CN114157680B

CN114157680B - ICU multi-device semantic interoperation data transmission system and method and readable storage medium

Info

Publication number: CN114157680B
Application number: CN202111457859.1A
Authority: CN
Inventors: 何昆仑; 庄严; 曹德森; 张政波; 李涛; 乔屾; 李宗任; 卢若谷; 张军雁
Original assignee: Chinese PLA General Hospital
Current assignee: Chinese PLA General Hospital
Priority date: 2021-12-01
Filing date: 2021-12-01
Publication date: 2022-07-08
Anticipated expiration: 2041-12-01
Also published as: CN114157680A

Abstract

The disclosure relates to a data transmission system and method for ICU multi-device semantic interoperation, comprising: the data acquisition layer is used for acquiring data uploaded by various medical equipment and sensors; the data conversion layer is used for analyzing and extracting various uploaded format data, organizing the format data in a standard format and uploading the data formatted in the standard format to the edge calculation layer; the edge calculation layer is used for carrying out secondary processing on the standard format data uploaded by the medical equipment, and adding the generated additional necessary data into the original data packet and uploading the additional necessary data to the cloud storage layer; and the cloud storage layer is used for storing the data packet sent by the edge computing layer. The method and the device realize multi-device interaction by using a unified top-layer body structure and standardized terms, and only a flow result and some original data need to be sent to a cloud storage layer in the data transmission process, so that network congestion and response time are effectively reduced, and the data transmission speed is improved.

Description

ICU multi-device semantic interoperation data transmission system and method and readable storage medium

Technical Field

The disclosure relates to the technical field of communication in the field of medicine, in particular to a data transmission system and a data transmission method for ICU multi-device semantic interoperation.

Background

With the development of new generation ICT technologies of cloud computing, big data, Internet of things and 5G, AI, the technology of everything interconnection is mature and gradually deepens into various industries, and the digital transformation of various industries is driven. The medical internet of things brings unprecedented challenges to the medical industry, and the development of the technology updating industry brings unprecedented opportunities to intelligent hospitals and intelligent services.

The Medical Internet of Things (IoMT) is an intelligent Internet of Things system which connects various sensors, Medical equipment and intelligent equipment with a hospital information system through sensing and communication technologies, supports data acquisition, transmission, processing, storage and analysis application in the Medical service and hospital operation process, and accordingly realizes interconnection and interaction of everything in a Medical scene. In an intelligent hospital, the IoMT can realize interconnection and intercommunication of any element at any time and any place, and meets the application development of medical intelligence.

The greatest challenge of the medical internet of things is the networking problem of a huge amount of medical equipment, and a huge fault exists between the medical equipment/sensors and the network.

Firstly, networking scenes are not considered in the design of a large number of existing medical internet-of-things instruments and equipment, the medical internet-of-things instruments and equipment are only used as single checking and inspecting equipment, and the equipment does not have networking capacity and only has a printing interface and a debugging interface. Data is typically acquired by manual entry into an electronic medical record system by a healthcare worker. Some current realization methods, through the patch cord mode access that RS232 changes RJ45, but because RS232 does not have unified safety control mechanism itself, also can bring huge safe risk for hospital intranet safety.

The second step is as follows: the medical terminal and the sensor have different communication modes, such as wired RS232, RS485, RJ45 and the like, and wireless Wi-Fi, RFID, BLE, Bluetooth, Zigbee, LoRa and the like; it is difficult to access the network in a uniform manner. Different sensors are different in scene, manufacturers also customize partial communication mechanisms on the basis of different communication, so that unified access is more difficult, access can only be realized through different gateways, the condition that different Bluetooth sensors are connected with different Bluetooth gateways exists, coexistence of multiple small networks is caused, information interaction is difficult, and an island is formed.

And thirdly: there is no unified internet of things interface standard for medical devices, and each device has its own API or protocol interface, such as HL7, Benelink, proprietary protocol, etc., so the interface protocols for acquiring data from medical devices are different. Therefore, the upper layer application needs to obtain the corresponding data from the device only through the device interaction only through a specific interface protocol of the device manufacturer. Because of these non-standard interface protocol limitations, a barrier is established between the medical device and the application, making it difficult to interconnect and communicate between the application and the device. Meanwhile, the security authentication capabilities supported by the protocol interfaces of the devices are different, and the data traffic output from the devices is directly forwarded to the application of the data center without being subjected to semantic analysis to confirm security, so that the risk is brought to the security of the whole network.

In addition, due to limited computing resources, internet of things devices often rely on cloud-hosted stream processing centralized platforms to perform complex analytical processing such as filtering, aggregation, classification, pattern detection, and prediction. Such remote data processing can lead to key problems such as loss of connection, high response time, and overhead for centralized computing systems. In view of the above situation, the industry has proposed the concept of edge computing, but because the hardware architecture of the internet of things device is heterogeneous, the processor, the memory and the communication capability are limited, the development of customized embedded software and the diversification of technology and programming language make the application of edge computing not a simple problem. Research and analysis have found several methods for bringing data analysis to the edge of the network in real time, with network traffic and network latency reduction as primary goals and memory consumption reduction, energy use reduction, data classification and recovery of incomplete data series as secondary goals. The most common techniques are pattern recognition, outlier detection and prediction. A common feature of these efforts is that the flow is customized manually, rather than using a standard development framework or API (application programming interface).

Disclosure of Invention

In order to overcome the problems in the related art, the present disclosure provides a data transmission system and method for ICU multi-device semantic interoperability.

The technical scheme adopted by the invention for solving the technical problems is as follows:

an ICU multi-device semantic interoperation data transmission system, comprising:

the data acquisition layer is used for acquiring data uploaded by various medical equipment and sensors;

the data conversion layer is used for analyzing and extracting various uploaded format data, organizing the format data in a standard format, and uploading the data after the standard format to the edge calculation layer;

the edge calculation layer is used for carrying out secondary processing on the standard format data uploaded by the medical equipment, and adding the generated additional necessary data into the original data packet and uploading the additional necessary data to the cloud storage layer;

and the cloud storage layer is used for storing the data packet sent by the edge computing layer.

In some embodiments, the step edge calculation layer comprises:

the data processing layer is used for processing JSON/XML data in a standard format generated by the data conversion layer through data cleaning, pre-polymerization and data statistics;

the body modeling layer carries out semantic modeling through an internet knowledge graph generated by the multi-equipment semantic operation body;

the body application layer is used for constructing edge terminal intelligent application based on the trained semantic model, and the edge terminal intelligent application has the functions of decision support, monitoring and early warning, knowledge reasoning and mode mining;

and the data enhancement layer is used for attaching the additional necessary data generated by the data processing layer, the ontology modeling layer and the ontology application layer to an original data packet and communicating with the cloud storage layer.

In some embodiments, the ontology modeling layer comprises:

the data stream acquisition layer is used for finishing the caching of the input JSON/XML data stream;

the body mapping layer is used for mapping the cached JSON/XML data stream to a body framework and constructing a multi-device semantic operation body through a controlled term set;

the semantic annotation layer is used for converting the JSON/XML data stream into an RDF semantic data stream conforming to the body definition and converting the multiple devices and the attributes thereof into an internet knowledge map;

and the data storage layer is used for storing the generated RDF semantic data stream into the RDF database.

In some embodiments, the ontology architecture includes concept definitions, attribute definitions, relationship definitions.

In some embodiments, the controlled term set comprises a vocabulary formed by a method of controlling the lexical meaning used and tracking related words.

In some embodiments, the data translation layer comprises:

and the data analyzer is used for analyzing and extracting various data formats acquired by the data acquisition layer.

The embodiment of the invention provides a data transmission method for ICU multi-device semantic interoperation, which comprises the following steps:

1) accessing medical equipment and sensors, and acquiring data information in various formats;

2) converting the collected data information in different formats into data information in a standard format;

3) processing data information in a standard format through a data processing layer, a body modeling layer and a body application layer, and adding extra data information generated after processing into an original data packet through a data enhancement layer to form a secondary data packet;

4) and sending the secondary data packet to a cloud storage layer for storage.

In some embodiments, the processing of the data information in the standard format by the data processing layer, the ontology modeling layer, and the ontology application layer, and the adding of the extra data information generated after the processing to the original data packet by the data enhancement layer to form the secondary data packet, includes:

data cleaning is carried out on the data information in the standard format through a data processing layer;

performing data reasoning on the input data information in the standard format through the body modeling layer and the body application layer;

and adding the additional data information generated by inference into the original data packet through the data enhancement layer to form a secondary data packet.

An embodiment of the present invention provides a non-transitory computer-readable storage medium, where instructions in the storage medium, when executed by a processor of a mobile terminal, enable the mobile terminal to execute the ICU multi-device semantic interoperation data transmission method as described above.

An embodiment of the present invention provides a computer program product, wherein when an instruction in the computer program product is executed by a processor of a mobile terminal, the mobile terminal is enabled to execute the ICU multi-device semantic interoperation data transmission method as described above.

The embodiment of the invention has the following beneficial effects:

the invention provides a data transmission system and a data transmission method for ICU multi-device semantic interoperability, which realize semantic interoperability through shared, definite and machine-understandable vocabularies, express shared and reused knowledge in an open format, and realize multi-device interaction through a unified top-level body architecture and standardized terms. And the medical internet of things equipment can be mapped to the knowledge graph based on the ontology through ontology mapping, and can be dynamically evolved to adapt to new context or usage, and joint intelligent reasoning is realized. And some computing processes are moved close to a data source through an edge computing technology, and a process result and some original data are sent to a remote cloud data center, so that delay is effectively reduced, energy consumption is reduced, cost is reduced, and network congestion and response time are reduced.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

FIG. 1 is a block diagram illustrating a data transfer system for ICU multi-device semantic interoperability in accordance with an exemplary embodiment.

FIG. 2 is an ontology architecture diagram illustrating ICU multi-device semantic interoperability, according to an example embodiment.

FIG. 3 is an instantiation diagram of an ontology architecture for ICU multi-device semantic interoperability, shown in accordance with an exemplary embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.

Fig. 1 is a block diagram of an ICU multi-device semantic interoperable data transmission system according to an exemplary embodiment, where the ICU multi-device semantic interoperable data transmission system specifically includes:

and the data acquisition layer is used for acquiring data uploaded by various medical equipment and sensors.

Specifically, when a specific application is performed, data of a plurality of devices is collected through a data collection layer in the system. The data acquisition layer currently supports access to a plurality of 400 models of life support class clinical devices, and the covering device classes comprise: monitor, respirator, transfer pump, hemodialysis machine, anesthesia machine, infant incubator etc.. With reference to fig. 1, data in the device a, the device B, the device C, and the device D may be acquired.

In connection with particular embodiments, the functions of the data acquisition layer include:

1. monitor data acquisition capability

Collecting vital sign data (heart rate, blood oxygen, body temperature, blood pressure, respiratory rate, pulse, etc.) and waveform data (electrocardiogram waveform, respiratory waveform, pulse rate waveform, etc.) of the monitor according to a specified frequency.

2. Ventilator data acquisition capability

Ventilator vital sign data (tidal volume, positive end-of-breath, minute ventilation, maximum airway pressure, etc.), waveform data (airway pressure waves, volume waves, flow waves) are collected at a specified frequency.

3. Data acquisition capacity of anesthesia machine

Anesthesia machine vital sign data (airway pressure, inhaled CO2, end-of-breath CO2, tidal volume, etc.), waveform data (airway pressure waves, volume waves, flow waves) are collected at a specified frequency.

4. Simultaneous multi-device data acquisition capability

And at most 4 devices are simultaneously connected for data acquisition by each acquisition terminal.

5. Multi-network data backhaul capability

And uplink data return is supported through a LAN wired network or a WLAN wireless network.

6. System logging and lookup capabilities

The acquisition terminal is based on an embedded Linux system and has a consultable log record.

7. Return data timestamp marking capability

The data transmission contains a timestamp, which is synchronized with the server clock.

8. Downlink Ethernet interface

And the 10M Ethernet port is used for acquiring the data of the medical equipment of the network port type by using a standard SCSI 14pin interface.

9. Downstream RS-232 serial interface

And the RS-232 serial port and the 10M Ethernet port share a SCSI 14PIN interface for collecting the serial port type medical equipment data.

10. Uplink Ethernet interface

10/100M adaptive Ethernet port for uploading data to the edge server.

11. Device plug and connect capability

The plug and play connection of the medical equipment is supported, and the connection delay is less than or equal to 5 s.

12. Software fault automatic restart, fault recovery capability

And fault automatic restart and automatic connection are supported.

And the data conversion layer is used for analyzing and extracting various uploaded format data, organizing the format data in a standard format, and uploading the standard formatted data to the edge calculation layer.

Specifically, the data conversion layer converts data in formats such as ascii (american Standard Code for Information exchange), JSON (JavaScript Object Notation), binary system, and the like, which are acquired by a Transmission communication Protocol such as RS-232 Standard interface (also called EIA RS-232), Transmission Control Protocol (TCP), User Datagram Protocol (UDP), into data in Standard format JSON/XML, and "/" means "or" means. The standard format consists of JSON/XML containing the attributes "medical device id", "data", "message type", "message sequence number" and "timestamp". The data translation layer may also provide data compression transmission capabilities.

In some embodiments, the data translation layer comprises: and the data analyzer is used for analyzing and extracting various data formats acquired by the data acquisition layer.

Specifically, the data conversion layer analyzes and extracts various data formats acquired by the data acquisition layer through the data analyzer.

And the edge computing layer is used for carrying out secondary processing on the standard format data uploaded by the medical equipment, and adding the generated additional necessary data into the original data packet and uploading the additional necessary data to the cloud storage layer.

Specifically, the JSON/XML data standardized in the above embodiment is subjected to secondary transformation and combination, and the generated additional necessary data is attached to the original data packet and uploaded to the cloud storage layer.

In some embodiments, the edge calculation layer comprises:

and the data processing layer is used for processing the JSON/XML data generated by the data conversion layer through data cleaning, pre-polymerization and data statistics.

Specifically, different data of multiple devices are converted into JSON/XML data through the above method, but the data is still huge, and the data can be processed for the second time through data cleaning, pre-polymerization and data statistics methods, where the data cleaning includes processing null values or invalid values, data normalization, unit conversion and the like. Pre-polymerization is the application of an aggregation function to a data set, such as minimum, maximum, sum, count, etc., for data description. Data statistics are statistics of the computed data set, such as mean, median, standard deviation, variance, skewness, etc., and may also be analyzed simply using a time or batch sliding window selection subset.

And the ontology modeling layer performs semantic modeling through the Internet knowledge graph generated by the multi-device semantic operation ontology.

Specifically, an internet knowledge graph generated by the multi-device semantic operation body is trained to obtain a trained semantic model.

In some embodiments, the ontology modeling layer comprises:

and the data stream acquisition layer is used for finishing the caching of the input JSON/XML data stream.

Specifically, the method is used for caching the JSON/XML data processed by the data processing layer.

And the ontology mapping layer is used for mapping the cached JSON/XML data stream to an ontology framework and constructing a multi-device semantic operation ontology through the controlled term set.

Specifically, after the definition of the ontology architecture and the controlled term set is completed, a globally unique identifier is allocated to each device, and a program is developed to perform automatic contrast conversion. A common practice for globally unique identifiers is to use the URI of the device. The standard for a URI is defined as URI ═ domain name/[ local path ]/[ autoId ]. In the present invention, the network domain name of the deployed application is used as a namespace (e.g., https:// www.301hospital.com.cn), the class name of the device in the IOT Domain ontology is used as a localpath (e.g., ventilator), and the serial number of the device is used as an autoId (e.g., 000F14049B 143172). Thus, for a device, its URI may be defined as:

URI＝https://www.301hospital.com.cn/iomt_ontology/device/monitor/id

similarly, URIs of other major entity types may be defined as follows:

monitoring: https:// www.301hospital.com.cn/iomt _ ontology/occupancy/id

Monitoring indexes are as follows: https:// www.301hospital.com.cn/iomt _ ontology/device/monitor/CO2

Monitoring the object: https:// www.301hospital.com.cn/iomt _ ontology/probability/id

The monitor: https:// www.301hospital.com.cn/iomt _ ontology/sector/id

And (3) monitoring results: https:// www.301hospital.com.cn/iomt _ ontology/result/id

After the global unique identifier is distributed, the generated JSON format data stream can be mapped to an ontology architecture to construct an ICU multi-device semantic interoperation ontology.

Specifically, before mapping the generated JSON/XML data stream onto the ontology architecture, an ontology architecture binding implementation suitable for ICU multi-device semantic interaction needs to be created first, as shown in fig. 2, which includes concepts (semantic types), attributes, relationship definitions and their interrelations. In this ontology, a Device class (Device) is a subclass of a Thing class (thining) that accomplishes a specific task by Device-provided monitoring (occupancy)/execution (action). Monitoring can be classified into various types, including Sign monitoring (Sign _ monitoring), Waveform detection (Waveform _ monitoring), and the like, one monitoring may have an association relationship such as monitoring index (observeproperty), monitored object (Observation _ object), monitor (Observator), monitoring Result (Result), monitoring associated check item (observationexammem), and the like, data of the monitoring index typically describes some Aspect (Aspect) of the real world (e.g., Waveform, Sign), and the monitoring Result may include MetaData (MetaData) (e.g., unit, precision).

Further, the concept definition in the ontology architecture includes: concept ID, URI, concept name, alias, tree number, definition, link, release time; the attribute definition includes: attribute ID, URI, attribute name, alias, definition, applicable semantic type, data type, link, release time; the relationship definition includes: relation ID, URI, relation name, tree number, definition, domain ID, domain, link, release time.

With reference to the specific embodiment, the relevant clinical diagnosis and treatment data (patient basic information, clinical diagnosis, medication information, examination and test result information, etc.) of the HIS may be obtained in a correlated manner through the id number of the monitoring object (patient), and the relevant information of the medical care personnel may be obtained through the monitor (medical staff), for example, as shown in fig. 3.

Through the design of the body framework, the interaction between different protocol standard devices can be realized, and the data in the clinical information system and the data of medical personnel can be connected for correlation analysis.

In some embodiments, the controlled term set contains a vocabulary formed by a method of controlling the lexical meaning used and tracking related words.

Specifically, after the ontology architecture suitable for ICU multi-device semantic interaction is created in the above embodiment, a controlled term set is created. A controlled term set is a vocabulary formed by a method of controlling the lexical meaning used and tracking related words, which constitutes an example of semantic categories in the ontology framework described above. Standardization of methods, definitions and results is achieved by normalizing data content and mapping ontologies. For example, the device class may include life support class devices under study such as monitors, ventilators, anesthesia machines, and infusion pumps; monitoring data services of the monitor can comprise invasive arterial diastolic pressure, invasive arterial systolic pressure, respiratory rate, ETCO2 (C02 at the end of breath), inhaled oxygen concentration, height, heart rate and other variables as monitoring indexes; the injection service of the infusion pump takes the injection amount as a monitoring index; aspects may include monitoring content of certain aspects such as waveform, blood pressure, respiration, etc. The definition of the instance comprises field information such as instance ID, instance name, English name, alternative name, definition, link, semantic type, upper concept, tree number, release time and the like.

And the semantic annotation layer is used for converting the JSON/XML data stream into an RDF semantic data stream conforming to the body definition and converting the multiple devices and the attributes thereof into an internet knowledge map.

Specifically, according to the ontology mapping relationship, the ontology parser is used for processing the internet of things perception data, relevant information such as types, attributes and relationships is obtained, and the JSON/XML data stream is automatically converted into the RDF semantic data stream conforming to the ontology definition. Through the mapping rule, various life support equipment and attributes thereof of the ICU can be converted into an Internet knowledge graph, the operation between the equipment is also converted into the operation of the Internet of things knowledge graph, and meanwhile, basic information, clinical diagnosis, medication information and examination and test result information of patients from the HIS are also brought into the body framework for unified processing.

Specifically, after the RDF semantic data stream is generated, the RDF semantic data stream is automatically stored in an RDF database, and data validity verification is performed. Due to the limitation of the storage capacity and the processing speed of the edge end system, the edge end RDF database stores data in a specified time period and is used for timely processing various conditions occurring in the current time period.

And the body application layer is used for constructing an edge terminal intelligent application based on the trained semantic model, and the edge terminal intelligent application has the functions of decision support, monitoring and early warning, knowledge reasoning and mode mining.

Specifically, the ontology application layer constructs edge-end intelligent applications. The trained semantic model is used for carrying out real-time query and simple reasoning on the monitored data, so that intelligent algorithms such as light-weight mode mining, early warning monitoring and the like can be realized, and quick decision support capability is provided for clinical operation. The knowledge service based on the RDF triples is realized by using a knowledge processing API general framework based on a semantic net and an associated data application program, nodes and edges in an internet of things knowledge graph are inquired, created, modified and deleted by using a standard SPARQL, the triples are stored by using a standard RDF database, and a rule inference engine based on the semantic net is used as an ontology rule inference engine. A series of inference rules are defined on the internet knowledge map data, potential knowledge is obtained through the inference process of a rule inference machine, and early warning and decision support are achieved.

In connection with a particular embodiment, Jena, Apache is used to implement knowledge services for RDF-based triples. SPARQL endpoints are generic service access terminals that provide standard SPARQL services. Through the SPARQL endpoint, nodes and edges in the knowledge graph of the Internet of things can be inquired, created, modified and deleted. Fuseki is the SPARQL service execution engine, providing for the parsing and execution of SPARQL state. The Jena rule inference engine is an ontology rule inference engine, can infer the execution condition of SPARQL according to rules defined in an ontology framework and a domain ontology, and Jena can automatically identify potential relations. The TDB is a database for storing the knowledge graph, the storage structure of the RDF triple is optimized, and the efficiency of the SPARQL service in the knowledge graph query is improved. The ICU device will generate a knowledge graph supporting semantic interoperability according to the mapping rules and store them in the TDB deployed at the edge end. All query, create, modify and delete operations operate the knowledge graph through SPARQL endpoints and indirectly operate internet of things devices.

In an example of edge-end knowledge inference, the lung capacity of a mechanical ventilation early warning event is less than 10ml/kg, and a corresponding ventilator monitoring index is obtained by querying a SPARQL of a knowledge graph: respiratory rate 5/min, vital capacity 7ml/kg, tidal volume 2.5ml/kg, PaCO2 ═ 55mmHg, maximum inspiratory pressure 21cmH2O and the like, and monitor monitoring indexes: the central venous pressure 12cmH2O, according to preset rules, was in compliance with mechanical ventilation conditions, but concerns were given about excessive central venous pressure.

Specifically, before an original data packet acquired by the data acquisition layer is transmitted to an application program, the data enhancement layer adds a data processing layer, an ontology modeling layer and a related processing result of the ontology application layer to the original data packet, and uploads the original data packet to the cloud. Although such processing will slightly increase the amount of data to be transmitted, the data to be uploaded can be selected by an algorithm after data enhancement.

According to the specific embodiment, reasoning is carried out through an edge calculation layer, the lung capacity of the mechanical ventilation early warning event is monitored to be less than 10ml/kg, and the SPARQL query of a knowledge graph is carried out to obtain a corresponding monitoring index of the breathing machine: respiratory rate 5/min, vital capacity 7ml/kg, tidal volume 2.5ml/kg, PaCO2 ═ 55mmHg, maximum inspiratory pressure 21cmH2O and the like, and monitor monitoring indexes: the central venous pressure is 12cmH2O, and the ontology application layer performs reasoning according to a semantic model in the ontology modeling layer, so that the mechanical ventilation condition is met, but the central venous pressure is too high. And adding the final inference result into the original data packet to realize the enhancement of the data.

And the cloud storage layer is used for storing the data packets sent by the edge computing layer.

In particular, local data storage, data security, data applications, and knowledge base management are included. The knowledge base management realizes the ontology construction and the full-scale knowledge base storage of cloud data by using the same ontology modeling process as that of the edge calculation layer. Training of the AI model by using the full-scale knowledge data is carried out in the layer, and the trained model can be pushed, deployed and applied to the RDF database at the side end to carry out more intelligent reasoning.

When the ICU multi-device semantic interoperation data transmission system is used, the ICU multi-device semantic interoperation data transmission method is provided, and the specific steps comprise:

1) accessing medical equipment and a sensor, and acquiring data information in various formats;

4) and sending the secondary data packet to a cloud storage layer for storage.

performing data reasoning on the input data information in the standard format through the ontology modeling layer and the ontology application layer;

In summary, the ICU multi-device semantic interoperation data transmission method provided by the present application implements semantic interoperation through the above steps by using shared, clear, machine-understandable vocabularies, expresses shared and reused knowledge in an open format, and implements multi-device interaction with a unified top-level ontology architecture and standardized terms. And the medical internet of things equipment can be mapped to the knowledge graph based on the ontology through ontology mapping, and can be dynamically evolved to adapt to new context or usage, and joint intelligent reasoning is realized. And some computing processes are moved close to a data source through an edge computing technology, and a process result and some original data are sent to a remote cloud data center, so that delay is effectively reduced, energy consumption is reduced, cost is reduced, and network congestion and response time are reduced.

The present application also provides a non-transitory computer readable storage medium having instructions that, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the steps of:

3) processing the data information in the standard format through a data processing layer, a body modeling layer and a body application layer, and adding the extra data information generated after processing into the original data packet through a data enhancement layer to form a secondary data packet;

4) and sending the secondary data packet to a cloud storage layer for storage.

It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The present application also provides a computer program product, wherein the instructions of the computer program product, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the steps of:

4) and sending the secondary data packet to a cloud storage layer for storage.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims

1. An ICU multi-device semantic interoperation data transmission system, comprising:

the cloud storage layer is used for storing the data packets sent by the edge computing layer;

wherein the edge calculation layer comprises:

the body modeling layer carries out semantic modeling through an internet knowledge graph generated by the multi-device semantic operation body;

the system comprises a body application layer, a semantic model and a database, wherein the body application layer is used for constructing edge end intelligent application based on the trained semantic model, and the edge end intelligent application has the functions of decision support, monitoring and early warning, knowledge reasoning and mode mining;

the data enhancement layer is used for attaching additional necessary data generated by the data processing layer, the ontology modeling layer and the ontology application layer to an original data packet and communicating with the cloud storage layer;

the body modeling layer includes:

the ontology mapping layer is used for mapping the cached JSON/XML data stream to an ontology architecture and constructing the multi-device semantic operation ontology through a controlled term set;

2. The ICU multi-device semantically interoperating data transmission system according to claim 1, wherein said controlled term set contains a vocabulary formed by a method of controlling lexical meanings used and tracking related words.

3. The ICU multi-device semantic interoperable data transfer system of claim 1, wherein the data translation layer comprises:

4. A data transmission method of an ICU multi-device semantic interoperability data transmission system according to claim 1, comprising the steps of:

3) processing data information in a standard format through a data processing layer, a body modeling layer and a body application layer, and adding extra necessary data generated after processing into an original data packet through a data enhancement layer to form a secondary data packet;

4) and sending the secondary data packet to a cloud storage layer for storage.

5. The ICU multi-device semantic interoperability data transmission method according to claim 4, wherein the data information in the standard format is processed through a data processing layer, an ontology modeling layer and an ontology application layer, and the additional necessary data generated after the processing is added to the original data packet through a data enhancement layer to form a secondary data packet, comprising:

the additional necessary data generated by inference is added to the original data packet through the data enhancement layer to form a secondary data packet.

6. A non-transitory computer readable storage medium, wherein instructions in the storage medium, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the ICU multi-device semantic interoperation data transmission method of any of claims 4-5.