Computational module, system, wearable device, glasses, and computer implementation method for determining personal identification information

Abstract

A computational module, system, and computer implementation method for determining an individual's identification information. The computational module is configured to acquire a signal representing the vibrations generated by the individual's heartbeat, determine a representative segment of the signal, and determine the individual's identification information by comparing the representative segment with a plurality of model segments, wherein each model segment is associated with model identification information.

Description

Technical Field

[0001] The present disclosure relates to a device and method for determining personal identification information.

Background Art

[0002] Personal identification information can be used to understand the name of the individual or other elements about who the individual is.

[0003] One purpose of determining personal identification information can be to achieve personal authentication. Personal authentication can be used, for example, in forms of identification and access control for entering a restricted area, making a payment using electronic payment, or accessing protected data, for example, in computer science.

[0004] Another purpose of determining personal identification information can be to personalize device parameters according to an individual's preferences. A device that recognizes an individual can use the personal parameters of the recognized individual. For example, the device can personalize curves for coloring e-chromic lenses, such as the speed of changing from one color shade to another or a table associating multiple color shades with multiple ambient light levels. The device can also personalize parameters related to the sound emitted by the device, such as the general level of sound or levels associated with different frequencies, using an equalizer. For example, it is also possible to personalize the welcome message displayed by a virtual reality or augmented reality headset.

[0005] Biometrics can be used to determine personal identification information. Biometrics are physical measurements and calculations related to human characteristics. Biometrics are thus measurable characteristics used to label and describe an individual.

[0006] Many different aspects of human physiology, chemistry, or behavior can be used as biometrics. These include aspects related to the shape of parts of an individual's body. Examples include fingerprints, palm vein patterns, facial recognition, DNA, palm prints, the geometric shape of the hand, iris recognition, the retina, scent / odor, voice, ear, and gait. However, these aspects of human physiology have drawbacks; DNA is too long to process for real-time applications, fingerprints are sensitive to changes in the skin of the fingers or the fingers themselves, and voice recognition is sensitive to upper respiratory tract diseases, such as the common cold. [Overview of the project] [Problems that the invention aims to solve]

[0007] Therefore, the object of this disclosure is to provide a method and device that enables the determination of an individual's identifying information using biometrics, without the drawbacks of prior art methods. [Means for solving the problem]

[0008] The following is a simplified overview to provide a basic understanding of the various aspects of this disclosure. This overview is not a comprehensive overview of all intended aspects, nor is it intended to identify the main or essential elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a preface to the more detailed descriptions presented later.

[0009] One aspect of this disclosure is a computational module for determining personal identification information. The computational module is configured to acquire a signal representing the vibrations generated by the heartbeat of an individual, determine a representative segment of the signal, and determine personal identification information by comparing the representative segment with a plurality of model segments, wherein each model segment is associated with model identification information.

[0010] The signal representing the vibrations generated by the heartbeat is also called an electrocardiogram (SCG). By analyzing the signal representing the vibrations caused by the heartbeat, it is possible to obtain information about various mechanical events in the cardiac cycle, such as the opening and closing of the aortic and mitral valves, atrial contraction, isovolumetric contraction, and relaxation.

[0011] The period of the cardiac cycle in which the heart muscle contracts is called systole and corresponds to the first oscillation produced by the heart. The period of the cardiac cycle in which the heart muscle relaxes is called diastole and corresponds to the second oscillation produced by the heart.

[0012] According to the article by AABui, Z. Yu and FMBui, "A biometric modality based on the seismocardiogram (SCG)," published by IEEE International Conference and Workshop on Computing and Communication (IEMCON), 2015, pp. 1-7, it is known that electrocardiograms can represent characteristics specific to each individual.

[0013] Therefore, the computational module of this disclosure enables reliable determination of personal identification information. Furthermore, by using heart rate as biometrics, a solution that is difficult to steal (compared to fingerprint and facial recognition) can be easily embedded in eyeglass frames, enabling identification and verification of the individual's survival simultaneously.

[0014] Another aspect of the present disclosure is a system comprising a wearable device and a computing module for determining the identification information of an individual wearing the wearable device, the wearable device comprising a sensor for determining a signal representing vibrations generated by the cardiac cycle of the individual's heart. The computing module is configured to receive a signal from the sensor representing vibrations generated by the heartbeat of the individual's heart, determine a representative segment of the signal, and determine the individual's identification information by comparing the representative segment with a plurality of model segments, each of which is associated with model identification information.

[0015] Another aspect of the present disclosure is a wearable device including a computing module for determining the identification information of an individual wearing the wearable device. The wearable device includes a sensor for determining a signal representing vibrations generated by the cardiac cycle of the individual's heart. The computing module is configured to receive a signal from the sensor representing vibrations generated by the heartbeat of the individual's heart, determine a representative segment of the signal, and determine the individual's identification information by comparing the representative segment with a plurality of model segments, each of which is associated with a model identification information.

[0016] Another aspect of the present disclosure is a pair of glasses including a computing module for determining the identification information of an individual wearing the glasses. The glasses include a sensor for determining a signal representing vibrations generated by the cardiac cycle of the individual's heart. The computing module is configured to receive a signal from the sensor representing vibrations generated by the heartbeat of the individual's heart, determine a representative segment of the signal, and determine the individual's identification information by comparing the representative segment with a plurality of model segments, each of which is associated with a model identification information.

[0017] Another aspect of the present disclosure is a computer method for determining personal identification information. The method includes obtaining a signal representing the vibrations generated by the heartbeat of an individual; determining a representative segment of the signal; and determining personal identification information by comparing the representative segment with a plurality of model segments, each of which is associated with a model identification information.

[0018] Another aspect of the present disclosure is a computer program including instructions, which, when executed by a computer, cause the computer to perform a method for determining personal identification information. The method includes obtaining a signal representing the vibrations generated by the heartbeat of a person; determining a representative segment of the signal; and determining personal identification information by comparing the representative segment with a plurality of model segments, each of which is associated with model identification information.

[0019] A computer may include memory and a processor. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on a chip (SoC), field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable hardware configured to perform various functions described throughout this disclosure. Memory may be computer-readable media. Examples, but not limited to, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage devices, magnetic disk storage devices, other magnetic storage devices, combinations of the computer-readable media of the types described above, or any other media that can be used to store computer executable code in the form of instructions or data structures that can be accessed by the computer's processor.

[0020] Another aspect of the present disclosure is a non-temporary program storage device that is computer-readable and tangibly embodies a program of computer-executable instructions for performing a method for determining personal identification information. The method includes obtaining a signal representing vibrations generated by the heartbeat of an individual; determining a representative segment of the signal; and determining personal identification information by comparing the representative segment with a plurality of model segments, each of which is associated with model identification information.

[0021] To gain a more detailed understanding of the descriptions and advantages provided herein, refer here to the following brief descriptions, which are read in conjunction with the accompanying drawings and detailed descriptions. Similar reference numbers represent similar parts. [Brief explanation of the drawing]

[0022] [Figure 1] Represents a system for determining an individual's identification information. [Figure 2] Represents glasses, an example of a wearable device. [Figure 3] Represents a removable clip that can be attached to glasses. [Figure 4] Represents augmented reality glasses, another example of a wearable device. [Figure 5] Represents a method for determining an individual's identification information. [Figure 6-a] Represents an example of an electrocardiogram signal. [Figure 6-b] Represents an example of an electrocardiogram signal. [Figure 6-c] Represents an example of an electrocardiogram signal. [Figure 6-d] Represents an example of an electrocardiogram signal. [Figure 7] Represents the first example of the step of determining a representative segment of a signal. [Figure 8] Represents the second example of the step of determining a representative segment of a signal.

Mode for Carrying Out the Invention

[0023] The detailed description presented below in connection with the accompanying drawings is intended as an explanation of various possible embodiments, but is not intended to represent the only embodiments in which the concepts described herein can be implemented. The detailed description includes specific details to provide a thorough understanding of the various concepts. However, those skilled in the art will understand that these concepts can be implemented without these specific details. In some cases, well-known structures and components are shown in block diagram form so as not to obscure such concepts.

[0024] Description of a system for determining an individual's identification information Figure 1 shows a system 101 for determining an individual's identification information. The system 101 includes a computing module 102 and a wearable device 103. The computing module 102 is configured to determine the identification information of an individual wearing the wearable device 103. The wearable device includes a sensor 103-a for determining a signal representing vibrations generated by the individual's heartbeat.

[0025] The computing module 102 includes memory 102-a and processor 102-b.

[0026] The computing module may be a low-resource computing module.

[0027] Examples of processors 102-b include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on a chip (SoC), baseband processors, field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable hardware configured to perform various functions described throughout this disclosure.

[0028] Memory 102-a is a computer-readable medium. For example, and not limited to, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage devices, magnetic disk storage devices, other magnetic storage devices, combinations of the computer-readable media of the above types, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by the processor 102-a of the computing module 102.

[0029] The computing module 102 may be an independent module, such as a smartphone or computer, a system-on-a-chip (SoC), or a graphics processing unit (GPU). The computing module 102 may be a virtual machine located on a cloud network, or a server or system 101 that is not located in the same location as the patient.

[0030] In other embodiments, the computing module 102 may be integrated into the wearable device 103 or may be attachable to the wearable device 103.

[0031] The system may also include a display unit. This display unit may be connected to a computing module 102 used to give instructions to an individual during the determination of their identification information.

[0032] In this embodiment, the computing module 102 may be part of the wearable device 103, for example, headphones, which may be circular headphones, over-ear headphones, or in-ear headphones.

[0033] Figure 2 shows an example of a wearable device 103, eyeglasses EY. Eyeglasses are also known as eyewear. This eyeglasses EY includes two lenses L1 and L2 as well as a frame F. Frame F includes two arms or temples A1 and A2 as well as a front section F1. The front section F1 includes a right rim R1 and a left rim R2, which are linked together by a bridge B. The front section F1 and the two arms A1 and A2 are linked using two hinges H1 and H2. Hinges H1 and H2 allow the individual to fold the arms A1 and A2 along the front section F1. The rims R1 and R2 of frame F1 are configured to receive and hold the lenses L1 and L2. Eyeglasses EY can be prescription eyeglasses or non-refractive eyeglasses, such as sunglasses, with the refraction adjusted for the individual by an eye care professional.

[0034] As shown in Figure 2, the EY glasses may integrate a sensor 103-a for determining signals representing vibrations generated by the cardiac cycle of an individual's heart. The sensor 103-a may be located on one or both of arms A1 and A2.

[0035] In one embodiment, the calculation module 102 can be integrated into the eyeglasses EY.

[0036] In other embodiments, the computing module 102 may be a module independent of the eyeglasses EY. In this case, the computing module 102 may be, for example, a smartphone.

[0037] In another embodiment shown in Figure 3, the removable clip 301 can be attached to eyeglasses EY. This removable clip 301 may include a sensor 103-a and optionally a computing module 102.

[0038] Figure 4 shows another example of a wearable device 103, augmented reality glasses ARE. These augmented reality glasses ARE also include two lenses L1 and L2 as well as a frame F. The frame F includes two arms or temples A1 and A2 as well as a front section F1. The front section F1 includes a right rim R1 and a left rim R2, which are linked together by a bridge B. The front section F1 and the two arms A1 and A2 are linked using two hinges H1 and H2. The hinges H1 and H2 allow the individual to fold the arms A1 and A2 along the front section F1. The rims R1 and R2 of the frame F1 are configured to receive and hold the lenses L1 and L2. Furthermore, the augmented reality glasses ARE include a screen SCR, commonly known as a see-through display or transparent display.

[0039] A screen SCR can form a display unit that can be used to give instructions to an individual while determining their identification information.

[0040] As shown in Figure 4, the augmented reality glasses ARE may integrate a sensor 103-a for determining signals representing vibrations generated by the cardiac cycle of an individual's heart. The sensor 103-a may be located on one or both of arms A1 and A2.

[0041] With respect to the eyeglasses EY, in the embodiment, the computing module 102 can be integrated into the augmented reality eyeglasses ARE.

[0042] With respect to the eyeglasses EY, in other embodiments, the computing module 102 may be a module independent of the augmented reality eyeglasses ARE. In this case, the computing module 102 may be, for example, a smartphone.

[0043] With respect to eyeglasses EY, in other embodiments, the removable clip 301 can be attached to augmented reality eyeglasses ARE.

[0044] A wearable device can be a watch, or more precisely, a wristwatch. A wristwatch is designed to be worn around the wrist and attached by a watch strap or other type of bracelet, including a metal band, leather strap, or other type of bracelet. In this case, the watch may include a sensor 103-a and optionally a computing module 102.

[0045] A watch can also be a smartwatch, which is a wearable computer in the form of a watch. Modern smartwatches generally provide a local touchscreen interface for everyday use, while the associated smartphone application may include sensors used to determine an individual's physiological parameters. In this case, sensor 103-a may be one of these sensors. The computing module 102 may be included in the smartwatch and may be shared with other functions of the smartwatch.

[0046] The sensor 103-a of the wearable device 103 is ·microphone, ·Accelerometer, Gyroscope It may be a MEMS sensor selected from among the following. The sensor 103-a of the wearable device 103 may be a capacitive sensor, a piezoelectric sensor, or an electrostatic sensor.

[0047] Description of methods for determining personal identification information To achieve this determination of personal identification information, memory 102-a can store a computer program that, when the program is executed by processor 102-b, causes control module 102 to execute a method for determining personal identification information, such as a computer implementation method. As shown in Figure 5, the method is: - Step 501 involves obtaining a signal that represents the vibrations generated by the individual's heartbeat, - Step 502 to determine a representative segment of the signal, - Step 503 involves comparing a representative segment with multiple model segments to determine an individual's identifying information, wherein each model segment is associated with model identifying information. Includes.

[0048] During step 501, the signal is acquired from sensor 103-a of the wearable device 103.

[0049] Examples of electrocardiograms are given in Figures 6-a to 6-d. This signal is an indicator of prepericardial oscillations generated by the beating heart, and the mechanical function of the heart can be explored with each heartbeat. In this signal, the following four reference points associated with the opening and closing of the aortic and mitral valves can be identified: - AO (aortic opening), - AC (aortic closure), - MO (Mitral valve open), and - MC (mitral valve closure).

[0050] Several other aspects of the signal are also interesting, including the following: - Signal point corresponding to the isovolumetric motion of the ventricles of the heart (IM), - The signal point (IC) corresponding to the isotonic contraction of the ventricles of the heart. - The signal point corresponding to rapid ventricular ejection (RE), - Point of maximum blood acceleration (MA), - The signal point (RF) corresponding to rapid ventricular filling.

[0051] In cardiac physiology, isometric contraction is an event that occurs in the early stages of systole, during which the ventricles contract without a corresponding volume change. This short portion of the cardiac cycle occurs while all the heart valves are closed.

[0052] In isotonic contraction, the length of the muscle changes, while the tension remains constant. Isotonic contraction differs from isokinetic contraction in that the muscle's velocity remains constant.

[0053] In the first example shown in Figure 7, step 502 for determining the representative segment of the signal is: Step 701 divides the signal into multiple segments, each segment corresponding to one of the periods of the cardiac cycle, Step 702 for each segment determines the feature points, Step 703 involves synchronizing segments corresponding to a predetermined period of the cardiac cycle, wherein the synchronization uses feature points, and Step 704: Average the synchronized segments to obtain a representative segment. It may include.

[0054] The cardiac cycle is the performance of the human heart from the start of one heartbeat to the start of the next. It consists of two phases: systole, the period of robust contraction and pumping of the blood, and diastole, the period of relaxation and filling of the heart muscle with blood. Conditions such as heart failure can cause a third phase to appear. In this case, these third phases can be removed from the signals used to achieve identification.

[0055] Using the first example, the signal can be divided into multiple segments. Each segment contains either one of the diastolic or systolic portions of the cardiac cycle. Then, a segment containing either the systolic or diastolic portions can be selected, these selected segments can be synchronized together, and finally, they can be averaged.

[0056] To split the signal, - Determining the duration of an individual's heart rate, - In the signal, determine at least two consecutive feature points associated with two different cardiac cycles, - Determining the time difference between two consecutive feature points. - Dividing the signal to form a first segment containing the first feature point of at least two consecutive feature points, - Dividing the signal to form a second segment containing the second of at least two consecutive feature points. This can be done, and if the time difference is greater than 1.2 times the duration of the heart rate, the signal can be split to form a third segment between the first and second segments.

[0057] The third segment may include an intermediate point between the first and second feature points. The duration between the intermediate point and the first feature point, or between the intermediate point and the second feature point, may be equal to the duration of the heart rate.

[0058] The characteristic points of the signal can correspond to the AO points.

[0059] The following formula can be used to determine feature points.

number

[0060] In the embodiment, after step 702 of determining feature points for each segment, the duration separating two feature points associated with two consecutive segments can be determined. If this duration is not a multiple of the heart rate duration, one of the feature points of the two consecutive segments can be moved so that the duration between the moved feature point and the other feature point is a multiple of the heart rate duration.

[0061] During step 703, when the segments are synchronized together, the moved feature points can be considered instead of the feature points that were initially determined.

[0062] Generally, the following feature points can be used to achieve synchronization: - Point (MC) of the segment corresponding to mitral valve closure, - Points in the segment corresponding to the isovolumetric motion of the ventricles of the heart (IM), - Point (AO) of the segment corresponding to the opening of the aortic valve. - The point (IC) of the segment corresponding to the isotonic contraction of the ventricles of the heart. - The segment point (RE) corresponding to rapid ventricular ejection.

[0063] The prominent points during systole are MC, IM, AO, IC, and RE. Using point AO is advantageous because it allows for a simpler and more robust method of making this identification.

[0064] The prominent points in diastole are AC, MO, and RF. Because these points are more characteristic of diastole than other points, it is advantageous to use point MO.

[0065] Steps 701-704 can be used to determine a representative segment that may represent the systolic or diastolic portion of the cardiac cycle.

[0066] After this segmentation, segments with excessive noise can be rejected. To achieve this rejection, - Select from multiple segments that have a quality level exceeding the quality threshold. - Determining the representative segment of the signal based only on the selected segments. It is possible to do so.

[0067] The threshold may depend on the level of recognition requirements. If strong identification is needed, only the clearest segments may be selected. One of the following metrics can be used to determine which segments to select: • SNR: Signal-to-noise ratio of a segment. • Relative bandwidth power of estimated frequencies within the cardiac frequency range: This allows us to assess whether the frequencies are only within the cardiac frequency range. 0.6 is not bad, and anything above 0.9 is very good. • PSNR: The peak signal-to-noise ratio of a segment. If it is generally linearly greater than 15, the segment can be selected.

[0068] In some embodiments, point AO, IC, and / or RE can be used to synchronize systolic segments in order to improve the quality of identification information determination. Advantageously, point AO may be used when there is only one systolic segment.

[0069] Regarding the expansion phase, synchronization can be achieved using the portion between points AC and MO. More precisely, synchronization can be achieved using point MO.

[0070] Figure 8 shows a second example of step 502 for determining the representative segment. In this example, step 502 is: - Step 801 divides the signal into a first plurality of first segments, each first segment corresponding to one of the periods of the cardiac cycle, - Step 802 for each first segment determines the first feature point, - Step 803, which synchronizes the first segments together to obtain the first synchronized segment, wherein the synchronization uses the first feature points, - Step 804 involves averaging the first synchronized segment to obtain the first averaged segment, - Step 805, which divides the signal into a second plurality of second segments, each second segment corresponding to another duration of the cardiac cycle, - Step 806 for each second segment to determine the second feature point, - Step 807, which synchronizes the second segment together to obtain the second synchronized segment, wherein the synchronization uses the second feature point, - Step 808 involves averaging the second synchronized segment to obtain the second averaged segment, - Step 809 involves concatenating the first averaged segment and the second averaged segment to obtain a representative segment. Includes.

[0071] In this second example, for example, a first averaged segment corresponding to the systolic phase and a second averaged segment corresponding to the diastolic phase are concatenated together to obtain a more accurate representative segment.

[0072] In other words, to improve the independent alignment of each part, cross-correlation can be used to calculate the lag between individual beats and envelope peaks. Aligning the beats allows us to obtain the "average beat" or "central beat." By calculating a new envelope for this central beat and the main peaks, we can identify the S1 and S2 peaks and use another cross-correlation to align the two main complex.

[0073] To implement step 503, which compares a representative segment with multiple model segments, the distance between the representative segment and each model segment can be determined. Then, by selecting the identification information associated with the model segment having the smallest distance, the individual's identification information can be determined.

[0074] In the embodiment, the metric used to determine the distance is - The distance between points in a sample of the representative segment and one of the model segments. - Mutual information, for example, normalized mutual information between two segments, - Hausdorff distance between two segments, - DTW (Dynamic Time Warp) You can choose from among them.

[0075] In other embodiments, a convolutional neural network (CNN) can be used to accomplish step 503, which involves comparing a representative segment with multiple model segments. This convolutional neural network may be pre-trained with multiple model identification pieces associated with each of the multiple model representative segments.

[0076] In the embodiment, an error message may be provided if the minimum distance exceeds a distance threshold. Generally, the distance threshold depends on the metric used to compare a representative segment with one of the model segments. The distance value may be amplitude-dependent; to avoid this, the curve can be normalized to have a threshold that is not dependent on the signal amplitude (which may be individual or wear condition-dependent).

[0077] When normalized mutual information (NMI) is used, the value is close to 0 when two segments contain no information about each other, and close to 1 when two segments contain complete information about each other. Depending on the "strength" of the identification, the threshold can be selected from 0.2 to 0.8 or higher. In this case, the closer the NMI is to 1, the closer the two segments are, and therefore the smaller the distance between each segment.

[0078] When DTW is used, a value close to 0 indicates that the segments are very close. Therefore, depending on the level of identification strength, the threshold can be set to a value close to 0.

[0079] When the Hausdorff distance is used, a value close to 0 indicates that the two segments are very close. Therefore, depending on the level of identification strength, the threshold can be set to a value close to 0.

[0080] Usage Examples In the first use case, an individual desires to perform an action that requires verification of their identification. This action could be, for example, achieving identification to enter a restricted area, make a payment using electronic payment, or access protected data.

[0081] An individual may wear a wearable device 103, for example, the eyeglasses EY shown in Figure 2 or Figure 3, or the augmented reality eyeglasses ARE shown in Figure 4. An external system approving an action may communicate with the computing module 102 to request authentication of the individual. This communication may be implemented using a wireless module that uses, for example, the Wi-Fi wireless network protocol, the cellular network protocol (e.g., the 5G standard), or the Bluetooth wireless technology standard.

[0082] When computing module 102 receives a request to authenticate an individual, it may initiate the method shown in Figure 5. Once computing module 102 determines the individual's identification information, it may transmit the determined identification information to a system that approves the action.

[0083] The external system approves or disapproves the action based on the received determined identification information and other parameter values ​​within the system.

[0084] Similar to the first use case, in the second use case, the individual also desires to perform an action that requires verification of their identification information. The type of action may be similar to that in the first use case.

[0085] Similar to the first use case, an individual may wear a wearable device 103, for example, the glasses EY shown in Figure 2 or Figure 3, or the augmented reality glasses ARE shown in Figure 4. An external system approving an action may communicate with the computing module 102 to request authentication of the individual. This communication may be implemented using a wireless module that uses, for example, the Wi-Fi wireless network protocol, the cellular network protocol (e.g., the 5G standard), or the Bluetooth wireless technology standard.

[0086] Unlike the first use case, when the computing module 102 receives a request to authenticate an individual, the computing module 102 may determine the time of the last determination of the individual's identification information. If the duration between the time of the last determination and the actual time is below the duration threshold and the individual has been continuously wearing the wearable device, the computing module may transmit the identification information determined during the last determination. If the duration exceeds the duration threshold or the individual has not been continuously wearing the wearable device, the computing module may determine the individual's identification information on the spot and transmit the newly determined identification information to the system approving the action.

[0087] In other words, to realize this second use case, the method shown in Figure 5 is: - Step of receiving a request for personal identification, - A step to determine the time of the last determination of an individual's identification information. This may also include the case where, if the duration between the time of the last determination and the actual time falls below the duration threshold, the calculation module is configured to send the identification information determined during the last determination.

[0088] The external system approves or disapproves the action based on the newly determined identification information received and other parameter values ​​within the system.

[0089] In one embodiment, the system 101, more precisely the computation module 102, may be configured to determine the confidence level of the last determined identification information. If the confidence level exceeds a predetermined value (and other prior conditions are respected), the computation module is configured to transmit the identification information determined during the last determination.

[0090] If at least one of the previously presented conditions is not respected, the computation module is configured to determine the personal identification information.

[0091] In one embodiment, a device requesting verification of identification information may request a minimum level of identification, such as using strong identification.

[0092] In the third use case, independently of or in addition to the first or second use case, the individual desires to be able to automatically configure an external system or wearable device 103 according to the determined identification information.

[0093] An individual may wear a wearable device 103, for example, the eyeglasses EY shown in Figure 2 or Figure 3, or the augmented reality eyeglasses ARE shown in Figure 4. An external system approving an action may communicate with the computing module 102 to request authentication of the individual. This communication may be implemented using a wireless module that uses, for example, the Wi-Fi wireless network protocol, the cellular network protocol (e.g., the 5G standard), or the Bluetooth wireless technology standard.

[0094] When computing module 102 receives a request to authenticate an individual, it may initiate the method shown in Figure 5. Once computing module 102 determines the individual's identification information, it may transmit the determined identification information to a system that approves the action.

[0095] Next, the external system or wearable device 103 can be automatically configured to meet individual requirements. For example, the wearable device 103 can personalize the curves for coloring the e-chromic lenses. The device can also use an equalizer to personalize parameters related to the sound emitted by the device, such as the general level of sound or levels associated with different frequencies. For example, it is also possible to personalize the welcome message displayed by the virtual reality or augmented reality headset. [Explanation of symbols]

[0096] 101 System 102 Computation Modules 102 Control Module 103 Wearable Devices 301 Removable Clip

Claims

1. A computation module (102) for determining personal identification information, - To obtain a signal representing the vibrations generated by the heartbeat of the aforementioned individual, - To determine the representative segment of the aforementioned signal, - To determine the identification information of the individual by comparing the representative segment with multiple model segments, and to determine that each model segment is associated with model identification information. A computing module (102) configured to perform the following.

2. - Dividing the signal into multiple segments, where each segment corresponds to one of the periods of the cardiac cycle, - For each segment, determine the characteristic points, - Synchronizing the segments corresponding to a predetermined period of the cardiac cycle, wherein the synchronization uses the feature points, - Averaging the synchronized segments to obtain the representative segment, The calculation module (102) according to claim 1, configured to determine the representative segment.

3. - Dividing the signal into a first plurality of first segments, each first segment corresponding to one of the periods of the cardiac cycle, - For each first segment, determine the first feature point, - Synchronizing the first segments together to obtain the first synchronized segment, wherein the synchronization uses and obtains the first feature points. - Averaging the first synchronized segments to obtain a first averaged segment, - Dividing the signal into a second plurality of second segments, each second segment corresponding to another of the periods of the cardiac cycle, - For each second segment, determine the second characteristic point, - Synchronizing the aforementioned second segment together to obtain the second synchronized segment, wherein the synchronization uses and obtains the aforementioned second feature point. - Averaging the aforementioned second synchronized segment to obtain a second averaged segment, - To obtain the representative segment by concatenating the first averaged segment and the second averaged segment, The calculation module (102) according to claim 1, configured to determine the representative segment.

4. - To determine the duration of the individual's heart rate, - In the signal, determine at least two consecutive feature points associated with two different cardiac cycles, - Determining the time difference between the two consecutive feature points mentioned above. - Dividing the signal to form a first segment including the first feature point among the at least two consecutive feature points, - Dividing the signal to form a second segment including the second feature point among the at least two consecutive feature points, The signal is thus configured to be divided, The computing module (102) according to claim 2 or 3, which is also configured to divide the signal to form a third segment between the first segment and the second segment if the time difference is greater than 1.2 times the duration of the heart rate.

5. - Selecting from among the multiple segments the segment having a quality level that exceeds the quality threshold, - Determining the representative segment of the signal based solely on the selected segments, A computing module (102) according to any one of claims 2 to 4, configured to perform the following:

6. The calculation module (102) according to any one of claims 1 to 5, which is also configured to determine the distance between the representative segment and the model segment for each of the model segments, and the identification information of the individual is the identification information associated with the model segment having the minimum distance.

7. The aforementioned characteristic features are, - Point (MC) of the segment corresponding to the closure of the mitral valve, - Points (IM) of the segment corresponding to the isovolumetric motion of the ventricles of the heart, - Point (AO) of the segment corresponding to the opening of the aortic valve, - The point (IC) of the segment corresponding to the isotonic contraction of the ventricle of the heart, and - Points (RE) of the segment corresponding to rapid ventricular ejection, A calculation module (102) according to any one of claims 2 to 6, selected from among the following.

8. - Receiving the aforementioned request for identification of the individual, - To determine the time of the last determination of the aforementioned identification information of the aforementioned individual, It is configured to do the following: A calculation module (102) according to any one of claims 1 to 7, configured to transmit the identification information determined during the last determination if the duration between the time of the last determination and the actual time falls below a duration threshold.

9. A system (101) comprising a wearable device (103) and a computing module (102) for determining the identification information of an individual wearing the wearable device (103), wherein the wearable device (103) includes a sensor (103-a) for determining a signal representing vibrations generated by the cardiac cycle of the individual's heart, and the computing module (102) - Receiving a signal from the sensor that represents vibrations generated by the heartbeat of the individual, - To determine the representative segment of the aforementioned signal, - To determine the identification information of the individual by comparing the representative segment with multiple model segments, and to determine that each model segment is associated with model identification information. A system (101) configured to perform the following actions.

10. The sensor (103-a) of the wearable device (103) is ·microphone, - Accelerometer, and ・Gyroscope, The system (101) according to claim 9, wherein the MEMS sensor is selected from among the above, or the sensor (103-a) of the wearable device (103) is a capacitive sensor, a piezoelectric sensor, or an electrostatic sensor.

11. The calculation module (102) is - Receiving the aforementioned request for identification of the individual, - To determine the time of the last determination of the aforementioned identification information of the aforementioned individual, The system (101) according to claim 9 or 10, configured to perform such a task, wherein if the duration between the time of the last determination and the actual time falls below a duration threshold and the individual has been continuously wearing the wearable device, the computing module is configured to transmit the identification information determined during the last determination.

12. A wearable device (103) comprising a computing module (102) for determining the identification information of an individual wearing the wearable device (103), and comprising a sensor (103-a) for determining a signal representing vibrations generated by the cardiac cycle of the individual's heart, wherein the computing module (102) - Receiving a signal from the sensor that represents vibrations generated by the heartbeat of the individual, - To determine the representative segment of the aforementioned signal, - To determine the identification information of the individual by comparing the representative segment with multiple model segments, and to determine that each model segment is associated with model identification information. A wearable device (103) configured to perform the following.

13. Eyeglasses (EY) comprising a computing module (102) for determining the identification information of an individual wearing the eyeglasses (EY), and comprising a sensor (103-a) for determining a signal representing vibrations generated by the cardiac cycle of the individual's heart, wherein the computing module (102) - Receiving a signal from the sensor that represents vibrations generated by the heartbeat of the individual, - To determine the representative segment of the aforementioned signal, - To determine the identification information of the individual by comparing the representative segment with multiple model segments, and to determine that each model segment is associated with model identification information. Eyeglasses (EY) configured to perform the following actions.

14. A computer method for determining personal identification information, - Obtaining a signal representing the vibrations generated by the heartbeat of the aforementioned individual (501), - Determining a representative segment of the signal (502), - The representative segment is compared with a plurality of model segments to determine the identification information of the individual (503), and the model segments are each associated with model identification information (503), A computer implementation method including

15. The aforementioned representative segment is, - Dividing the signal into multiple segments (701), wherein each segment corresponds to one of the periods of the cardiac cycle, - For each segment, determine the feature points (702), - Synchronizing the segments corresponding to a predetermined period of the cardiac cycle (703), wherein the synchronization uses the feature points, - Averaging the synchronized segments to obtain the representative segment (704), The computer implementation method according to claim 14, determined by...

Images