CN117153365B - Dialysis equipment running state early warning method and system based on audio identification - Google Patents
Dialysis equipment running state early warning method and system based on audio identification Download PDFInfo
- Publication number
- CN117153365B CN117153365B CN202311418270.XA CN202311418270A CN117153365B CN 117153365 B CN117153365 B CN 117153365B CN 202311418270 A CN202311418270 A CN 202311418270A CN 117153365 B CN117153365 B CN 117153365B
- Authority
- CN
- China
- Prior art keywords
- microphone
- signal
- state
- dialysis
- frequency
- 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.)
- Active
Links
- 238000000502 dialysis Methods 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 58
- 230000002159 abnormal effect Effects 0.000 claims abstract description 44
- 230000004044 response Effects 0.000 claims description 92
- 238000010223 real-time analysis Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 101100492406 Caenorhabditis elegans unc-85 gene Proteins 0.000 claims 1
- 101100436058 Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987) asf-1 gene Proteins 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 10
- 238000012423 maintenance Methods 0.000 abstract description 8
- 230000005236 sound signal Effects 0.000 description 19
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 208000032368 Device malfunction Diseases 0.000 description 2
- 208000037656 Respiratory Sounds Diseases 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012351 Integrated analysis Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M1/00—Suction or pumping devices for medical purposes; Devices for carrying-off, for treatment of, or for carrying-over, body-liquids; Drainage systems
- A61M1/14—Dialysis systems; Artificial kidneys; Blood oxygenators ; Reciprocating systems for treatment of body fluids, e.g. single needle systems for hemofiltration or pheresis
- A61M1/16—Dialysis systems; Artificial kidneys; Blood oxygenators ; Reciprocating systems for treatment of body fluids, e.g. single needle systems for hemofiltration or pheresis with membranes
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R29/00—Monitoring arrangements; Testing arrangements
- H04R29/004—Monitoring arrangements; Testing arrangements for microphones
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/18—General characteristics of the apparatus with alarm
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/70—General characteristics of the apparatus with testing or calibration facilities
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Emergency Management (AREA)
- Heart & Thoracic Surgery (AREA)
- General Physics & Mathematics (AREA)
- Urology & Nephrology (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Anesthesiology (AREA)
- Veterinary Medicine (AREA)
- Computational Linguistics (AREA)
- Vascular Medicine (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Hematology (AREA)
- Emergency Medicine (AREA)
- Otolaryngology (AREA)
- External Artificial Organs (AREA)
Abstract
The invention discloses a dialysis equipment running state early warning method and system based on audio identification, and relates to the technical field of dialysis equipment running state monitoring. According to the invention, through analyzing the running state of the microphone, when the running state of the microphone has abnormal hidden danger, an early warning prompt is sent out to prompt medical staff to arrange related overhaul and maintenance work in advance on the microphone possibly having abnormal hidden danger, so that the efficient running of the microphone is ensured, the situation that the equipment cannot be subjected to audio recognition and voice signal analysis due to the abnormal running state of the microphone is effectively prevented, the running state of the dialysis equipment is effectively monitored, the safety risk of a patient during dialysis is furthest reduced, and the dialysis equipment is further convenient for the efficient dialysis of the patient.
Description
Technical Field
The invention relates to the technical field of dialysis equipment operation state monitoring, in particular to an audio recognition-based dialysis equipment operation state early warning method and system.
Background
A dialysis machine based on audio recognition is a medical device that uses voice signal recognition and analysis techniques to monitor and evaluate the operating state of the dialysis machine. Dialysis is a therapeutic method for replacing kidney function by removing waste and excess fluid from the body to maintain electrolyte balance. The dialysis equipment based on audio recognition monitors the state of the equipment in real time through the sound signal generated by the analysis equipment so as to discover abnormal conditions in advance and ensure the safety and the effectiveness of dialysis treatment.
Such devices typically include a microphone, a real-time analysis system, a state recognition model, an alarm system, and control and operation interfaces integrated with other components of the dialysis device, which operate on the principle that sounds generated during operation of the dialysis device are captured by the microphone, and whether the device is in a normal state is determined by analyzing the characteristics of the sounds, and if an abnormal sound pattern is found, an alarm may be triggered to notify an operator or medical staff to take measures in time.
The prior art has the following defects: the microphone is a critical component for capturing the device sound signal, if the microphone operating condition is abnormal, the device may not be able to perform audio recognition and sound signal analysis, thereby failing to monitor the operating condition of the device, which, when present, may result in an increased safety risk in patient dialysis, thereby rendering the dialysis device more efficient in dialysis of the patient (e.g., if the microphone is unable to detect air bubbles entering the dialysate pathway, may result in a risk of air lock, e.g., if the microphone is abnormal, abnormal sounds such as component friction, which may be early indications of device malfunction or problems, if not timely detected, may result in further deterioration of the device malfunction, adversely affecting the dialysis patient).
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide a dialysis equipment operation state early warning method and system based on audio identification, which analyze the operation state of a microphone, send out early warning prompts when the operation state of the microphone has abnormal hidden danger, prompt medical staff to arrange related overhaul and maintenance work in advance for the microphone possibly having abnormal hidden danger, ensure the efficient operation of the microphone, effectively prevent the failure of audio identification and voice signal analysis of equipment caused by the abnormal operation state of the microphone, ensure the efficient monitoring of the operation state of the dialysis equipment, furthest reduce the safety risk of patients during dialysis, and further facilitate the dialysis equipment to carry out efficient dialysis on the patients so as to solve the problems in the background technology.
In order to achieve the above object, the present invention provides the following technical solutions: the dialysis equipment running state early warning system based on audio identification comprises an information acquisition module, a real-time analysis module, a comparison analysis module, a comprehensive analysis module and a prompt module;
The information acquisition module acquires a plurality of pieces of running state information, including equipment performance information and audio response information, of the microphone in the dialysis equipment based on audio identification, processes the equipment performance information and the audio response information of the microphone in running and transmits the processed equipment performance information and the processed audio response information to the real-time analysis module;
the real-time analysis module is used for comprehensively analyzing the processed equipment performance information and the audio response information during the operation of the microphone to generate a state index, and transmitting the state index to the comparison analysis module;
the comparison analysis module is used for comparing and analyzing the state index generated during the operation of the microphone with a preset state index reference threshold value to generate a high hidden danger signal or a low hidden danger signal and transmitting the hidden danger signal to the comprehensive analysis module;
and the comprehensive analysis module is used for comprehensively analyzing a plurality of state indexes generated later when the microphone operates after receiving the high hidden danger signals generated when the microphone operates, generating risk signals, transmitting the signals to the prompt module, and sending early warning prompts through the prompt module.
Preferably, the device performance information of the microphone during operation comprises a frequency response flatness coefficient and a signal to noise ratio abnormal hiding coefficient, and after acquisition, the information acquisition module respectively marks the frequency response flatness coefficient and the signal to noise ratio abnormal hiding coefficient as And->；
The audio response information of the microphone in operation comprises a frequency offset coefficient, and after acquisition, the information acquisition module marks the frequency offset coefficient as。
Preferably, the logic for obtaining the frequency response flatness coefficient is as follows:
a101, acquiring a plurality of actual frequency responses of a microphone in the dialysis equipment based on audio identification in a T time, and calibrating the actual frequency responses asY represents the number of the actual frequency response in time T when the microphone is operating in the dialysis device based on audio recognition, y=1, 2, 3, 4, … …, n being a positive integer;
a102, calculating an actual frequency response standard deviation of the microphone in the T time when the microphone operates, and calibrating the actual frequency response standard deviation to be L, wherein:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>For the average value of the actual frequency response of the microphone in the time T, the obtained calculation formula is as follows: />；
A103, calculating a frequency response flatness coefficient through an actual frequency response standard deviation L, wherein the calculated expression is as follows:。
preferably, the logic for obtaining the signal-to-noise ratio outlier concealment coefficients is as follows:
b101, obtaining microphone runtime in dialysis equipment based on audio recognitionAnd calibrating the optimal SNR range as ；
B102, acquiring actual signal-to-noise ratios of different moments in T time when a microphone in the dialysis equipment based on audio identification operates, and calibrating the actual signal-to-noise ratios asK represents the number of the actual signal-to-noise ratio at different moments in time T when the microphone is in operation, k=1, 2, 3, 4, … …, h being a positive integer;
b103, acquiring the microphone in the time T when the microphone is operated and not in the optimal signal-to-noise ratio rangeIs recalibrated to +.>V denotes +.f. in the range of the optimal signal to noise ratio acquired during the time T when the microphone is running>K=1, 2, 3, 4, … …, p being a positive integer;
b104, by actual signal-to-noise ratioCalculating the signal-to-noise ratio abnormal hiding coefficient, wherein the calculated expression is as follows:wherein->，/>Indicating that the actual signal-to-noise ratio acquired during the time T during which the microphone is operating is not within the optimum signal-to-noise ratio range +.>Is used for the time period of (a),。
preferably, the logic for obtaining the frequency offset coefficient is as follows:
c101, acquiring a plurality of input signal frequencies and output signal frequencies under corresponding frequencies in T time when a microphone in the dialysis equipment based on audio identification operates, and calibrating the input signal frequencies and the output signal frequencies under the corresponding frequencies as respectively And->X represents the number of the input signal frequency and the output signal frequency at the corresponding frequency in the time T when the microphone is operated, x=1, 2, 3, 4, … …, m is a positive integer;
c102 by input signal frequencyAnd the output signal frequency at the corresponding frequency +.>Calculating a frequency offset coefficient, wherein the calculated expression is: />。
Preferably, the real-time analysis module obtains the frequency response flatness coefficientSignal-to-noise ratio anomaly concealment coefficientFrequency offset coefficient +.>Then, a data analysis model is built to generate a state index +.>The formula according to is:in (1) the->、/>、/>Respectively the frequency response flatness coefficient +.>Signal-to-noise ratio abnormality concealment coefficient +.>Frequency offset coefficient +.>Is a preset proportionality coefficient of>、/>、/>Are all greater than 0.
Preferably, the comparison and analysis module compares the state index generated during the operation of the microphone with a preset state index reference threshold, if the state index is greater than or equal to the state index reference threshold, a high hidden danger signal is generated through the comparison and analysis module, and the signal is transmitted to the comprehensive analysis module;
if the state index is smaller than the state index reference threshold, a low hidden danger signal is generated through the comparison analysis module, and the signal is transmitted to the comprehensive analysis module.
Preferably, the analysis-by-synthesis module receives a high generated during operation of the microphoneAfter hidden danger signals, a data set is established for a plurality of state indexes which are subsequently generated when the microphone operates, and the state indexes in the data set are respectively matched with a preset gradient threshold reference threshold valueAnd->Performing comparison, wherein the gradient threshold is referenced to the threshold +.>And->Are all greater than the state index reference threshold and +.>；
Referencing the state index within the analysis set to the gradient thresholdAnd->Performing comparison, wherein the comparison value is larger than or equal to the state index reference threshold value and smaller than the gradient threshold value reference threshold value +.>The state indexes of (2) are scaled as first-order state indexes, the total number of the first-order state indexes is marked as F1, and the gradient threshold value reference threshold value is larger than or equal to +.>And less than the gradient threshold reference thresholdThe state indexes of (2) are scaled as secondary state indexes, the total number of the secondary state indexes is marked as F2, and the gradient threshold value reference threshold value is greater than or equal to +.>The state indexes of the system are calibrated to be three-level state indexes, the total number of the three-level state indexes is marked as F3, the total number of the first-level state indexes F1, the total number of the second-level state indexes F2 and the total number of the three-level state indexes F3 are subjected to formulated analysis, and risk indexes are generated according to the following formula: / >In (1) the->、/>、/>The weight factors of the total number of the first-level state indexes F1, the total number of the second-level state indexes F2 and the total number of the third-level state indexes F3 are respectively, and ∈>，/>。
Preferably, the risk index generated by the state index in the data set when the microphone is operatedReference threshold value of gradient of risk index preset>And->Performing comparison, wherein->The comparison is divided into the following cases:
if it isThen the integrated analysis module generates a highThe level risk signal is transmitted to the prompt module, and the prompt module sends out a high-level risk early warning prompt;
if it isGenerating a medium-level risk signal through the comprehensive analysis module, transmitting the signal to the prompting module, and sending out a medium-level risk early warning prompt through the prompting module;
if it isAnd generating a low-level risk signal through the comprehensive analysis module, transmitting the signal to the prompt module, and sending out early warning prompt without the prompt module.
An audio recognition-based dialysis equipment running state early warning method comprises the following steps:
collecting a plurality of pieces of running state information, including equipment performance information and audio response information, of a microphone in dialysis equipment based on audio identification when the microphone runs, and processing the equipment performance information and the audio response information of the microphone when the microphone runs after the collection;
Comprehensively analyzing the processed equipment performance information and the audio response information during the operation of the microphone to generate a state index;
comparing and analyzing a state index generated during the operation of the microphone with a preset state index reference threshold value to generate a high hidden danger signal or a low hidden danger signal;
after receiving the high hidden trouble signal generated during the operation of the microphone, comprehensively analyzing a plurality of state indexes generated subsequently during the operation of the microphone, generating a risk signal, and sending out an early warning prompt to the risk signal.
In the technical scheme, the invention has the technical effects and advantages that:
according to the invention, through analyzing the running state of the microphone, when the running state of the microphone has abnormal hidden danger, an early warning prompt is sent out to prompt medical staff to arrange related overhaul and maintenance work in advance for the microphone possibly having abnormal hidden danger, so that the efficient running of the microphone is ensured, the situation that the equipment cannot be subjected to audio recognition and acoustic signal analysis due to the abnormal running state of the microphone is effectively prevented, the running state of the dialysis equipment is effectively monitored, the safety risk of a patient during dialysis is furthest reduced, and the dialysis equipment is further convenient for the patient to carry out efficient dialysis;
According to the invention, when the operation state of the microphone is perceived to have potential anomaly hazards, the operation state of the microphone is comprehensively analyzed, the severity of the potential anomaly hazards caused by the operation state of the microphone is judged, and meanwhile, early warning prompts with different severity are sent out, so that maintenance management personnel can know the severity of the potential anomaly hazards of the microphone in time, and the maintenance management personnel can overhaul the microphone efficiently.
Drawings
For a clearer description of embodiments of the present application or of the solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments described in the present invention, and that other drawings may be obtained according to these drawings for a person skilled in the art.
Fig. 1 is a schematic block diagram of a dialysis equipment running state early warning method and system based on audio recognition.
Fig. 2 is a flow chart of a method and system for early warning of the running state of dialysis equipment based on audio recognition according to the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
The invention provides a dialysis equipment running state early warning system based on audio frequency identification as shown in figure 1, which comprises an information acquisition module, a real-time analysis module, a comparison analysis module, a comprehensive analysis module and a prompt module;
the information acquisition module acquires a plurality of pieces of running state information, including equipment performance information and audio response information, of the microphone in the dialysis equipment based on audio identification, processes the equipment performance information and the audio response information of the microphone in running and transmits the processed equipment performance information and the processed audio response information to the real-time analysis module;
the equipment performance information during the operation of the microphone comprises a frequency response flatness coefficient and a signal to noise ratio abnormal hiding coefficient, and after the acquisition, the information acquisition module respectively marks the frequency response flatness coefficient and the signal to noise ratio abnormal hiding coefficient asAnd；
in dialysis devices based on audio recognition, the frequency response of a microphone during operation refers to the response of the microphone to sound signals at different frequencies, in other words, the frequency response describes the sensitivity or gain of the microphone when various frequency sound signals are input, the frequency response can show the efficiency of capturing sound of the microphone at different frequencies, thus affecting the transmission and analysis of sound signals, and poor flatness of the frequency response during operation of the microphone can lead to potential safety risks, which are possible problems and increased correlation with safety risks:
Distorted sound signal: if the microphone has poor flatness of the frequency response, the sound signals of different frequencies may be amplified or attenuated, resulting in sound distortion, in dialysis devices there may be sound signals that need to be accurately identified and analyzed, such as physiological data of the patient or monitoring alarms, if the sound signals are distorted, this may lead to identification errors, false positives or missing important information, increasing the safety risk of the patient;
interfering sound signal: poor frequency response flatness may make the microphone more sensitive to ambient noise or interference signals of specific frequencies, which may cause the dialysis device to erroneously recognize or respond to these interference signals, thereby interfering with normal operation or monitoring procedures;
medical alert identification problem: during dialysis, medical alert sounds may trigger the response of the device, which if the microphone's frequency response is not flat may cause some medical alert sounds to be attenuated or altered in the sound recognition, thereby affecting the device's response to an emergency situation;
the data accuracy is reduced: dialysis devices may require acquisition of critical physiological data of a patient by voice recognition, such as heart rate or respiration rate, which may lead to inaccurate acquisition of such data, thereby affecting monitoring and assessment of patient status;
Therefore, the frequency response of the microphone in the dialysis equipment based on audio identification is monitored, and the abnormal hidden trouble that the flatness of the frequency response is poor when the microphone runs can be timely found;
the logic for obtaining the frequency response flatness coefficient is as follows:
a101, acquiring a plurality of actual frequency responses of a microphone in the dialysis equipment based on audio identification in a T time, and calibrating the actual frequency responses asY represents the number of the actual frequency response in time T when the microphone is operating in the dialysis device based on audio recognition, y=1, 2, 3, 4, … …, n being a positive integer;
it should be noted that, some specially designed devices may measure the frequency response of a microphone, and these devices may be used to measure the frequency response of a microphone by transmitting sound signals of different frequencies, for example, a frequency response tester (Frequency Response Test Set), which is a device specially used to measure the frequency response of a sound device, and the frequency response tester generally includes a Generator and a measuring instrument, and may generate sound signals of different frequencies, and measure the response of a microphone, for example, a Signal Generator (Signal Generator), which may generate stable sound signals, may be used to test the response of a microphone at different frequencies, and the Signal Generator may be used in conjunction with sound analysis software or a measuring device to obtain frequency response data;
A102, calculating an actual frequency response standard deviation of the microphone in the T time when the microphone operates, and calibrating the actual frequency response standard deviation to be L, wherein:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>For the average value of the actual frequency response of the microphone in the time T, the obtained calculation formula is as follows: />；
As can be seen from the actual frequency response standard deviation L, the larger the expression value of the actual frequency response standard deviation L in the T time when the microphone operates, the worse the actual frequency response flatness in the T time when the microphone operates, otherwise, the better the actual frequency response flatness in the T time when the microphone operates;
a103, calculating a frequency response flatness coefficient through an actual frequency response standard deviation L, wherein the calculated expression is as follows:；
as can be seen from the calculation expression of the frequency response flatness coefficient, the larger the expression value of the frequency response flatness coefficient generated when the microphone operates in the time T in the dialysis equipment based on the audio identification is, the worse the operation state of the microphone is, the larger the hidden danger that the operation state of the microphone is abnormal is, otherwise, the better the operation state of the microphone is, and the smaller the hidden danger that the operation state of the microphone is abnormal is;
in dialysis devices based on audio recognition, a higher or lower signal-to-noise ratio at microphone operation may lead to an increased safety risk for the patient during dialysis due to abnormal microphone operation, and the problems that may occur in both cases are described in detail below:
1. Microphone signal to noise ratio is high: if the microphone signal-to-noise ratio is high, i.e. the signal strength is much higher than the noise, the following problems may result:
sensitivity is too high: microphones may be too sensitive, capturing small sound changes or noise in the environment, which may lead to false identifications, e.g. non-critical sounds may be interpreted as important sounds by mistake, leading to false alarms or unnecessary interventions;
excessive amplification: a high signal-to-noise ratio may cause the microphone to amplify small sound variations in the environment and may even amplify noise that is not desired to be amplified, which may affect patient privacy or cause false alarms in case of emergency;
reduced tolerance: the device may become too sensitive to various sounds in the environment to properly filter out irrelevant sounds, which may cause the device to react excessively to external noise, thereby reducing the tolerance and practicality of the device;
dynamic range increases: in some scenarios, there may be a large sound dynamic range, i.e., high volume and low volume sounds exist at the same time, and an excessively high signal-to-noise ratio may make it difficult for the device to capture these different intensities of sounds at the same time;
2. microphone signal-to-noise ratio is low: if the microphone signal-to-noise ratio is low, i.e. the noise strength is much higher than the signal, the following problems may arise:
Loss of signal: a low signal-to-noise ratio may result in the desired signal being masked by noise, resulting in signal loss. For example, in dialysis devices, a patient's vital call may be masked by noise, delaying a timely response to the patient;
monitoring inaccuracy: the device may not accurately capture and monitor the patient's sound changes, and thus may not accurately assess the patient's state, which may increase the health risk during the patient's dialysis process;
failure of the security alarm: the device may not properly identify the emergency or abnormal event, resulting in a security alarm failure, which may prevent timely intervention and handling;
therefore, the hidden trouble that the signal-to-noise ratio is abnormal when the microphone operates can be timely found out by monitoring the signal-to-noise ratio when the microphone operates in the dialysis equipment based on audio identification;
the logic for obtaining the signal-to-noise ratio abnormal concealment coefficients is as follows:
b101, obtaining the optimal signal-to-noise ratio range of the microphone in the dialysis equipment based on audio identification when running, and calibrating the optimal signal-to-noise ratio range as；
It should be noted that the requirements of the signal-to-noise ratio may be different for different application scenarios, for example, if the device is mainly used to capture low volume heart beat sounds or breathing sounds, a higher signal-to-noise ratio is required to ensure accurate voice recognition, and in other cases, a slightly lower signal-to-noise ratio may be acceptable; different types of sound signals have different dynamic ranges and frequency spectrum characteristics, certain signals can be accurately identified by needing higher signal-to-noise ratio, and other signals can have lower requirements on the signal-to-noise ratio, so that the optimal signal-to-noise ratio range when the microphone operates is not particularly limited, and can be adjusted according to actual application scenes and requirements;
B102, acquiring actual signal-to-noise ratios of different moments in T time when a microphone in the dialysis equipment based on audio identification operates, and calibrating the actual signal-to-noise ratios asK represents the number of the actual signal-to-noise ratio at different moments in time T when the microphone is in operation, k=1, 2, 3, 4, … …, h being a positive integer;
it should be noted that, the actual signal-to-noise ratio of the microphone at different moments during operation can be measured in real time by using a power spectral density analysis method, which is a common method, the energy distribution of the signal and noise is calculated by performing spectral analysis on the audio signal recorded in real time, the intensity of the useful signal can be estimated according to the energy peak value of the signal on the spectrum, and then the signal-to-noise ratio can be calculated in the background noise energy range;
b103, obtaining the microphone in the time of T and not in the optimal signal-to-noise ratioRangeIs recalibrated to +.>V denotes +.f. in the range of the optimal signal to noise ratio acquired during the time T when the microphone is running>K=1, 2, 3, 4, … …, p being a positive integer;
b104, by actual signal-to-noise ratioCalculating the signal-to-noise ratio abnormal hiding coefficient, wherein the calculated expression is as follows: Wherein->，/>Indicating that the actual signal-to-noise ratio acquired during the time T during which the microphone is operating is not within the optimum signal-to-noise ratio range +.>Is used for the time period of (a),；
the calculation expression of the signal-to-noise ratio abnormal hiding coefficient shows that the larger the expression value of the signal-to-noise ratio abnormal hiding coefficient generated when the microphone operates in the T time in dialysis equipment based on audio identification is, the worse the operation state of the microphone is, the larger the hidden danger that the operation state of the microphone is abnormal is, otherwise, the better the operation state of the microphone is, and the smaller the hidden danger that the operation state of the microphone is abnormal is;
the audio response information during microphone operation includes frequency offset coefficients, and after acquisition, the informationThe acquisition module calibrates the frequency offset coefficient as；
By frequency offset is meant that the microphone has a difference between the frequency of its output signal and the frequency of its input signal in response to the sound signal, for example, assuming that the frequency of the external sound signal is 1000 hertz (Hz), but because of the frequency offset of the microphone, the microphone may output a slightly different frequency, such as 1010 Hz, the difference between the frequency of this output signal and the frequency of the input signal being the frequency offset;
in dialysis devices based on audio recognition, frequency offset of the microphone may lead to an increased safety risk for the patient during dialysis, the following are possible reasons:
False recognition alarm signal: dialysis devices typically use acoustic signals to convey alarm information, such as equipment malfunction or problems in treatment, which if the microphone frequency is shifted may result in the device not capturing or identifying these alarm signals accurately, thereby delaying the taking of necessary emergency measures, increasing the safety risk for the patient in an emergency situation;
misleading patient guidance: the dialysis device may use sound guidance to guide the patient through the procedure, such as inserting a dialysis needle or adjusting treatment parameters, and if the microphone frequency is shifted, the patient may be subjected to incorrect sound guidance, resulting in incorrect operation, thereby increasing the risk of operation;
influence sound monitoring: in some cases, the dialysis device may monitor the respiratory sounds or other physiological signals of the patient to assess the condition of the patient, and if the microphone frequency is shifted, the monitoring result may be inaccurate, thereby affecting the assessment of the patient's state, increasing the risk of failing to timely detect the patient's problem;
interfere with communication with healthcare workers: in emergency situations, medical staff may need to communicate with patients through the voice communication function on the equipment, and frequency deviation may cause unclear voice in communication, which affects effective communication between the medical staff and the patients, thereby increasing patient safety risks;
Therefore, the output signal frequency and the input signal frequency of the microphone in the dialysis equipment based on audio identification are monitored, and the abnormal hidden trouble of frequency deviation during the operation of the microphone can be found in time;
the logic for frequency offset coefficient acquisition is as follows:
c101, acquiring a plurality of input signal frequencies and output signal frequencies under corresponding frequencies in T time when a microphone in the dialysis equipment based on audio identification operates, and calibrating the input signal frequencies and the output signal frequencies under the corresponding frequencies as respectivelyAnd->X represents the number of the input signal frequency and the output signal frequency at the corresponding frequency in the time T when the microphone is operated, x=1, 2, 3, 4, … …, m is a positive integer;
it should be noted that, by using professional test instruments such as a sound frequency analyzer or a spectrum analyzer, the frequency of the input signal and the frequency of the output signal of the microphone can be directly measured, and these instruments can accurately analyze the frequency spectrum component of the sound signal, so as to obtain accurate frequency information, and then, in order to compare and analyze the frequency of the input signal when the microphone is operated with the frequency of the output signal at the corresponding frequency, the frequency of the input signal when the microphone is operated is set to be the same as the subscript of the frequency of the output signal at the corresponding frequency;
C102 by input signal frequencyAnd the output signal frequency at the corresponding frequency +.>Calculating a frequency offset coefficient, wherein the calculated expression is: />；
As can be seen from the calculation expression of the frequency offset coefficient, the larger the expression value of the frequency offset coefficient generated when the microphone in the dialysis equipment based on audio identification operates in the time T is, the worse the operation state of the microphone is, the larger the hidden danger that the operation state of the microphone is abnormal is, otherwise, the better the operation state of the microphone is, and the smaller the hidden danger that the operation state of the microphone is abnormal is;
the real-time analysis module is used for comprehensively analyzing the processed equipment performance information and the audio response information during the operation of the microphone to generate a state index, and transmitting the state index to the comparison analysis module;
the real-time analysis module obtains the flatness coefficient of the frequency responseSignal-to-noise ratio abnormality concealment coefficient +.>Frequency offset coefficient +.>Then, a data analysis model is built to generate a state index +.>The formula according to is:in (1) the->、/>、/>Respectively the frequency response flatness coefficient +.>Signal-to-noise ratio abnormality concealment coefficient +.>Frequency offset coefficient +.>Is a preset proportionality coefficient of>、/>、/>Are all greater than 0;
From the calculation formula, the greater the frequency response flatness coefficient generated when the microphone operates in the T time, the greater the signal-to-noise ratio abnormality hiding coefficient and the greater the frequency offset coefficient in the dialysis equipment based on the audio identification, namely the state index generated when the microphone operates in the T timeThe larger the expression value of (2) is, the worse the operation state of the microphone is, the larger the hidden trouble that the operation state of the microphone is abnormal is, the smaller the frequency response flatness coefficient generated when the microphone operates in the T time, the smaller the signal to noise ratio abnormality hiding coefficient is, the smaller the frequency offset coefficient is, namely, the state index generated when the microphone operates in the T time is->The smaller the expression value of the microphone is, the better the operation state of the microphone is, and the smaller the hidden trouble that the operation state of the microphone is abnormal is;
the comparison analysis module is used for comparing and analyzing the state index generated during the operation of the microphone with a preset state index reference threshold value to generate a high hidden danger signal or a low hidden danger signal and transmitting the hidden danger signal to the comprehensive analysis module;
the comparison analysis module compares the state index generated during the operation of the microphone with a preset state index reference threshold value, if the state index is greater than or equal to the state index reference threshold value, a high hidden danger signal is generated through the comparison analysis module, and the signal is transmitted to the comprehensive analysis module;
If the state index is smaller than the state index reference threshold, generating a low hidden danger signal through the comparison analysis module, and transmitting the signal to the comprehensive analysis module;
it should be noted that, the selection of the above-mentioned T time is a time period with a relatively short time, and the time in the time period is not limited herein, and may be set according to practical situations, so as to monitor the running state of the microphone in the dialysis device based on audio recognition in the T time, so that the running state of the microphone in the dialysis device based on audio recognition in different time periods (in the T time) is monitored in this way;
the comprehensive analysis module is used for comprehensively analyzing a plurality of state indexes generated later when the microphone operates after receiving the high hidden trouble signals generated when the microphone operates, generating risk signals, transmitting the signals to the prompt module, and sending early warning prompts through the prompt module;
after the comprehensive analysis module receives a high hidden trouble signal generated during microphone operation, a data set is established for a plurality of state indexes generated subsequently during microphone operation, and the plurality of state indexes in the data set are respectively matched with a preset gradient threshold reference threshold value And->Performing comparison, wherein the gradient threshold is referenced to the threshold +.>And->Are all greater than the state index reference threshold and +.>；
Referencing the state index within the analysis set to the gradient thresholdAnd->Performing comparison, wherein the comparison value is larger than or equal to the state index reference threshold value and smaller than the gradient threshold value reference threshold value +.>The state indexes of (2) are scaled as first-order state indexes, the total number of the first-order state indexes is marked as F1, and the gradient threshold value reference threshold value is larger than or equal to +.>And less than the gradient threshold reference thresholdThe state indexes of (2) are scaled as secondary state indexes, the total number of the secondary state indexes is marked as F2, and the gradient threshold value reference threshold value is greater than or equal to +.>The state indexes of the system are calibrated to be three-level state indexes, the total number of the three-level state indexes is marked as F3, the total number of the first-level state indexes F1, the total number of the second-level state indexes F2 and the total number of the three-level state indexes F3 are subjected to formulated analysis, and risk indexes are generated according to the following formula: />In (1) the->、/>、/>The weight factors are respectively the total number F1 of the first-level state indexes, the total number F2 of the second-level state indexes and the total number F3 of the third-level state indexes, wherein the weight factors are as followsThe sub-components are used for balancing the duty ratio of each item of data in the formula so as to promote the accuracy of the calculation result, and ，/>；
From the calculation formula, the risk index generated by the state index in the data set when the microphone is in operationThe larger the expression value of the microphone is, the more serious the degree of abnormal hidden danger appears in the operation state of the microphone is, otherwise, the less serious the degree of abnormal hidden danger appears in the operation state of the microphone is;
risk index generated by state index in data set when microphone is operatedReference threshold value of gradient of risk index preset>And->Performing comparison, wherein->The comparison is divided into the following cases:
if it isGenerating a high-level risk signal through the comprehensive analysis module, transmitting the signal to the prompt module, and sending out a high-level risk early warning prompt through the prompt module, wherein when the high-level risk signal is generated during the operation of the microphone, the microphone is indicated to have a poor operation state;
if it isThen a medium-level risk message is generated through the comprehensive analysis moduleThe method comprises the steps of transmitting signals to a prompt module, sending out medium-level risk early warning prompts through the prompt module, and when a microphone runs to generate medium-level risk signals, indicating that the running state of the microphone is poor, wherein the risk degree is lower than that of the high-level risk signals generated when the microphone runs;
if it is The comprehensive analysis module is used for generating a low-level risk signal and transmitting the signal to the prompt module, the early warning prompt is not sent out by the prompt module, and when the microphone is operated and the low-level risk signal is generated, the microphone is indicated to be in a good operation state, and the operation of the microphone is possibly caused by sudden accidental conditions;
according to the invention, through analyzing the running state of the microphone, when the running state of the microphone has abnormal hidden danger, an early warning prompt is sent out to prompt medical staff to arrange related overhaul and maintenance work in advance for the microphone possibly having abnormal hidden danger, so that the efficient running of the microphone is ensured, the situation that the equipment cannot be subjected to audio recognition and acoustic signal analysis due to the abnormal running state of the microphone is effectively prevented, the running state of the dialysis equipment is effectively monitored, the safety risk of a patient during dialysis is furthest reduced, and the dialysis equipment is further convenient for the patient to carry out efficient dialysis;
according to the invention, when the operation state of the microphone is perceived to have potential anomaly hazards, the operation state of the microphone is comprehensively analyzed, the severity of the potential anomaly hazards caused by the operation state of the microphone is judged, and meanwhile, early warning prompts with different severity are sent out, so that maintenance management personnel can know the severity of the potential anomaly hazards of the microphone in time, and the maintenance management personnel can overhaul the microphone efficiently.
The invention provides a dialysis equipment running state early warning method based on audio frequency identification as shown in fig. 2, which comprises the following steps:
collecting a plurality of pieces of running state information, including equipment performance information and audio response information, of a microphone in dialysis equipment based on audio identification when the microphone runs, and processing the equipment performance information and the audio response information of the microphone when the microphone runs after the collection;
comprehensively analyzing the processed equipment performance information and the audio response information during the operation of the microphone to generate a state index;
comparing and analyzing a state index generated during the operation of the microphone with a preset state index reference threshold value to generate a high hidden danger signal or a low hidden danger signal;
after receiving a high hidden trouble signal generated during microphone operation, comprehensively analyzing a plurality of state indexes generated later during microphone operation, generating a risk signal, and sending an early warning prompt to the risk signal;
the embodiment of the invention provides a dialysis equipment running state early warning method based on audio frequency identification, which is realized by the dialysis equipment running state early warning system based on audio frequency identification, and the specific method and the flow of the dialysis equipment running state early warning method based on audio frequency identification are detailed in the embodiment of the dialysis equipment running state early warning system based on audio frequency identification, and are not repeated here.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (8)
1. The dialysis equipment running state early warning system based on the audio identification is characterized by comprising an information acquisition module, a real-time analysis module, a comparison analysis module, a comprehensive analysis module and a prompt module;
The information acquisition module acquires a plurality of pieces of running state information, including equipment performance information and audio response information, of the microphone in the dialysis equipment based on audio identification, processes the equipment performance information and the audio response information of the microphone in running and transmits the processed equipment performance information and the processed audio response information to the real-time analysis module;
the equipment performance information during the operation of the microphone comprises a frequency response flatness coefficient and a signal to noise ratio abnormal hiding coefficient, and after the acquisition, the information acquisition module respectively marks the frequency response flatness coefficient and the signal to noise ratio abnormal hiding coefficient asAnd->；
The audio response information of the microphone in operation comprises a frequency offset coefficient, and after acquisition, the information acquisition module marks the frequency offset coefficient as；
The real-time analysis module is used for comprehensively analyzing the processed equipment performance information and the audio response information during the operation of the microphone to generate a state index, and transmitting the state index to the comparison analysis module;
the real-time analysis module obtains the flatness coefficient of the frequency responseSignal-to-noise ratio abnormality concealment coefficient +.>Frequency offset coefficient +.>Then, a data analysis model is built to generate a state index +.>The formula according to is:
in (1) the->、/>、/>Respectively the frequency response flatness coefficient +. >Signal-to-noise ratio abnormality concealment coefficient +.>Frequency offset coefficient +.>Is a preset proportionality coefficient of>、/>、/>Are all greater than 0;
the comparison analysis module is used for comparing and analyzing the state index generated during the operation of the microphone with a preset state index reference threshold value to generate a high hidden danger signal or a low hidden danger signal and transmitting the hidden danger signal to the comprehensive analysis module;
and the comprehensive analysis module is used for comprehensively analyzing a plurality of state indexes generated later when the microphone operates after receiving the high hidden danger signals generated when the microphone operates, generating risk signals, transmitting the signals to the prompt module, and sending early warning prompts through the prompt module.
2. The dialysis machine operating condition pre-alarm system of claim 1, wherein the frequency response flatness factor acquisition logic is as follows:
a101, acquiring a plurality of actual frequency responses of a microphone in the dialysis equipment based on audio identification in a T time, and calibrating the actual frequency responses as，yA number representing the actual frequency response during T time when the microphone is running in the audio recognition based dialysis device,y=1、2、3、4、……、n，nis a positive integer;
a102, calculating the actual frequency response standard deviation of the microphone in the T time during operation, and calibrating the actual frequency response standard deviation as LThen:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>For the average value of the actual frequency response of the microphone in the time T, the obtained calculation formula is as follows: />；
A103, response standard deviation by actual frequencyLCalculating a frequency response flatness coefficient, wherein the calculated expression is:。
3. the dialysis machine operating condition pre-warning system based on audio recognition according to claim 2, wherein the logic for obtaining the signal-to-noise ratio abnormality concealment coefficients is as follows:
b101, obtaining the optimal signal-to-noise ratio range of the microphone in the dialysis equipment based on audio identification when running, and calibrating the optimal signal-to-noise ratio range as；
B102, acquiring actual signal-to-noise ratios of different moments in T time when a microphone in the dialysis equipment based on audio identification operates, and calibrating the actual signal-to-noise ratios as，kA number representing the actual signal-to-noise ratio at different times during the time T when the microphone is running,k=1、2、3、4、……、h，his a positive integer;
b103, acquiring the microphone in the time T when the microphone is operated and not in the optimal signal-to-noise ratio rangeIs recalibrated to +.>，vRepresenting that the microphone is not in the optimal signal-to-noise ratio range acquired during time TIs used to determine the number of actual signal to noise ratios,k=1、2、3、4、……、p，pis a positive integer;
b104, by actual signal-to-noise ratio Calculating the signal-to-noise ratio abnormal hiding coefficient, wherein the calculated expression is as follows:wherein->，/>Indicating that the actual signal-to-noise ratio acquired during the time T during which the microphone is operating is not within the optimum signal-to-noise ratio range +.>Is used for the time period of (a),。
4. the dialysis machine operating condition pre-alarm system of claim 3, wherein the frequency offset coefficient acquisition logic is as follows:
c101, acquiring a plurality of input signal frequencies and output signal frequencies under corresponding frequencies in T time when a microphone in the dialysis equipment based on audio identification operates, and calibrating the input signal frequencies and the output signal frequencies under the corresponding frequencies as respectivelyAnd->，xA number representing the frequency of the input signal and the frequency of the output signal at the corresponding frequency in time T when the microphone is in operation,x=1、2、3、4、……、m，mis a positive integer;
c102 by input signal frequencyAnd the output signal frequency at the corresponding frequency +.>Calculating a frequency offset coefficient, wherein the calculated expression is: />。
5. The dialysis equipment operating state early warning system based on audio recognition according to claim 4, wherein the comparison analysis module compares a state index generated during microphone operation with a preset state index reference threshold value, and if the state index is greater than or equal to the state index reference threshold value, generates a high hidden danger signal through the comparison analysis module and transmits the signal to the comprehensive analysis module;
If the state index is smaller than the state index reference threshold, a low hidden danger signal is generated through the comparison analysis module, and the signal is transmitted to the comprehensive analysis module.
6. The dialysis equipment operating state early warning system based on audio recognition according to claim 5, wherein after the comprehensive analysis module receives the high hidden danger signal generated during microphone operation, a data set is established for a plurality of state indexes generated subsequently during microphone operation, and the plurality of state indexes in the data set are respectively compared with a preset gradient threshold reference thresholdAnd->Performing comparison, wherein the gradient threshold is referenced to the threshold +.>And->Are all greater than the state index reference threshold and +.>；
Referencing the state index within the analysis set to the gradient thresholdAnd->Performing comparison, wherein the comparison value is larger than or equal to the state index reference threshold value and smaller than the gradient threshold value reference threshold value +.>Is scaled to a first order state index, and the total number of the first order state indexes is recorded asF1, equal to or greater than ladderDegree threshold reference threshold->And is smaller than the gradient threshold reference threshold +.>Is scaled to a secondary state index and the total number of secondary state indexes is recorded asF2, will be greater than or equal to the gradient threshold reference threshold +. >Is scaled to a three-level state index, and the total number of the three-level state indexes is recorded asF3, the total number of the first-order state indexesF1. Total number of secondary state indexesF2. Total number of three-level state indexesF3, carrying out formulated analysis to generate a risk index according to the following formula:
in (1) the->、/>、/>Respectively the total number of the first-order state indexesF1. Total number of secondary state indexesF2. Total number of three-level state indexesFWeight factor of 3, and->，。
7. According to claim 6An audio recognition-based dialysis equipment running state early warning system is characterized in that a risk index generated by a state index in a data set when a microphone is operatedReference threshold value of gradient of risk index preset>And->Performing comparison, wherein->The comparison is divided into the following cases:
if it isGenerating an advanced risk signal through the comprehensive analysis module, transmitting the signal to the prompting module, and sending an advanced risk early warning prompt through the prompting module;
if it isGenerating a medium-level risk signal through the comprehensive analysis module, transmitting the signal to the prompting module, and sending out a medium-level risk early warning prompt through the prompting module;
if it isAnd generating a low-level risk signal through the comprehensive analysis module, transmitting the signal to the prompt module, and sending out early warning prompt without the prompt module.
8. An audio recognition-based dialysis equipment operation state early warning method implemented by the audio recognition-based dialysis equipment operation state early warning system according to any one of claims 1 to 7, characterized by comprising the steps of:
collecting a plurality of pieces of running state information, including equipment performance information and audio response information, of a microphone in dialysis equipment based on audio identification when the microphone runs, and processing the equipment performance information and the audio response information of the microphone when the microphone runs after the collection;
comprehensively analyzing the processed equipment performance information and the audio response information during the operation of the microphone to generate a state index;
comparing and analyzing a state index generated during the operation of the microphone with a preset state index reference threshold value to generate a high hidden danger signal or a low hidden danger signal;
after receiving the high hidden trouble signal generated during the operation of the microphone, comprehensively analyzing a plurality of state indexes generated subsequently during the operation of the microphone, generating a risk signal, and sending out an early warning prompt to the risk signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311418270.XA CN117153365B (en) | 2023-10-30 | 2023-10-30 | Dialysis equipment running state early warning method and system based on audio identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311418270.XA CN117153365B (en) | 2023-10-30 | 2023-10-30 | Dialysis equipment running state early warning method and system based on audio identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117153365A CN117153365A (en) | 2023-12-01 |
| CN117153365B true CN117153365B (en) | 2024-03-12 |
Family
ID=88904678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311418270.XA Active CN117153365B (en) | 2023-10-30 | 2023-10-30 | Dialysis equipment running state early warning method and system based on audio identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117153365B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117476040B (en) * | 2023-12-25 | 2024-03-29 | 深圳市鑫闻达电子有限公司 | Audio identification method and identification system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108986419A (en) * | 2018-10-17 | 2018-12-11 | 暨南大学 | A kind of data alarm method for haemodialysis |
| CN114118152A (en) * | 2021-11-26 | 2022-03-01 | 歌尔光学科技有限公司 | Head-mounted display equipment and gesture recognition method and device thereof and storage medium |
| CN115061877A (en) * | 2022-06-29 | 2022-09-16 | 淮安市第二人民医院 | Hemodialysis instrument fault analysis feedback early warning system based on data processing |
| CN115471827A (en) * | 2022-08-26 | 2022-12-13 | 岱特智能科技（上海）有限公司 | Hemodialysis machine pump state early warning method and system based on audio recognition |
| CN116389304A (en) * | 2023-04-12 | 2023-07-04 | 国网湖北省电力有限公司荆州供电公司 | SG-TMS-based network operation state trend analysis system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114145025B (en) * | 2020-07-24 | 2024-04-12 | 深圳市大疆创新科技有限公司 | Audio processing method and electronic equipment |
-
2023
- 2023-10-30 CN CN202311418270.XA patent/CN117153365B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108986419A (en) * | 2018-10-17 | 2018-12-11 | 暨南大学 | A kind of data alarm method for haemodialysis |
| CN114118152A (en) * | 2021-11-26 | 2022-03-01 | 歌尔光学科技有限公司 | Head-mounted display equipment and gesture recognition method and device thereof and storage medium |
| CN115061877A (en) * | 2022-06-29 | 2022-09-16 | 淮安市第二人民医院 | Hemodialysis instrument fault analysis feedback early warning system based on data processing |
| CN115471827A (en) * | 2022-08-26 | 2022-12-13 | 岱特智能科技（上海）有限公司 | Hemodialysis machine pump state early warning method and system based on audio recognition |
| CN116389304A (en) * | 2023-04-12 | 2023-07-04 | 国网湖北省电力有限公司荆州供电公司 | SG-TMS-based network operation state trend analysis system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117153365A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117153365B (en) | Dialysis equipment running state early warning method and system based on audio identification | |
| CN102186416A (en) | Apnea detection program, apnea detector, and apnea detection method | |
| JP5233342B2 (en) | Sleep apnea detection program, sleep apnea detection device, and sleep apnea detection method | |
| US8348839B2 (en) | Systems and methods for active listening/observing and event detection | |
| CN102760203B (en) | Warning information processing device and alarm information processing method | |
| CN110085006A (en) | Ship monitoring method, device, system and storage medium | |
| US9633168B2 (en) | Biometric identity validation for use with unattended tests for medical conditions | |
| US20150150512A1 (en) | Systems and methods for tracking and analysis of electrical-physiological interference | |
| CN102828919A (en) | Method for acoustically monitoring wind turbine, acoustic monitoring system and re-equipment kit | |
| CN102547526B (en) | Real-time monitoring method and system of microphone working state | |
| CN115435843A (en) | Medical imaging equipment operation supervisory systems based on big data | |
| CN116365716B (en) | Electricity inspection system based on internet of things platform | |
| US20240057965A1 (en) | Deriving insights into health through analysis of audio data generated by digital stethoscopes | |
| CN209032422U (en) | A kind of cardiechema signals detection device | |
| JP3333494B2 (en) | Device abnormality diagnosis method | |
| CN117268534B (en) | Remote intelligent control metering detection device and method for noise measurement analysis instrument | |
| JP2004177359A (en) | Method and device for acoustically monitoring operating state of facility | |
| CN116772125A (en) | Oil transportation station pipeline inspection system and method | |
| CN109698998B (en) | Fault diagnosis system and method for sound system | |
| CN112905463A (en) | Software test monitoring method and device, electronic equipment and readable storage medium | |
| TW202145962A (en) | Household sleeping monitor, household sleeping monitoring system and household sleep monitoring and method for sleep breathing event classification | |
| KR20230078819A (en) | Method, program, and system for diagnosing equipment | |
| US20130041279A1 (en) | System and method for monitoring physiological functions | |
| Al-Zaben et al. | Tele-Monitoring System of Risk in Respiratory Patients | |
| CN117976228A (en) | Capacity reactivity prediction system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |