A (en) | 2021-02-09 |
Family
ID=74356092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011207990.8A Pending CN112349404A (en) | 2020-11-03 | 2020-11-03 | Multi-center medical equipment big data cloud platform based on cloud-edge-end architecture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112349404A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990767A (en) * | 2021-04-20 | 2021-06-18 | 上海领健信息技术有限公司 | Vertical consumption medical SaaS production data calculation method, system, terminal and medium |
| CN113012821A (en) * | 2021-03-18 | 2021-06-22 | 日照职业技术学院 | Implementation method of multi-modal rehabilitation diagnosis and treatment cloud platform based on machine learning |
| CN113192614A (en) * | 2021-04-22 | 2021-07-30 | 广州中康数字科技有限公司 | Medical information management system based on big data |
| CN113192624A (en) * | 2021-07-01 | 2021-07-30 | 京东方科技集团股份有限公司 | Emergency treatment system, emergency treatment method and electronic device |
| CN113674837A (en) * | 2021-07-20 | 2021-11-19 | 中电通商数字技术(上海)有限公司 | High-performance, high-fault-tolerance and extensible medical data acquisition method and system |
| CN113764091A (en) * | 2021-09-24 | 2021-12-07 | 卫宁健康科技集团股份有限公司 | Intelligent management platform for medical quality |
| CN113821503A (en) * | 2021-09-23 | 2021-12-21 | 北京金山云网络技术有限公司 | Medical data processing method and device and edge server |
| CN113836235A (en) * | 2021-09-29 | 2021-12-24 | 平安医疗健康管理股份有限公司 | Data processing method based on data center and related equipment thereof |
| CN113961634A (en) * | 2021-11-18 | 2022-01-21 | 贵州电网有限责任公司 | Staff health data acquisition method |
| CN114003599A (en) * | 2021-10-12 | 2022-02-01 | 中山大学中山眼科中心 | Mass medical image processing system, system training method and image labeling method |
| CN114022769A (en) * | 2021-11-10 | 2022-02-08 | 南京工业大学 | Intelligent diagnosis method for steel bridge bolt diseases constructed based on ModelArt platform |
| CN114219165A (en) * | 2021-12-21 | 2022-03-22 | 烟台战歌电子有限公司 | Electricity consumption big data storage system, prediction algorithm and visual display platform |
| CN114880524A (en) * | 2022-05-05 | 2022-08-09 | 深圳艾灵网络有限公司 | Data lake-based data communication method, electronic device and storage medium |
| CN116366649A (en) * | 2023-06-01 | 2023-06-30 | 中电云脑(天津)科技有限公司 | Side cloud cooperative electroencephalogram data task scheduling method and system |
| CN116895375A (en) * | 2023-09-08 | 2023-10-17 | 南通大学附属医院 | A medical device management traceability method and system based on data sharing |
| CN117012364A (en) * | 2023-10-08 | 2023-11-07 | 吉林大学 | Medical health service cloud platform based on industrial Internet technology |
| CN119092088A (en) * | 2024-11-08 | 2024-12-06 | 四川省商投信息技术有限责任公司 | A multi-center medical equipment big data cloud platform based on cloud-edge-end architecture |
| CN119274744A (en) * | 2024-09-24 | 2025-01-07 | 广州健之杰洁具有限公司 | A safety management system for hydrotherapy equipment used for rehabilitation treatment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2370377A (en) * | 2000-08-18 | 2002-06-26 | Resource Partners Group Ltd | System for managing the prescibing and dispensing of medical items |
| US20130110547A1 (en) * | 2011-04-07 | 2013-05-02 | Master Mobile Products, Llc | Medical software application and medical communication services software application |
| CN107610760A (en) * | 2017-08-31 | 2018-01-19 | 上海德衡数据科技有限公司 | A kind of intelligent region emergency medical integrated data centric system architecture based on software definition |
| WO2018032976A1 (en) * | 2016-08-19 | 2018-02-22 | 京东方科技集团股份有限公司 | Medical data management method and apparatus, and medical data system |
| CN110008286A (en) * | 2019-03-26 | 2019-07-12 | 华南理工大学 | A system and method for collecting and storing big data of injection molding equipment |
| CA3050220A1 (en) * | 2018-07-19 | 2020-01-19 | Bank Of Montreal | Systems and methods for data storage and processing |
| CN111161860A (en) * | 2019-12-27 | 2020-05-15 | 杭州中科先进技术研究院有限公司 | Edge calculation-based basic medical information processing system and method |
| CN111324671A (en) * | 2020-03-02 | 2020-06-23 | 苏州工业园区洛加大先进技术研究院 | Biomedical high-speed information processing and analyzing system based on big data technology |
| CN111371830A (en) * | 2019-11-26 | 2020-07-03 | 航天科工网络信息发展有限公司 | Intelligent cooperative cloud architecture based on data driving under ten thousand network fusion scene |
| CN111404932A (en) * | 2020-03-16 | 2020-07-10 | 北京工业大学 | A method for a medical institution system to access a smart medical cloud service platform |
| CN111768850A (en) * | 2020-06-05 | 2020-10-13 | 上海森亿医疗科技有限公司 | Hospital data analysis method, hospital data analysis platform, device and medium |
| EP3907641A1 (en) * | 2019-01-09 | 2021-11-10 | Wangsu Science & Technology Co., Ltd. | Intelligent management method and system based on edge computing |
-
2020
- 2020-11-03 CN CN202011207990.8A patent/CN112349404A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2370377A (en) * | 2000-08-18 | 2002-06-26 | Resource Partners Group Ltd | System for managing the prescibing and dispensing of medical items |
| US20130110547A1 (en) * | 2011-04-07 | 2013-05-02 | Master Mobile Products, Llc | Medical software application and medical communication services software application |
| WO2018032976A1 (en) * | 2016-08-19 | 2018-02-22 | 京东方科技集团股份有限公司 | Medical data management method and apparatus, and medical data system |
| CN107610760A (en) * | 2017-08-31 | 2018-01-19 | 上海德衡数据科技有限公司 | A kind of intelligent region emergency medical integrated data centric system architecture based on software definition |
| CA3050220A1 (en) * | 2018-07-19 | 2020-01-19 | Bank Of Montreal | Systems and methods for data storage and processing |
| EP3907641A1 (en) * | 2019-01-09 | 2021-11-10 | Wangsu Science & Technology Co., Ltd. | Intelligent management method and system based on edge computing |
| CN110008286A (en) * | 2019-03-26 | 2019-07-12 | 华南理工大学 | A system and method for collecting and storing big data of injection molding equipment |
| CN111371830A (en) * | 2019-11-26 | 2020-07-03 | 航天科工网络信息发展有限公司 | Intelligent cooperative cloud architecture based on data driving under ten thousand network fusion scene |
| CN111161860A (en) * | 2019-12-27 | 2020-05-15 | 杭州中科先进技术研究院有限公司 | Edge calculation-based basic medical information processing system and method |
| CN111324671A (en) * | 2020-03-02 | 2020-06-23 | 苏州工业园区洛加大先进技术研究院 | Biomedical high-speed information processing and analyzing system based on big data technology |
| CN111404932A (en) * | 2020-03-16 | 2020-07-10 | 北京工业大学 | A method for a medical institution system to access a smart medical cloud service platform |
| CN111768850A (en) * | 2020-06-05 | 2020-10-13 | 上海森亿医疗科技有限公司 | Hospital data analysis method, hospital data analysis platform, device and medium |
Non-Patent Citations (1)
| Title |
|---|
| 袁华: ""基于ELK和Spark的日志分析系统的研究与实现"" * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113012821B (en) * | 2021-03-18 | 2022-04-15 | 日照职业技术学院 | Implementation method of multi-modal rehabilitation diagnosis and treatment cloud platform based on machine learning |
| CN113012821A (en) * | 2021-03-18 | 2021-06-22 | 日照职业技术学院 | Implementation method of multi-modal rehabilitation diagnosis and treatment cloud platform based on machine learning |
| CN112990767B (en) * | 2021-04-20 | 2021-08-20 | 上海领健信息技术有限公司 | Vertical consumption medical SaaS production data calculation method, system, terminal and medium |
| CN112990767A (en) * | 2021-04-20 | 2021-06-18 | 上海领健信息技术有限公司 | Vertical consumption medical SaaS production data calculation method, system, terminal and medium |
| CN113192614A (en) * | 2021-04-22 | 2021-07-30 | 广州中康数字科技有限公司 | Medical information management system based on big data |
| CN113192614B (en) * | 2021-04-22 | 2024-02-13 | 广州中康数字科技有限公司 | Medical information management system based on big data |
| CN113192624B (en) * | 2021-07-01 | 2022-05-31 | 京东方科技集团股份有限公司 | Emergency treatment system, emergency treatment method and electronic device |
| CN113192624A (en) * | 2021-07-01 | 2021-07-30 | 京东方科技集团股份有限公司 | Emergency treatment system, emergency treatment method and electronic device |
| CN113674837A (en) * | 2021-07-20 | 2021-11-19 | 中电通商数字技术(上海)有限公司 | High-performance, high-fault-tolerance and extensible medical data acquisition method and system |
| CN113821503A (en) * | 2021-09-23 | 2021-12-21 | 北京金山云网络技术有限公司 | Medical data processing method and device and edge server |
| CN113764091A (en) * | 2021-09-24 | 2021-12-07 | 卫宁健康科技集团股份有限公司 | Intelligent management platform for medical quality |
| CN113764091B (en) * | 2021-09-24 | 2024-03-01 | 卫宁健康科技集团股份有限公司 | Medical quality intelligent management platform |
| CN113836235A (en) * | 2021-09-29 | 2021-12-24 | 平安医疗健康管理股份有限公司 | Data processing method based on data center and related equipment thereof |
| CN113836235B (en) * | 2021-09-29 | 2024-04-09 | 平安医疗健康管理股份有限公司 | Data processing method based on data center and related equipment thereof |
| CN114003599A (en) * | 2021-10-12 | 2022-02-01 | 中山大学中山眼科中心 | Mass medical image processing system, system training method and image labeling method |
| CN114022769A (en) * | 2021-11-10 | 2022-02-08 | 南京工业大学 | Intelligent diagnosis method for steel bridge bolt diseases constructed based on ModelArt platform |
| CN113961634A (en) * | 2021-11-18 | 2022-01-21 | 贵州电网有限责任公司 | Staff health data acquisition method |
| CN114219165A (en) * | 2021-12-21 | 2022-03-22 | 烟台战歌电子有限公司 | Electricity consumption big data storage system, prediction algorithm and visual display platform |
| CN114880524A (en) * | 2022-05-05 | 2022-08-09 | 深圳艾灵网络有限公司 | Data lake-based data communication method, electronic device and storage medium |
| CN114880524B (en) * | 2022-05-05 | 2024-09-20 | 深圳艾灵网络有限公司 | Data lake-based data communication method, electronic equipment and storage medium |
| CN116366649B (en) * | 2023-06-01 | 2023-09-05 | 中电云脑(天津)科技有限公司 | A method and system for EEG data task scheduling based on edge-cloud collaboration |
| CN116366649A (en) * | 2023-06-01 | 2023-06-30 | 中电云脑(天津)科技有限公司 | Side cloud cooperative electroencephalogram data task scheduling method and system |
| CN116895375A (en) * | 2023-09-08 | 2023-10-17 | 南通大学附属医院 | A medical device management traceability method and system based on data sharing |
| CN116895375B (en) * | 2023-09-08 | 2023-12-01 | 南通大学附属医院 | A medical device management traceability method and system based on data sharing |
| CN117012364A (en) * | 2023-10-08 | 2023-11-07 | 吉林大学 | Medical health service cloud platform based on industrial Internet technology |
| CN119274744A (en) * | 2024-09-24 | 2025-01-07 | 广州健之杰洁具有限公司 | A safety management system for hydrotherapy equipment used for rehabilitation treatment |
| CN119274744B (en) * | 2024-09-24 | 2025-03-11 | 广州健之杰洁具有限公司 | A safety management system for hydrotherapy equipment used for rehabilitation treatment |
| CN119092088A (en) * | 2024-11-08 | 2024-12-06 | 四川省商投信息技术有限责任公司 | A multi-center medical equipment big data cloud platform based on cloud-edge-end architecture |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112349404A (en) | Multi-center medical equipment big data cloud platform based on cloud-edge-end architecture | |
| El Aboudi et al. | Big data management for healthcare systems: architecture, requirements, and implementation | |
| US7890517B2 (en) | Appliance for enterprise information integration and enterprise resource interoperability platform and methods | |
| Lyko et al. | Big data acquisition | |
| Di Martino et al. | Big data (lost) in the cloud | |
| CN108021809A (en) | A kind of data processing method and system | |
| US11276484B1 (en) | Clinical activity network generation | |
| CN112653703A (en) | Multi-medical-protocol conversion analysis method and system based on edge calculation | |
| US20250021767A1 (en) | Machine Learning Model Training Data Generation from Generative Artificial Intelligence and User Feedback | |
| US12287790B2 (en) | Runtime systems query coordinator | |
| CN111046022A (en) | Database auditing method based on big data technology | |
| Alexandru et al. | Big data: concepts, technologies and applications in the public sector | |
| Raj et al. | Big data analytics processes and platforms facilitating smart cities | |
| WO2022147566A1 (en) | A method and system for machine learning using a derived machine learning blueprint | |
| US20250232227A1 (en) | Systems And Methods For Quantifying Change Between Machine Learning Models | |
| Anderson et al. | Architectural Implications of Social Media Analytics in Support of Crisis Informatics Research. | |
| Akhtar et al. | Challenges in managing real-time data in health information system (HIS) | |
| Nesi et al. | Auditing and assessment of data traffic flows in an IoT architecture | |
| US12158884B1 (en) | Embedded tokens for searches in rendering dashboards | |
| Sassi et al. | Business information architecture for big data and Internet of Things | |
| US12072913B1 (en) | Unhandled data protection for programmatic input/output routing to datasets with user-defined partitions | |
| Baby et al. | Big data: an ultimate solution in health care | |
| da Silva Rocha et al. | Aggregating data center measurements for availability analysis | |
| US11835989B1 (en) | FPGA search in a cloud compute node | |
| Ribeiro et al. | A scalable data integration architecture for smart cities: implementation and evaluation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210209 |
|
| RJ01 | Rejection of invention patent application after publication |