CN106778561B - Identity recognition method and device of wearable equipment - Google Patents
Identity recognition method and device of wearable equipment Download PDFInfo
- Publication number
- CN106778561B CN106778561B CN201611095517.9A CN201611095517A CN106778561B CN 106778561 B CN106778561 B CN 106778561B CN 201611095517 A CN201611095517 A CN 201611095517A CN 106778561 B CN106778561 B CN 106778561B
- Authority
- CN
- China
- Prior art keywords
- user
- waves
- parameters
- wave
- amplitude
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The identity recognition method or the identity recognition device of the wearable device obtains the ratio of the R wave amplitude to the T wave amplitude of the user and the QTC time interval according to the filtered and denoised electrocardiosignals, and compares the two parameters serving as the judgment standard of the user identity with the pre-stored characteristic template so as to determine the user identity. Compared with the prior art that only the peak value or the initial point of various waves is used as a judgment standard, the ratio of the amplitude of the R wave to the amplitude of the T wave and the time interval of the QTC are used as important judgment parameters, and the two parameters are more stable, so that the judgment is more accurate; and the two parameters are extracted based on the real-domain characteristics of the electrocardiosignals, so that the calculated amount is lower, and the power consumption of the wearable device can be reduced.
Description
Technical Field
The invention belongs to the technical field of identity recognition, and particularly relates to an identity recognition method and an identity recognition device of wearable equipment.
Background
The wearable device is small in size, most of functional designs are related to personal health data or personal motion data, and when the personal data fed back by the wearable device are managed and analyzed, a manager cannot know whether the current data are data of the owner of the wearable device easily, and misjudgment easily occurs. Therefore, the wearable device mostly needs to identify the identity of the user.
The most adopted methods in the market of the existing identity recognition methods are two methods:
one method is to use a camera or fingerprint recognition technology to identify the identity of an individual, and the product prepared by the method is expensive in cost, complex in structure and not suitable for being applied to wearable equipment with a small size.
Another common method is to use Electrocardiogram (ECG) technology for personal identification. The electrocardiogram has been demonstrated by academia as an important feature for human body identification, and the electrocardiogram identification technology usually compares the user electrocardiogram features with an electrocardiogram feature template library to identify the individual identity. The method can save cost and popularize products. However, when the wearable device in the market collects the personal electrocardiogram characteristic parameters, the peak value or the start-stop point of each wave is generally used as the characteristic parameter to perform judgment or calculation independently based on the PQRST, the result obtained by the judgment method is often inaccurate, and very large calculation is needed, especially analysis of the frequency domain consumes very much calculation, so that the power consumption of the wearable device is wasted.
Disclosure of Invention
The invention provides an identity recognition method and an identity recognition device of wearable equipment, and aims to solve the problems of inaccurate identity recognition and waste of power consumption.
In order to solve the technical problem, the invention provides an identity recognition method of wearable equipment, which comprises the following steps:
carrying out filtering and denoising processing on the acquired electrocardiosignals of the user;
obtaining the electrocardiosignal characteristic parameters of the user according to the filtered and denoised electrocardiosignals, wherein the electrocardiosignal characteristic parameters at least comprise: the ratio of the amplitude of the R wave to the amplitude of the T wave, and the time interval of the QTC;
matching the electrocardiosignal characteristic parameters with the electrocardiosignal characteristic template in the mapping relation based on the mapping relation between the prestored electrocardiosignal characteristic template and the user identity, and identifying the user identity based on the matching result.
Further, before performing filtering and denoising processing on the acquired electrocardiosignals of the user, the method further includes: acquiring a heart rate change result of a user by adopting a photoelectric volume pulse wave tracing technology; determining that the wearable device is out of hand by combining the heart rate variation result; if the judgment result is that the user is not out of hand, determining the user identity as the user identified last time; and if the judgment result is that the user is away from the hand, executing the step of filtering and denoising the acquired electrocardiosignals of the user.
Further, the characteristic parameters of the cardiac signal further include: time interval of QR, time interval of QRs.
Further, the method further comprises: and after the user identity is successfully identified, the electrocardiosignal characteristic parameters are used as the latest characteristic template, and the electrocardiosignal characteristic parameters are utilized to update the original electrocardiosignal characteristic template of the user in the mapping relation.
Further, the method further comprises: if the user identity is not identified, determining that the user is a new user, acquiring the identity information of the new user, and storing the mapping relation between the identity information and the electrocardiosignal characteristic parameters.
The invention also provides an identity recognition device of the wearable equipment, which comprises:
the acquisition denoising module is used for carrying out filtering denoising processing on the acquired electrocardiosignals of the user;
the characteristic extraction module is used for obtaining the electrocardiosignal characteristic parameters of the user according to the filtered and denoised electrocardiosignals, and the electrocardiosignal characteristic parameters at least comprise: the ratio of the amplitude of the R wave to the amplitude of the T wave, and the time interval of the QTC;
and the identification module is used for matching the electrocardiosignal characteristic parameters with the electrocardiosignal characteristic template in the mapping relation based on the mapping relation between the prestored electrocardiosignal characteristic template and the user identity and identifying the user identity based on the matching result.
Further, the device further comprises a hand-off judging module, wherein the hand-off judging module is specifically used for: acquiring a heart rate change result of a user by adopting a photoelectric volume pulse wave tracing technology; determining that the wearable device is out of hand by combining the heart rate variation result; if the judgment result is that the user is not out of hand, determining the user identity as the user identified last time; and if the judgment result is that the user leaves the hand, executing the operation of the denoising module.
Further, the characteristic parameters of the cardiac signal further include: time interval of QR, time interval of QRs.
Further, the apparatus further comprises: and the updating module is used for taking the electrocardiosignal characteristic parameters as the latest characteristic template after the identity of the user is successfully identified, and updating the original electrocardiosignal characteristic template of the user in the mapping relation by utilizing the electrocardiosignal characteristic parameters.
Further, the apparatus further comprises: and the new user recording module is used for determining that the user is a new user if the user identity is not identified, acquiring the identity information of the new user and storing the mapping relation between the identity information and the electrocardiosignal characteristic parameters.
Compared with the prior art, the invention has the beneficial effects that:
the method or the device provided by the invention obtains the ratio of the amplitude of the R wave to the amplitude of the T wave of the user and the time interval of the QTC according to the filtered and denoised electrocardiosignals, and compares the two parameters serving as the judgment standard of the user identity with the pre-stored characteristic template so as to determine the user identity. Compared with the prior art that only the peak value or the initial point of various waves is used as a judgment standard, the ratio of the amplitude of the R wave to the amplitude of the T wave and the time interval of the QTC are used as important judgment parameters, and the two parameters are more stable, so that the judgment is more accurate; and the two parameters are extracted based on the real-domain characteristics of the electrocardiosignals, so that the calculated amount is lower, and the power consumption of the wearable device can be reduced.
Drawings
Fig. 1 is a flowchart of an identity recognition method of a wearable device according to a first embodiment of the present invention;
fig. 2 is a flowchart of an identity recognition method of a wearable device according to a second embodiment of the present invention;
fig. 3 is a schematic view of an identification device of a wearable device according to a third embodiment of the present invention;
fig. 4 is a schematic view of an identification device of a wearable device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As a first embodiment of the present invention, as shown in fig. 1, the present invention provides an identity recognition method for a wearable device, the method including:
step S101: and carrying out filtering and denoising processing on the acquired electrocardiosignals of the user.
Step S102: obtaining the characteristic parameters of the electrocardiosignals of the user according to the filtered and denoised electrocardiosignals, wherein the characteristic parameters of the electrocardiosignals at least comprise: the ratio of the amplitude of the R wave to the amplitude of the T wave, and the time interval of the QTC.
Wherein, step S102 specifically includes: respectively extracting parameters of start points and stop points of Q waves, R waves, S waves and T waves in the electrocardiosignals subjected to filtering and denoising, and respectively extracting amplitude parameters of the R waves and the T waves; and respectively calculating QTC time intervals based on the start-stop point parameters of the Q wave, the R wave, the S wave and the T wave, and calculating the ratio of the amplitude of the R wave to the amplitude of the T wave based on the amplitude parameters of the R wave and the T wave.
It should be noted that Q wave, R wave, S wave, T wave, and QTC are all basic indexes or parameters in the current field of electrocardiogram, and therefore, they are not explained in detail in the present invention.
Step S103: based on the mapping relation between the pre-stored electrocardiosignal characteristic template and the user identity, matching the electrocardiosignal characteristic parameters of the user with the electrocardiosignal characteristic template in the mapping relation, and identifying the user identity based on the matching result.
In summary, the method provided in the first embodiment of the present invention obtains the ratio of the R wave amplitude to the T wave amplitude of the user and the QTC time interval according to the filtered and denoised electrocardiographic signal, and compares the two parameters serving as the judgment standard of the user identity with the pre-stored characteristic template, thereby determining the user identity. Compared with the prior art that only the peak value or the initial point of various waves is used as a judgment standard, the ratio of the amplitude of the R wave to the amplitude of the T wave and the time interval of the QTC are used as important judgment parameters, and the two parameters are more stable, so that the judgment is more accurate; and the two parameters are extracted based on the real-domain characteristics of the electrocardiosignals, so that the calculated amount is lower, and the power consumption of the wearable device can be reduced.
As a second embodiment of the present invention, as shown in fig. 2, the present invention provides an identity recognition method for a wearable device, the method including:
step S201: adopt the photoplethysmography technique (PPG, photoplethysmography) to obtain user's heart rate variation result, combine this heart rate variation result to carry out the judgement of leaving one's hand to wearable equipment: if the judgment result is that the user is not out of hand, determining that the user identity is still the user identified last time; if the judgment result is that the user is away from the hand, step S202 is executed.
The PPG technique and the hands-off determination method are both prior art, and are not described in detail in the present invention. In step S201, the PPG technique is applied to a hands-off determination method, and the PPG technique first determines the heart rate change of the user based on the principle of light reflection, and then further determines hands-off according to the heart rate change result.
Step S202: and carrying out filtering and denoising processing on the acquired electrocardiosignals of the user.
Step S203: obtaining the characteristic parameters of the electrocardiosignals of the user according to the filtered and denoised electrocardiosignals, wherein the characteristic parameters of the electrocardiosignals at least comprise: the ratio of the amplitude of the R wave to the amplitude of the T wave, and the time interval of the QTC. Further, the characteristic parameters of the cardiac signal further include: time interval of QR, time interval of QRs.
The ratio of the amplitude of the R wave to the amplitude of the T wave and the time interval of the QTC are used as important judgment parameters, and the two parameters are more stable, so that the judgment is more accurate; and the two parameters are extracted based on the real-domain characteristics of the electrocardiosignals, so that the calculated amount is lower, and the power consumption of the wearable device can be reduced. Meanwhile, the time interval of QR and the time interval of QRS also have higher stability, the time interval of QR and the time interval of QRS are used as judgment parameters, so that the judgment is more accurate, the two parameters are extracted based on the real-domain features of the electrocardiosignals, the calculated amount is lower, and the power consumption of the wearable device can be reduced.
Step S203 includes: respectively extracting parameters of start points and stop points of Q waves, R waves, S waves and T waves in the electrocardiosignals subjected to filtering and denoising, and respectively extracting amplitude parameters of the R waves and the T waves; respectively calculating a QR time interval, a QRS time interval and a QTC time interval based on the start and stop point parameters of Q waves, R waves, S waves and T waves, and calculating the ratio of the amplitude of the R waves to the amplitude of the T waves based on the amplitude parameters of the R waves and the T waves.
It should be noted that Q wave, R wave, S wave and T wave, as well as QR, QRs and QTC are all basic indexes or parameters in the current field of electrocardiogram, and therefore, they are not explained in detail in the present invention.
Step S204: and matching the electrocardiosignal characteristic parameters obtained in the step S203 with the electrocardiosignal characteristic template in the mapping relation based on the mapping relation between the prestored electrocardiosignal characteristic template and the user identity, and identifying the user identity based on the matching result.
If the user identity is successfully identified, executing step S205; if the matching result indicates that the user identity is not recognized, indicating that the user is a new user, step S206 is performed.
Step S205: after the identity of the user is successfully identified, the electrocardiosignal characteristic parameters are used as the latest characteristic template, and the electrocardiosignal characteristic parameters are utilized to update the original electrocardiosignal characteristic template of the user in the mapping relation.
Because the electrocardiographic signal feature of each user changes with time, in this embodiment, step S205 updates the original electrocardiographic signal feature template of the user every time, so as to ensure that the electrocardiographic signal feature template of the user is always in the latest and optimized state, thereby being capable of identifying the identity of the user more accurately. Further, the present invention can set the execution process of step S205 to be performed in the idle time of the wearable device, and does not occupy the working time of the wearable device, so as not to reduce the working efficiency of the wearable device.
Step S206: if the user identity is not identified, determining that the user is a new user, acquiring the identity information of the new user, and storing the mapping relation between the identity information of the new user and the electrocardiosignal characteristic parameters of the user.
It should be noted that, before the electrocardiosignal characteristic parameters are used for user identity identification, the invention firstly adopts the hands-off judgment technology to judge whether the user takes the wearable device away from the hands, if the judgment result is that the user does not take the hands, the current user identity can be determined as the user identified last time, and the steps from S202 to S205 do not need to be executed again to identify the user identity repeatedly. Therefore, the operation of obtaining, filtering and denoising, extracting the characteristic parameters of the electrocardiosignals and comparing the characteristic parameters of the electrocardiosignals with the preset template is avoided by performing the operation of judging the user identity before the user is left, so that a plurality of calculation processes are avoided, the calculated amount is greatly reduced, the power consumption of the wearable device is reduced, and the efficiency of the wearable device for identifying the user identity is greatly improved.
It should be noted that, when the user uses the wearable device for the first time, the user may input his/her own identity information, the wearable device stores the mapping relationship between the identity information and the characteristic parameters of the electrocardiographic signals, and the wearable device stores the characteristic parameters of the electrocardiographic signals acquired for the first time as the characteristic template of the electrocardiographic signals of the user in advance.
In summary, the method provided by the second embodiment of the present invention has the advantages of more accurate determination, lower computation, and reduced power consumption of the wearable device, thereby greatly improving the efficiency of the wearable device in identifying the user identity.
As a third embodiment of the present invention, as shown in fig. 3, the present invention provides an identity recognition apparatus for a wearable device, which includes an acquisition denoising module 11, a feature extraction module 22, and a recognition module 33.
And the acquiring and denoising module 11 is used for performing filtering and denoising processing on the acquired electrocardiosignals of the user.
The feature extraction module 22 is configured to obtain an electrocardiographic signal feature parameter of the user according to the filtered and denoised electrocardiographic signal, where the electrocardiographic signal feature parameter at least includes: the ratio of the amplitude of the R wave to the amplitude of the T wave, and the time interval of the QTC.
The feature extraction module 22 is specifically configured to: respectively extracting parameters of start points and stop points of Q waves, R waves, S waves and T waves in the electrocardiosignals subjected to filtering and denoising, and respectively extracting amplitude parameters of the R waves and the T waves; and respectively calculating QTC time intervals based on the start-stop point parameters of the Q wave, the R wave, the S wave and the T wave, and calculating the ratio of the amplitude of the R wave to the amplitude of the T wave based on the amplitude parameters of the R wave and the T wave.
It should be noted that Q wave, R wave, S wave, T wave, and QTC are all basic indexes or parameters in the current field of electrocardiogram, and therefore, they are not explained in detail in the present invention.
The identification module 33 is configured to match the electrocardiographic signal characteristic parameters of the user with the electrocardiographic signal characteristic templates in the mapping relationship based on the mapping relationship between the prestored electrocardiographic signal characteristic templates and the user identities, and identify the user identities based on the matching results.
In summary, in the apparatus provided in the third embodiment of the present invention, the apparatus obtains the ratio of the R wave amplitude to the T wave amplitude and the QTC time interval of the user according to the filtered and denoised electrocardiographic signal, and compares the two parameters serving as the criterion of the user identity with the pre-stored characteristic template, thereby determining the user identity. Compared with the prior art that only the peak value or the initial point of various waves is used as a judgment standard, the ratio of the amplitude of the R wave to the amplitude of the T wave and the time interval of the QTC are used as important judgment parameters, and the two parameters are more stable, so that the judgment is more accurate; and the two parameters are extracted based on the real-domain characteristics of the electrocardiosignals, so that the calculated amount is lower, and the power consumption of the wearable device can be reduced.
As a fourth embodiment of the present invention, as shown in fig. 4, the present invention provides an identity recognition apparatus for a wearable device, which includes an acquisition denoising module 11, a feature extraction module 22, a recognition module 33, a hands-off judgment module 44, an update module 55, and a new user recording module 66.
From hand judgement module 44 for adopt PPG technique to acquire user's rhythm of the heart change result, combine this rhythm of the heart change result to the wearable equipment judges from the hand: if the judgment result is that the user is not out of hand, determining that the user identity is still the user identified last time; if the judgment result is that the user is out of hand, the next step is operated by the acquiring denoising module 11.
The PPG technique and the hands-off determination method are both prior art, and are not described in detail in the present invention. In step S201, the PPG technique is applied to a hands-off determination method, and the PPG technique first determines the heart rate change of the user based on the principle of light reflection, and then further determines hands-off according to the heart rate change result.
And the acquiring and denoising module 11 is used for performing filtering and denoising processing on the acquired electrocardiosignals of the user.
The feature extraction module 22 is configured to obtain an electrocardiographic signal feature parameter of the user according to the filtered and denoised electrocardiographic signal, where the electrocardiographic signal feature parameter at least includes: the ratio of the amplitude of the R wave to the amplitude of the T wave, and the time interval of the QTC. Further, the characteristic parameters of the cardiac signal further include: time interval of QR, time interval of QRs.
The ratio of the amplitude of the R wave to the amplitude of the T wave and the time interval of the QTC are used as important judgment parameters, and the two parameters are more stable, so that the judgment is more accurate; and the two parameters are extracted based on the real-domain characteristics of the electrocardiosignals, so that the calculated amount is lower, and the power consumption of the wearable device can be reduced. Meanwhile, the time interval of QR and the time interval of QRS also have higher stability, the time interval of QR and the time interval of QRS are used as judgment parameters, so that the judgment is more accurate, and the two parameters are extracted based on the real-domain features of the electrocardiosignals, so that the calculation amount is lower, and the power consumption of the wearable device can be reduced.
It should be noted that the feature extraction module 22 is specifically configured to: respectively extracting parameters of start points and stop points of Q waves, R waves, S waves and T waves in the electrocardiosignals subjected to filtering and denoising, and respectively extracting amplitude parameters of the R waves and the T waves; respectively calculating a QR time interval, a QRS time interval and a QTC time interval based on the start and stop point parameters of Q waves, R waves, S waves and T waves, and calculating the ratio of the amplitude of the R waves to the amplitude of the T waves based on the amplitude parameters of the R waves and the T waves.
It should be noted that Q wave, R wave, S wave and T wave, as well as QR, QRs and QTC are all basic indexes or parameters in the current field of electrocardiogram, and therefore, they are not explained in detail in the present invention.
The identification module 33 is configured to match the electrocardiographic signal feature parameters obtained by the feature extraction module 22 with the electrocardiographic signal feature templates in the mapping relationship based on the pre-stored mapping relationship between the electrocardiographic signal feature templates and the user identities, and identify the user identities based on the matching results.
If the user identity is successfully identified, the next step is performed by the update module 55; if the matching result indicates that the user identity is not recognized, indicating that the user is a new user, the new user recording module 66 operates next.
And the updating module 55 is configured to, after the user identity is successfully identified, use the characteristic parameter of the electrocardiographic signal as the latest characteristic template, and update the original electrocardiographic signal characteristic template of the user in the mapping relationship by using the characteristic parameter of the electrocardiographic signal.
Because the electrocardiographic signal characteristic of each user changes with time, the updating module 55 in this embodiment updates the original electrocardiographic signal characteristic template of the user each time, so as to ensure that the electrocardiographic signal characteristic template of the user is always in the latest and optimized state, thereby identifying the user identity more accurately. Further, the present invention can set the execution process of the update module 55 to be performed in the idle time of the wearable device, and does not occupy the working time of the wearable device, thereby not reducing the working efficiency of the wearable device.
And the new user recording module 66 is configured to determine that the user is a new user if the identity of the user is not identified, acquire identity information of the new user, and store a mapping relationship between the identity information of the new user and the electrocardiographic signal characteristic parameter of the user.
It should be noted that, before the electrocardiosignal characteristic parameters are used for user identity identification, the invention firstly adopts the hands-off judgment technology to judge whether the user takes the wearable device away from the hands, if the judgment result is that the user does not take the hands, the current user identity can be determined as the user identified last time, and repeated operation of the modules 11 to 55 is not needed. Therefore, the operation of obtaining, filtering and denoising, extracting the characteristic parameters of the electrocardiosignals and comparing the characteristic parameters of the electrocardiosignals with the preset template is avoided by performing the operation of judging the user identity before the user is left, so that a plurality of calculation processes are avoided, the calculated amount is greatly reduced, the power consumption of the wearable device is reduced, and the efficiency of the wearable device for identifying the user identity is greatly improved.
It should be noted that, when the user uses the wearable device for the first time, the user may input his/her own identity information, the wearable device stores the mapping relationship between the identity information and the characteristic parameters of the electrocardiographic signals, and the wearable device stores the characteristic parameters of the electrocardiographic signals acquired for the first time as the characteristic template of the electrocardiographic signals of the user in advance.
In summary, the apparatus provided in the fourth embodiment of the present invention determines more accurately, calculates less amount, reduces power consumption of the wearable device, and greatly improves efficiency of the wearable device in identifying the user identity.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A method for identifying an identity of a wearable device, the method comprising:
carrying out filtering and denoising processing on the acquired electrocardiosignals of the user;
obtaining the electrocardiosignal characteristic parameters of the user according to the filtered and denoised electrocardiosignals, wherein the electrocardiosignal characteristic parameters at least comprise: the ratio of the amplitude of the R wave to the amplitude of the T wave, and the time interval of the QTC;
matching the electrocardiosignal characteristic parameters with the electrocardiosignal characteristic template in the mapping relation based on the mapping relation between the prestored electrocardiosignal characteristic template and the user identity, and identifying the user identity based on the matching result;
the characteristic parameters of the electrocardiosignals specifically comprise: respectively extracting parameters of start points and stop points of Q waves, R waves, S waves and T waves in the electrocardiosignals subjected to filtering and denoising, and respectively extracting amplitude parameters of the R waves and the T waves; and respectively calculating QTC time intervals based on the start-stop point parameters of the Q wave, the R wave, the S wave and the T wave, and calculating the ratio of the amplitude of the R wave to the amplitude of the T wave based on the amplitude parameters of the R wave and the T wave.
2. The method as claimed in claim 1, wherein said filtering and denoising the acquired cardiac signal of the user further comprises:
acquiring a heart rate change result of a user by adopting a photoelectric volume pulse wave tracing technology;
determining that the wearable device is out of hand by combining the heart rate variation result;
if the judgment result is that the user is not out of hand, determining the user identity as the user identified last time;
and if the judgment result is that the user is away from the hand, executing the step of filtering and denoising the acquired electrocardiosignals of the user.
3. The method of claim 1, wherein the cardiac signal characteristic parameters further comprise: time interval of QR, time interval of QRs.
4. A method according to any one of claims 1 to 3, wherein the method further comprises:
and after the user identity is successfully identified, the electrocardiosignal characteristic parameters are used as the latest characteristic template, and the electrocardiosignal characteristic parameters are utilized to update the original electrocardiosignal characteristic template of the user in the mapping relation.
5. The method of claim 1, wherein the method further comprises:
if the user identity is not identified, determining that the user is a new user, acquiring the identity information of the new user, and storing the mapping relation between the identity information and the electrocardiosignal characteristic parameters.
6. An identification device for a wearable device, the device comprising:
the acquisition denoising module is used for carrying out filtering denoising processing on the acquired electrocardiosignals of the user;
the characteristic extraction module is used for obtaining the electrocardiosignal characteristic parameters of the user according to the filtered and denoised electrocardiosignals, and the electrocardiosignal characteristic parameters at least comprise: the ratio of the amplitude of the R wave to the amplitude of the T wave, and the time interval of the QTC;
the characteristic parameters of the electrocardiosignals specifically comprise: respectively extracting parameters of start points and stop points of Q waves, R waves, S waves and T waves in the electrocardiosignals subjected to filtering and denoising, and respectively extracting amplitude parameters of the R waves and the T waves; respectively calculating QTC time intervals based on the start and stop point parameters of Q waves, R waves, S waves and T waves, and calculating the ratio of the amplitude of the R waves to the amplitude of the T waves based on the amplitude parameters of the R waves and the T waves;
and the identification module is used for matching the electrocardiosignal characteristic parameters with the electrocardiosignal characteristic template in the mapping relation based on the mapping relation between the prestored electrocardiosignal characteristic template and the user identity and identifying the user identity based on the matching result.
7. The apparatus of claim 6, further comprising a hands-off determination module, the hands-off determination module specifically configured to:
and if the judgment result is that the user leaves the hand, executing the operation of acquiring the denoising module.
8. The apparatus of claim 6, wherein the cardiac signal characteristic parameters further comprise: time interval of QR, time interval of QRs.
9. The apparatus of any one of claims 6 to 8, further comprising:
and the updating module is used for taking the electrocardiosignal characteristic parameters as the latest characteristic template after the identity of the user is successfully identified, and updating the original electrocardiosignal characteristic template of the user in the mapping relation by utilizing the electrocardiosignal characteristic parameters.
10. The apparatus of claim 6, wherein the apparatus further comprises:
and the new user recording module is used for determining that the user is a new user if the user identity is not identified, acquiring the identity information of the new user and storing the mapping relation between the identity information and the electrocardiosignal characteristic parameters.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2016110249359 | 2016-11-16 | ||
| CN201611024935 | 2016-11-16 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106778561A CN106778561A (en) | 2017-05-31 |
| CN106778561B true CN106778561B (en) | 2020-09-01 |
Family
ID=58883415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611095517.9A Active CN106778561B (en) | 2016-11-16 | 2016-12-02 | Identity recognition method and device of wearable equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778561B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110869930B (en) * | 2019-10-08 | 2021-08-06 | 北京微动数联科技有限公司 | Identity recognition method based on cardiac shock signal, electronic device and storage medium |
| CN112370065A (en) * | 2020-10-21 | 2021-02-19 | 华南理工大学 | Identity recognition method, system and medium based on electrocardiosignal dynamics characteristics |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573458B (en) * | 2014-12-30 | 2017-05-31 | 深圳先进技术研究院 | A kind of personal identification method based on electrocardiosignal, apparatus and system |
-
2016
- 2016-12-02 CN CN201611095517.9A patent/CN106778561B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106778561A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102835954B (en) | Method for generating heart beating waveform template and treating ventricular premature beat detection and device | |
| CN101773394B (en) | Identification method and identification system using identification method | |
| CN109833035B (en) | Classification prediction data processing method of pulse wave blood pressure measuring device | |
| Udhayakumar et al. | Approximate entropy profile: a novel approach to comprehend irregularity of short-term HRV signal | |
| JP2020528336A (en) | Electrocardiographic signal detection | |
| CN103584854B (en) | Extraction method of electrocardiosignal R waves | |
| CN109117730A (en) | Electrocardiogram auricular fibrillation real-time judge method, apparatus, system and storage medium | |
| CN111657889A (en) | Non-contact driver fatigue detection method based on millimeter wave radar | |
| CN104771178B (en) | The method and device of identification | |
| CN101828918A (en) | Electrocardiosignal R peak detection method based on waveform characteristic matching | |
| CN104840186A (en) | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) | |
| CN104305992B (en) | A kind of interactive fast automatic extracting method of Fetal ECG | |
| CN106874722A (en) | A kind of personal identification method and its device based on electrocardiosignal | |
| CN101919704B (en) | Heart sound signal positioning and segmenting method | |
| CN111053552B (en) | QRS wave detection method based on deep learning | |
| CN109124620A (en) | A kind of atrial fibrillation detection method, device and equipment | |
| Chin et al. | Bayesian real-time QRS complex detector for healthcare system | |
| CN109044340B (en) | Electrocardiogram data classification method and device, electronic equipment and storage medium | |
| CN109106345A (en) | Pulse signal characteristic detection method and device | |
| CN111832537B (en) | Abnormal electrocardiosignal identification method and abnormal electrocardiosignal identification device | |
| CN106778561B (en) | Identity recognition method and device of wearable equipment | |
| CN109009004A (en) | A kind of physical examinations method based on Chinese medicine pulse analysis | |
| Akhbari et al. | Fiducial points extraction and characteristicwaves detection in ECG signal using a model-based bayesian framework | |
| Li et al. | A novel abnormal ECG beats detection method | |
| CN110491504B (en) | Method for acquiring medical index data of heart sound signal |
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 |