CN117717351B - Bluetooth transmission-based electrocardiograph quick auxiliary matching method and system - Google Patents
Bluetooth transmission-based electrocardiograph quick auxiliary matching method and system Download PDFInfo
- Publication number
- CN117717351B CN117717351B CN202410176797.4A CN202410176797A CN117717351B CN 117717351 B CN117717351 B CN 117717351B CN 202410176797 A CN202410176797 A CN 202410176797A CN 117717351 B CN117717351 B CN 117717351B
- Authority
- CN
- China
- Prior art keywords
- user
- ecg signal
- mobile terminal
- bluetooth transmission
- target
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 106
- 238000013135 deep learning Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 6
- 230000008859 change Effects 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims 1
- 208000019622 heart disease Diseases 0.000 description 16
- 238000013527 convolutional neural network Methods 0.000 description 11
- 230000008901 benefit Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002107 myocardial effect Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application relates to a Bluetooth transmission-based electrocardiograph quick auxiliary matching method and a Bluetooth transmission-based electrocardiograph quick auxiliary matching system, wherein the method comprises the following steps: acquiring an ECG signal of a user based on an electrocardiograph carried by the user; inputting the ECG signal of the user into a plurality of analysis models based on deep learning training, and outputting a first probability of whether the ECG signal of the user belongs to target classification; summarizing first probabilities of whether ECG signals of users output by the plurality of analysis models belong to target classification based on weights corresponding to the preset plurality of analysis models, and obtaining second probabilities of whether the ECG signals of the users belong to the target classification; when the second probability of whether the ECG signal of the user belongs to the target classification exceeds a preset value, matching the ECG signal with a mobile terminal carried by the user through a Bluetooth transmission module of an electrocardiograph; and sending prompt information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module. The application can automatically inform the user of the ECG signal classification condition focused by the user through the prompt information.
Description
Technical Field
The invention relates to the field of intelligent medical treatment, in particular to a Bluetooth transmission-based quick auxiliary matching method and system for an electrocardiograph.
Background
The electrocardiograph can automatically record bioelectric signals generated by myocardial activation during heart activity to form Electrocardiogram (ECG) signals, and is a medical electronic instrument commonly used for clinical diagnosis and scientific research. Along with the rapid development of electronic information and manufacturing technology, a portable or wearable electrocardiograph which is small in size and suitable for carrying is produced, so that a user can conveniently acquire ECG signals at any time, and the ECG signals can be transmitted to a mobile phone end for display in a wireless transmission mode such as Bluetooth.
In the prior art, whether the connection of the electrocardiograph and the mobile phone is mainly controlled by a user or not brings a certain operation amount to the user, and when the heart activity of the user is in a normal state, the ECG signal acquired by the electrocardiograph is not concerned by the user. Therefore, a new technical solution is needed to realize automatic matching connection between the electrocardiograph and the mobile terminal and to transmit the detection result data to be focused to the user.
Disclosure of Invention
In order to solve the technical problems, the application provides a Bluetooth transmission-based quick auxiliary matching method and a Bluetooth transmission-based quick auxiliary matching system for an electrocardiograph, which can realize automatic matching connection between the electrocardiograph and a mobile terminal and transmit detection result data to be focused to a user.
In a first aspect, the present invention provides a method for fast auxiliary matching of an electrocardiograph based on bluetooth transmission, including: acquiring an ECG signal of a user based on an electrocardiograph carried by the user; inputting the ECG signal of the user into a plurality of analysis models trained based on deep learning, outputting a first probability of whether the ECG signal of the user belongs to the target class by the plurality of analysis models, and when the number of the plurality of analysis models is n, outputting a first probability of whether the ECG signal of the user output by the ith analysis model belongs to the target class by the ith analysis model as followsX represents the ECG signal of the user, the plurality of analysis models have corresponding weights, and the weight corresponding to the ith analysis model is/>，/>Representing a sample ECG signal,/>A first probability representing whether the sample ECG signal output by the ith analysis model belongs to the target class,/>A first probability representing whether the sample ECG signal output by a j-th analysis model of the plurality of analysis models belongs to the target class; summarizing a first probability of whether the ECG signals of the user output by the plurality of analysis models belong to the target classification based on preset weights corresponding to the plurality of analysis models, so as to obtain a second probability/>, of whether the ECG signals of the user belong to the target classification; Judging whether the second probability of whether the ECG signal of the user belongs to the target classification exceeds a preset value, and matching the ECG signal of the user with a mobile terminal carried by the user through a Bluetooth transmission module of the electrocardiograph when the second probability of whether the ECG signal of the user belongs to the target classification exceeds the preset value; and sending prompt information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module, wherein the prompt information is used for prompting the possibility that the ECG signal of the user belongs to the target classification.
Optionally, before the step of sending, by the bluetooth transmission module, the prompt information related to the target classification to the mobile terminal of the user, the foregoing bluetooth transmission-based electrocardiograph rapid auxiliary matching method further includes: collecting geographic coordinate information of the position of the user at the current moment t based on the mobile terminal of the user) ; Calculating the distance between the position of the user at the current moment t and a plurality of preset target positions, wherein when the number of the target positions is m, the distance between the position of the user at the current moment t and the kth target position in the target positions is/>Wherein the geographic position information of the kth target position is) ; At/>When the method is used, the step of sending prompt information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module is executed, wherein/>Is a preset first reference distance.
Optionally, before the step of sending, by the bluetooth transmission module, the prompt information related to the target classification to the mobile terminal of the user, the foregoing method for fast auxiliary matching of an electrocardiograph based on bluetooth transmission further includes: calculating the distance between the position of the user at the current time t and the position of the user at the historical time t-1The geographical position information of the position of the user at the historical moment t-1 is @) ; In determining/>After that, as/>Executing the step of sending prompt information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module, wherein/>Is a preset second reference distance.
Optionally, before the step of sending, by the bluetooth transmission module, the prompt information related to the target classification to the mobile terminal of the user, the foregoing bluetooth transmission-based electrocardiograph rapid auxiliary matching method further includes: acquiring the gesture of the user at the current time t based on the mobile terminal of the user; calculating the gesture change amplitude of the user according to the gesture of the user at the current time t and the gesture of the user at the historical time t-1; judging whether the user is in a motion state according to the gesture change amplitude of the user; and when the user is not in the motion state, executing the step of sending prompt information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module.
Optionally, the step of "acquiring the ECG signal of the user based on the electrocardiograph carried by the user" further includes: extracting wavelet coefficients a for any position on the user's ECG signal; correcting the wavelet coefficient a of the ECG signal of the user, wherein the corrected new wavelet coefficient is as follows: Where N is the length of the user's ECG signal; and reconstructing the ECG signal of the user based on the modified new wavelet coefficient.
Optionally, in the foregoing method for fast auxiliary matching of an electrocardiograph based on bluetooth transmission, one of the multiple analysis models is a CNN network, and when training the CNN network, a change value of any parameter of the CNN network isWherein/>And b is the trained times of the CNN network, and R is a preset change weight.
Optionally, the foregoing method for fast auxiliary matching of electrocardiograph based on bluetooth transmission "sends, through the bluetooth transmission module, prompt information related to the target classification to the mobile terminal of the user" further includes: inquiring a pre-recorded notification mode corresponding to the target classification, wherein the notification mode comprises one or more of vibration, text notification and voice playing; and controlling the mobile terminal of the user to inform the user to view the prompt information according to the informing mode corresponding to the target classification.
Optionally, the foregoing method for fast auxiliary matching of an electrocardiograph based on bluetooth transmission further includes, when the time for sending the prompt message to the mobile terminal of the user exceeds a preset time length: checking whether the user has checked the prompt information; inquiring the contact information of the contact person of the user from the mobile terminal of the user when the user does not view the prompt information; and sending the prompt information to the mobile terminal of the contact person according to the contact way of the contact person.
In a second aspect, the present invention provides an electrocardiograph rapid auxiliary matching system based on bluetooth transmission, including: the signal acquisition module is used for acquiring an ECG signal of a user based on an electrocardiograph carried by the user; a first probability calculation module for inputting the ECG signal of the user into a plurality of analysis models trained based on deep learning, outputting a first probability of whether the ECG signal of the user belongs to the target class by the plurality of analysis models, and when the number of the plurality of analysis models is n, outputting a first probability of whether the ECG signal of the user output by the ith analysis model belongs to the target class by the ith analysis model as followsX represents the ECG signal of the user, the plurality of analysis models have corresponding weights, and the weight corresponding to the ith analysis model is/>，/>Representing a sample ECG signal,/>A first probability representing whether the sample ECG signal output by the ith analysis model belongs to the target class,/>A first probability representing whether the sample ECG signal output by a j-th analysis model of the plurality of analysis models belongs to the target class; the second probability calculation module is used for summarizing the first probability of whether the ECG signals of the user belong to the target classification or not based on the weights corresponding to the preset analysis models, so as to obtain the second probability/>, of whether the ECG signals of the user belong to the target classification or not; The matching module is used for judging whether the second probability of the ECG signal of the user belonging to the target classification exceeds a preset value, and matching the ECG signal of the user belonging to the target classification with the mobile terminal carried by the user through the Bluetooth transmission module of the electrocardiograph when the second probability of the ECG signal of the user belonging to the target classification exceeds the preset value; and the prompting module is used for sending prompting information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module and prompting the possibility that the ECG signal of the user belongs to the target classification.
The technical scheme provided by the invention has at least one or more of the following beneficial effects:
According to the technical scheme, a user does not need to manually control Bluetooth transmission between an electrocardiograph and a mobile terminal, analysis is performed by utilizing a plurality of analysis models based on deep learning after the electrocardiograph detects ECG signals of the user, after target classification (such as heart diseases) is identified, in order to ensure that an identification result is correct, integrated calculation is performed on results of the analysis models, weight corresponding to the result of each analysis model in the calculation process is reasonably set according to the analysis condition of sample data in the analysis process, so that probability of accurately reflecting whether the ECG signals of the user belong to the target classification is finally obtained, when the probability is higher, the electrocardiograph is controlled to be in Bluetooth connection with the mobile terminal of the user if the ECG signal analysis condition of the target classification is focused by the user, the user is automatically informed of the ECG signal classification condition of the user through prompt information, and when the probability is lower, the ECG signal analysis condition of the non-target classification is not focused by the user is not required to be connected with the electrocardiograph through Bluetooth, and interference to the user is avoided.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a flowchart of an electrocardiograph quick auxiliary matching method based on bluetooth transmission according to an embodiment of the present application;
fig. 2 is a partial flowchart of an electrocardiograph quick auxiliary matching method based on bluetooth transmission according to an embodiment of the present application;
FIG. 3 is another partial flow chart of a Bluetooth transmission-based electrocardiograph quick auxiliary matching method according to an embodiment of the present application;
FIG. 4 is a further partial flow chart of a Bluetooth transmission based electrocardiograph quick assist matching method according to an embodiment of the present application;
FIG. 5 is a partial flow chart of a method for fast auxiliary matching of an electrocardiograph based on Bluetooth transmission according to an embodiment of the present application;
Fig. 6 is a block diagram of an electrocardiograph quick auxiliary matching system based on bluetooth transmission according to an embodiment of the present application.
Detailed Description
Some embodiments of the invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
As shown in fig. 1, in one embodiment of the present invention, there is provided a fast auxiliary matching method for an electrocardiograph based on bluetooth transmission, including:
Step S110, ECG signals of the user are acquired based on an electrocardiograph carried by the user.
In this embodiment, the ECG signal is an electrocardiogram signal, and the electrocardiograph is a portable or wearable device, and has a bluetooth transmission module, which can be connected with a mobile terminal (such as a mobile phone) of a user by bluetooth, and transmit an ECG signal analysis result.
Step S120, inputting the ECG signal of the user into a plurality of analysis models trained based on deep learning, outputting a first probability of whether the ECG signal of the user belongs to the target class from the plurality of analysis models, wherein when the number of the plurality of analysis models is n, the first probability of whether the ECG signal of the user output by the ith analysis model belongs to the target class isX represents the ECG signal of the user, and the multiple analysis models all have corresponding weights, then the weight corresponding to the ith analysis model is，/>Representing a sample ECG signal,/>A first probability indicating whether the sample ECG signal output by the ith analysis model belongs to the target class,/>A first probability indicating whether a sample ECG signal output by a j-th analysis model of the plurality of analysis models belongs to a target classification.
In this embodiment, the target classification is not limited, and for example, the target classification may be a classification corresponding to a certain heart disease.
Step S130, summarizing the first probability of whether the ECG signal of the user belongs to the target class or not output by the plurality of analysis models based on the weights corresponding to the preset plurality of analysis models, to obtain the second probability of whether the ECG signal of the user belongs to the target class or not。
In this embodiment, it is easy to understand by those skilled in the art that higher accuracy is required for data analysis of ECG signals, so that a plurality of analysis models based on deep learning are used for analysis at the same time to obtain a plurality of first probabilities reflecting whether ECG signals of users belong to target classifications, and the performances of the plurality of data analysis models may be different, so that there may be a difference between the plurality of first probabilities reflecting whether ECG signals of users belong to target classifications, and the first probabilities output by the plurality of analysis models are reasonably integrated.
Step S140, determining whether the second probability of the ECG signal of the user belonging to the target class exceeds a preset value, and matching with the mobile terminal carried by the user through the bluetooth transmission module of the electrocardiograph when the second probability of the ECG signal of the user belonging to the target class exceeds the preset value.
In this embodiment, assuming that the target classification is a classification corresponding to a certain heart disease, when the second probability is high, it is indicated that the probability that the ECG signal of the user belongs to the classification corresponding to the certain heart disease is high, at this time, the electrocardiograph is controlled to perform bluetooth connection with the mobile terminal of the user, and when the second probability is low, it is indicated that the probability that the ECG signal of the user belongs to the classification corresponding to the certain heart disease is low, at this time, the electrocardiograph and the mobile terminal do not need to be connected through bluetooth.
Step S150, the prompting information related to the target classification is sent to the mobile terminal of the user through the Bluetooth transmission module, and the prompting information is used for prompting the possibility of whether the ECG signal of the user belongs to the target classification.
In this embodiment, after the electrocardiograph is connected with the mobile terminal of the user through bluetooth, prompt information related to the target classification (for example, ECG signals of the user reflect that a certain heart disease may exist in the user) can be timely sent to the user.
According to the technical scheme of the embodiment, a user does not need to manually control Bluetooth transmission between an electrocardiograph and a mobile terminal, analysis is performed by utilizing a plurality of analysis models based on deep learning after the electrocardiograph detects ECG signals of the user, after target classification (such as heart diseases) is identified, in order to ensure that an identification result is correct, integrated calculation is performed on results of the plurality of analysis models, weight corresponding to the result of each analysis model in the calculation process is reasonably set according to the analysis condition of sample data by the analysis model, so that probability that whether the ECG signals of the user belong to the target classification can be accurately reflected is finally obtained, when the probability is higher, the electrocardiograph is controlled to be in Bluetooth connection with the mobile terminal of the user if the ECG signal analysis condition of the target classification is focused by the user, the user is automatically informed of the ECG signal classification condition of the user through prompt information, and when the probability is lower, the ECG signal analysis condition of the non-target classification is not focused by the user is not required to be connected with the electrocardiograph and the mobile terminal by Bluetooth, and interference to the user is avoided.
As shown in fig. 2, in one embodiment of the present invention, an electrocardiograph quick auxiliary matching method based on bluetooth transmission is provided, and compared with the foregoing embodiment, the electrocardiograph quick auxiliary matching method based on bluetooth transmission in this embodiment further includes, before step S150:
Step S210, collecting geographic coordinate information of the position of the user at the current moment t based on the mobile terminal of the user )。
Step S220, calculating the distance between the position of the user at the current time t and a plurality of preset target positions, wherein when the number of the target positions is m, the distance between the position of the user at the current time t and the kth target position in the target positions isWherein the geographic location information of the kth target location is (/ >)。
In this embodiment, the plurality of target locations may be a user's residence, workplace, or the like.
Step S230, atWhen the user is at the current moment t, calculating the distance/>, between the position of the user at the current moment t and the position of the user at the historical moment t-1The geographical location information of the user at the location of the historic time t-1 is (/ >)) Wherein/>Is a preset first reference distance.
In this embodiment, the first reference distance is not limited, and when the distance between the current position of the user and the positions of the house and the workplace is small, the user is more likely to be in a stationary state, and at this time, the distance between the positions of the user at two adjacent time points is calculated.
Step S240, e.gStep S150 is performed, wherein/>Is a preset second reference distance.
In this embodiment, the second reference distance is not limited, when the distance between the positions of two adjacent time points of the user is smaller, it is further described that the user may be in a static state, the user is more suitable for viewing the prompt information through the mobile terminal in the static state, at this time, the electrocardiograph is controlled to send the prompt information to the mobile terminal of the user, otherwise, the user is not suitable for viewing the prompt information through the mobile terminal in a non-static state, for example, when driving or walking, at this time, the prompt information is not sent, so as to avoid interference to the user.
As shown in fig. 3, in one embodiment of the present invention, an electrocardiograph quick auxiliary matching method based on bluetooth transmission is provided, and compared with the foregoing embodiment, the electrocardiograph quick auxiliary matching method based on bluetooth transmission in this embodiment further includes, before step S150:
Step S310, acquiring the gesture of the user at the current time t based on the mobile terminal of the user.
In this embodiment, the gesture of the user may be determined by the information of the gesture sensor in the mobile terminal.
Step S320, calculating the gesture change amplitude of the user according to the gesture of the user at the current time t and the gesture of the user at the historical time t-1.
In this embodiment, when the gesture change amplitude of the user is large, the user is often in a motion state, and when the gesture change amplitude of the user is small, the user is often in a stationary state.
Step S330, judging whether the user is in a motion state according to the gesture change amplitude of the user.
Step S340, when it is determined that the user is not in a motion state, step S150 is performed.
In this embodiment, the user is more suitable for viewing the prompt information through the mobile terminal in the non-motion state, and controls the electrocardiograph to send the prompt information to the user mobile terminal at this time, otherwise, the user is not suitable for viewing the prompt information through the mobile terminal in the motion state, and does not send the prompt information at this time, so as to avoid causing interference to the user.
As shown in fig. 4, in an embodiment of the present invention, an electrocardiograph quick auxiliary matching method based on bluetooth transmission is provided, and compared with the foregoing embodiment, step S110 includes:
step S410 extracts wavelet coefficients a for any position on the user' S ECG signal.
Step S420, the wavelet coefficient a of the ECG signal of the user is modified, and the modified new wavelet coefficient is: Where N is the length of the user's ECG signal.
Step S430, reconstructing the ECG signal of the user based on the modified new wavelet coefficients.
In this embodiment, a wavelet coefficient correction formula is designed according to the length of the ECG signal, and experiments prove that the noise interference in the original ECG signal can be significantly reduced by calculating a new wavelet coefficient according to the formula and realizing the reconstruction of the ECG signal.
Compared with the foregoing embodiment, the Bluetooth transmission-based electrocardiograph quick auxiliary matching method provided in one embodiment of the present invention, wherein one of a plurality of analysis models is a CNN network, and when training the CNN network, the change value of any parameter is as followsWherein/>And b is the trained times of the CNN network, and R is a preset change weight.
According to the technical scheme of the embodiment, the analysis of the ECG signal is realized by using the CNN network (convolutional neural network), and in order to improve the accuracy of analysis results of the CNN network, a formula for gradually reducing parameter change values along with the training times of the CNN network is designed, so that the parameter change in the training process is smaller and smaller, and the accuracy is improved.
As shown in fig. 5, in one embodiment of the present invention, an electrocardiograph quick auxiliary matching method based on bluetooth transmission is provided, and compared with the foregoing embodiment, the electrocardiograph quick auxiliary matching method based on bluetooth transmission in this embodiment, step S150 further includes:
In step S510, a pre-recorded notification mode corresponding to the target classification is queried, where the notification mode includes one or more of vibration, text notification, and voice playing.
In this embodiment, for example, when the target classification matches the type a heart disease, the prompting is performed through text notification, and when the target classification matches the type B heart disease, the voice playing function can be started to prompt the user through voice, that is, different modes can be selected to prompt the user according to different classifications of ECG matching.
Step S520, the mobile terminal of the user is controlled to inform the user to view the prompt information according to the informing mode corresponding to the target classification.
In step S530, when the time for sending the prompt message to the mobile terminal of the user exceeds the preset time length, it is checked whether the user has checked the prompt message.
Step S540, when the user does not view the prompt information, the contact information of the contact person of the user is inquired from the mobile terminal of the user.
Step S550, according to the contact information of the contact person, the prompt information is sent to the mobile terminal of the contact person.
In this embodiment, since the ECG signal of the user is monitored, for example, if the target classification matches a certain heart disease, and the user does not view the prompt message for a long time, it indicates that there is a possibility of the occurrence of the user's dirty disease, and at this time, the user contacts are automatically searched for the address book to select the user contacts, and the user contacts are notified of the situation in time.
As shown in fig. 6, in one embodiment of the present invention, there is provided an electrocardiograph rapid auxiliary matching system based on bluetooth transmission, including:
the signal acquisition module 610 acquires the user's ECG signal based on the electrocardiograph carried by the user.
In this embodiment, the ECG signal is an electrocardiogram signal, and the electrocardiograph is a portable or wearable device, and has a bluetooth transmission module, which can be connected with a mobile terminal (such as a mobile phone) of a user by bluetooth, and transmit an ECG signal analysis result.
The first probability calculation module 620 inputs the ECG signal of the user into a plurality of analysis models trained based on deep learning, outputs a first probability of whether the ECG signal of the user belongs to the target class from the plurality of analysis models, and when the number of the plurality of analysis models is n, the first probability of whether the ECG signal of the user output by the i-th analysis model belongs to the target class isX represents the ECG signal of the user, and a plurality of analysis models have corresponding weights, so that the weight corresponding to the ith analysis model is/>，/>Representing a sample ECG signal,/>A first probability indicating whether the sample ECG signal output by the ith analysis model belongs to the target class,/>A first probability indicating whether a sample ECG signal output by a j-th analysis model of the plurality of analysis models belongs to a target classification.
In this embodiment, the target classification is not limited, and for example, the target classification may be a classification corresponding to a certain heart disease.
The second probability calculation module 630 sums up the first probabilities of whether the ECG signals of the user output by the multiple analysis models belong to the target classification based on weights corresponding to the preset multiple analysis models, to obtain a second probability of whether the ECG signals of the user belong to the target classification。
In this embodiment, it is easy to understand by those skilled in the art that higher accuracy is required for data analysis of ECG signals, so that a plurality of analysis models based on deep learning are used for analysis at the same time to obtain a plurality of first probabilities reflecting whether ECG signals of users belong to target classifications, and the performances of the plurality of data analysis models may be different, so that there may be a difference between the plurality of first probabilities reflecting whether ECG signals of users belong to target classifications, and the first probabilities output by the plurality of analysis models are reasonably integrated.
The matching module 640 is configured to determine whether the second probability that the ECG signal of the user belongs to the target class exceeds a preset value, and match the second probability that the ECG signal of the user belongs to the target class with a mobile terminal carried by the user through the bluetooth transmission module of the electrocardiograph when the second probability that the ECG signal of the user belongs to the target class exceeds the preset value.
In this embodiment, assuming that the target classification is a classification corresponding to a certain heart disease, when the second probability is high, it is indicated that the probability that the ECG signal of the user belongs to the classification corresponding to the certain heart disease is high, at this time, the electrocardiograph is controlled to perform bluetooth connection with the mobile terminal of the user, and when the second probability is low, it is indicated that the probability that the ECG signal of the user belongs to the classification corresponding to the certain heart disease is low, at this time, the electrocardiograph and the mobile terminal do not need to be connected through bluetooth.
The prompting module 650 sends prompting information related to the target classification to the mobile terminal of the user through the bluetooth transmission module, and is used for prompting whether the ECG signal of the user belongs to the possibility of the target classification.
In this embodiment, after the electrocardiograph is connected with the mobile terminal of the user through bluetooth, prompt information related to the target classification (for example, ECG signals of the user reflect that a certain heart disease may exist in the user) can be timely sent to the user.
According to the technical scheme of the embodiment, a user does not need to manually control Bluetooth transmission between an electrocardiograph and a mobile terminal, analysis is performed by utilizing a plurality of analysis models based on deep learning after the electrocardiograph detects ECG signals of the user, after target classification (such as heart diseases) is identified, in order to ensure that an identification result is correct, integrated calculation is performed on results of the plurality of analysis models, weight corresponding to the result of each analysis model in the calculation process is reasonably set according to the analysis condition of sample data by the analysis model, so that probability that whether the ECG signals of the user belong to the target classification can be accurately reflected is finally obtained, when the probability is higher, the electrocardiograph is controlled to be in Bluetooth connection with the mobile terminal of the user if the ECG signal analysis condition of the target classification is focused by the user, the user is automatically informed of the ECG signal classification condition of the user through prompt information, and when the probability is lower, the ECG signal analysis condition of the non-target classification is not focused by the user is not required to be connected with the electrocardiograph and the mobile terminal by Bluetooth, and interference to the user is avoided.
The basic principles of the present application have been described above in connection with specific embodiments, but it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be construed as necessarily possessed by the various embodiments of the application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (7)
1. An electrocardiograph quick auxiliary matching method based on Bluetooth transmission is characterized by comprising the following steps of:
acquiring an ECG signal of a user based on an electrocardiograph carried by the user;
Inputting the ECG signal of the user into a plurality of analysis models based on deep learning training, outputting a first probability of whether the ECG signal of the user belongs to a target class by the plurality of analysis models, wherein when the number of the plurality of analysis models is n, the first probability of whether the ECG signal of the user output by an ith analysis model belongs to the target class is p i (X), X represents the ECG signal of the user, the plurality of analysis models all have corresponding weights, and the weight corresponding to the ith analysis model is X 0 denotes a sample ECG signal, p i(X0) denotes a first probability of whether the sample ECG signal output by the i-th analysis model belongs to the target class, p j(X0) denotes a first probability of whether the sample ECG signal output by the j-th analysis model of the plurality of analysis models belongs to the target class;
Summarizing a first probability of whether the ECG signals of the user output by the plurality of analysis models belong to the target classification based on preset weights corresponding to the plurality of analysis models, so as to obtain a second probability of whether the ECG signals of the user belong to the target classification
Judging whether the second probability of whether the ECG signal of the user belongs to the target classification exceeds a preset value, and matching the ECG signal of the user with a mobile terminal carried by the user through a Bluetooth transmission module of the electrocardiograph when the second probability of whether the ECG signal of the user belongs to the target classification exceeds the preset value;
the Bluetooth transmission module is used for sending prompt information related to the target classification to the mobile terminal of the user and prompting the possibility that the ECG signal of the user belongs to the target classification;
Before the step of sending the prompt information related to the target classification to the mobile terminal of the user through the bluetooth transmission module, the method further comprises:
Collecting geographic coordinate information (x t,yt) of the position of the user at the current moment t based on the mobile terminal of the user;
calculating the distance between the position of the user at the current moment t and a plurality of preset target positions, wherein when the number of the target positions is m, the distance between the position of the user at the current moment t and the kth target position in the target positions is Wherein the geographic location information of the kth target location is (x k,yk);
At the position of When the method is used, a step of sending prompt information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module is executed, wherein L 0 is a preset first reference distance;
before the step of sending the prompt information related to the target classification to the mobile terminal of the user through the bluetooth transmission module is performed, the method further comprises:
calculating the distance between the position of the user at the current time t and the position of the user at the historical time t-1 The geographic position information of the position of the user at the historical time t-1 is (x t-1,yt-1);
In determining And if L < L 0 ', executing the step of sending the prompt information related to the target classification to the mobile terminal of the user through the bluetooth transmission module, wherein L 0' is a preset second reference distance.
2. The bluetooth transmission-based electrocardiograph rapid assisted matching method according to claim 1, further comprising, before the step of transmitting the prompt information related to the target classification to the user's mobile terminal through the bluetooth transmission module:
acquiring the gesture of the user at the current time t based on the mobile terminal of the user;
Calculating the gesture change amplitude of the user according to the gesture of the user at the current time t and the gesture of the user at the historical time t-1;
Judging whether the user is in a motion state according to the gesture change amplitude of the user;
And when the user is not in the motion state, executing the step of sending prompt information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module.
3. The bluetooth transmission based electrocardiograph rapid assisted matching method according to claim 1, wherein the step of acquiring the ECG signal of the user based on the electrocardiograph carried by the user further comprises:
Extracting a wavelet coefficient a of the ECG signal wavelet conversion processing of the user;
Correcting the wavelet coefficient a of the ECG signal of the user, wherein the corrected new wavelet coefficient is as follows: Where N is the length of the user's ECG signal;
and reconstructing the ECG signal of the user based on the modified new wavelet coefficient.
4. The method for rapid assisted matching of a bluetooth transmission based electrocardiograph according to claim 1, wherein,
One of the analysis models is a CNN network, and when the CNN network is trained, the change value of any CNN network parameter is as followsWherein R is an initial change value of the parameter, b is the trained times of the CNN network, and R is a preset change weight.
5. The bluetooth transmission-based electrocardiograph rapid assisted matching method according to claim 1, wherein the step of transmitting the prompt information related to the target classification to the user's mobile terminal through the bluetooth transmission module further comprises:
Inquiring a pre-recorded notification mode corresponding to the target classification, wherein the notification mode comprises one or more of vibration, text notification and voice playing;
And controlling the mobile terminal of the user to inform the user to view the prompt information according to the informing mode corresponding to the target classification.
6. The bluetooth transmission based electrocardiograph rapid assisted matching method according to claim 5, further comprising:
When the time for sending the prompt information to the mobile terminal of the user exceeds a preset time length, checking whether the user has checked the prompt information;
inquiring the contact information of the contact person of the user from the mobile terminal of the user when the user does not view the prompt information;
and sending the prompt information to the mobile terminal of the contact person according to the contact way of the contact person.
7. An electrocardiograph quick auxiliary matching system based on Bluetooth transmission, which is characterized by comprising:
the signal acquisition module is used for acquiring an ECG signal of a user based on an electrocardiograph carried by the user;
A first probability calculation module, for inputting the ECG signal of the user into a plurality of analysis models trained based on deep learning, outputting a first probability of whether the ECG signal of the user belongs to a target class by the plurality of analysis models, when the number of the plurality of analysis models is n, the first probability of whether the ECG signal of the user output by the ith analysis model belongs to the target class is p i (X), X represents the ECG signal of the user, the plurality of analysis models all have corresponding weights, and the weight corresponding to the ith analysis model is X 0 denotes a sample ECG signal, p i(X0) denotes a first probability of whether the sample ECG signal output by the i-th analysis model belongs to the target class, p j(X0) denotes a first probability of whether the sample ECG signal output by the j-th analysis model of the plurality of analysis models belongs to the target class;
The second probability calculation module is used for summarizing the first probability of whether the ECG signals of the user belong to the target classification or not based on the weights corresponding to the preset analysis models, so as to obtain the second probability of whether the ECG signals of the user belong to the target classification or not
The matching module is used for judging whether the second probability of the ECG signal of the user belonging to the target classification exceeds a preset value, and matching the ECG signal of the user belonging to the target classification with the mobile terminal carried by the user through the Bluetooth transmission module of the electrocardiograph when the second probability of the ECG signal of the user belonging to the target classification exceeds the preset value;
The prompting module is used for sending prompting information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module and prompting the possibility that the ECG signal of the user belongs to the target classification;
Before the step of sending the prompt information related to the target classification to the mobile terminal of the user through the bluetooth transmission module, the method further comprises:
Collecting geographic coordinate information (x t,yt) of the position of the user at the current moment t based on the mobile terminal of the user;
calculating the distance between the position of the user at the current moment t and a plurality of preset target positions, wherein when the number of the target positions is m, the distance between the position of the user at the current moment t and the kth target position in the target positions is Wherein the geographic location information of the kth target location is (x k,yk);
At the position of When the method is used, a step of sending prompt information related to the target classification to the mobile terminal of the user through the Bluetooth transmission module is executed, wherein L 0 is a preset first reference distance;
before the step of sending the prompt information related to the target classification to the mobile terminal of the user through the bluetooth transmission module is performed, the method further comprises:
calculating the distance between the position of the user at the current time t and the position of the user at the historical time t-1 The geographic position information of the position of the user at the historical time t-1 is (x t-1,yt-1);
In determining And if L < L 0 ', executing the step of sending the prompt information related to the target classification to the mobile terminal of the user through the bluetooth transmission module, wherein L 0' is a preset second reference distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410176797.4A CN117717351B (en) | 2024-02-08 | 2024-02-08 | Bluetooth transmission-based electrocardiograph quick auxiliary matching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410176797.4A CN117717351B (en) | 2024-02-08 | 2024-02-08 | Bluetooth transmission-based electrocardiograph quick auxiliary matching method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117717351A CN117717351A (en) | 2024-03-19 |
| CN117717351B true CN117717351B (en) | 2024-05-14 |
Family
ID=90200195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410176797.4A Active CN117717351B (en) | 2024-02-08 | 2024-02-08 | Bluetooth transmission-based electrocardiograph quick auxiliary matching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117717351B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107708192A (en) * | 2017-10-11 | 2018-02-16 | 普联技术有限公司 | A kind of method and device of automatic switchover bluetooth mode of operation |
| CN110974216A (en) * | 2019-12-20 | 2020-04-10 | 首都医科大学宣武医院 | Remote control system of wireless electrocardiogram monitoring sensor |
| CN112106074A (en) * | 2018-05-01 | 2020-12-18 | 国际商业机器公司 | Seizure detection and prediction using techniques such as deep learning methods |
| CN112603327A (en) * | 2019-12-18 | 2021-04-06 | 华为技术有限公司 | Electrocardiosignal detection method, device, terminal and storage medium |
| KR20210126803A (en) * | 2020-04-10 | 2021-10-21 | 최서안 | Vehicle control system via smart cruise control during cardiac arrest using heartbeat sensor smart band |
| CN114429816A (en) * | 2021-12-29 | 2022-05-03 | 海南视联大健康智慧医疗科技有限公司 | Electrocardiogram analysis method, device, equipment and medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516896A (en) * | 2015-12-02 | 2016-04-20 | 惠州Tcl移动通信有限公司 | Bluetooth interconnection method and system for wearable device and mobile terminal |
| US10963757B2 (en) * | 2018-12-14 | 2021-03-30 | Industrial Technology Research Institute | Neural network model fusion method and electronic device using the same |
| CN114338585A (en) * | 2021-11-30 | 2022-04-12 | 青岛海尔科技有限公司 | Message pushing method and device, storage medium and electronic device |
-
2024
- 2024-02-08 CN CN202410176797.4A patent/CN117717351B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107708192A (en) * | 2017-10-11 | 2018-02-16 | 普联技术有限公司 | A kind of method and device of automatic switchover bluetooth mode of operation |
| CN112106074A (en) * | 2018-05-01 | 2020-12-18 | 国际商业机器公司 | Seizure detection and prediction using techniques such as deep learning methods |
| CN112603327A (en) * | 2019-12-18 | 2021-04-06 | 华为技术有限公司 | Electrocardiosignal detection method, device, terminal and storage medium |
| CN110974216A (en) * | 2019-12-20 | 2020-04-10 | 首都医科大学宣武医院 | Remote control system of wireless electrocardiogram monitoring sensor |
| KR20210126803A (en) * | 2020-04-10 | 2021-10-21 | 최서안 | Vehicle control system via smart cruise control during cardiac arrest using heartbeat sensor smart band |
| CN114429816A (en) * | 2021-12-29 | 2022-05-03 | 海南视联大健康智慧医疗科技有限公司 | Electrocardiogram analysis method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117717351A (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3992845A1 (en) | Action identification method based on artificial intelligence and related apparatus | |
| US20190385066A1 (en) | Method for predicting emotion status and robot | |
| CN105009204B (en) | Speech recognition power management | |
| CN108735209B (en) | Wake-up word binding method, intelligent device and storage medium | |
| CN110033851B (en) | Information recommendation method and device, storage medium and server | |
| CN110096580B (en) | FAQ conversation method and device and electronic equipment | |
| EP3923273B1 (en) | Voice recognition method and device, storage medium, and air conditioner | |
| JP2016126330A (en) | Speech recognition device and speech recognition method | |
| CN110599557A (en) | Image description generation method, model training method, device and storage medium | |
| CN111105852B (en) | Electronic medical record recommendation method, device, terminal and storage medium | |
| JP7285589B2 (en) | INTERACTIVE HEALTH CONDITION EVALUATION METHOD AND SYSTEM THEREOF | |
| CN107515900B (en) | Intelligent robot and event memo system and method thereof | |
| CN111754998B (en) | Artificial intelligence device and method of operating an artificial intelligence device | |
| CN111192574A (en) | Intelligent voice interaction method, mobile terminal and computer readable storage medium | |
| CN111951943B (en) | Intelligent triage method and device, electronic equipment and storage medium | |
| CN111510357A (en) | Health state detection method, system and device, intelligent sound box and storage medium | |
| US20200121277A1 (en) | Systems and methods for detecting physiological information using a smart stethoscope | |
| EP4097992B1 (en) | Use of a camera for hearing device algorithm training. | |
| CN113177928A (en) | Image identification method and device, electronic equipment and storage medium | |
| CN104977038B (en) | Identifying movement using motion sensing device coupled with associative memory | |
| CN117717351B (en) | Bluetooth transmission-based electrocardiograph quick auxiliary matching method and system | |
| CN111883261B (en) | Epidemic situation self-checking method, device, computer equipment and storage medium | |
| EP3826009A1 (en) | Electronic device and method for controlling the same, and storage medium | |
| CN116416545A (en) | Behavior detection method, apparatus, device and computer readable storage medium | |
| Santos et al. | Context inference for mobile applications in the UPCASE project |
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 |