CN111314486A - Low-delay AI artificial intelligence analysis data transmission method - Google Patents
Low-delay AI artificial intelligence analysis data transmission method Download PDFInfo
- Publication number
- CN111314486A CN111314486A CN202010170880.2A CN202010170880A CN111314486A CN 111314486 A CN111314486 A CN 111314486A CN 202010170880 A CN202010170880 A CN 202010170880A CN 111314486 A CN111314486 A CN 111314486A
- Authority
- CN
- China
- Prior art keywords
- data
- server
- segment
- artificial intelligence
- fragment
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 113
- 238000004458 analytical method Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 36
- 239000012634 fragment Substances 0.000 claims abstract description 52
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 238000012806 monitoring device Methods 0.000 claims description 38
- 238000004891 communication Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 abstract description 24
- 238000003745 diagnosis Methods 0.000 abstract description 19
- 230000004962 physiological condition Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 206010003119 arrhythmia Diseases 0.000 description 2
- 230000006793 arrhythmia Effects 0.000 description 2
- 230000000747 cardiac effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 206010008479 Chest Pain Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 238000004171 remote diagnosis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1074—Peer-to-peer [P2P] networks for supporting data block transmission mechanisms
- H04L67/1078—Resource delivery mechanisms
- H04L67/108—Resource delivery mechanisms characterised by resources being split in blocks or fragments
-
- 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
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/565—Conversion or adaptation of application format or content
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a low-delay AI artificial intelligence analysis data transmission method, which comprises the following steps: the monitoring equipment divides the acquired data at intervals of a first time period to obtain N pieces of first segment data; the monitoring equipment sequentially sends the obtained N pieces of first segment data to an AI server; and the AI server combines the received N data and analyzes the combined second fragment data. According to the invention, each small segment is sequentially transmitted to the AI server, so that when abnormal physiological conditions occur to a patient, the abnormal segments can be quickly uploaded to the server, and the diagnosis accuracy is improved.
Description
Technical Field
The invention relates to the technical field of medical electronic equipment, in particular to a low-delay AI artificial intelligence analysis data transmission method.
Background
Along with the technical development in the medical electronic field, the vital sign monitoring product is more and more miniaturized to various wearing formula measuring equipment have appeared, and the patient is in the in-process of using, as long as wear equipment on one's body, can carry out the monitoring of vital sign parameter. After the wearable monitoring equipment measures the physiological parameters of the patient, the measured results can be uploaded to the background server through a wireless transmission technology, and the doctor analyzes and diagnoses the parameters through the background server to obtain a diagnosis conclusion.
According to the difference of wireless transmission technology, wearable monitoring equipment can be divided into two types, one type is in-hospital remote monitoring equipment, and the other type is remote transmission monitoring equipment.
The remote monitoring equipment in the hospital mainly depends on a wireless network in the hospital, the wireless network can be in the modes of Wi-Fi, radio frequency, Bluetooth and the like, the remote monitoring equipment can send data to a hospital background server through the wireless transmission technologies, and a doctor obtains corresponding patient data through the server to perform analysis and diagnosis.
The remote transmission monitoring equipment is mainly applied to the scene outside a hospital, data transmission is carried out through a wireless network of an operator, for example, through 4G,3G or GPRS or future 5G transmission technology and the like, similarly, the data is sent to a hospital background server through the operator network, and a doctor obtains corresponding patient data through the server to carry out analysis and diagnosis.
In the above application, no matter what wireless transmission method and technology are based on, there are two main data transmission methods:
the transmission mode is generally applied to a hospital remote monitoring scene, and the remote monitoring equipment can transmit the acquired data to a background server in real time.
And (4) segmented transmission, wherein the transmission mode is usually applied to an out-of-hospital scene. Such as the teletransmission monitoring device which combines the physiological parameter acquisition and analysis of the patient with the mobile communication technology, which is also introduced in the market at present. When a patient breaks out of illness and physiological parameters are abnormal, the remote transmission monitoring equipment starts recording of abnormal data, after recording for a period of time, for example, abnormal segments with the time being 1-5 minutes are recorded usually, after the abnormal segments are recorded, the abnormal segment data are uploaded to a hospital background server in a mobile data communication mode such as 5G, 4G,3G or GPRS, and after a background on-duty doctor receives the abnormal electrocardio segments, the abnormal segments are analyzed and diagnosed to be determined as abnormal electrocardio signals, and under the condition that emergency early warning is needed, the doctor can contact the patient urgently and even arrange an ambulance to be on site for medical intervention.
For the real-time transmission mode, the data transmission mode is very dependent on the network in the application process, the data transmission is possibly interrupted, the alarm of network disconnection is sent out, and the communication connection is recovered until the patient returns to the position with stronger signal.
The real-time transmission mode is characterized in that the wireless communication module is continuously opened and is in a data sending state for a long time, the power consumption of the real-time transmission mode is larger, the wearable telemetering monitoring equipment is powered by a lithium battery or an AA battery, and the longer power consumption affects the endurance time of the product.
The biggest problem for the fragmented transmission is that the delay is too long and the real-time performance is not enough. And recording abnormal segments from abnormal physiological parameters of the patient, uploading the segments after the abnormal segments are recorded, and analyzing and diagnosing the segments by a doctor on duty at a background. The whole process takes several minutes, and for a patient in a critical condition, the time is too long, and the optimal medical intervention opportunity may be missed.
Thus, the prior art has yet to be improved and enhanced.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a low-latency AI artificial intelligence analysis data transmission method to solve the problems in the prior art.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a low-latency AI artificial intelligence analysis data transmission method, comprising:
the monitoring equipment divides the acquired data at intervals of a first time period to obtain N pieces of first segment data;
the monitoring equipment sequentially sends the obtained N pieces of first segment data to an AI server;
and the AI server combines the received N data and analyzes the combined second fragment data.
The low-delay AI artificial intelligence analysis data transmission method, wherein the monitoring device segments the acquired data at intervals of a first time period to obtain N first segment data specifically includes:
acquiring a transmission mode of current data;
if the current data transmission mode is segment-type transmission, recording third segment data acquired in a second time period by the monitoring equipment;
the monitoring device divides the third segment data according to the first time segment to obtain N first segment data, wherein N is the second time segment/the first time segment.
The low-latency AI artificial intelligence analysis data transmission method, wherein the AI server combines the received N data and analyzes the combined second fragment data specifically includes:
if the current data transmission mode is fragment-type transmission, the AI server combines the received N data to obtain second fragment data which is the same as the third fragment data;
the combined second fragment data is analyzed.
The low-delay AI artificial intelligence analysis data transmission method, wherein the monitoring device segments the acquired data at intervals of a first time period to obtain N first segment data specifically includes:
acquiring a transmission mode of current data;
if the current data transmission mode is real-time transmission, the monitoring equipment continuously divides the acquired data at every interval of the first time period to obtain N pieces of first segment data.
The low-latency AI artificial intelligence analysis data transmission method, wherein the AI server combines the received N data and analyzes the combined second fragment data specifically includes:
if the current data transmission mode is real-time transmission, the AI server combines N received data at intervals of a first time period to obtain second fragment data of a third time period, wherein the N data are data acquired in the current time period and N-1 data closest to the current time period;
the combined second fragment data is analyzed.
The low-delay AI artificial intelligence analysis data transmission method, wherein the monitoring device sequentially sends the obtained N first segment data to the AI server specifically includes:
and the monitoring equipment compresses the N pieces of the first segment data and sequentially sends the compressed data to the AI server.
The low-latency AI artificial intelligence analysis data transmission method, wherein the AI server combines the received N data, and the analyzing the combined second fragment data specifically comprises:
and the AI server decompresses the received data and combines the decompressed N data.
A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which are executable by one or more processors to implement the steps in the low-latency AI artificial intelligence analysis data transmission method as described in any one of the above.
A low-latency AI artificial intelligence analysis data transmission system, wherein it comprises: the monitoring device and the AI server are in communication connection with the monitoring device;
the monitoring device is used for segmenting the acquired data at intervals of a first time period to obtain N pieces of first segment data, and sequentially sending the obtained N pieces of first segment data to the AI server;
and the AI server is used for combining the received N data and analyzing the combined second fragment data.
Has the advantages that: compared with the prior art, the invention provides a low-delay AI artificial intelligence analysis data transmission method, which comprises the following steps: the monitoring equipment divides the acquired data at intervals of a first time period to obtain N pieces of first segment data; the monitoring equipment sequentially sends the obtained N pieces of first segment data to an AI server; and the AI server combines the received N data and analyzes the combined second fragment data. . According to the invention, each small segment is sequentially transmitted to the AI server, so that when abnormal physiological conditions occur to a patient, the abnormal segments can be quickly uploaded to the server, and the diagnosis accuracy is improved.
Drawings
Fig. 1 is a flowchart of a low-latency AI artificial intelligence analysis data transmission method provided by the present invention.
Fig. 2 is a functional block diagram of a telemetry monitoring device or a teletransmission monitoring device according to the present invention.
Fig. 3 is a diagram of the network connection structure of the teletransmission monitoring device and the telemonitoring device provided by the present invention.
Fig. 4 is a schematic diagram of data transmission of a conventional remote transmission device according to the present invention.
Fig. 5 is a flow chart of a data transmission method provided by the present invention.
Fig. 6 is a schematic diagram of a data transmission method of real-time data stream according to the present invention.
Detailed Description
The invention provides a low-delay AI artificial intelligence analysis data transmission method, which is further described in detail below by referring to the attached drawings and embodiments in order to make the purposes, technical schemes and effects of the invention clearer and clearer. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The invention will be further explained by the description of the embodiments with reference to the drawings.
The embodiment provides a low-latency AI artificial intelligence analysis data transmission method, as shown in fig. 1, the method includes:
s100, dividing acquired data by monitoring equipment at intervals of a first time period to obtain N pieces of first segment data;
s200, the monitoring equipment sequentially sends the obtained N first segment data to an AI server;
s300, the AI server combines the received N data and analyzes the combined second fragment data.
In this embodiment, the monitoring devices may be classified into two types according to the difference of wireless transmission technologies, one type is an in-hospital remote monitoring device, and the other type is a remote transmission monitoring device.
The remote monitoring equipment in the hospital mainly depends on a wireless network in the hospital, the wireless network can be in the modes of Wi-Fi, radio frequency, Bluetooth and the like, the remote monitoring equipment can send data to a hospital background server through the wireless transmission technologies, and a doctor obtains corresponding patient data through the server to perform analysis and diagnosis.
The remote transmission monitoring equipment is mainly applied to the scene outside a hospital, data transmission is carried out through a wireless network of an operator, for example, through 4G,3G or GPRS or future 5G transmission technology and the like, similarly, the data is sent to a hospital background server through the operator network, and a doctor obtains corresponding patient data through the server to carry out analysis and diagnosis.
Further, as shown in fig. 2, fig. 2 is a functional schematic block diagram of a telemetry monitoring device or a teletransmission monitoring device provided by the present invention, which specifically includes:
the central processing unit 101 is a central control processor of a telemetering monitoring device or a remote transmission monitoring device terminal, and is responsible for processing and calculating various physiological parameters, controlling data receiving and transmitting, displaying and the like. The unit is located as a core control device of the whole product, on an internal circuit board. The unit is used for the telemetering equipment, so that the power consumption is generally low, and the data operation processing capacity is poor.
The power supply unit 102 is composed of a battery and a power management circuit, and the battery can be a built-in lithium polymer battery or a replaceable rechargeable battery. The energy storage unit can store electric energy and release electric energy at the same time, and the unit is installed on an internal battery compartment of the equipment at the same time. The power management circuit mainly provides proper voltage power for each component and supports the operation of each component.
The touch and key unit 103 is mainly composed of keys, a touch screen and other human-computer interaction input devices, and an operator operates and controls the equipment through the unit.
An accessory unit 104 that is connected at one end to a specific measurement site on the patient and at the other end to a telemetry or telemonitoring device.
The parameter acquisition unit 105, which is mainly an analog front-end circuit for acquiring various parameters, is composed of a signal filter, an amplification circuit and the like, and is responsible for acquiring and amplifying physiological parameters of a patient body and sending the physiological parameters to the central processing unit 101, and the unit is a circuit for acquiring and converting signals and is positioned on an internal circuit board.
And the display unit 106 is used for displaying conventional man-machine interaction information, measured physiological parameter information, alarm information and the like. The display screen unit is arranged on the front shell of the whole machine.
The wireless communication unit 107 may be a 5G, 4G,3G or GPRS communication module using an operator network, or a Wi-Fi communication module, a radio frequency communication module or a bluetooth module suitable for use in a hospital, for different models and application scenarios. The function of the system is to upload data of the equipment end to a hospital background server.
The alarm unit 108 is mainly an audible and visual alarm signal and is composed of a red-yellow-blue three-color indicator light, a loudspeaker and alarm character information.
Further, fig. 3 is a diagram of a network connection structure of a remote transmission monitoring device and a remote measurement monitoring device, as shown in fig. 3, the remote transmission monitoring device is mainly applied outside a hospital, and transmits the acquired physiological parameter waveform and data to a network of the hospital through a 5G or 4G or 3G or GPRS or other data network of an operator (china mobile, china unicom, or chinese telecom, etc.), after the data is analyzed by an AI server, a doctor checks the analysis result and confirms through background diagnostic software, and then determines whether a medical intervention scheme is needed to be further adopted according to the emergency degree of the physical condition of the patient, such as communicating with the family members of the patient by telephone, confirming other physical sign expressions of the patient, and even arranging an ambulance to take rescue measures in an emergency to the scene.
The telemetering monitor is mainly applied to hospitals, physiological parameters acquired by telemetering monitor equipment are sent to an AI server through networks such as Wi-Fi or radio frequency distributed in the hospitals, acquired physiological parameter waveforms and data are sent to the networks of the hospitals, after the data are analyzed by the AI server, doctors check and confirm analysis results through background diagnosis software, and whether medical emergency measures need to be taken further is determined according to the emergency degree of physical conditions of patients.
No matter an operator network or in-hospital Wi-Fi, radio frequency and the like are adopted, according to the current technical level, the communication bandwidth can be guaranteed, the conventional network is more than 1MB/s, and the signal can reach more than 10MB/s under the better condition, which is equivalent to the transmission data of hundred megabroadband.
The physiological parameters of the patient are limited in data volume, mainly waveform information and numerical information of the physiological parameters of the patient, so that the data transmission volume is about several KB/S to dozens of KB/S, which is much lower than the transmission speed of the transmission mode.
For the telemetering and monitoring equipment applied in a hospital, the conventional data transmission mode is real-time data transmission, that is, the telemetering and monitoring equipment does not perform any processing and directly transmits the acquired physiological parameter data to a server of the hospital in real time.
In this embodiment, the sending, by the monitoring device, the obtained N first segment data to the AI server in sequence specifically includes: the monitoring equipment compresses the N pieces of first segment data and sequentially sends the compressed data to the AI server; the AI server combines the received N data, and the analyzing the combined second fragment data specifically includes: and the AI server decompresses the received data and combines the decompressed N data. For example, for an out-of-hospital telemonitoring device, the conventional data transmission scheme is shown in fig. 4: the remote transmission monitoring equipment records fragment data K1 with the time length of T1, after the recording is completed, K1 is compressed into a data packet C1, the C1 data packet passes through an operator network and is sent to a server after the time length of T2, and after the server receives the data packet, the data packet is decompressed and is recovered into fragment data K2 with the time length of T1. And then the data is sent to an AI server for analysis to obtain a diagnosis result.
In the whole process, at least a time interval of T1+ T2 is needed when the physiological parameter is monitored by the remote transmission monitoring equipment and the abnormal segment is sent to the AI server, the segment data sent to the AI server is delayed by T1+ T2 time compared with the actual occurrence time of the data, and the time is about tens of seconds.
In an implementation manner of this embodiment, the dividing, by the monitoring device, the acquired data every interval of the first time period to obtain N pieces of first segment data specifically includes:
s101, acquiring a transmission mode of current data;
s102, if the current data transmission mode is segment-type transmission, recording third segment data acquired in a second time period by the monitoring equipment;
s103, the monitoring device segments the third segment data according to the first time period to obtain N first segment data, where N is the second time period/the first time period.
Further, the combining, by the AI server, the received N data, and analyzing the combined second fragment data specifically includes:
s201, if the current data transmission mode is fragment-type transmission, the AI server combines the received N data to obtain second fragment data which is the same as the third fragment data;
and S202, analyzing the combined second fragment data.
Specifically, the explanation will be given taking the fragment data K1 of the same time length T1 in the data stream as an example.
In S10, K1 is segment data with a certain period of time T1 in a patient physiological parameter data stream acquired by a teletransmission monitoring device and a telemonitoring device (hereinafter, collectively referred to as a device side).
In S20, the device divides the fragment data with the duration of T1 into n small data fragments S1 to Sn with the duration of T3, where the duration of T3 is several seconds, and optionally may be defined as 4 seconds. That is, when T1 is 72 seconds and T3 is 4 seconds, n is 18, that is, the device divides the original 72-second segment data into 18 segments of 4-second segment data.
In S30, when the device terminal finishes collecting small fragment data of T3 duration, the fragment is compressed and packaged, and is sent to the server terminal in a data packet manner. As mentioned above, in the case of the remote transmission monitoring device, the data transmission mode is mainly through the 5G or 4G or 3G or GPRS data network of the operator (china mobile, china unicom or chinese telecom, etc.). If the monitoring equipment is telemetering, the data transmission mode is mainly Wi-Fi, radio frequency or Bluetooth and the like.
S40 is the local area network server in the hospital, the data packet sent out at S30 is sent to the server after T4 time. The specific time of T4 seems to be the quality of the network, and when the network information quality is good, the duration may be tens of milliseconds, which is almost negligible; this duration may also be on the order of hundreds of milliseconds or even seconds when the quality of the operator network used is poor.
Further, the server decompresses and restores the received data packet to obtain S1 'to Sn' fragment data consistent with the device side.
In S50, the server combines the received S1 '-Sn' according to the time axis, that is, the T1 time length segment K1 ', K1' is completely consistent with the original K1, and the time length can meet the requirement of the AI artificial intelligence analysis server, and can be directly sent to the AI server for analysis.
In the whole process of S10-S50, compared with the K1 of the device side, the delay time of the K1' of the server side is only the duration of T3+ T4. As mentioned above, T3 is usually several seconds, and T4 is usually milliseconds, so the delay time of the data stream during the whole data transmission process can be controlled within several seconds, which is much lower than the delay time of tens of seconds in the conventional data transmission method. For example, if the segment S1 is an abnormal physiological parameter, the delay time from when the device side monitors the abnormal data to when the server receives the abnormal signal is T3+ T4, which is about several seconds long.
The above is a description of a certain fragment data transmission scheme.
In an implementation manner of this embodiment, the dividing, by the monitoring device, the acquired data every interval of the first time period to obtain N pieces of first segment data specifically includes:
s104, acquiring a transmission mode of current data;
and S105, if the current data transmission mode is real-time transmission, the monitoring equipment continuously divides the acquired data at intervals of a first time period to obtain N pieces of first-segment data.
Further, the combining, by the AI server, the received N data, and analyzing the combined second fragment data specifically includes:
s203, if the current data transmission mode is real-time transmission, the AI server combines N received data at intervals of a first time period to obtain second fragment data of a third time period, wherein the N data are data acquired in the current time period and N-1 data closest to the current time period;
and S204, analyzing the combined second fragment data.
Specifically, the step is for a complete continuous real-time data traffic, and the data transmission manner is as shown in fig. 6:
601 is real-time data at the device end, and the device continuously collects physiological parameters of the patient.
The device segments the continuous real-time data with a duration of T3, where the duration of T3 is several seconds, and optionally 4 seconds.
603, when the device finishes collecting the fragment data with the time length of T3, the device compresses and packs the data to form a data packet of the fragment with the time length of T3. As mentioned above, in the case of the remote transmission monitoring device, the data transmission mode is mainly through the 5G or 4G or 3G or GPRS data network of the operator (china mobile, china unicom or chinese telecom, etc.). If the monitoring equipment is telemetering, the data transmission mode is mainly Wi-Fi, radio frequency or Bluetooth and the like.
604 is the local area network server in the hospital, and the data packet sent by 603 is sent to the server after the time duration of T4. The specific time of T4 seems to be the quality of the network, and when the network information quality is good, the duration may be tens of milliseconds, which is almost negligible; this duration may also be on the order of hundreds of milliseconds or even seconds when the quality of the operator network used is poor.
Further, the server decompresses and restores the received data packet to obtain F1 'to Fn' fragment data consistent with the device side.
605, the server integrates the received F1 ' -Fn ' fragment data, and N groups of F1 ' -Fn ' fragment data can be combined into a group of long fragment data J1 ' with the duration of T1; similarly, after the time of T3, the server may combine N sets of F2 'to F' N +1 fragment data into a set of long fragment data J2 'with the duration of T1, and after the time of T3, the server may combine N sets of F3' to F 'N +3 fragment data into a set of long fragment data J3' with the duration of T1, and so on.
The combined long fragment data with the time length of T1, such as J1 ', J2 ', J3 ' and the like, can be directly sent to an AI server for analysis and diagnosis, and an analysis and diagnosis conclusion can be obtained.
Further, in the real-time data transmission mode, when an abnormal signal occurs in the data, for example, the Fn segment in the figure is an abnormal physiological parameter monitored in real time. After being divided, transmitted and decompressed, the abnormal small segment data is finally combined into different segments of long segment data J1 ', J2 ', J3 ' and the like for diagnosis and analysis by an AI server, and the accuracy of analysis of the abnormal segment can be improved and the risk of analysis errors can be reduced by carrying out multiple rounds of AI analysis on the same abnormal small segment.
Further, the AI server is an AI artificial intelligence server which is an automatic analysis and diagnosis software platform based on artificial intelligence technology, supports multi-center data acquisition, remote diagnosis and hierarchical diagnosis and treatment, can assist network informatization construction of hospitals, standardizes work flow, improves work efficiency, realizes data and report sharing of whole hospitals, realizes interconnection and intercommunication of medical institutions, and provides an integral solution for chest pain centers, hospital units, remote medical construction and the like.
Compared with the traditional diagnosis mode, the diagnosis accuracy is high. For example, in the field of electrocardio AI diagnosis, the normal electrocardiogram diagnosis accuracy reaches 99%, and the arrhythmia and cardiac excitation conduction abnormality diagnosis accuracy reaches 95.2%. The diagnosis range is wide. Most arrhythmia and cardiac activation conduction abnormalities are covered, and up to 74 types of electrocardiogram events can be diagnosed. The clinical application is specialized. The artificial intelligence deep learning algorithm is applied, the limitation that the traditional algorithm cannot accurately analyze difficult cardiac diseases is broken through, and a professional doctor is assisted in analyzing and diagnosing complex electrocardio types.
In addition, with the help of a server with strong computing power, which is extremely fast, the analysis of the time slices can be completed in an extremely short time, which can be in the order of ms alternatively.
The AI artificial intelligence server needs a certain time duration, usually a segment length of several tens of seconds, for artificial intelligence analysis of the patient physiological parameter data, which is called T1, and the AI artificial intelligence server needs a data size based on the time duration of T1 to perform a relatively complete analysis and judgment on the data. Alternatively, the segment length may be 72 seconds.
The present invention also provides a computer-readable storage medium storing one or more programs, which are executable by one or more processors to implement the steps in the low-latency AI artificial intelligence analysis data transmission method according to the above embodiments.
The invention also provides a low-delay AI artificial intelligence analysis data transmission system, which comprises: the monitoring device and the AI server are in communication connection with the monitoring device;
the monitoring device is used for segmenting the acquired data at intervals of a first time period to obtain N pieces of first segment data, and sequentially sending the obtained N pieces of first segment data to the AI server;
and the AI server is used for combining the received N data and analyzing the combined second fragment data.
In this embodiment, optionally, the data transmission mode may be referred to as "Time Domain Sliding Window Technology (TDSWT)" based on which the real-Time diagnosis and critical value transmission of the physiological parameter of the monitoring process are implemented.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A low-delay AI artificial intelligence analysis data transmission method is characterized by comprising the following steps:
the monitoring equipment divides the acquired data at intervals of a first time period to obtain N pieces of first segment data;
the monitoring equipment sequentially sends the obtained N pieces of first segment data to an AI server;
and the AI server combines the received N data and analyzes the combined second fragment data.
2. The low-latency AI artificial intelligence analysis data transmission method according to claim 1, wherein the monitoring device segments the acquired data every first interval time period to obtain N first segment data specifically includes:
acquiring a transmission mode of current data;
if the current data transmission mode is segment-type transmission, recording third segment data acquired in a second time period by the monitoring equipment;
the monitoring device divides the third segment data according to the first time segment to obtain N first segment data, wherein N is the second time segment/the first time segment.
3. The low-latency AI artificial intelligence analysis data transmission method according to claim 2, wherein the AI server combines the N received data, and analyzing the combined second fragment data specifically comprises:
if the current data transmission mode is fragment-type transmission, the AI server combines the received N data to obtain second fragment data which is the same as the third fragment data;
the combined second fragment data is analyzed.
4. The low-latency AI artificial intelligence analysis data transmission method according to claim 1, wherein the monitoring device segments the acquired data every first interval time period to obtain N first segment data specifically includes:
acquiring a transmission mode of current data;
if the current data transmission mode is real-time transmission, the monitoring equipment continuously divides the acquired data at every interval of the first time period to obtain N pieces of first segment data.
5. The low-latency AI artificial intelligence analysis data transmission method according to claim 4, wherein the AI server combines the N received data and the analyzing the combined second fragment data specifically comprises:
if the current data transmission mode is real-time transmission, the AI server combines N received data at intervals of a first time period to obtain second fragment data of a third time period, wherein the N data are data acquired in the current time period and N-1 data closest to the current time period;
the combined second fragment data is analyzed.
6. The low-latency AI artificial intelligence analysis data transmission method according to claim 1, wherein the sending, by the monitoring device, the obtained N first segment data to the AI server in sequence is specifically:
and the monitoring equipment compresses the N pieces of the first segment data and sequentially sends the compressed data to the AI server.
7. The low-latency AI artificial intelligence analysis data transmission method according to claim 6, wherein the AI server combines the N received data, and the analyzing the combined second fragment data specifically comprises:
and the AI server decompresses the received data and combines the decompressed N data.
8. A computer-readable storage medium storing one or more programs, which are executable by one or more processors, to implement the steps in the low-latency AI artificial intelligence analysis data transmission method according to any one of claims 1 to 7.
9. A low-latency AI artificial intelligence analysis data transmission system, comprising: the monitoring device and the AI server are in communication connection with the monitoring device;
the monitoring device is used for segmenting the acquired data at intervals of a first time period to obtain N pieces of first segment data, and sequentially sending the obtained N pieces of first segment data to the AI server;
and the AI server is used for combining the received N data and analyzing the combined second fragment data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010170880.2A CN111314486A (en) | 2020-03-12 | 2020-03-12 | Low-delay AI artificial intelligence analysis data transmission method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010170880.2A CN111314486A (en) | 2020-03-12 | 2020-03-12 | Low-delay AI artificial intelligence analysis data transmission method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111314486A true CN111314486A (en) | 2020-06-19 |
Family
ID=71151219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010170880.2A Pending CN111314486A (en) | 2020-03-12 | 2020-03-12 | Low-delay AI artificial intelligence analysis data transmission method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111314486A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010111489A2 (en) * | 2009-03-27 | 2010-09-30 | LifeWatch Corp. | Methods and apparatus for processing physiological data acquired from an ambulatory physiological monitoring unit |
| US20120259233A1 (en) * | 2011-04-08 | 2012-10-11 | Chan Eric K Y | Ambulatory physiological monitoring with remote analysis |
| CN102920450A (en) * | 2012-11-09 | 2013-02-13 | 郭英杰 | Time-phased wireless transmission Holter electrocardiograph monitoring system |
| CN104469616A (en) * | 2014-12-17 | 2015-03-25 | 天脉聚源（北京）教育科技有限公司 | Method and device for transmitting sound signals of intelligent teaching system |
| CN104735722A (en) * | 2015-04-07 | 2015-06-24 | 青岛科技大学 | Efficient and energy-efficient sensor network data transmission method |
| CN106327324A (en) * | 2016-08-23 | 2017-01-11 | 杭州同盾科技有限公司 | Network behavior characteristic rapid calculation method and system |
| CN109431490A (en) * | 2018-09-28 | 2019-03-08 | 上海优加利健康管理有限公司 | Artificial intelligence real-time analysis method and system for cardioelectric monitor |
| CN109662708A (en) * | 2019-01-21 | 2019-04-23 | 郑州大学第附属医院 | A kind of postoperative patient behavior monitoring method based on deep neural network |
-
2020
- 2020-03-12 CN CN202010170880.2A patent/CN111314486A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010111489A2 (en) * | 2009-03-27 | 2010-09-30 | LifeWatch Corp. | Methods and apparatus for processing physiological data acquired from an ambulatory physiological monitoring unit |
| US20120259233A1 (en) * | 2011-04-08 | 2012-10-11 | Chan Eric K Y | Ambulatory physiological monitoring with remote analysis |
| CN102920450A (en) * | 2012-11-09 | 2013-02-13 | 郭英杰 | Time-phased wireless transmission Holter electrocardiograph monitoring system |
| CN104469616A (en) * | 2014-12-17 | 2015-03-25 | 天脉聚源（北京）教育科技有限公司 | Method and device for transmitting sound signals of intelligent teaching system |
| CN104735722A (en) * | 2015-04-07 | 2015-06-24 | 青岛科技大学 | Efficient and energy-efficient sensor network data transmission method |
| CN106327324A (en) * | 2016-08-23 | 2017-01-11 | 杭州同盾科技有限公司 | Network behavior characteristic rapid calculation method and system |
| CN109431490A (en) * | 2018-09-28 | 2019-03-08 | 上海优加利健康管理有限公司 | Artificial intelligence real-time analysis method and system for cardioelectric monitor |
| CN109662708A (en) * | 2019-01-21 | 2019-04-23 | 郑州大学第附属医院 | A kind of postoperative patient behavior monitoring method based on deep neural network |
Non-Patent Citations (2)
| Title |
|---|
| KABALAN CHACCOUR: "Sway analysis and fall prediction method based on spatio-temporal sliding window technique", 《2016 IEEE 18TH INTERNATIONAL CONFERENCE ON E-HEALTH NETWORKING, APPLICATIONS AND SERVICES (HEALTHCOM)》 * |
| 王勇: "基于私有云家庭远程医疗监护系统设计", 《信息通信》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pathinarupothi et al. | IoT-based smart edge for global health: Remote monitoring with severity detection and alerts transmission | |
| CN102054118B (en) | A kind of Telemedicine System | |
| JP3738009B2 (en) | Data transmission between the remote monitoring unit and the central monitoring unit | |
| CN104490388A (en) | Extensible human health remote recording, monitoring and diagnosis system | |
| CN109326347A (en) | A kind of electrocardiogram remote monitoring system based on artificial intelligence | |
| CN110115569B (en) | Whole-process monitoring method and vital sign monitoring equipment | |
| WO2019073288A1 (en) | Remote ecg monitoring and alerting methods and sensing device | |
| CN105007338A (en) | Elderly health monitoring and alarming intelligent IOT application service platform | |
| KR20080085205A (en) | Method and apparatus for remote mobile monitoring electronic physiological data based on wan | |
| CN102349829A (en) | Remote monitoring system of electrocardiosignal | |
| AU2002338434A1 (en) | Data transmission between remote and central monitoring unit | |
| CN204336910U (en) | A kind of extendible health remote logging, monitoring and diagnostic system | |
| CN107440709B (en) | Intelligent wearable electrocardiograph monitoring system | |
| CN107582046B (en) | Real-time electrocardio monitoring method | |
| CN203153715U (en) | Multi-parameter long-distance medical monitoring system | |
| CN209884133U (en) | Wearable electrocardiogram monitor and electrocardiogram monitoring system based on wireless network | |
| CN214856634U (en) | Physiological signal acquisition system | |
| Badr et al. | 12-lead ecg platform for real-time monitoring and early anomaly detection | |
| CN111314486A (en) | Low-delay AI artificial intelligence analysis data transmission method | |
| CN103169459A (en) | Medical device and implementation method | |
| CN115565682A (en) | Life information supervisory system based on big health management | |
| CN112022116A (en) | Patient condition nursing monitoring system based on intelligent wearable watch | |
| CN209733985U (en) | Wireless 12-lead dynamic electrocardiogram real-time monitor | |
| KR101459651B1 (en) | System for monitoring Electrocardiogram and method thereof | |
| CN215078667U (en) | Symptom recording device with disease early warning function and capable of being worn for long time |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200619 |